From 54d9a15096414354d2f548d58bccbd9d8872f538 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MacBook-Pro-2.local>
Date: Mon, 5 Aug 2024 11:02:36 -0700
Subject: [PATCH 01/27] adding draft script to fix reference

---
 scripts/fix-ref/README.md                     | 30 +++++++
 .../fix_ensembletr_snpstr_reference.py        | 79 +++++++++++++++++++
 2 files changed, 109 insertions(+)
 create mode 100644 scripts/fix-ref/README.md
 create mode 100755 scripts/fix-ref/fix_ensembletr_snpstr_reference.py

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
new file mode 100644
index 0000000..1dc7e2a
--- /dev/null
+++ b/scripts/fix-ref/README.md
@@ -0,0 +1,30 @@
+# Clean up the EnsembleTR SNP-TR reference panel
+
+TODO:
+* Remove duplicate records and those with incorrect reference allele
+* Add required header line
+* Add informative variant IDs to STRs
+* Run script to add beagle info
+* Release bref versions alongside the VCFs
+
+## Step 1: Fix reference VCF files
+
+```
+chrom=11
+./fix_ensembletr_snpstr_reference.py \
+	--vcf chr${chrom}_final_SNP_merged_additional_TRs.vcf.gz \
+	--ref Homo_sapiens_assembly38.fasta \
+	--out ensembletr_refpanel_v3_chr${chrom}
+```
+
+## Step 2: Add beagle info
+
+```
+TODO
+```
+
+## Step 3: Convert to bref
+
+```
+TODO
+```
\ No newline at end of file
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
new file mode 100755
index 0000000..0259ac9
--- /dev/null
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+
+"""
+Script to clean up SNP/TR reference haplotype panels
+"""
+
+import argparse
+import cyvcf2
+import pyfaidx
+import sys
+
+def IsTRRecord(record_id):
+	return record_id is None or record_id.strip() == "."
+
+def GetTRRecordID(record):
+	return "EnsTR:%s:%s"%(record.CHROM, record.POS)
+
+def CheckReference(record, refgenome):
+	# REF in VCF should match what is in the reference genome
+	refseq = refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)]
+	return (refseq == record.REF)
+
+def run():
+    args = getargs()
+    if args == None:
+        sys.exit(1)
+    else:
+        retcode = main(args)
+        sys.exit(retcode)
+
+def getargs(): # pragma: no cover
+    parser = argparse.ArgumentParser(__doc__)
+    parser.add_argument("--vcf", help="Input SNP/TR VCF file", type=str, required=True)
+    parser.add_argument("--ref", help="Reference fasta file", type=str, required=True)
+    parser.add_argument("--out", help="Prefix for output VCF file", type=str, required=True)
+    parser.add_argument("--max-records", help="Quit after processing this many records (for debug)", \
+    	default=-1, type=int)
+    args = parser.parse_args()
+    return args
+
+def main(args):
+    # Set up VCF reader
+    reader = cyvcf2.Reader(args.vcf)
+
+    # Set up the reference
+    refgenome = pyfaidx.Fasta(args.ref)
+
+    # Set up writer, adding the missing header
+    reader.add_to_header("##command=hipstr;note this is a dummy header line")
+    writer = cyvcf2.Writer(args.out + ".vcf", reader)
+
+    # Go through each record
+    # If SNP: just print it
+    # if STR: filter records with incorrect reference,
+    #   and modify ID
+    num_records_processed = 0
+    for record in reader:
+    	num_records_processed += 1
+    	if args.max_records > 0 and num_records_processed > args.max_records:
+    		break # for debug
+    	if not IsTRRecord(record.ID):
+    		writer.write_record(record)
+    	else:
+    		# Check reference
+    		if not CheckReference(record, refgenome):
+    			sys.stderr.write("Skipping record %s:%s:%s, bad ref sequence\n"%(record.ID,record.CHROM,record.POS))
+    			sys.stderr.write("  REF=%s\n"%record.REF)
+    			sys.stderr.write("  Refseq=%s\n"%refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)])
+    			continue # skip this record
+    		# Modify ID
+    		record.ID = GetTRRecordID(record)
+    		# Write to file
+    		writer.write_record(record)
+
+    reader.close()
+    writer.close()
+
+if __name__ == "__main__":
+    run()
\ No newline at end of file

From 386fb7cb0238791c75450803b3204fbd31404677 Mon Sep 17 00:00:00 2001
From: nichole <nicholema621@gmail.com>
Date: Tue, 6 Aug 2024 10:24:59 -0700
Subject: [PATCH 02/27] add convert to bref3

---
 scripts/fix-ref/README.md                     |  8 +---
 scripts/fix-ref/convert_to_bref3.sh           | 28 +++++++++++++
 .../fix_ensembletr_snpstr_reference.py        | 40 ++++++++++++-------
 3 files changed, 55 insertions(+), 21 deletions(-)
 create mode 100644 scripts/fix-ref/convert_to_bref3.sh

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index 1dc7e2a..2be9aa0 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -17,13 +17,7 @@ chrom=11
 	--out ensembletr_refpanel_v3_chr${chrom}
 ```
 
-## Step 2: Add beagle info
-
-```
-TODO
-```
-
-## Step 3: Convert to bref
+## Step 2: Convert to bref
 
 ```
 TODO
diff --git a/scripts/fix-ref/convert_to_bref3.sh b/scripts/fix-ref/convert_to_bref3.sh
new file mode 100644
index 0000000..e6fa514
--- /dev/null
+++ b/scripts/fix-ref/convert_to_bref3.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+
+ref=$1
+bref="bref3.27May24.118.jar"
+
+
+
+#bgzip and index ref
+echo "bgzip and index ref"
+bgzip ${ref}.vcf
+tabix -p vcf ${ref}.vcf.gz
+
+#dowaload bref3.jar
+# Check if the file exists locally
+if [ ! -f "$bref" ]; then
+    echo "File does not exist. Downloading..."
+    wget https://faculty.washington.edu/browning/beagle/bref3.27May24.118.jar 
+else
+    echo "File already exists. Continuing..."
+fi
+
+#convert vcf to bref3
+echo "converting vcf to bref3 format"
+#zcat ${ref}.vcf.gz | java -jar $bref > ${ref}.bref3
+zcat ${ref}.vcf.gz 
+echo "Done converting"
+
+ 
\ No newline at end of file
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 0259ac9..f4b9790 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python3
+#!/usr/bin/env python
 
 """
 Script to clean up SNP/TR reference haplotype panels
@@ -8,6 +8,9 @@
 import cyvcf2
 import pyfaidx
 import sys
+import subprocess
+import os
+
 
 def IsTRRecord(record_id):
 	return record_id is None or record_id.strip() == "."
@@ -54,26 +57,35 @@ def main(args):
     # if STR: filter records with incorrect reference,
     #   and modify ID
     num_records_processed = 0
+    #fail_positions = {201312,225414,18455865}
     for record in reader:
-    	num_records_processed += 1
-    	if args.max_records > 0 and num_records_processed > args.max_records:
-    		break # for debug
-    	if not IsTRRecord(record.ID):
-    		writer.write_record(record)
-    	else:
+        num_records_processed += 1
+        if args.max_records > 0 and num_records_processed > args.max_records:
+            break # for debug
+        if not IsTRRecord(record.ID):
+            writer.write_record(record)
+        else:
     		# Check reference
-    		if not CheckReference(record, refgenome):
-    			sys.stderr.write("Skipping record %s:%s:%s, bad ref sequence\n"%(record.ID,record.CHROM,record.POS))
-    			sys.stderr.write("  REF=%s\n"%record.REF)
-    			sys.stderr.write("  Refseq=%s\n"%refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)])
-    			continue # skip this record
+            if not CheckReference(record, refgenome):
+                #if record.POS in fail_positions:
+                    #print('bcftools merge fail detected %s'%record.POS)
+                #sys.stderr.write("Skipping record %s:%s:%s, bad ref sequence\n"%(record.ID,record.CHROM,record.POS))
+                #sys.stderr.write("  REF=%s\n"%record.REF)
+                #sys.stderr.write("  Refseq=%s\n"%refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)])
+                continue # skip this record
     		# Modify ID
-    		record.ID = GetTRRecordID(record)
+            record.ID = GetTRRecordID(record)
     		# Write to file
-    		writer.write_record(record)
+            writer.write_record(record)
 
     reader.close()
     writer.close()
 
+
+    # Run bash script to convert to bref3
+    cmd = "bash convert_to_bref3.sh {filename}".format(filename=args.out)
+    output = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE).stdout.read()
+    print(output.decode("utf-8"))
+
 if __name__ == "__main__":
     run()
\ No newline at end of file

From 08d52a2ac8aff77ee45f8c46021e365d5b5ffe5c Mon Sep 17 00:00:00 2001
From: nichole <nicholema621@gmail.com>
Date: Tue, 6 Aug 2024 10:51:59 -0700
Subject: [PATCH 03/27] add script to download hg38 ref panel

---
 scripts/fix-ref/download.sh | 8 ++++++++
 1 file changed, 8 insertions(+)
 create mode 100644 scripts/fix-ref/download.sh

diff --git a/scripts/fix-ref/download.sh b/scripts/fix-ref/download.sh
new file mode 100644
index 0000000..f9ed154
--- /dev/null
+++ b/scripts/fix-ref/download.sh
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#download and index hg38 ref panel
+wget https://storage.googleapis.com/genomics-public-data/resources/broad/hg38/v0/Homo_sapiens_assembly38.fasta
+samtools faidx Homo_sapiens_assembly38.fasta
+
+#download bref3.jar file
+wget  https://faculty.washington.edu/browning/beagle/bref3.27May24.118.jar 
\ No newline at end of file

From f963e562113f07ea57430c572c62fc8b9ed81317 Mon Sep 17 00:00:00 2001
From: nichole <nicholema621@gmail.com>
Date: Tue, 6 Aug 2024 12:01:39 -0700
Subject: [PATCH 04/27] fix bug

---
 scripts/fix-ref/convert_to_bref3.sh | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/scripts/fix-ref/convert_to_bref3.sh b/scripts/fix-ref/convert_to_bref3.sh
index e6fa514..0826682 100644
--- a/scripts/fix-ref/convert_to_bref3.sh
+++ b/scripts/fix-ref/convert_to_bref3.sh
@@ -21,8 +21,7 @@ fi
 
 #convert vcf to bref3
 echo "converting vcf to bref3 format"
-#zcat ${ref}.vcf.gz | java -jar $bref > ${ref}.bref3
-zcat ${ref}.vcf.gz 
+zcat ${ref}.vcf.gz | java -jar $bref > ${ref}.bref3
 echo "Done converting"
 
  
\ No newline at end of file

From 2e93e6420d249808288bc840602f45d1ba928a4a Mon Sep 17 00:00:00 2001
From: nichole <nicholema621@gmail.com>
Date: Thu, 8 Aug 2024 10:20:05 -0700
Subject: [PATCH 05/27] add INFO field VT=OTHER/TR

---
 scripts/fix-ref/convert_to_bref3.sh                | 2 +-
 scripts/fix-ref/fix_ensembletr_snpstr_reference.py | 5 ++++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/scripts/fix-ref/convert_to_bref3.sh b/scripts/fix-ref/convert_to_bref3.sh
index 0826682..63e0d96 100644
--- a/scripts/fix-ref/convert_to_bref3.sh
+++ b/scripts/fix-ref/convert_to_bref3.sh
@@ -21,7 +21,7 @@ fi
 
 #convert vcf to bref3
 echo "converting vcf to bref3 format"
-zcat ${ref}.vcf.gz | java -jar $bref > ${ref}.bref3
+zcat < ${ref}.vcf.gz | java -jar $bref > ${ref}.bref3
 echo "Done converting"
 
  
\ No newline at end of file
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index f4b9790..017bc74 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -49,7 +49,8 @@ def main(args):
     refgenome = pyfaidx.Fasta(args.ref)
 
     # Set up writer, adding the missing header
-    reader.add_to_header("##command=hipstr;note this is a dummy header line")
+    reader.add_to_header('##command=hipstr;note this is a dummy header line')
+    reader.add_to_header('##INFO=<ID=VT,Number=1,Type=String,Description="Type of variant">')
     writer = cyvcf2.Writer(args.out + ".vcf", reader)
 
     # Go through each record
@@ -63,6 +64,7 @@ def main(args):
         if args.max_records > 0 and num_records_processed > args.max_records:
             break # for debug
         if not IsTRRecord(record.ID):
+            record.INFO["VT"] = "OTHER"
             writer.write_record(record)
         else:
     		# Check reference
@@ -75,6 +77,7 @@ def main(args):
                 continue # skip this record
     		# Modify ID
             record.ID = GetTRRecordID(record)
+            record.INFO["VT"] =  "TR"
     		# Write to file
             writer.write_record(record)
 

From f93bab68dafb38bba4c95e9ca14a196da00acdb9 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MacBook-Pro-2.local>
Date: Wed, 14 Aug 2024 12:30:26 -0700
Subject: [PATCH 06/27] updating how we get locus IDs to accommodate duplicates

---
 scripts/fix-ref/README.md                     | 21 +++----
 .../fix_ensembletr_snpstr_reference.py        | 58 +++++++++++--------
 2 files changed, 42 insertions(+), 37 deletions(-)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index 1dc7e2a..e9cdfc3 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -1,15 +1,14 @@
 # Clean up the EnsembleTR SNP-TR reference panel
 
-TODO:
-* Remove duplicate records and those with incorrect reference allele
-* Add required header line
-* Add informative variant IDs to STRs
-* Run script to add beagle info
-* Release bref versions alongside the VCFs
-
 ## Step 1: Fix reference VCF files
 
+This step:
+* Removes records with incorrect reference allele
+* Adds required header line for TRTools
+* Adds informative variant IDs to STRs
+
 ```
+# Test on chr11
 chrom=11
 ./fix_ensembletr_snpstr_reference.py \
 	--vcf chr${chrom}_final_SNP_merged_additional_TRs.vcf.gz \
@@ -17,13 +16,7 @@ chrom=11
 	--out ensembletr_refpanel_v3_chr${chrom}
 ```
 
-## Step 2: Add beagle info
-
-```
-TODO
-```
-
-## Step 3: Convert to bref
+## Step 2: Convert to bref
 
 ```
 TODO
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 0259ac9..8723d9e 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -9,16 +9,26 @@
 import pyfaidx
 import sys
 
+MAX_ALLOWED_DUPS = 1000
+
 def IsTRRecord(record_id):
-	return record_id is None or record_id.strip() == "."
+    return record_id is None or record_id.strip() == "."
 
-def GetTRRecordID(record):
-	return "EnsTR:%s:%s"%(record.CHROM, record.POS)
+def GetTRRecordID(record, allids):
+    locid = "EnsTR:%s:%s"%(record.CHROM, record.POS)
+    if locid not in allids:
+        return locid
+    for i in range(1, MAX_ALLOWED_DUPS):
+        newlocid = "%s-%s"%(locid, i)
+        if newlocid not in allids:
+            sys.stderr.write("Adding duplicate locus %s\n"%newlocid)
+            return newlocid
+    raise ValueError("Error: too many duplicates of %s"%locid)
 
 def CheckReference(record, refgenome):
-	# REF in VCF should match what is in the reference genome
-	refseq = refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)]
-	return (refseq == record.REF)
+    # REF in VCF should match what is in the reference genome
+    refseq = refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)]
+    return (refseq == record.REF)
 
 def run():
     args = getargs()
@@ -34,7 +44,7 @@ def getargs(): # pragma: no cover
     parser.add_argument("--ref", help="Reference fasta file", type=str, required=True)
     parser.add_argument("--out", help="Prefix for output VCF file", type=str, required=True)
     parser.add_argument("--max-records", help="Quit after processing this many records (for debug)", \
-    	default=-1, type=int)
+        default=-1, type=int)
     args = parser.parse_args()
     return args
 
@@ -53,24 +63,26 @@ def main(args):
     # If SNP: just print it
     # if STR: filter records with incorrect reference,
     #   and modify ID
+    allids = set()
     num_records_processed = 0
     for record in reader:
-    	num_records_processed += 1
-    	if args.max_records > 0 and num_records_processed > args.max_records:
-    		break # for debug
-    	if not IsTRRecord(record.ID):
-    		writer.write_record(record)
-    	else:
-    		# Check reference
-    		if not CheckReference(record, refgenome):
-    			sys.stderr.write("Skipping record %s:%s:%s, bad ref sequence\n"%(record.ID,record.CHROM,record.POS))
-    			sys.stderr.write("  REF=%s\n"%record.REF)
-    			sys.stderr.write("  Refseq=%s\n"%refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)])
-    			continue # skip this record
-    		# Modify ID
-    		record.ID = GetTRRecordID(record)
-    		# Write to file
-    		writer.write_record(record)
+        num_records_processed += 1
+        if args.max_records > 0 and num_records_processed > args.max_records:
+            break # for debug
+        if not IsTRRecord(record.ID):
+            writer.write_record(record)
+        else:
+            # Check reference
+            if not CheckReference(record, refgenome):
+                sys.stderr.write("Skipping record %s:%s:%s, bad ref sequence\n"%(record.ID,record.CHROM,record.POS))
+                sys.stderr.write("  REF=%s\n"%record.REF)
+                sys.stderr.write("  Refseq=%s\n"%refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)])
+                continue # skip this record
+            # Modify ID
+            record.ID = GetTRRecordID(record, allids)
+            allids.add(record.ID)
+            # Write to file
+            writer.write_record(record)
 
     reader.close()
     writer.close()

From fd3daa6ba1abedb284bc5e182b166701fcb3066c Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Fri, 30 Aug 2024 21:21:35 -0700
Subject: [PATCH 07/27] checks to remove loci with too many or too few alleles

---
 scripts/fix-ref/README.md                          |  3 ++-
 scripts/fix-ref/fix_ensembletr_snpstr_reference.py | 12 ++++++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index e9cdfc3..a1d8713 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -13,7 +13,8 @@ chrom=11
 ./fix_ensembletr_snpstr_reference.py \
 	--vcf chr${chrom}_final_SNP_merged_additional_TRs.vcf.gz \
 	--ref Homo_sapiens_assembly38.fasta \
-	--out ensembletr_refpanel_v3_chr${chrom}
+	--out ensembletr_refpanel_v3_chr${chrom} \
+	--max-alleles 50 --min-alleles 2
 ```
 
 ## Step 2: Convert to bref
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 43432c5..86212ac 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -46,6 +46,8 @@ def getargs(): # pragma: no cover
     parser.add_argument("--vcf", help="Input SNP/TR VCF file", type=str, required=True)
     parser.add_argument("--ref", help="Reference fasta file", type=str, required=True)
     parser.add_argument("--out", help="Prefix for output VCF file", type=str, required=True)
+    parser.add_argument("--max-alleles", help="Ignore loci with more than this many alleles", type=int, default=-1)
+    parser.add_argument("--min-alleles", help="Ignore loci with fewer than this many alleles", type=int, default=-1)
     parser.add_argument("--max-records", help="Quit after processing this many records (for debug)", \
         default=-1, type=int)
     args = parser.parse_args()
@@ -80,6 +82,16 @@ def main(args):
     		# Check reference
             if not CheckReference(record, refgenome):
                 continue # skip this record
+            # Check if too many alleles
+            if args.max_alleles != -1 and (1+len(record.ALT)) > args.max_alleles:
+                sys.stderr.write("Skipping {}:{} with {} ALT alleles\n".format(record.CHROM, record.POS, len(record.ALT)))
+                continue 
+            # Check if too few alleles
+            # Include cases where there is an ALT listed but the AF is 0
+            if (args.min_alleles != -1 and (1+len(record.ALT)) < args.min_alleles) or \
+                (record.INFO["AF"]==0):
+                sys.stderr.write("Skipping {}:{} with {} ALT alleles, AF={}\n".format(record.CHROM, record.POS, len(record.ALT), str(record.INFO["AF"])))
+                continue
     		# Modify ID
             record.ID = GetTRRecordID(record, allids)
             allids.add(record.ID)

From 017c688211a30d115200039d8d05fa4acc444995 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Sat, 31 Aug 2024 08:52:16 -0700
Subject: [PATCH 08/27] update readme with description of fixes

---
 scripts/fix-ref/README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index a1d8713..c30e894 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -6,6 +6,8 @@ This step:
 * Removes records with incorrect reference allele
 * Adds required header line for TRTools
 * Adds informative variant IDs to STRs
+* Remove loci with too many or too few alleles
+* Remove loci with AF=0
 
 ```
 # Test on chr11

From 4b376113e9033d910c78e5c1cb563d9b516b954c Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MacBook-Pro-2.local>
Date: Fri, 6 Sep 2024 08:29:46 -0700
Subject: [PATCH 09/27] updating print statements in fix ref script

---
 .../fix_ensembletr_snpstr_reference.py        | 25 +++++++++++--------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 86212ac..43e7799 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -2,6 +2,8 @@
 
 """
 Script to clean up SNP/TR reference haplotype panels
+
+TODO: remove alleles with AC=0
 """
 
 import argparse
@@ -18,15 +20,15 @@ def IsTRRecord(record_id):
     return record_id is None or record_id.strip() == "."
 
 def GetTRRecordID(record, allids):
-    locid = "EnsTR:%s:%s"%(record.CHROM, record.POS)
+    locid = "EnsTR:{chrom}:{pos}"%.format(chrom=record.CHROM, pos=record.POS)
     if locid not in allids:
         return locid
     for i in range(1, MAX_ALLOWED_DUPS):
-        newlocid = "%s-%s"%(locid, i)
+        newlocid = "{locid}:{i}"
         if newlocid not in allids:
-            sys.stderr.write("Adding duplicate locus %s\n"%newlocid)
+            sys.stderr.write("Adding duplicate locus {newlocid}\n")
             return newlocid
-    raise ValueError("Error: too many duplicates of %s"%locid)
+    raise ValueError("Error: too many duplicates of {locid}")
 
 def CheckReference(record, refgenome):
     # REF in VCF should match what is in the reference genome
@@ -82,15 +84,20 @@ def main(args):
     		# Check reference
             if not CheckReference(record, refgenome):
                 continue # skip this record
+            # TODO - remove alleles with AF=0
             # Check if too many alleles
             if args.max_alleles != -1 and (1+len(record.ALT)) > args.max_alleles:
-                sys.stderr.write("Skipping {}:{} with {} ALT alleles\n".format(record.CHROM, record.POS, len(record.ALT)))
+                sys.stderr.write("Skipping {chrom}:{pos} with {numalt} ALT alleles\n".format(
+                    chrom=record.CHROM, pos=record.POS, numalt=len(record.ALT))
+                )
                 continue 
             # Check if too few alleles
             # Include cases where there is an ALT listed but the AF is 0
             if (args.min_alleles != -1 and (1+len(record.ALT)) < args.min_alleles) or \
                 (record.INFO["AF"]==0):
-                sys.stderr.write("Skipping {}:{} with {} ALT alleles, AF={}\n".format(record.CHROM, record.POS, len(record.ALT), str(record.INFO["AF"])))
+                sys.stderr.write("Skipping {chrom}:{pos} with {numalt} ALT alleles, AF={alleles}\n".format(
+                    chrom=record.CHROM, pos=record.POS, numalt=len(record.ALT), alleles=str(record.INFO["AF"]))
+                )
                 continue
     		# Modify ID
             record.ID = GetTRRecordID(record, allids)
@@ -101,11 +108,7 @@ def main(args):
 
     reader.close()
     writer.close()
-
-    # Run bash script to convert to bref3
-    cmd = "bash convert_to_bref3.sh {filename}".format(filename=args.out)
-    output = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE).stdout.read()
-    print(output.decode("utf-8"))
+    sys.exit(0)
 
 if __name__ == "__main__":
     run()
\ No newline at end of file

From 9923347f36a7a24e9724b8a0a52c320c07d6e8e7 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@college9-169-233-125-37.resnet.ucsc.edu>
Date: Fri, 6 Sep 2024 12:12:13 -0700
Subject: [PATCH 10/27] overhaul of fixref script to remove alleles with
 count=0

---
 scripts/fix-ref/README.md                     |  10 +-
 .../fix_ensembletr_snpstr_reference.py        | 139 ++++++++++++++----
 2 files changed, 117 insertions(+), 32 deletions(-)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index c30e894..2dcc403 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -16,11 +16,15 @@ chrom=11
 	--vcf chr${chrom}_final_SNP_merged_additional_TRs.vcf.gz \
 	--ref Homo_sapiens_assembly38.fasta \
 	--out ensembletr_refpanel_v3_chr${chrom} \
-	--max-alleles 50 --min-alleles 2
+	--max-alleles 100 --min-alleles 2
+bgzip ensembletr_refpanel_v3_chr${chrom}.vcf.gz
+tabix -p vcf ensembletr_refpanel_v3_chr${chrom}.vcf.gz
 ```
 
 ## Step 2: Convert to bref
 
-```
-TODO
+wget https://faculty.washington.edu/browning/beagle/bref3.27May24.118.jar
+chrom=11
+zcat ensembletr_refpanel_v3_chr${chrom}.vcf.gz | \
+    java -jar bref3.27May24.118.jar > ensembletr_refpanel_v3_chr${chrom}.bref
 ```
\ No newline at end of file
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 43e7799..6a3adc1 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -2,8 +2,6 @@
 
 """
 Script to clean up SNP/TR reference haplotype panels
-
-TODO: remove alleles with AC=0
 """
 
 import argparse
@@ -12,26 +10,97 @@
 import sys
 import subprocess
 import os
-
+import tempfile
 
 MAX_ALLOWED_DUPS = 1000
 
+def GetWriter(fname, reader):
+    """
+    Get regular file writer, not cyvcf2.Writer
+    Since we are going to update INFO/FORMAT downstream
+    """
+    outf = open(fname, "w")
+    # Get header from reader, but remove DS/GP
+    header = reader.raw_header
+    for line in header.split("\n"):
+        if line.startswith("##FORMAT=<ID=DS,") or \
+            line.startswith("##FORMAT=<ID=GP,") or \
+            line.strip() == "":
+            continue
+        outf.write(line.strip() + "\n")
+    return outf
+
+def GetAlleleCounts(record):
+    """
+    Returns:
+    - allele_counts: dictionary of allele_string:allele_count
+    - allele_order: list of alleles, in same order as original 
+      but with those with AC=0 removed
+    """
+    alleles = [record.REF] + record.ALT
+    all_allele_calls = []
+    for genotype in record.genotypes:
+        all_allele_calls.append(alleles[genotype[0]])
+        all_allele_calls.append(alleles[genotype[1]])
+    allele_counts = {}
+    for a in alleles:
+        acount = all_allele_calls.count(a)
+        if acount > 0: allele_counts[a] = acount
+    # Keep order same as original
+    allele_order = [item for item in alleles if item in allele_counts.keys()]
+    return allele_counts, allele_order
+
+def WriteRecord(writer, record):
+    """simple function to write the record as is """
+    writer.write(str(record).strip()+"\n")
+
+def UpdateINFO(INFO, allele_counts, allele_order):
+    """
+    Keep INFO as is, except update AC/AF
+    """
+    info_items = []
+    for infokey in dict(INFO).keys():
+        if infokey in ["AC", "AF"]:
+            continue
+        else:
+            # Note all other INFO fields are single values
+            infoval = INFO.get(infokey)
+            info_items.append(f"{infokey}={infoval}")
+    # Add AC/AF
+    num_chroms = sum(allele_counts.values())
+    ac_vals = [allele_counts[a] for a in allele_order[1:]]
+    af_vals = [allele_counts[a]/num_chroms for a in allele_order[1:]]
+    info_items.append("AC=" + ",".join([str(item) for item in ac_vals]))
+    info_items.append("AF=" + ",".join(["%.4f"%item for item in af_vals]))
+    return ";".join(info_items)
+
+def GetGT(sample, orig_alleles, allele_order):
+    """Update the GT based on new allele order"""
+    if sample[2] == True:
+        sep = "|"
+    else: sep = "/"
+    a1 = allele_order.index(orig_alleles[sample[0]])
+    a2 = allele_order.index(orig_alleles[sample[1]])
+    return f"{a1}{sep}{a2}"
+
 def IsTRRecord(record_id):
+    """Check if the record is a TR"""
     return record_id is None or record_id.strip() == "."
 
 def GetTRRecordID(record, allids):
-    locid = "EnsTR:{chrom}:{pos}"%.format(chrom=record.CHROM, pos=record.POS)
+    """Get new uniquified record ID"""
+    locid = "EnsTR:{chrom}:{pos}".format(chrom=record.CHROM, pos=record.POS)
     if locid not in allids:
         return locid
     for i in range(1, MAX_ALLOWED_DUPS):
-        newlocid = "{locid}:{i}"
+        newlocid = f"{locid}:{i}"
         if newlocid not in allids:
-            sys.stderr.write("Adding duplicate locus {newlocid}\n")
+            sys.stderr.write(f"Adding duplicate locus {newlocid}\n")
             return newlocid
-    raise ValueError("Error: too many duplicates of {locid}")
+    raise ValueError(f"Error: too many duplicates of {locid}")
 
 def CheckReference(record, refgenome):
-    # REF in VCF should match what is in the reference genome
+    """ REF in VCF should match what is in the reference genome"""
     refseq = refgenome[record.CHROM][record.POS-1:record.POS-1+len(record.REF)]
     return (refseq == record.REF)
 
@@ -65,12 +134,14 @@ def main(args):
     # Set up writer, adding the missing header
     reader.add_to_header('##command=hipstr;note this is a dummy header line')
     reader.add_to_header('##INFO=<ID=VT,Number=1,Type=String,Description="Type of variant">')
-    writer = cyvcf2.Writer(args.out + ".vcf", reader)
+    writer = GetWriter(args.out + ".vcf", reader)
 
     # Go through each record
     # If SNP: just print it
-    # if STR: filter records with incorrect reference,
-    #   and modify ID
+    # if STR: (1) Filter records with incorrect reference
+    #         (2) Filter too many/too few alleles
+    #         (3) Modify record ID
+    #         (4) Write record, without DP/GS, with updated AF/AC and without AC=0
     allids = set()
     num_records_processed = 0
     for record in reader:
@@ -79,32 +150,42 @@ def main(args):
             break # for debug
         if not IsTRRecord(record.ID):
             record.INFO["VT"] = "OTHER"
-            writer.write_record(record)
+            WriteRecord(writer, record)
         else:
-    		# Check reference
+    		# (1) Filter records with incorrect reference
             if not CheckReference(record, refgenome):
                 continue # skip this record
-            # TODO - remove alleles with AF=0
-            # Check if too many alleles
-            if args.max_alleles != -1 and (1+len(record.ALT)) > args.max_alleles:
-                sys.stderr.write("Skipping {chrom}:{pos} with {numalt} ALT alleles\n".format(
-                    chrom=record.CHROM, pos=record.POS, numalt=len(record.ALT))
+
+            # (2) Filter too many/too few alleles
+            allele_order = [record.REF] + record.ALT
+            # Note: GetAlleleCounts() doesn't include things with AC=0
+            allele_counts, allele_order = GetAlleleCounts(record)
+            num_alleles = len(allele_counts.keys())
+            if args.max_alleles != -1 and num_alleles > args.max_alleles:
+                sys.stderr.write("Skipping {chrom}:{pos} with {num} alleles\n".format(
+                    chrom=record.CHROM, pos=record.POS, num=num_alleles)
                 )
-                continue 
-            # Check if too few alleles
-            # Include cases where there is an ALT listed but the AF is 0
-            if (args.min_alleles != -1 and (1+len(record.ALT)) < args.min_alleles) or \
-                (record.INFO["AF"]==0):
-                sys.stderr.write("Skipping {chrom}:{pos} with {numalt} ALT alleles, AF={alleles}\n".format(
-                    chrom=record.CHROM, pos=record.POS, numalt=len(record.ALT), alleles=str(record.INFO["AF"]))
+                continue # skip this record
+            if args.min_alleles != -1 and num_alleles < args.min_alleles:
+                sys.stderr.write("Skipping {chrom}:{pos} with {num} alleles\n".format(
+                    chrom=record.CHROM, pos=record.POS, num=num_alleles)
                 )
-                continue
-    		# Modify ID
+                continue # skip this record
+
+            # (3) Modify record ID
             record.ID = GetTRRecordID(record, allids)
             allids.add(record.ID)
             record.INFO["VT"] =  "TR"
-    		# Write to file
-            writer.write_record(record)
+
+            # (4) Write record to file, update AC/AF, only include GT, exclude AC=0
+            orig_alleles = [record.REF] + record.ALT
+            updated_info = UpdateINFO(record.INFO, allele_counts, allele_order)
+            out_items = [record.CHROM, record.POS, record.ID, \
+                allele_order[0], ",".join(allele_order[1:]), \
+                ".", "PASS", updated_info, "GT"]
+            for sample in record.genotypes:
+                out_items.append(GetGT(sample, orig_alleles, allele_order))
+            writer.write("\t".join([str(item) for item in out_items])+"\n")
 
     reader.close()
     writer.close()

From dbba8ab8b7b2560707d0276326d06306a93150c7 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@college9-169-233-125-37.resnet.ucsc.edu>
Date: Fri, 6 Sep 2024 12:12:48 -0700
Subject: [PATCH 11/27] remove convert to bref script

---
 scripts/fix-ref/convert_to_bref3.sh | 27 ---------------------------
 1 file changed, 27 deletions(-)
 delete mode 100644 scripts/fix-ref/convert_to_bref3.sh

diff --git a/scripts/fix-ref/convert_to_bref3.sh b/scripts/fix-ref/convert_to_bref3.sh
deleted file mode 100644
index 63e0d96..0000000
--- a/scripts/fix-ref/convert_to_bref3.sh
+++ /dev/null
@@ -1,27 +0,0 @@
-#!/bin/bash
-
-ref=$1
-bref="bref3.27May24.118.jar"
-
-
-
-#bgzip and index ref
-echo "bgzip and index ref"
-bgzip ${ref}.vcf
-tabix -p vcf ${ref}.vcf.gz
-
-#dowaload bref3.jar
-# Check if the file exists locally
-if [ ! -f "$bref" ]; then
-    echo "File does not exist. Downloading..."
-    wget https://faculty.washington.edu/browning/beagle/bref3.27May24.118.jar 
-else
-    echo "File already exists. Continuing..."
-fi
-
-#convert vcf to bref3
-echo "converting vcf to bref3 format"
-zcat < ${ref}.vcf.gz | java -jar $bref > ${ref}.bref3
-echo "Done converting"
-
- 
\ No newline at end of file

From ee145ec10afa844c6118418e97a3fe7e64d53309 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@college9-169-233-125-37.resnet.ucsc.edu>
Date: Fri, 6 Sep 2024 12:18:54 -0700
Subject: [PATCH 12/27] update to write to stdout so we can pipe to bgzip

---
 scripts/fix-ref/README.md                          | 4 +---
 scripts/fix-ref/fix_ensembletr_snpstr_reference.py | 6 ++++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index 2dcc403..5e96e64 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -15,9 +15,7 @@ chrom=11
 ./fix_ensembletr_snpstr_reference.py \
 	--vcf chr${chrom}_final_SNP_merged_additional_TRs.vcf.gz \
 	--ref Homo_sapiens_assembly38.fasta \
-	--out ensembletr_refpanel_v3_chr${chrom} \
-	--max-alleles 100 --min-alleles 2
-bgzip ensembletr_refpanel_v3_chr${chrom}.vcf.gz
+	--max-alleles 100 --min-alleles 2 | bgzip -c > ensembletr_refpanel_v3_chr${chrom}.vcf.gz
 tabix -p vcf ensembletr_refpanel_v3_chr${chrom}.vcf.gz
 ```
 
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 6a3adc1..92cd834 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -19,7 +19,9 @@ def GetWriter(fname, reader):
     Get regular file writer, not cyvcf2.Writer
     Since we are going to update INFO/FORMAT downstream
     """
-    outf = open(fname, "w")
+    if fname == "stdout.vcf":
+        outf = sys.stdout
+    else: outf = open(fname, "w")
     # Get header from reader, but remove DS/GP
     header = reader.raw_header
     for line in header.split("\n"):
@@ -116,7 +118,7 @@ def getargs(): # pragma: no cover
     parser = argparse.ArgumentParser(__doc__)
     parser.add_argument("--vcf", help="Input SNP/TR VCF file", type=str, required=True)
     parser.add_argument("--ref", help="Reference fasta file", type=str, required=True)
-    parser.add_argument("--out", help="Prefix for output VCF file", type=str, required=True)
+    parser.add_argument("--out", help="Prefix for output VCF file. or 'stdout' for standard output", type=str, default="stdout")
     parser.add_argument("--max-alleles", help="Ignore loci with more than this many alleles", type=int, default=-1)
     parser.add_argument("--min-alleles", help="Ignore loci with fewer than this many alleles", type=int, default=-1)
     parser.add_argument("--max-records", help="Quit after processing this many records (for debug)", \

From 403c1d7e07bc34d05e923e4d98e3516f48e7f959 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@college9-169-233-125-37.resnet.ucsc.edu>
Date: Fri, 6 Sep 2024 12:23:45 -0700
Subject: [PATCH 13/27] fix readme format issue

---
 scripts/fix-ref/README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index 5e96e64..6248aa2 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -21,6 +21,7 @@ tabix -p vcf ensembletr_refpanel_v3_chr${chrom}.vcf.gz
 
 ## Step 2: Convert to bref
 
+```
 wget https://faculty.washington.edu/browning/beagle/bref3.27May24.118.jar
 chrom=11
 zcat ensembletr_refpanel_v3_chr${chrom}.vcf.gz | \

From e76b3cd238cc9ef5e5630184946665770627bcfc Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@college9-169-233-125-37.resnet.ucsc.edu>
Date: Fri, 6 Sep 2024 12:24:30 -0700
Subject: [PATCH 14/27] fix readme format issue

---
 scripts/fix-ref/README.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index 6248aa2..c17e03c 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -6,8 +6,10 @@ This step:
 * Removes records with incorrect reference allele
 * Adds required header line for TRTools
 * Adds informative variant IDs to STRs
+* Adds VT field
 * Remove loci with too many or too few alleles
-* Remove loci with AF=0
+* Remove alleles with AF=0
+* Strip DS/GP fields
 
 ```
 # Test on chr11

From f1bcc576e99b8ff9d638e5059874ccaa40ce2b4c Mon Sep 17 00:00:00 2001
From: Yang_Li <yli091230@gmail.com>
Date: Mon, 9 Sep 2024 13:25:20 -0700
Subject: [PATCH 15/27] update the main README.md and make some changes on the
 fix_ensembletr_snpstr_reference.py

---
 README.md                                     | 10 +++++++
 .../fix_ensembletr_snpstr_reference.py        | 27 +++++++++++--------
 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index 9014d9a..8b0c686 100644
--- a/README.md
+++ b/README.md
@@ -211,6 +211,16 @@ https://ensemble-tr.s3.us-east-2.amazonaws.com/split/ensemble_chr"$chr"_filtered
 For version I of phased panels, please use 
 https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz.csi for tbi file.
 
+## Version III
+
+All files description and download links can be downloaded [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_3_readme.txt). The version III of EnsembleTR calls set fix the following issues:
+1. Remove TRs are not match the reference record.
+2. Remove TRs have more than 100 alleles.
+3. Remove TRs have less than 2 alleles.
+4. For each loci, remove alelles with 0 count. DS/GP field also been removed. 
+5. For TRs with the same POS, add the duplicate number of the TR following format: EnsTR:CHROM:POS:Duplicate_num. Add VT field. 
+6. Add the .bref format files.
+
 ## Notes on HipSTR input
 
 HipSTR might expand the coordinates of the repeat if there is a nearby SNP. If you have multiple HipSTR outputs from different individuals and want to use mergeSTR to merge them, please use our python script, *Hipstr_correction.py*, to correct the merged HipSTR VCF file ensuring that multiple records from the same repeat culminate in a single unified record.
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 92cd834..aea784a 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -146,6 +146,12 @@ def main(args):
     #         (4) Write record, without DP/GS, with updated AF/AC and without AC=0
     allids = set()
     num_records_processed = 0
+    num_snps_keeped = 0
+    num_strs_keeped = 0
+    num_str_failed_ref = 0
+    num_str_failed_max_allele = 0
+    num_str_failed_min_allele = 0
+
     for record in reader:
         num_records_processed += 1
         if args.max_records > 0 and num_records_processed > args.max_records:
@@ -153,32 +159,31 @@ def main(args):
         if not IsTRRecord(record.ID):
             record.INFO["VT"] = "OTHER"
             WriteRecord(writer, record)
+            num_snps_keeped += 1
         else:
     		# (1) Filter records with incorrect reference
             if not CheckReference(record, refgenome):
+                num_str_failed_ref += 1
                 continue # skip this record
 
             # (2) Filter too many/too few alleles
-            allele_order = [record.REF] + record.ALT
             # Note: GetAlleleCounts() doesn't include things with AC=0
             allele_counts, allele_order = GetAlleleCounts(record)
             num_alleles = len(allele_counts.keys())
             if args.max_alleles != -1 and num_alleles > args.max_alleles:
-                sys.stderr.write("Skipping {chrom}:{pos} with {num} alleles\n".format(
-                    chrom=record.CHROM, pos=record.POS, num=num_alleles)
-                )
+                num_str_failed_max_allele += 1
+                sys.stderr.write(f"Skipping {record.CHROM}:{record.POS} with {num_alleles} alleles\n")
                 continue # skip this record
             if args.min_alleles != -1 and num_alleles < args.min_alleles:
-                sys.stderr.write("Skipping {chrom}:{pos} with {num} alleles\n".format(
-                    chrom=record.CHROM, pos=record.POS, num=num_alleles)
-                )
+                num_str_failed_min_allele += 1
+                sys.stderr.write(f"Skipping {record.CHROM}:{record.POS} with {num_alleles} alleles\n")
                 continue # skip this record
 
             # (3) Modify record ID
             record.ID = GetTRRecordID(record, allids)
             allids.add(record.ID)
-            record.INFO["VT"] =  "TR"
-
+            record.INFO["VT"] = "TR"
+            num_strs_keeped += 1
             # (4) Write record to file, update AC/AF, only include GT, exclude AC=0
             orig_alleles = [record.REF] + record.ALT
             updated_info = UpdateINFO(record.INFO, allele_counts, allele_order)
@@ -188,10 +193,10 @@ def main(args):
             for sample in record.genotypes:
                 out_items.append(GetGT(sample, orig_alleles, allele_order))
             writer.write("\t".join([str(item) for item in out_items])+"\n")
-
+    sys.stdout.write(f"All {num_records_processed:,} records processed: keep {num_snps_keeped:,} snps, {num_strs_keeped:,} STRs; remove {num_str_failed_ref:,} STRs mismatch with reference, {num_str_failed_max_allele:,} STRs with more than {args.max_alleles:,} alleles, {num_str_failed_min_allele:,} STRs less than {args.min_alleles} alleles.\n")
     reader.close()
     writer.close()
     sys.exit(0)
 
 if __name__ == "__main__":
-    run()
\ No newline at end of file
+    run()

From 70d2b665bc777dd2f38086a2f8a2ccb27b34974e Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Mon, 9 Sep 2024 20:02:34 -0700
Subject: [PATCH 16/27] adding links to v3 panel

---
 README.md                      | 106 +++++++++++++--------------------
 archive_ensembletr_datasets.md |  89 +++++++++++++++++++++++++++
 2 files changed, 130 insertions(+), 65 deletions(-)
 create mode 100644 archive_ensembletr_datasets.md

diff --git a/README.md b/README.md
index 8b0c686..587da08 100644
--- a/README.md
+++ b/README.md
@@ -79,6 +79,10 @@ statSTR --vcf EnsembleTR_file.vcf.gz
         --out EnsembleTR_per_locus_allele_frequency
 ```
 
+# EnsembleTR data releases
+
+Archived datasets, including the Version II calls and Version II haplotype panel files can be found [here](archive_ensembletr_datasets.md).
+
 ## Version II of EnsembleTR calls on samples from 1000 Genomes Project and H3Africa
 
 Chromosome 1 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntrs/ensemble_chr1_filtered.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntrs/ensemble_chr1_filtered.vcf.gz.tbi)
@@ -125,101 +129,73 @@ Chromosome 21 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntr
 
 Chromosome 22 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntrs/ensemble_chr22_filtered.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntrs/ensemble_chr22_filtered.vcf.gz.tbi)
 
-## Version II of reference SNP+TR haplotype panel for imputation of TR variants
-
-### Dataset description
-
-[Phased variants](http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20220422_3202_phased_SNV_INDEL_SV/) of 3,202 samples from the 1000 Genomes Project (1kGP).
+## Version III of reference SNP+TR haplotype panel for imputation of TR variants
 
-TRs imputed from 3,202 1kGP samples.
+These files contain:
+* [Phased SNP and indel variants](http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20220422_3202_phased_SNV_INDEL_SV/) of 3,202 samples from the 1000 Genomes Project (1kGP).
+* TRs phased/imputed from 3,202 1kGP samples based on EnsembleTR calls.
 
-Total 70,692,015 variants + 1,091,550 TR markers.
+There are in total 1,070,698 TRs and 70,692,015 SNPs/indels.
 
 All the coordinates are based on **hg38** human reference genome.
 
-### Availability
-
-Chromosome 1 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-Chromosome 2 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-Chromosome 3 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-Chromosome 4 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+These files contain the same data as [Version II](archive_ensembletr_datasets.md), with the following updates to facilitate use in downstream imputation pipelines:
 
-Chromosome 5 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+1. Remove TRs for which the REF allele does not match the expected sequence based on CHR:POS
+2. For each TR, remove alelles with 0 count. 
+3. Remove TRs which have more than 100 alleles.
+4. Remove TRs which have less than 2 alleles.
+5. Remove the DS/GP fields which are large and not used by downstream steps.
+6. Add unique IDs for each TR of the format EnsTR:CHROM:POS. For TRs with the same CHR:POS, add the duplicate number of the TR following format: EnsTR:CHROM:POS:Duplicate_num.
+7. Add VT field, set to VT=TR for TRs and VT=OTHER for other variant types
+8. Add the .bref format files which have the same information as the VCFs but can improve Beagle imputation performance.
 
-Chromosome 6 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+All file description and download links can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_3_readme.txt). Data and links for each chromosome for the Verson III panel are also provided below. 
 
-Chromosome 7 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 1 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref) SNPs/indels=5,759,060 TRs=92,372
 
-Chromosome 8 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 2 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref) SNPs/indels=6,088,598 TRs=91,133
 
-Chromosome 9 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 3 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref) SNPs/indels=4,983,185 TRs=75,233
 
-Chromosome 10 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 4 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref) SNPs/indels=4,875,465 TRs=69,325
 
-Chromosome 11 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 5 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref) SNPs/indels=4,536,819 TRs=66,493
 
-Chromosome 12 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 6 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref) SNPs/indels=4,315,217 TRs=65,938
 
-Chromosome 13 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 7 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref) SNPs/indels=4,137,254 TRs=59,410
 
-Chromosome 14 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 8 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref) SNPs/indels=3,886,222 TRs=55,141
 
-Chromosome 15 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 9 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref) SNPs/indels=3,165,513 TRs=44,188
 
-Chromosome 16 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 10 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref) SNPs/indels=3,495,473 TRs=51,637
 
-Chromosome 17 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 11 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref) SNPs/indels=3,423,341 TRs=49,599
 
-Chromosome 18 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 12 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref) SNPs/indels=3,332,788 TRs=55,886
 
-Chromosome 19 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-Chromosome 20 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-Chromosome 21 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-Chromosome 22 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-### Usage
-
-Use [Beagle](https://faculty.washington.edu/browning/beagle/beagle.html) to impute TRs into SNP data:
-
-```
-java -Xmx4g -jar beagle.version.jar \
-            gt=SNPs.vcf.gz \
-            ref=${chrom}_final_SNP_merged.vcf.gz \
-            out=imputed_TR_SNPs
-```
+Chromosome 13 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref) SNPs/indels=2,509,179 TRs=35,720
 
-Please use the [version 5.4](https://github.com/gymreklab/1000Genomes-TR-Analysis/raw/main/phasing/validation/beagle.19Apr22.7c0.jar) for this analysis as we had issues with the newer versions of Beagle and we are right now communicating it with Beagle developers.
+Chromosome 14 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref) SNPs/indels=2,290,400 TRs=36,199
 
-## Additional resources
+Chromosome 15 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref) SNPs/indels=2,109,285 TRs=32,336
 
-Per locus summary statistics can be downloaded from [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/repeat_tables.zip). Each table has information on coordinates, repeat unit sequence, and potential overlap with genes listed in GENCODE v22 for repeats in EnsembleTR catalog.
+Chromosome 16 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref) SNPs/indels=2,362,361 TRs=35,451
 
-Population-specific per locus statistics on allele frequency, heterozygosity, and the number of called samples can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/afreq_tables.zip). Statistics are computed using statSTR from the TRTools package.
+Chromosome 17 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref) SNPs/indels=2,073,624 TRs=38,377
 
+Chromosome 18 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref) SNPs/indels=1,963,845 TRs=28,444
 
-## Version I
+Chromosome 19 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref) SNPs/indels=1,670,692 TRs=33,536
 
-For version I of EnsembleTR calls, please use 
-https://ensemble-tr.s3.us-east-2.amazonaws.com/split/ensemble_chr"$chr"_filtered.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/split/ensemble_chr"$chr"_filtered.vcf.gz.tbi for tbi file.
+Chromosome 20 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref) SNPs/indels=1,644,384 TRs=25,743
 
-For version I of phased panels, please use 
-https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz.csi for tbi file.
+Chromosome 21 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref) SNPs/indels=1,002,753 TRs=12,894
 
-## Version III
+Chromosome 22 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref) SNPs/indels=1,066,557 TRs=15,643
 
-All files description and download links can be downloaded [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_3_readme.txt). The version III of EnsembleTR calls set fix the following issues:
-1. Remove TRs are not match the reference record.
-2. Remove TRs have more than 100 alleles.
-3. Remove TRs have less than 2 alleles.
-4. For each loci, remove alelles with 0 count. DS/GP field also been removed. 
-5. For TRs with the same POS, add the duplicate number of the TR following format: EnsTR:CHROM:POS:Duplicate_num. Add VT field. 
-6. Add the .bref format files.
 
 ## Notes on HipSTR input
 
diff --git a/archive_ensembletr_datasets.md b/archive_ensembletr_datasets.md
new file mode 100644
index 0000000..a415a18
--- /dev/null
+++ b/archive_ensembletr_datasets.md
@@ -0,0 +1,89 @@
+# EnsembleTR archived datasets
+
+This page contains links to older versions of ensembleTR files
+
+## Version II of reference SNP+TR haplotype panel for imputation of TR variants
+
+### Dataset description
+
+[Phased variants](http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20220422_3202_phased_SNV_INDEL_SV/) of 3,202 samples from the 1000 Genomes Project (1kGP).
+
+TRs imputed from 3,202 1kGP samples.
+
+Total 70,692,015 variants + 1,091,550 TR markers.
+
+All the coordinates are based on **hg38** human reference genome.
+
+### Availability
+
+Chromosome 1 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 2 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 3 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 4 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 5 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 6 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 7 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 8 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 9 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 10 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 11 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 12 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 13 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 14 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 15 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 16 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 17 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 18 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 19 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 20 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 21 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 22 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+### Usage
+
+Use [Beagle](https://faculty.washington.edu/browning/beagle/beagle.html) to impute TRs into SNP data:
+
+```
+java -Xmx4g -jar beagle.version.jar \
+            gt=SNPs.vcf.gz \
+            ref=${chrom}_final_SNP_merged.vcf.gz \
+            out=imputed_TR_SNPs
+```
+
+Please use the [version 5.4](https://github.com/gymreklab/1000Genomes-TR-Analysis/raw/main/phasing/validation/beagle.19Apr22.7c0.jar) for this analysis as we had issues with the newer versions of Beagle and we are right now communicating it with Beagle developers.
+
+## Additional resources
+
+Per locus summary statistics can be downloaded from [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/repeat_tables.zip). Each table has information on coordinates, repeat unit sequence, and potential overlap with genes listed in GENCODE v22 for repeats in EnsembleTR catalog.
+
+Population-specific per locus statistics on allele frequency, heterozygosity, and the number of called samples can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/afreq_tables.zip). Statistics are computed using statSTR from the TRTools package.
+
+
+## Version I
+
+For version I of EnsembleTR calls, please use 
+https://ensemble-tr.s3.us-east-2.amazonaws.com/split/ensemble_chr"$chr"_filtered.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/split/ensemble_chr"$chr"_filtered.vcf.gz.tbi for tbi file.
+
+For version I of phased panels, please use 
+https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz.csi for tbi file.
\ No newline at end of file

From 510820f5c4fe6b9a6ffab80306bf2a6a990a914b Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Mon, 9 Sep 2024 20:03:40 -0700
Subject: [PATCH 17/27] adding links to v3 panel

---
 README.md                      | 6 ++++++
 archive_ensembletr_datasets.md | 7 -------
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 587da08..3db6cf8 100644
--- a/README.md
+++ b/README.md
@@ -196,6 +196,12 @@ Chromosome 21 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-re
 
 Chromosome 22 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref) SNPs/indels=1,066,557 TRs=15,643
 
+## Additional resources
+
+Per locus summary statistics can be downloaded from [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/repeat_tables.zip). Each table has information on coordinates, repeat unit sequence, and potential overlap with genes listed in GENCODE v22 for repeats in EnsembleTR catalog.
+
+Population-specific per locus statistics on allele frequency, heterozygosity, and the number of called samples can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/afreq_tables.zip). Statistics are computed using statSTR from the TRTools package.
+
 
 ## Notes on HipSTR input
 
diff --git a/archive_ensembletr_datasets.md b/archive_ensembletr_datasets.md
index a415a18..b511645 100644
--- a/archive_ensembletr_datasets.md
+++ b/archive_ensembletr_datasets.md
@@ -73,13 +73,6 @@ java -Xmx4g -jar beagle.version.jar \
 
 Please use the [version 5.4](https://github.com/gymreklab/1000Genomes-TR-Analysis/raw/main/phasing/validation/beagle.19Apr22.7c0.jar) for this analysis as we had issues with the newer versions of Beagle and we are right now communicating it with Beagle developers.
 
-## Additional resources
-
-Per locus summary statistics can be downloaded from [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/repeat_tables.zip). Each table has information on coordinates, repeat unit sequence, and potential overlap with genes listed in GENCODE v22 for repeats in EnsembleTR catalog.
-
-Population-specific per locus statistics on allele frequency, heterozygosity, and the number of called samples can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/afreq_tables.zip). Statistics are computed using statSTR from the TRTools package.
-
-
 ## Version I
 
 For version I of EnsembleTR calls, please use 

From 3503a58f6e1be17b0c2688fd4adf6ed36eff8e56 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Mon, 9 Sep 2024 20:09:56 -0700
Subject: [PATCH 18/27] adding links to v3 panel

---
 README.md | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/README.md b/README.md
index 3db6cf8..bd8bfb5 100644
--- a/README.md
+++ b/README.md
@@ -196,6 +196,19 @@ Chromosome 21 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-re
 
 Chromosome 22 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref) SNPs/indels=1,066,557 TRs=15,643
 
+### Usage
+
+Use [Beagle](https://faculty.washington.edu/browning/beagle/beagle.html) to impute TRs into SNP data:
+
+```
+java -Xmx4g -jar beagle.version.jar \
+            gt=SNPs_chr${chrom}.vcf.gz \
+            ref=ensembletr_refpanel_v3_chr${chrom}.bref \
+            out=imputed_TR_SNPs_chr${chrom}
+```
+
+We have tested this with Beagle jar file [beagle.27May24.118.jar](https://faculty.washington.edu/browning/beagle/beagle.27May24.118.jar). Earlier releases of Beagle 5.4 had problems imputing from this panel due to a file decompression issue.
+
 ## Additional resources
 
 Per locus summary statistics can be downloaded from [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/tables/repeat_tables.zip). Each table has information on coordinates, repeat unit sequence, and potential overlap with genes listed in GENCODE v22 for repeats in EnsembleTR catalog.

From b8fbefd28e933bcbb31db567f642858cdd73178f Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Mon, 9 Sep 2024 20:10:21 -0700
Subject: [PATCH 19/27] adding links to v3 panel

---
 archive_ensembletr_datasets.md | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/archive_ensembletr_datasets.md b/archive_ensembletr_datasets.md
index b511645..5716122 100644
--- a/archive_ensembletr_datasets.md
+++ b/archive_ensembletr_datasets.md
@@ -60,18 +60,6 @@ Chromosome 21 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/addition
 
 Chromosome 22 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-### Usage
-
-Use [Beagle](https://faculty.washington.edu/browning/beagle/beagle.html) to impute TRs into SNP data:
-
-```
-java -Xmx4g -jar beagle.version.jar \
-            gt=SNPs.vcf.gz \
-            ref=${chrom}_final_SNP_merged.vcf.gz \
-            out=imputed_TR_SNPs
-```
-
-Please use the [version 5.4](https://github.com/gymreklab/1000Genomes-TR-Analysis/raw/main/phasing/validation/beagle.19Apr22.7c0.jar) for this analysis as we had issues with the newer versions of Beagle and we are right now communicating it with Beagle developers.
 
 ## Version I
 

From 19cec77639233e7e949b74781c70be7c77aed709 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Mon, 9 Sep 2024 20:11:58 -0700
Subject: [PATCH 20/27] adding links to v3 panel

---
 archive_ensembletr_datasets.md | 45 +++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 23 deletions(-)

diff --git a/archive_ensembletr_datasets.md b/archive_ensembletr_datasets.md
index 5716122..29e2d5f 100644
--- a/archive_ensembletr_datasets.md
+++ b/archive_ensembletr_datasets.md
@@ -16,50 +16,49 @@ All the coordinates are based on **hg38** human reference genome.
 
 ### Availability
 
-Chromosome 1 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref)] SNPs/indels=5,759,060 TRs=92,372
 
-Chromosome 2 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref)] SNPs/indels=6,088,598 TRs=91,133
 
-Chromosome 3 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref)] SNPs/indels=4,983,185 TRs=75,233
 
-Chromosome 4 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref)] SNPs/indels=4,875,465 TRs=69,325
 
-Chromosome 5 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref)] SNPs/indels=4,536,819 TRs=66,493
 
-Chromosome 6 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref)] SNPs/indels=4,315,217 TRs=65,938
 
-Chromosome 7 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref)] SNPs/indels=4,137,254 TRs=59,410
 
-Chromosome 8 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref)] SNPs/indels=3,886,222 TRs=55,141
 
-Chromosome 9 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref)] SNPs/indels=3,165,513 TRs=44,188
 
-Chromosome 10 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref)] SNPs/indels=3,495,473 TRs=51,637
 
-Chromosome 11 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref)] SNPs/indels=3,423,341 TRs=49,599
 
-Chromosome 12 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref)] SNPs/indels=3,332,788 TRs=55,886
 
-Chromosome 13 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref)] SNPs/indels=2,509,179 TRs=35,720
 
-Chromosome 14 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref)] SNPs/indels=2,290,400 TRs=36,199
 
-Chromosome 15 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref)] SNPs/indels=2,109,285 TRs=32,336
 
-Chromosome 16 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref)] SNPs/indels=2,362,361 TRs=35,451
 
-Chromosome 17 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref)] SNPs/indels=2,073,624 TRs=38,377
 
-Chromosome 18 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref)] SNPs/indels=1,963,845 TRs=28,444
 
-Chromosome 19 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref)] SNPs/indels=1,670,692 TRs=33,536
 
-Chromosome 20 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref)] SNPs/indels=1,644,384 TRs=25,743
 
-Chromosome 21 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz.tbi)
-
-Chromosome 22 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref)] SNPs/indels=1,002,753 TRs=12,894
 
+Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref)] SNPs/indels=1,066,557 TRs=15,643
 
 ## Version I
 

From 507e4c99ed4ea19badf0c244f358696410b8b202 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Mon, 9 Sep 2024 20:13:10 -0700
Subject: [PATCH 21/27] adding links to v3 panel

---
 README.md                      | 44 ++++++++++++++++-----------------
 archive_ensembletr_datasets.md | 45 +++++++++++++++++-----------------
 2 files changed, 45 insertions(+), 44 deletions(-)

diff --git a/README.md b/README.md
index bd8bfb5..58541a0 100644
--- a/README.md
+++ b/README.md
@@ -152,49 +152,49 @@ These files contain the same data as [Version II](archive_ensembletr_datasets.md
 
 All file description and download links can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_3_readme.txt). Data and links for each chromosome for the Verson III panel are also provided below. 
 
-Chromosome 1 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref) SNPs/indels=5,759,060 TRs=92,372
+Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref)] SNPs/indels=5,759,060 TRs=92,372
 
-Chromosome 2 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref) SNPs/indels=6,088,598 TRs=91,133
+Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref)] SNPs/indels=6,088,598 TRs=91,133
 
-Chromosome 3 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref) SNPs/indels=4,983,185 TRs=75,233
+Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref)] SNPs/indels=4,983,185 TRs=75,233
 
-Chromosome 4 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref) SNPs/indels=4,875,465 TRs=69,325
+Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref)] SNPs/indels=4,875,465 TRs=69,325
 
-Chromosome 5 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref) SNPs/indels=4,536,819 TRs=66,493
+Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref)] SNPs/indels=4,536,819 TRs=66,493
 
-Chromosome 6 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref) SNPs/indels=4,315,217 TRs=65,938
+Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref)] SNPs/indels=4,315,217 TRs=65,938
 
-Chromosome 7 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref) SNPs/indels=4,137,254 TRs=59,410
+Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref)] SNPs/indels=4,137,254 TRs=59,410
 
-Chromosome 8 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref) SNPs/indels=3,886,222 TRs=55,141
+Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref)] SNPs/indels=3,886,222 TRs=55,141
 
-Chromosome 9 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref) SNPs/indels=3,165,513 TRs=44,188
+Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref)] SNPs/indels=3,165,513 TRs=44,188
 
-Chromosome 10 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref) SNPs/indels=3,495,473 TRs=51,637
+Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref)] SNPs/indels=3,495,473 TRs=51,637
 
-Chromosome 11 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref) SNPs/indels=3,423,341 TRs=49,599
+Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref)] SNPs/indels=3,423,341 TRs=49,599
 
-Chromosome 12 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref) SNPs/indels=3,332,788 TRs=55,886
+Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref)] SNPs/indels=3,332,788 TRs=55,886
 
-Chromosome 13 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref) SNPs/indels=2,509,179 TRs=35,720
+Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref)] SNPs/indels=2,509,179 TRs=35,720
 
-Chromosome 14 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref) SNPs/indels=2,290,400 TRs=36,199
+Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref)] SNPs/indels=2,290,400 TRs=36,199
 
-Chromosome 15 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref) SNPs/indels=2,109,285 TRs=32,336
+Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref)] SNPs/indels=2,109,285 TRs=32,336
 
-Chromosome 16 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref) SNPs/indels=2,362,361 TRs=35,451
+Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref)] SNPs/indels=2,362,361 TRs=35,451
 
-Chromosome 17 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref) SNPs/indels=2,073,624 TRs=38,377
+Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref)] SNPs/indels=2,073,624 TRs=38,377
 
-Chromosome 18 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref) SNPs/indels=1,963,845 TRs=28,444
+Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref)] SNPs/indels=1,963,845 TRs=28,444
 
-Chromosome 19 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref) SNPs/indels=1,670,692 TRs=33,536
+Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref)] SNPs/indels=1,670,692 TRs=33,536
 
-Chromosome 20 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref) SNPs/indels=1,644,384 TRs=25,743
+Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref)] SNPs/indels=1,644,384 TRs=25,743
 
-Chromosome 21 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref) SNPs/indels=1,002,753 TRs=12,894
+Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref)] SNPs/indels=1,002,753 TRs=12,894
 
-Chromosome 22 [VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz) [tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi) [bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref) SNPs/indels=1,066,557 TRs=15,643
+Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref)] SNPs/indels=1,066,557 TRs=15,643
 
 ### Usage
 
diff --git a/archive_ensembletr_datasets.md b/archive_ensembletr_datasets.md
index 29e2d5f..5716122 100644
--- a/archive_ensembletr_datasets.md
+++ b/archive_ensembletr_datasets.md
@@ -16,49 +16,50 @@ All the coordinates are based on **hg38** human reference genome.
 
 ### Availability
 
-Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref)] SNPs/indels=5,759,060 TRs=92,372
+Chromosome 1 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr1_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref)] SNPs/indels=6,088,598 TRs=91,133
+Chromosome 2 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr2_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref)] SNPs/indels=4,983,185 TRs=75,233
+Chromosome 3 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr3_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref)] SNPs/indels=4,875,465 TRs=69,325
+Chromosome 4 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr4_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref)] SNPs/indels=4,536,819 TRs=66,493
+Chromosome 5 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr5_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref)] SNPs/indels=4,315,217 TRs=65,938
+Chromosome 6 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr6_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref)] SNPs/indels=4,137,254 TRs=59,410
+Chromosome 7 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr7_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref)] SNPs/indels=3,886,222 TRs=55,141
+Chromosome 8 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr8_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref)] SNPs/indels=3,165,513 TRs=44,188
+Chromosome 9 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr9_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref)] SNPs/indels=3,495,473 TRs=51,637
+Chromosome 10 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr10_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref)] SNPs/indels=3,423,341 TRs=49,599
+Chromosome 11 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr11_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref)] SNPs/indels=3,332,788 TRs=55,886
+Chromosome 12 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr12_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref)] SNPs/indels=2,509,179 TRs=35,720
+Chromosome 13 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr13_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref)] SNPs/indels=2,290,400 TRs=36,199
+Chromosome 14 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr14_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref)] SNPs/indels=2,109,285 TRs=32,336
+Chromosome 15 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr15_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref)] SNPs/indels=2,362,361 TRs=35,451
+Chromosome 16 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr16_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref)] SNPs/indels=2,073,624 TRs=38,377
+Chromosome 17 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr17_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref)] SNPs/indels=1,963,845 TRs=28,444
+Chromosome 18 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr18_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref)] SNPs/indels=1,670,692 TRs=33,536
+Chromosome 19 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr19_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref)] SNPs/indels=1,644,384 TRs=25,743
+Chromosome 20 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr20_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref)] SNPs/indels=1,002,753 TRs=12,894
+Chromosome 21 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr21_final_SNP_merged_additional_TRs.vcf.gz.tbi)
+
+Chromosome 22 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/additional-phased-trs/chr22_final_SNP_merged_additional_TRs.vcf.gz.tbi)
 
-Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref)] SNPs/indels=1,066,557 TRs=15,643
 
 ## Version I
 

From 24e1e61465a2dd91ff93fde35376f02b8f29a2b8 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MacBook-Pro-2.local>
Date: Mon, 23 Sep 2024 13:30:12 -0700
Subject: [PATCH 22/27] use bref3

---
 scripts/fix-ref/README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index c17e03c..6b50a4c 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -27,5 +27,5 @@ tabix -p vcf ensembletr_refpanel_v3_chr${chrom}.vcf.gz
 wget https://faculty.washington.edu/browning/beagle/bref3.27May24.118.jar
 chrom=11
 zcat ensembletr_refpanel_v3_chr${chrom}.vcf.gz | \
-    java -jar bref3.27May24.118.jar > ensembletr_refpanel_v3_chr${chrom}.bref
+    java -jar bref3.27May24.118.jar > ensembletr_refpanel_v3_chr${chrom}.bref3
 ```
\ No newline at end of file

From 4a469207173012bccc24fcf3a72766feebf70544 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MacBook-Pro-2.local>
Date: Tue, 24 Sep 2024 09:28:40 -0700
Subject: [PATCH 23/27] update fixref script to remove duplicates

---
 scripts/fix-ref/fix_ensembletr_snpstr_reference.py | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index aea784a..33c2ccd 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -141,10 +141,12 @@ def main(args):
     # Go through each record
     # If SNP: just print it
     # if STR: (1) Filter records with incorrect reference
-    #         (2) Filter too many/too few alleles
+    #         (2) Filter too many/too few alleles, plus remove if duplicate after that
+    #               (based on chr:pos:alleles)
     #         (3) Modify record ID
     #         (4) Write record, without DP/GS, with updated AF/AC and without AC=0
     allids = set()
+    allloci = set() # chrom:pos:ref:alt to keep track of duplicates
     num_records_processed = 0
     num_snps_keeped = 0
     num_strs_keeped = 0
@@ -178,12 +180,20 @@ def main(args):
                 num_str_failed_min_allele += 1
                 sys.stderr.write(f"Skipping {record.CHROM}:{record.POS} with {num_alleles} alleles\n")
                 continue # skip this record
+            # Check if duplicate
+            locinfo = f"{record.CHROM}:{record.POS}:"+",".join(allele_order)
+            if locinfo in allloci:
+                sys.stderr.write(f"Skipping duplicate {locinfo}\n")
+                continue
+            else:
+                allloci.add(locinfo)
 
             # (3) Modify record ID
             record.ID = GetTRRecordID(record, allids)
             allids.add(record.ID)
             record.INFO["VT"] = "TR"
             num_strs_keeped += 1
+
             # (4) Write record to file, update AC/AF, only include GT, exclude AC=0
             orig_alleles = [record.REF] + record.ALT
             updated_info = UpdateINFO(record.INFO, allele_counts, allele_order)
@@ -193,7 +203,7 @@ def main(args):
             for sample in record.genotypes:
                 out_items.append(GetGT(sample, orig_alleles, allele_order))
             writer.write("\t".join([str(item) for item in out_items])+"\n")
-    sys.stdout.write(f"All {num_records_processed:,} records processed: keep {num_snps_keeped:,} snps, {num_strs_keeped:,} STRs; remove {num_str_failed_ref:,} STRs mismatch with reference, {num_str_failed_max_allele:,} STRs with more than {args.max_alleles:,} alleles, {num_str_failed_min_allele:,} STRs less than {args.min_alleles} alleles.\n")
+    sys.stderr.write(f"All {num_records_processed:,} records processed: keep {num_snps_keeped:,} snps, {num_strs_keeped:,} STRs; remove {num_str_failed_ref:,} STRs mismatch with reference, {num_str_failed_max_allele:,} STRs with more than {args.max_alleles:,} alleles, {num_str_failed_min_allele:,} STRs less than {args.min_alleles} alleles.\n")
     reader.close()
     writer.close()
     sys.exit(0)

From 705af298cb8e146dd871daa27f688843d1ef3d05 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MacBook-Pro-2.local>
Date: Tue, 24 Sep 2024 16:29:57 -0700
Subject: [PATCH 24/27] document rm dups for fix-ref

---
 scripts/fix-ref/README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/scripts/fix-ref/README.md b/scripts/fix-ref/README.md
index 6b50a4c..4aecf60 100644
--- a/scripts/fix-ref/README.md
+++ b/scripts/fix-ref/README.md
@@ -9,6 +9,7 @@ This step:
 * Adds VT field
 * Remove loci with too many or too few alleles
 * Remove alleles with AF=0
+* Remove loci that have the same chr:pos:ref:alt after the above steps
 * Strip DS/GP fields
 
 ```

From 842b119c1b1446005756901f9c949438124b84b2 Mon Sep 17 00:00:00 2001
From: Yang_Li <yli091230@gmail.com>
Date: Thu, 26 Sep 2024 21:58:22 -0700
Subject: [PATCH 25/27] fix file name, remove duplicate loci and update README

---
 README.md                                     | 50 +++++++++----------
 .../fix_ensembletr_snpstr_reference.py        |  5 +-
 2 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/README.md b/README.md
index 58541a0..5881c7c 100644
--- a/README.md
+++ b/README.md
@@ -146,55 +146,55 @@ These files contain the same data as [Version II](archive_ensembletr_datasets.md
 3. Remove TRs which have more than 100 alleles.
 4. Remove TRs which have less than 2 alleles.
 5. Remove the DS/GP fields which are large and not used by downstream steps.
-6. Add unique IDs for each TR of the format EnsTR:CHROM:POS. For TRs with the same CHR:POS, add the duplicate number of the TR following format: EnsTR:CHROM:POS:Duplicate_num.
+6. Add unique IDs for each TR of the format EnsTR:CHROM:POS. For TRs with the same CHR:POS, add the duplicate number of the TR following format: EnsTR:CHROM:POS:Duplicate_num. Duplicated loci with identical alleles are removed.
 7. Add VT field, set to VT=TR for TRs and VT=OTHER for other variant types
-8. Add the .bref format files which have the same information as the VCFs but can improve Beagle imputation performance.
+8. Add the bref format files which have the same information as the VCFs but can improve Beagle imputation performance.
 
 All file description and download links can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_3_readme.txt). Data and links for each chromosome for the Verson III panel are also provided below. 
 
-Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref)] SNPs/indels=5,759,060 TRs=92,372
+Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref3)] SNPs/indels=5,759,060 TRs=92,372
 
-Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref)] SNPs/indels=6,088,598 TRs=91,133
+Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref3)] SNPs/indels=6,088,598 TRs=91,132
 
-Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref)] SNPs/indels=4,983,185 TRs=75,233
+Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref3)] SNPs/indels=4,983,185 TRs=75,233
 
-Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref)] SNPs/indels=4,875,465 TRs=69,325
+Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref3)] SNPs/indels=4,875,465 TRs=69,325
 
-Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref)] SNPs/indels=4,536,819 TRs=66,493
+Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref3)] SNPs/indels=4,536,819 TRs=66,492
 
-Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref)] SNPs/indels=4,315,217 TRs=65,938
+Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref3)] SNPs/indels=4,315,217 TRs=65,937
 
-Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref)] SNPs/indels=4,137,254 TRs=59,410
+Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref3)] SNPs/indels=4,137,254 TRs=59,409
 
-Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref)] SNPs/indels=3,886,222 TRs=55,141
+Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref3)] SNPs/indels=3,886,222 TRs=55,141
 
-Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref)] SNPs/indels=3,165,513 TRs=44,188
+Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref3)] SNPs/indels=3,165,513 TRs=44,188
 
-Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref)] SNPs/indels=3,495,473 TRs=51,637
+Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref3)] SNPs/indels=3,495,473 TRs=51,637
 
-Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref)] SNPs/indels=3,423,341 TRs=49,599
+Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref3)] SNPs/indels=3,423,341 TRs=49,598
 
-Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref)] SNPs/indels=3,332,788 TRs=55,886
+Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref3)] SNPs/indels=3,332,788 TRs=55,883
 
-Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref)] SNPs/indels=2,509,179 TRs=35,720
+Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref3)] SNPs/indels=2,509,179 TRs=35,720
 
-Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref)] SNPs/indels=2,290,400 TRs=36,199
+Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref3)] SNPs/indels=2,290,400 TRs=36,199
 
-Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref)] SNPs/indels=2,109,285 TRs=32,336
+Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref3)] SNPs/indels=2,109,285 TRs=32,336
 
-Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref)] SNPs/indels=2,362,361 TRs=35,451
+Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref3)] SNPs/indels=2,362,361 TRs=35,450
 
-Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref)] SNPs/indels=2,073,624 TRs=38,377
+Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref3)] SNPs/indels=2,073,624 TRs=38,377
 
-Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref)] SNPs/indels=1,963,845 TRs=28,444
+Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref3)] SNPs/indels=1,963,845 TRs=28,443
 
-Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref)] SNPs/indels=1,670,692 TRs=33,536
+Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref3)] SNPs/indels=1,670,692 TRs=33,535
 
-Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref)] SNPs/indels=1,644,384 TRs=25,743
+Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref3)] SNPs/indels=1,644,384 TRs=25,742
 
-Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref)] SNPs/indels=1,002,753 TRs=12,894
+Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref3)] SNPs/indels=1,002,753 TRs=12,893
 
-Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref)] SNPs/indels=1,066,557 TRs=15,643
+Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref3)] SNPs/indels=1,066,557 TRs=15,643
 
 ### Usage
 
@@ -203,7 +203,7 @@ Use [Beagle](https://faculty.washington.edu/browning/beagle/beagle.html) to impu
 ```
 java -Xmx4g -jar beagle.version.jar \
             gt=SNPs_chr${chrom}.vcf.gz \
-            ref=ensembletr_refpanel_v3_chr${chrom}.bref \
+            ref=ensembletr_refpanel_v3_chr${chrom}.bref3 \
             out=imputed_TR_SNPs_chr${chrom}
 ```
 
diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 33c2ccd..ccfa5e5 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -153,7 +153,7 @@ def main(args):
     num_str_failed_ref = 0
     num_str_failed_max_allele = 0
     num_str_failed_min_allele = 0
-
+    num_str_duplicated = 0
     for record in reader:
         num_records_processed += 1
         if args.max_records > 0 and num_records_processed > args.max_records:
@@ -184,6 +184,7 @@ def main(args):
             locinfo = f"{record.CHROM}:{record.POS}:"+",".join(allele_order)
             if locinfo in allloci:
                 sys.stderr.write(f"Skipping duplicate {locinfo}\n")
+                num_str_duplicated += 1
                 continue
             else:
                 allloci.add(locinfo)
@@ -203,7 +204,7 @@ def main(args):
             for sample in record.genotypes:
                 out_items.append(GetGT(sample, orig_alleles, allele_order))
             writer.write("\t".join([str(item) for item in out_items])+"\n")
-    sys.stderr.write(f"All {num_records_processed:,} records processed: keep {num_snps_keeped:,} snps, {num_strs_keeped:,} STRs; remove {num_str_failed_ref:,} STRs mismatch with reference, {num_str_failed_max_allele:,} STRs with more than {args.max_alleles:,} alleles, {num_str_failed_min_allele:,} STRs less than {args.min_alleles} alleles.\n")
+    sys.stderr.write(f"All {num_records_processed:,} records processed: keep {num_snps_keeped:,} snps, {num_strs_keeped:,} STRs; remove {num_str_failed_ref:,} STRs mismatch with reference, {num_str_failed_max_allele:,} STRs with more than {args.max_alleles:,} alleles, {num_str_failed_min_allele:,} STRs less than {args.min_alleles} alleles, {num_str_duplicated:,} duplicated STRs.\n")
     reader.close()
     writer.close()
     sys.exit(0)

From 94904c9fdaa78a8f50494a5ea0f26322b6766ab1 Mon Sep 17 00:00:00 2001
From: Melissa Gymrek <melissagymrek@Melissas-MBP-2.attlocal.net>
Date: Sun, 3 Nov 2024 12:58:03 -0800
Subject: [PATCH 26/27] fix issue with REF count 0 in fix ref script

---
 scripts/fix-ref/fix_ensembletr_snpstr_reference.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
index 33c2ccd..4461ae5 100755
--- a/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
+++ b/scripts/fix-ref/fix_ensembletr_snpstr_reference.py
@@ -47,7 +47,9 @@ def GetAlleleCounts(record):
     allele_counts = {}
     for a in alleles:
         acount = all_allele_calls.count(a)
-        if acount > 0: allele_counts[a] = acount
+        # Note: force REF to be in dict even if acount=0
+        if acount > 0 or a == record.REF:
+            allele_counts[a] = acount
     # Keep order same as original
     allele_order = [item for item in alleles if item in allele_counts.keys()]
     return allele_counts, allele_order

From ab3044bee36ce1edaf50c46bf75d2bd39b801912 Mon Sep 17 00:00:00 2001
From: Yang_Li <yli091230@gmail.com>
Date: Wed, 6 Nov 2024 14:20:43 -0800
Subject: [PATCH 27/27] fix the missing reference allele

---
 README.md                      | 57 ++++++++++++++-------------
 archive_ensembletr_datasets.md | 72 +++++++++++++++++++++++++++++++++-
 2 files changed, 100 insertions(+), 29 deletions(-)

diff --git a/README.md b/README.md
index 5881c7c..2193f78 100644
--- a/README.md
+++ b/README.md
@@ -81,7 +81,7 @@ statSTR --vcf EnsembleTR_file.vcf.gz
 
 # EnsembleTR data releases
 
-Archived datasets, including the Version II calls and Version II haplotype panel files can be found [here](archive_ensembletr_datasets.md).
+Archived datasets, including the Version II calls and other versions of haplotype panel files can be found [here](archive_ensembletr_datasets.md).
 
 ## Version II of EnsembleTR calls on samples from 1000 Genomes Project and H3Africa
 
@@ -129,20 +129,21 @@ Chromosome 21 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntr
 
 Chromosome 22 [VCF file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntrs/ensemble_chr22_filtered.vcf.gz) and [tbi file](https://ensemble-tr.s3.us-east-2.amazonaws.com/add-vntrs/ensemble_chr22_filtered.vcf.gz.tbi)
 
-## Version III of reference SNP+TR haplotype panel for imputation of TR variants
+## Version IV of reference SNP+TR haplotype panel for imputation of TR variants
 
 These files contain:
 * [Phased SNP and indel variants](http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20220422_3202_phased_SNV_INDEL_SV/) of 3,202 samples from the 1000 Genomes Project (1kGP).
 * TRs phased/imputed from 3,202 1kGP samples based on EnsembleTR calls.
 
-There are in total 1,070,698 TRs and 70,692,015 SNPs/indels.
+There are in total 1,070,762 TRs and 70,692,015 SNPs/indels.
 
 All the coordinates are based on **hg38** human reference genome.
 
 These files contain the same data as [Version II](archive_ensembletr_datasets.md), with the following updates to facilitate use in downstream imputation pipelines:
 
 1. Remove TRs for which the REF allele does not match the expected sequence based on CHR:POS
-2. For each TR, remove alelles with 0 count. 
+2. For each TR, remove alelles with 0 count.
+    * If reference allele have 0 count, keep the reference alleles.
 3. Remove TRs which have more than 100 alleles.
 4. Remove TRs which have less than 2 alleles.
 5. Remove the DS/GP fields which are large and not used by downstream steps.
@@ -150,51 +151,51 @@ These files contain the same data as [Version II](archive_ensembletr_datasets.md
 7. Add VT field, set to VT=TR for TRs and VT=OTHER for other variant types
 8. Add the bref format files which have the same information as the VCFs but can improve Beagle imputation performance.
 
-All file description and download links can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_3_readme.txt). Data and links for each chromosome for the Verson III panel are also provided below. 
+All file description and download links can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_4_readme.txt). Data and links for each chromosome for the Verson IV panel are also provided below. 
 
-Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref3)] SNPs/indels=5,759,060 TRs=92,372
+Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr1.bref3)] SNPs/indels=5,759,060 TRs=92,378
 
-Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref3)] SNPs/indels=6,088,598 TRs=91,132
+Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr2.bref3)] SNPs/indels=6,088,598 TRs=91,137
 
-Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref3)] SNPs/indels=4,983,185 TRs=75,233
+Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr3.bref3)] SNPs/indels=4,983,185 TRs=75,243
 
-Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref3)] SNPs/indels=4,875,465 TRs=69,325
+Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr4.bref3)] SNPs/indels=4,875,465 TRs=69,327
 
-Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref3)] SNPs/indels=4,536,819 TRs=66,492
+Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr5.bref3)] SNPs/indels=4,536,819 TRs=66,492
 
-Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref3)] SNPs/indels=4,315,217 TRs=65,937
+Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr6.bref3)] SNPs/indels=4,315,217 TRs=65,940
 
-Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref3)] SNPs/indels=4,137,254 TRs=59,409
+Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr7.bref3)] SNPs/indels=4,137,254 TRs=59,422
 
-Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref3)] SNPs/indels=3,886,222 TRs=55,141
+Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr8.bref3)] SNPs/indels=3,886,222 TRs=55,144
 
-Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref3)] SNPs/indels=3,165,513 TRs=44,188
+Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr9.bref3)] SNPs/indels=3,165,513 TRs=44,189
 
-Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref3)] SNPs/indels=3,495,473 TRs=51,637
+Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr10.bref3)] SNPs/indels=3,495,473 TRs=51,640
 
-Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref3)] SNPs/indels=3,423,341 TRs=49,598
+Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr11.bref3)] SNPs/indels=3,423,341 TRs=49,603
 
-Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref3)] SNPs/indels=3,332,788 TRs=55,883
+Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr12.bref3)] SNPs/indels=3,332,788 TRs=55,887
 
-Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref3)] SNPs/indels=2,509,179 TRs=35,720
+Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr13.bref3)] SNPs/indels=2,509,179 TRs=35,720
 
-Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref3)] SNPs/indels=2,290,400 TRs=36,199
+Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr14.bref3)] SNPs/indels=2,290,400 TRs=36,203
 
-Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref3)] SNPs/indels=2,109,285 TRs=32,336
+Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr15.bref3)] SNPs/indels=2,109,285 TRs=32,338
 
-Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref3)] SNPs/indels=2,362,361 TRs=35,450
+Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr16.bref3)] SNPs/indels=2,362,361 TRs=35,452
 
-Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref3)] SNPs/indels=2,073,624 TRs=38,377
+Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr17.bref3)] SNPs/indels=2,073,624 TRs=38,382
 
-Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref3)] SNPs/indels=1,963,845 TRs=28,443
+Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr18.bref3)] SNPs/indels=1,963,845 TRs=28,446
 
-Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref3)] SNPs/indels=1,670,692 TRs=33,535
+Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr19.bref3)] SNPs/indels=1,670,692 TRs=33,536
 
-Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref3)] SNPs/indels=1,644,384 TRs=25,742
+Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr20.bref3)] SNPs/indels=1,644,384 TRs=25,745
 
-Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref3)] SNPs/indels=1,002,753 TRs=12,893
+Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr21.bref3)] SNPs/indels=1,002,753 TRs=12,894
 
-Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref3)] SNPs/indels=1,066,557 TRs=15,643
+Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v4/ensembletr_refpanel_v4_chr22.bref3)] SNPs/indels=1,066,557 TRs=15,644
 
 ### Usage
 
@@ -203,7 +204,7 @@ Use [Beagle](https://faculty.washington.edu/browning/beagle/beagle.html) to impu
 ```
 java -Xmx4g -jar beagle.version.jar \
             gt=SNPs_chr${chrom}.vcf.gz \
-            ref=ensembletr_refpanel_v3_chr${chrom}.bref3 \
+            ref=ensembletr_refpanel_v4_chr${chrom}.bref3 \
             out=imputed_TR_SNPs_chr${chrom}
 ```
 
diff --git a/archive_ensembletr_datasets.md b/archive_ensembletr_datasets.md
index 5716122..7ba0f65 100644
--- a/archive_ensembletr_datasets.md
+++ b/archive_ensembletr_datasets.md
@@ -2,6 +2,76 @@
 
 This page contains links to older versions of ensembleTR files
 
+## Version III of reference SNP+TR haplotype panel for imputation of TR variants
+
+### Dataset description
+These files contain:
+* [Phased SNP and indel variants](http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20220422_3202_phased_SNV_INDEL_SV/) of 3,202 samples from the 1000 Genomes Project (1kGP).
+* TRs phased/imputed from 3,202 1kGP samples based on EnsembleTR calls.
+
+There are in total 1,070,685 TRs and 70,692,015 SNPs/indels.
+
+All the coordinates are based on **hg38** human reference genome.
+
+These files contain the same data as [Version II](archive_ensembletr_datasets.md), with the following updates to facilitate use in downstream imputation pipelines:
+
+1. Remove TRs for which the REF allele does not match the expected sequence based on CHR:POS
+2. For each TR, remove alelles with 0 count.
+3. Remove TRs which have more than 100 alleles.
+4. Remove TRs which have less than 2 alleles.
+5. Remove the DS/GP fields which are large and not used by downstream steps.
+6. Add unique IDs for each TR of the format EnsTR:CHROM:POS. For TRs with the same CHR:POS, add the duplicate number of the TR following format: EnsTR:CHROM:POS:Duplicate_num. Duplicated loci with identical alleles are removed.
+7. Add VT field, set to VT=TR for TRs and VT=OTHER for other variant types
+8. Add the bref format files which have the same information as the VCFs but can improve Beagle imputation performance.
+
+### Availability
+
+All file description and download links can be found [here](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_3_readme.txt). Data and links for each chromosome for the Verson IV panel are also provided below.
+
+Chromosome 1 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr1.bref3)] SNPs/indels=5,759,060 TRs=92,372
+
+Chromosome 2 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr2.bref3)] SNPs/indels=6,088,598 TRs=91,132
+
+Chromosome 3 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr3.bref3)] SNPs/indels=4,983,185 TRs=75,233
+
+Chromosome 4 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr4.bref3)] SNPs/indels=4,875,465 TRs=69,325
+
+Chromosome 5 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr5.bref3)] SNPs/indels=4,536,819 TRs=66,492
+
+Chromosome 6 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr6.bref3)] SNPs/indels=4,315,217 TRs=65,937
+
+Chromosome 7 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr7.bref3)] SNPs/indels=4,137,254 TRs=59,409
+
+Chromosome 8 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr8.bref3)] SNPs/indels=3,886,222 TRs=55,141
+
+Chromosome 9 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr9.bref3)] SNPs/indels=3,165,513 TRs=44,188
+
+Chromosome 10 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr10.bref3)] SNPs/indels=3,495,473 TRs=51,637
+
+Chromosome 11 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr11.bref3)] SNPs/indels=3,423,341 TRs=49,598
+
+Chromosome 12 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr12.bref3)] SNPs/indels=3,332,788 TRs=55,883
+
+Chromosome 13 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr13.bref3)] SNPs/indels=2,509,179 TRs=35,720
+
+Chromosome 14 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr14.bref3)] SNPs/indels=2,290,400 TRs=36,199
+
+Chromosome 15 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr15.bref3)] SNPs/indels=2,109,285 TRs=32,336
+
+Chromosome 16 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr16.bref3)] SNPs/indels=2,362,361 TRs=35,450
+
+Chromosome 17 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr17.bref3)] SNPs/indels=2,073,624 TRs=38,377
+
+Chromosome 18 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr18.bref3)] SNPs/indels=1,963,845 TRs=28,443
+
+Chromosome 19 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr19.bref3)] SNPs/indels=1,670,692 TRs=33,535
+
+Chromosome 20 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr20.bref3)] SNPs/indels=1,644,384 TRs=25,742
+
+Chromosome 21 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr21.bref3)] SNPs/indels=1,002,753 TRs=12,893
+
+Chromosome 22 [[VCF](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz)] [[tbi](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.vcf.gz.tbi)] [[bref](https://ensemble-tr.s3.us-east-2.amazonaws.com/ensembletr-refpanel-v3/ensembletr_refpanel_v3_chr22.bref3)] SNPs/indels=1,066,557 TRs=15,643
+
 ## Version II of reference SNP+TR haplotype panel for imputation of TR variants
 
 ### Dataset description
@@ -67,4 +137,4 @@ For version I of EnsembleTR calls, please use
 https://ensemble-tr.s3.us-east-2.amazonaws.com/split/ensemble_chr"$chr"_filtered.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/split/ensemble_chr"$chr"_filtered.vcf.gz.tbi for tbi file.
 
 For version I of phased panels, please use 
-https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz.csi for tbi file.
\ No newline at end of file
+https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz for VCF file and https://ensemble-tr.s3.us-east-2.amazonaws.com/phased-split/chr"$chr"_final_SNP_merged.vcf.gz.csi for tbi file.