Update dockerfile, dependencies, and tests

.travis.yml

@@ -12,8 +12,10 @@ install:
   - docker image prune -f
   - wget -P tests https://data.cyri.ac/Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz
   - gzip -d tests/Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz
-  - wget -P tests https://data.cyri.ac/homo_sapiens_vep_101_GRCh38_chr21.tar.gz
-  - tar -zxf tests/homo_sapiens_vep_101_GRCh38_chr21.tar.gz -C tests
+  - wget -P tests https://data.cyri.ac/homo_sapiens_vep_102_GRCh38_chr21.tar.gz
+  - tar -zxf tests/homo_sapiens_vep_102_GRCh38_chr21.tar.gz -C tests
 
 script:
   - perl tests/vcf2maf.t
+  - perl tests/vcf2vcf.t
+  - perl tests/maf2vcf.t

Dockerfile

@@ -1,32 +1,34 @@
 FROM clearlinux:latest AS builder
 
 # Install a minimal versioned OS into /install_root, and bundled tools if any
-ENV CLEAR_VERSION=33910
+ENV CLEAR_VERSION=33980
 RUN swupd os-install --no-progress --no-boot-update --no-scripts \
     --version ${CLEAR_VERSION} \
     --path /install_root \
     --statedir /swupd-state \
     --bundles os-core-update,which
 
 # Download and install conda into /usr/bin
-ENV MINICONDA_VERSION=py37_4.8.3
+ENV MINICONDA_VERSION=py37_4.9.2
 RUN swupd bundle-add --no-progress curl && \
     curl -sL https://repo.anaconda.com/miniconda/Miniconda3-${MINICONDA_VERSION}-Linux-x86_64.sh -o /tmp/miniconda.sh && \
     sh /tmp/miniconda.sh -bfp /usr
 
 # Use conda to install remaining tools/dependencies into /usr/local
-ENV VEP_VERSION=101.0 \
-    HTSLIB_VERSION=1.9 \
-    BCFTOOLS_VERSION=1.9 \
-    SAMTOOLS_VERSION=1.9
+ENV VEP_VERSION=102.0 \
+    HTSLIB_VERSION=1.10.2 \
+    BCFTOOLS_VERSION=1.10.2 \
+    SAMTOOLS_VERSION=1.10 \
+    LIFTOVER_VERSION=377
 RUN conda create -qy -p /usr/local \
-        -c conda-forge \
-        -c bioconda \
-        -c defaults \
-        ensembl-vep==${VEP_VERSION} \
-        htslib==${HTSLIB_VERSION} \
-        bcftools==${BCFTOOLS_VERSION} \
-        samtools==${SAMTOOLS_VERSION}
+    -c conda-forge \
+    -c bioconda \
+    -c defaults \
+    ensembl-vep==${VEP_VERSION} \
+    htslib==${HTSLIB_VERSION} \
+    bcftools==${BCFTOOLS_VERSION} \
+    samtools==${SAMTOOLS_VERSION} \
+    ucsc-liftover==${LIFTOVER_VERSION}
 
 # Deploy the minimal OS and tools into a clean target layer
 FROM scratch

maf2maf.pl

@@ -16,7 +16,7 @@
 my ( $tum_depth_col, $tum_rad_col, $tum_vad_col ) = qw( t_depth t_ref_count t_alt_count );
 my ( $nrm_depth_col, $nrm_rad_col, $nrm_vad_col ) = qw( n_depth n_ref_count n_alt_count );
 my ( $vep_path, $vep_data, $vep_forks, $buffer_size, $any_allele ) = ( "$ENV{HOME}/miniconda3/bin", "$ENV{HOME}/.vep", 4, 5000, 0 );
-my ( $ref_fasta, $filter_vcf ) = ( "$ENV{HOME}/.vep/homo_sapiens/101_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz", "" );
+my ( $ref_fasta, $filter_vcf ) = ( "$ENV{HOME}/.vep/homo_sapiens/102_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz", "" );
 my ( $species, $ncbi_build, $cache_version, $maf_center, $max_filter_ac ) = ( "homo_sapiens", "GRCh37", "", ".", 10 );
 my $perl_bin = $Config{perlpath};
 
@@ -385,7 +385,7 @@ =head1 OPTIONS
  --species        Ensembl-friendly name of species (e.g. mus_musculus for mouse) [homo_sapiens]
  --ncbi-build     NCBI reference assembly of variants in MAF (e.g. GRCm38 for mouse) [GRCh37]
  --cache-version  Version of offline cache to use with VEP (e.g. 75, 84, 91) [Default: Installed version]
- --ref-fasta      Reference FASTA file [~/.vep/homo_sapiens/101_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz]
+ --ref-fasta      Reference FASTA file [~/.vep/homo_sapiens/102_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz]
  --help           Print a brief help message and quit
  --man            Print the detailed manual
 

maf2vcf.pl

@@ -9,7 +9,7 @@
 use Pod::Usage qw( pod2usage );
 
 # Set any default paths and constants
-my $ref_fasta = "$ENV{HOME}/.vep/homo_sapiens/91_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa.gz";
+my $ref_fasta = "$ENV{HOME}/.vep/homo_sapiens/102_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz";
 my ( $tum_depth_col, $tum_rad_col, $tum_vad_col ) = qw( t_depth t_ref_count t_alt_count );
 my ( $nrm_depth_col, $nrm_rad_col, $nrm_vad_col ) = qw( n_depth n_ref_count n_alt_count );
 
@@ -352,7 +352,7 @@ =head1 OPTIONS
  --input-maf      Path to input file in MAF format
  --output-dir     Path to output directory where VCFs will be stored, one per TN-pair
  --output-vcf     Path to output multi-sample VCF containing all TN-pairs [<output-dir>/<input-maf-name>.vcf]
- --ref-fasta      Path to reference Fasta file [~/.vep/homo_sapiens/91_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa.gz]
+ --ref-fasta      Path to reference Fasta file [~/.vep/homo_sapiens/102_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz]
  --per-tn-vcfs    Specify this to generate VCFs per-TN pair, in addition to the multi-sample VCF
  --tum-depth-col  Name of MAF column for read depth in tumor BAM [t_depth]
  --tum-rad-col    Name of MAF column for reference allele depth in tumor BAM [t_ref_count]

tests/maf2maf.t

@@ -12,8 +12,8 @@ chdir $script_dir;
 
 # Set the number of tests we'll run, and run them
 use Test::Simple tests => 8;
-ok( system( "perl maf2maf.pl --help > /dev/null" ) == 0 );
-ok( system( "perl maf2maf.pl --man > /dev/null" ) == 0 );
+ok( system( "docker run --rm vcf2maf:master perl maf2maf.pl --help > /dev/null" ) == 0 );
+ok( system( "docker run --rm vcf2maf:master perl maf2maf.pl --man > /dev/null" ) == 0 );
 
 # Test standard operation, diff, and cleanup
 ok( system( "perl maf2maf.pl --input-maf tests/test.maf --output-maf tests/test_output.vep_isoforms.new.maf" ) == 0 );

tests/maf2vcf.t

@@ -11,16 +11,11 @@ my $script_dir = dirname( $test_dir );
 chdir $script_dir;
 
 # Set the number of tests we'll run, and run them
-use Test::Simple tests => 6;
-ok( system( "perl maf2vcf.pl --help > /dev/null" ) == 0 );
-ok( system( "perl maf2vcf.pl --man > /dev/null" ) == 0 );
+use Test::Simple tests => 4;
+ok( system( "docker run --rm vcf2maf:master perl maf2vcf.pl --help > /dev/null" ) == 0 );
+ok( system( "docker run --rm vcf2maf:master perl maf2vcf.pl --man > /dev/null" ) == 0 );
 
 # Test standard operation, diff, and cleanup
-ok( system( "perl maf2vcf.pl --input-maf tests/test.maf --output-dir tests --output-vcf tests/test_maf2vcf.new.vcf" ) == 0 );
-ok( system( "diff tests/test_maf2vcf.vcf tests/test_maf2vcf.new.vcf" ) == 0 );
-system( "rm -f tests/test_maf2vcf.new.vcf tests/test.pairs.tsv" );
-
-# Test standard operation with the TSV file with minimal MAF columns, diff, and cleanup
-ok( system( "perl maf2vcf.pl --input-maf tests/test.tsv --output-dir tests --output-vcf tests/test_maf2vcf.new.vcf" ) == 0 );
-ok( system( "diff tests/test_maf2vcf.vcf tests/test_maf2vcf.new.vcf" ) == 0 );
-system( "rm -f tests/test_maf2vcf.new.vcf tests/test.pairs.tsv" );
+ok( system( "docker run --rm -v $test_dir:/opt/tests vcf2maf:master perl maf2vcf.pl --input-maf tests/test_b38_output.maf --output-dir tests --output-vcf tests/test_b38.new.vcf --ref-fasta tests/Homo_sapiens.GRCh38.dna.chromosome.21.fa" ) == 0 );
+ok( system( "bash -c 'diff <(cat tests/test_b38.vcf) <(grep -v ^##reference tests/test_b38.new.vcf)'" ) == 0 );
+system( "rm -f tests/test_b38.new.vcf tests/test_b38_output.pairs.tsv" );

tests/test_b37.vcf

@@ -0,0 +1,31 @@
+##fileformat=VCFv4.2
+##fileDate=20201207
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic Depths of REF and ALT(s) in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	TUMOR	NORMAL
+21	36164589	.	A	C	.	.		GT:AD:DP	0/1:.,21:54	0/0:.,.:0
+21	36164775	.	C	T	.	.		GT:AD:DP	0/1:778,123:901	0/0:482,0:482
+21	36252846	.	T	C	.	.		GT:AD:DP	0/1:450,54:504	0/0:.,.:0
+21	36252852	.	A	ACCTCTT	.	.		GT:AD:DP	0/1:658,225:883	0/0:343,0:343
+21	36252892	.	C	T	.	.		GT:AD:DP	0/1:788,74:862	0/0:522,1:523
+21	36252947	.	T	TG	.	.		GT:AD:DP	0/1:449,162:611	0/0:527,1:528
+21	36259208	.	G	A	.	.		GT:AD:DP	0/1:34,17:51	0/0:.,.:0
+21	37416080	.	C	G	.	.		GT:AD:DP	0/1:1010,130:1140	0/0:975,0:975
+21	39755547	.	T	C	.	.		GT:AD:DP	0/1:329,23:352	0/0:.,.:0
+21	39772519	.	G	A	.	.		GT:AD:DP	0/1:892,307:1199	0/0:566,1:567
+21	39772528	.	G	T	.	.		GT:AD:DP	0/1:190,153:343	0/0:507,0:507
+21	39775581	.	C	T	.	.		GT:AD:DP	0/1:149,138:287	0/0:.,.:0
+21	39947608	.	G	A	.	.		GT:AD:DP	0/1:92,99:191	0/0:.,.:0
+21	39947622	.	C	T	.	.		GT:AD:DP	0/1:223,96:331	0/0:442,0:449
+21	42851109	.	GT	G	.	.		GT:AD:DP	0/1:435,77:512	0/0:695,0:695
+21	42851146	.	C	T	.	.		GT:AD:DP	0/1:782,373:1224	0/0:996,0:1044
+21	42860421	.	G	T	.	.		GT:AD:DP	0/1:350,30:380	0/0:.,.:0
+21	42866477	.	T	C	.	.		GT:AD:DP	0/1:260,96:356	0/0:781,0:781
+21	43505435	.	C	T	.	.		GT:AD:DP	0/1:193,173:366	0/0:.,.:0
+21	44513238	.	C	T	.	.		GT:AD:DP	0/1:425,29:454	0/0:344,0:344
+21	44524485	.	A	G	.	.		GT:AD:DP	0/1:607,60:667	0/0:.,.:0
+21	44838997	.	C	T	.	.		GT:AD:DP	0/1:.,45:113	0/0:.,.:0
+21	45655257	.	C	A	.	.		GT:AD:DP	0/1:88,13:101	0/0:153,0:153
+21	45656786	.	C	T	.	.		GT:AD:DP	0/1:827,123:950	0/0:629,1:630
+21	45656994	.	C	T	.	.		GT:AD:DP	0/1:745,199:944	0/0:596,0:596

tests/test_b38.vcf

@@ -1,9 +1,31 @@
 ##fileformat=VCFv4.2
+##contig=<ID=21,length=46709983>
 ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
-##FORMAT=<ID=AD,Number=G,Type=Integer,Description="Allelic Depths of REF and ALT(s) in the order listed">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic Depths of REF and ALT(s) in the order listed">
 ##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	TUMOR	NORMAL
-21	43094659	.	T	TCTCATA	.	.	.	GT:AD:DP	0/1:10,10:20	0/0:11,0:11
-21	43094660	.	C	CTCATAC	.	.	.	GT:AD:DP	0/1:10,10:20	0/0:11,0:11
-21	43094667	.	T	C	.	.	.	GT:AD:DP	0/1:10,10:20	0/0:11,0:11
-21	43104346	.	G	T	.	.	.	GT:AD:DP	0/1:10,10:20	0/0:11,0:11
+21	34792292	.	A	C	.	.	.	GT:AD:DP	0/1:.,21:54	0/0:.,.:0
+21	34792478	.	C	T	.	.	.	GT:AD:DP	0/1:778,123:901	0/0:482,0:482
+21	34880549	.	T	C	.	.	.	GT:AD:DP	0/1:450,54:504	0/0:.,.:0
+21	34880555	.	A	ACCTCTT	.	.	.	GT:AD:DP	0/1:658,225:883	0/0:343,0:343
+21	34880595	.	C	T	.	.	.	GT:AD:DP	0/1:788,74:862	0/0:522,1:523
+21	34880650	.	T	TG	.	.	.	GT:AD:DP	0/1:449,162:611	0/0:527,1:528
+21	34886911	.	G	A	.	.	.	GT:AD:DP	0/1:34,17:51	0/0:.,.:0
+21	36043782	.	C	G	.	.	.	GT:AD:DP	0/1:1010,130:1140	0/0:975,0:975
+21	38383625	.	T	C	.	.	.	GT:AD:DP	0/1:329,23:352	0/0:.,.:0
+21	38400597	.	G	A	.	.	.	GT:AD:DP	0/1:892,307:1199	0/0:566,1:567
+21	38400606	.	G	T	.	.	.	GT:AD:DP	0/1:190,153:343	0/0:507,0:507
+21	38403659	.	C	T	.	.	.	GT:AD:DP	0/1:149,138:287	0/0:.,.:0
+21	38575684	.	G	A	.	.	.	GT:AD:DP	0/1:92,99:191	0/0:.,.:0
+21	38575698	.	C	T	.	.	.	GT:AD:DP	0/1:223,96:331	0/0:442,0:449
+21	41479182	.	GT	G	.	.	.	GT:AD:DP	0/1:435,77:512	0/0:695,0:695
+21	41479219	.	C	T	.	.	.	GT:AD:DP	0/1:782,373:1224	0/0:996,0:1044
+21	41488494	.	G	T	.	.	.	GT:AD:DP	0/1:350,30:380	0/0:.,.:0
+21	41494550	.	T	C	.	.	.	GT:AD:DP	0/1:260,96:356	0/0:781,0:781
+21	42085325	.	C	T	.	.	.	GT:AD:DP	0/1:193,173:366	0/0:.,.:0
+21	43093128	.	C	T	.	.	.	GT:AD:DP	0/1:425,29:454	0/0:344,0:344
+21	43104375	.	A	G	.	.	.	GT:AD:DP	0/1:607,60:667	0/0:.,.:0
+21	43419117	.	C	T	.	.	.	GT:AD:DP	0/1:.,45:113	0/0:.,.:0
+21	44235374	.	C	A	.	.	.	GT:AD:DP	0/1:88,13:101	0/0:153,0:153
+21	44236903	.	C	T	.	.	.	GT:AD:DP	0/1:827,123:950	0/0:629,1:630
+21	44237111	.	C	T	.	.	.	GT:AD:DP	0/1:745,199:944	0/0:596,0:596