Merge pull request #658 from genomic-medicine-sweden/pad_bed

padding bed file

CHANGELOG.md

@@ -23,7 +23,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Fixed`
 
-- Restrict deepvariant analysis of WES samples to bait regions [#633](https://github.com/nf-core/raredisease/pull/633)
+- Restrict deepvariant analysis of WES samples to bait regions [#633](https://github.com/nf-core/raredisease/pull/633), [#658](https://github.com/nf-core/raredisease/pull/658)
 - bcftools annotate declaration in annotate CADD subworkflow [#624](https://github.com/nf-core/raredisease/pull/624)
 - Rhocallviz subworkflow will only be invocated once per sample [#621](https://github.com/nf-core/raredisease/pull/621)
 - Updated createCaseChannel function to include a check for maternal and paternal ids being set to a numeric 0 [#643](https://github.com/nf-core/raredisease/pull/643)

CITATIONS.md

@@ -16,6 +16,10 @@
 
   > Danecek P, Bonfield JK, Liddle J, et al. Twelve years of SAMtools and BCFtools. GigaScience. 2021;10(2):giab008. doi:10.1093/gigascience/giab008
 
+- [BEDTools](https://academic.oup.com/bioinformatics/article/26/6/841/244688)
+
+  > Quinlan AR, Hall IM. BEDTools: a flexible suite of utilities for comparing genomic features. Bioinformatics. 2010;26(6):841-842. doi:10.1093/bioinformatics/btq033
+
 - [BWA-MEM](https://arxiv.org/abs/1303.3997)
 
   > Li H. Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM. Published online May 26, 2013. Accessed March 14, 2023. http://arxiv.org/abs/1303.3997

conf/modules/prepare_references.config

@@ -104,6 +104,16 @@ process {
         ext.args2 = '--csi'
     }
 
+    withName: '.*PREPARE_REFERENCES:BEDTOOLS_PAD_TARGET_BED' {
+        ext.when   = { !params.target_bed.equals(null) && params.bait_padding > 0 }
+        ext.prefix = { "${meta.id}_pad${params.bait_padding}" }
+        ext.args   = { "-b ${params.bait_padding}" }
+    }
+
+    withName: '.*PREPARE_REFERENCES:TABIX_BGZIPINDEX_PADDED_BED' {
+        ext.prefix = { "${meta.id}_pad${params.bait_padding}" }
+    }
+
     withName: '.*PREPARE_REFERENCES:GATK_BILT' {
         ext.when = { !params.target_bed.equals(null) }
         ext.prefix = { "${meta.id}_target" }

modules.json

@@ -55,6 +55,11 @@
                         "git_sha": "bfa8975eefb8df3e480a44ac9e594f23f52b2963",
                         "installed_by": ["modules"]
                     },
+                    "bedtools/slop": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "bwa/index": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",

subworkflows/local/prepare_references.nf

@@ -2,6 +2,7 @@
 // Prepare reference files
 //
 
+include { BEDTOOLS_SLOP as BEDTOOLS_PAD_TARGET_BED           } from '../../modules/nf-core/bedtools/slop/main'
 include { BWA_INDEX as BWA_INDEX_GENOME                      } from '../../modules/nf-core/bwa/index/main'
 include { BWA_INDEX as BWA_INDEX_MT                          } from '../../modules/nf-core/bwa/index/main'
 include { BWA_INDEX as BWA_INDEX_MT_SHIFT                    } from '../../modules/nf-core/bwa/index/main'
@@ -24,6 +25,7 @@ include { SENTIEON_BWAINDEX as SENTIEON_BWAINDEX_GENOME      } from '../../modul
 include { SENTIEON_BWAINDEX as SENTIEON_BWAINDEX_MT          } from '../../modules/nf-core/sentieon/bwaindex/main'
 include { SENTIEON_BWAINDEX as SENTIEON_BWAINDEX_MT_SHIFT    } from '../../modules/nf-core/sentieon/bwaindex/main'
 include { TABIX_BGZIPTABIX as TABIX_PBT                      } from '../../modules/nf-core/tabix/bgziptabix/main'
+include { TABIX_BGZIPTABIX as TABIX_BGZIPINDEX_PADDED_BED    } from '../../modules/nf-core/tabix/bgziptabix/main'
 include { TABIX_BGZIPTABIX as TABIX_BGZIPINDEX_VCFANNOEXTRA  } from '../../modules/nf-core/tabix/bgziptabix/main'
 include { TABIX_TABIX as TABIX_VCFANNOEXTRA                  } from '../../modules/nf-core/tabix/tabix/main'
 include { TABIX_TABIX as TABIX_DBSNP                         } from '../../modules/nf-core/tabix/tabix/main'
@@ -97,8 +99,18 @@ workflow PREPARE_REFERENCES {
         // Vcf, tab and bed indices
         TABIX_DBSNP(ch_known_dbsnp)
         TABIX_GNOMAD_AF(ch_gnomad_af_tab)
-        TABIX_PT(ch_target_bed).tbi.set { ch_tbi }
-        TABIX_PBT(ch_target_bed).gz_tbi.set { ch_bgzip_tbi }
+
+        // Index target bed file in case of gz input
+        TABIX_PT(ch_target_bed)
+        ch_target_bed
+            .join(TABIX_PT.out.tbi)
+            .set{ ch_trgt_bed_tbi }
+        // Compress and index target bed file in case of uncompressed input
+        TABIX_PBT(ch_target_bed).gz_tbi
+            .set { ch_bgzip_tbi }
+        ch_target_bed_gz_tbi = Channel.empty()
+            .mix(ch_trgt_bed_tbi, ch_bgzip_tbi)
+
         ch_vcfanno_extra_unprocessed
             .branch { it ->
                 bgzipindex: !it[1].toString().endsWith(".gz")
@@ -121,6 +133,15 @@ workflow PREPARE_REFERENCES {
             .mix(ch_vcfanno_bgzip, ch_vcfanno_index)
             .collect()
             .set{ch_vcfanno_extra}
+
+        // Pad bed file
+        BEDTOOLS_PAD_TARGET_BED(
+            ch_target_bed,
+            ch_fai.map { _meta, fai -> return fai }
+        )
+        TABIX_BGZIPINDEX_PADDED_BED(BEDTOOLS_PAD_TARGET_BED.out.bed).gz_tbi
+            .set { ch_target_bed_gz_tbi }
+
         // Generate bait and target intervals
         GATK_BILT(ch_target_bed, ch_dict).interval_list
         GATK_ILT(GATK_BILT.out.interval_list)
@@ -163,6 +184,8 @@ workflow PREPARE_REFERENCES {
         ch_versions = ch_versions.mix(TABIX_BGZIPINDEX_VCFANNOEXTRA.out.versions)
         ch_versions = ch_versions.mix(TABIX_VCFANNOEXTRA.out.versions)
         ch_versions = ch_versions.mix(TABIX_DBSNP.out.versions)
+        ch_versions = ch_versions.mix(BEDTOOLS_PAD_TARGET_BED.out.versions)
+        ch_versions = ch_versions.mix(TABIX_BGZIPINDEX_PADDED_BED.out.versions)
         ch_versions = ch_versions.mix(GATK_BILT.out.versions)
         ch_versions = ch_versions.mix(GATK_ILT.out.versions)
         ch_versions = ch_versions.mix(CAT_CAT_BAIT.out.versions)
@@ -190,10 +213,9 @@ workflow PREPARE_REFERENCES {
         mtshift_fasta         = GATK_SHIFTFASTA.out.shift_fa.collect()                                       // channel: [ val(meta), path(fasta) ]
         mtshift_bwa_index     = ch_bwa_mtshift                                                               // channel: [ val(meta), path(index) ]
         mtshift_bwamem2_index = BWAMEM2_INDEX_MT_SHIFT.out.index.collect()                                   // channel: [ val(meta), path(index) ]
-
         gnomad_af_idx         = TABIX_GNOMAD_AF.out.tbi.collect()                                            // channel: [ val(meta), path(fasta) ]
         known_dbsnp_tbi       = TABIX_DBSNP.out.tbi.collect()                                                // channel: [ val(meta), path(fasta) ]
-        target_bed            = Channel.empty().mix(ch_tbi, ch_bgzip_tbi).collect()                          // channel: [ val(meta), path(bed), path(tbi) ]
+        target_bed            = ch_target_bed_gz_tbi.collect()                                               // channel: [ val(meta), path(bed), path(tbi) ]
         vcfanno_extra         = ch_vcfanno_extra.ifEmpty([[]])                                               // channel: [ [path(vcf), path(tbi)] ]
         bait_intervals        = CAT_CAT_BAIT.out.file_out.map{ meta, inter -> inter}.collect().ifEmpty([[]]) // channel: [ path(intervals) ]
         target_intervals      = GATK_BILT.out.interval_list.map{ meta, inter -> inter}.collect()             // channel: [ path(interval_list) ]

subworkflows/local/utils_nfcore_raredisease_pipeline/main.nf

@@ -302,6 +302,7 @@ def toolCitationText() {
     ]
     other_citation_text = [
         "BCFtools (Danecek et al., 2021),",
+        "BEDTools (Quinlan & Hall, 2010),",
         "GATK (McKenna et al., 2010),",
         "MultiQC (Ewels et al. 2016),",
         params.skip_peddy     ? "" : "Peddy (Pedersen & Quinlan, 2017),",
@@ -432,7 +433,8 @@ def toolBibliographyText() {
         params.run_rtgvcfeval ? "<li>Cleary, J. G., Braithwaite, R., Gaastra, K., Hilbush, B. S., Inglis, S., Irvine, S. A., Jackson, A., Littin, R., Rathod, M., Ware, D., Zook, J. M., Trigg, L., & Vega, F. M. D. L. (2015). Comparing Variant Call Files for Performance Benchmarking of Next-Generation Sequencing Variant Calling Pipelines (p. 023754). bioRxiv. https://doi.org/10.1101/023754</li>" : "",
         "<li>Li, H., Handsaker, B., Wysoker, A., Fennell, T., Ruan, J., Homer, N., Marth, G., Abecasis, G., Durbin, R., & 1000 Genome Project Data Processing Subgroup. (2009). The Sequence Alignment/Map format and SAMtools. Bioinformatics, 25(16), 2078–2079. https://doi.org/10.1093/bioinformatics/btp352</li>",
         (!params.skip_smncopynumbercaller && params.analysis_type.equals("wgs")) ? "<li>Chen, X., Sanchis-Juan, A., French, C. E., Connell, A. J., Delon, I., Kingsbury, Z., Chawla, A., Halpern, A. L., Taft, R. J., Bentley, D. R., Butchbach, M. E. R., Raymond, F. L., & Eberle, M. A. (2020). Spinal muscular atrophy diagnosis and carrier screening from genome sequencing data. Genetics in Medicine, 22(5), 945–953. https://doi.org/10.1038/s41436-020-0754-0</li>" : "",
-        "<li>Li, H. (2011). Tabix: Fast retrieval of sequence features from generic TAB-delimited files. Bioinformatics, 27(5), 718–719. https://doi.org/10.1093/bioinformatics/btq671</li>"
+        "<li>Li, H. (2011). Tabix: Fast retrieval of sequence features from generic TAB-delimited files. Bioinformatics, 27(5), 718–719. https://doi.org/10.1093/bioinformatics/btq671</li>",
+        "<li>Quinlan, AR., Hall IM. (2010). BEDTools: a flexible suite of utilities for comparing genomic features. Bioinfomatics, 26(6), 841-842. https://doi.org/10.1093/bioinformatics/btq033</li>"
     ]
 
     def concat_text = align_text +