diff --git a/.travis.yml b/.travis.yml index fd6a099..eb99731 100644 --- a/.travis.yml +++ b/.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 diff --git a/Dockerfile b/Dockerfile index 04d168e..1d2daa3 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,7 +1,7 @@ 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 ${CLEAR_VERSION} \ --path /install_root \ @@ -9,24 +9,26 @@ RUN swupd os-install --no-progress --no-boot-update --no-scripts \ --bundles os-core-update,which # Download and install conda into /usr/bin -ENV MINICONDA_VERSION=py37_4.8.3 +ENV MINICONDA_VERSION=py37_4.9.2 RUN swupd bundle-add --no-progress curl && \ curl -sL https://repo.anaconda.com/miniconda/Miniconda3-${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 diff --git a/maf2maf.pl b/maf2maf.pl index 735f78a..213629c 100644 --- a/maf2maf.pl +++ b/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 diff --git a/maf2vcf.pl b/maf2vcf.pl index 5493712..a3e1a6e 100644 --- a/maf2vcf.pl +++ b/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 [/.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] diff --git a/tests/maf2maf.t b/tests/maf2maf.t index da5bf84..4020241 100644 --- a/tests/maf2maf.t +++ b/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 ); diff --git a/tests/maf2vcf.t b/tests/maf2vcf.t index 8391fe1..e0734c7 100644 --- a/tests/maf2vcf.t +++ b/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" ); diff --git a/tests/test_b37.vcf b/tests/test_b37.vcf new file mode 100644 index 0000000..7531a73 --- /dev/null +++ b/tests/test_b37.vcf @@ -0,0 +1,31 @@ +##fileformat=VCFv4.2 +##fileDate=20201207 +##FORMAT= +##FORMAT= +##FORMAT= +#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 diff --git a/tests/test_b38.vcf b/tests/test_b38.vcf index d74089a..7ae54e2 100644 --- a/tests/test_b38.vcf +++ b/tests/test_b38.vcf @@ -1,9 +1,31 @@ ##fileformat=VCFv4.2 +##contig= ##FORMAT= -##FORMAT= +##FORMAT= ##FORMAT= #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 diff --git a/tests/test_b38_output.maf b/tests/test_b38_output.maf index 543b999..ec414af 100644 --- a/tests/test_b38_output.maf +++ b/tests/test_b38_output.maf @@ -1,6 +1,27 @@ #version 2.4 Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type Reference_Allele Tumor_Seq_Allele1 Tumor_Seq_Allele2 dbSNP_RS dbSNP_Val_Status Tumor_Sample_Barcode Matched_Norm_Sample_Barcode Match_Norm_Seq_Allele1 Match_Norm_Seq_Allele2 Tumor_Validation_Allele1 Tumor_Validation_Allele2 Match_Norm_Validation_Allele1 Match_Norm_Validation_Allele2 Verification_Status Validation_Status Mutation_Status Sequencing_Phase Sequence_Source Validation_Method Score BAM_File Sequencer Tumor_Sample_UUID Matched_Norm_Sample_UUID HGVSc HGVSp HGVSp_Short Transcript_ID Exon_Number t_depth t_ref_count t_alt_count n_depth n_ref_count n_alt_count all_effects Allele Gene Feature Feature_type Consequence cDNA_position CDS_position Protein_position Amino_acids Codons Existing_variation ALLELE_NUM DISTANCE STRAND_VEP SYMBOL SYMBOL_SOURCE HGNC_ID BIOTYPE CANONICAL CCDS ENSP SWISSPROT TREMBL UNIPARC RefSeq SIFT PolyPhen EXON INTRON DOMAINS AF AFR_AF AMR_AF ASN_AF EAS_AF EUR_AF SAS_AF AA_AF EA_AF CLIN_SIG SOMATIC PUBMED MOTIF_NAME MOTIF_POS HIGH_INF_POS MOTIF_SCORE_CHANGE IMPACT PICK VARIANT_CLASS TSL HGVS_OFFSET PHENO MINIMISED ExAC_AF ExAC_AF_AFR ExAC_AF_AMR ExAC_AF_EAS ExAC_AF_FIN ExAC_AF_NFE ExAC_AF_OTH ExAC_AF_SAS GENE_PHENO FILTER flanking_bps vcf_id vcf_qual ExAC_AF_Adj ExAC_AC_AN_Adj ExAC_AC_AN ExAC_AC_AN_AFR ExAC_AC_AN_AMR ExAC_AC_AN_EAS ExAC_AC_AN_FIN ExAC_AC_AN_NFE ExAC_AC_AN_OTH ExAC_AC_AN_SAS ExAC_FILTER gnomAD_AF gnomAD_AFR_AF gnomAD_AMR_AF gnomAD_ASJ_AF gnomAD_EAS_AF gnomAD_FIN_AF gnomAD_NFE_AF gnomAD_OTH_AF gnomAD_SAS_AF vcf_pos -U2AF1 7307 . GRCh38 21 43094659 43094660 + In_Frame_Ins INS - - CTCATA rs1349995283 TUMOR NORMAL - - c.472_477dup p.Tyr158_Glu159dup p.Y158_E159dup ENST00000291552 6/8 20 10 10 11 11 0 U2AF1,inframe_insertion,p.Tyr85_Glu86dup,ENST00000459639,NM_001025204.1;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000291552,NM_006758.3;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,3_prime_UTR_variant,,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000496462,; CTCATA ENSG00000160201 ENST00000291552 Transcript inframe_insertion 553-554/945 477-478/723 159-160/240 -/YE -/TATGAG rs1349995283 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 6/8 Pfam:PF00642,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 MODERATE 1 insertion 1 1 . ATC . . 3.978e-06 8.795e-06 43094659 -U2AF1 7307 . GRCh38 21 43094660 43094661 + In_Frame_Ins INS - - TCATAC novel TUMOR NORMAL - - c.472_477dup p.Tyr158_Glu159dup p.Y158_E159dup ENST00000291552 6/8 20 10 10 11 11 0 U2AF1,inframe_insertion,p.Tyr85_Glu86dup,ENST00000459639,NM_001025204.1;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000291552,NM_006758.3;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,3_prime_UTR_variant,,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000496462,; TCATAC ENSG00000160201 ENST00000291552 Transcript inframe_insertion 552-553/945 476-477/723 159/240 E/EYE gag/gaGTATGAg 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 6/8 Pfam:PF00642,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 MODERATE 1 insertion 1 -1 1 . TCT . . 43094660 -U2AF1 7307 . GRCh38 21 43094667 43094667 + Missense_Mutation SNP T T C rs371246226 TUMOR NORMAL T T c.470A>G p.Gln157Arg p.Q157R ENST00000291552 6/8 20 10 10 11 11 0 U2AF1,missense_variant,p.Gln84Arg,ENST00000459639,NM_001025204.1;U2AF1,missense_variant,p.Gln157Arg,ENST00000291552,NM_006758.3;U2AF1,missense_variant,p.Gln157Arg,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,3_prime_UTR_variant,,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000496462,; C ENSG00000160201 ENST00000291552 Transcript missense_variant 546/945 470/723 157/240 Q/R cAg/cGg rs371246226,COSV52341120,COSV52341147 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 deleterious(0) probably_damaging(0.971) 6/8 Pfam:PF00642,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 0.0001163 likely_pathogenic 0,1,1 22158538,23029227,23861105 MODERATE 1 SNV 1 1,1,1 1 . CTG . . 2.387e-05 6.16e-05 9.923e-05 3.519e-05 43094667 -U2AF1 7307 . GRCh38 21 43104346 43104346 + Missense_Mutation SNP G G T rs371769427 TUMOR NORMAL G G c.101C>A p.Ser34Tyr p.S34Y ENST00000291552 2/8 20 10 10 11 11 0 U2AF1,missense_variant,p.Ser34Tyr,ENST00000291552,NM_006758.3;U2AF1,missense_variant,p.Ser34Tyr,ENST00000380276,NM_001025203.1;U2AF1,5_prime_UTR_variant,,ENST00000459639,NM_001025204.1;AP001631.2,upstream_gene_variant,,ENST00000668861,;U2AF1,missense_variant,p.Ser34Tyr,ENST00000464750,;U2AF1,missense_variant,p.Ser34Tyr,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000496462,;U2AF1,non_coding_transcript_exon_variant,,ENST00000463599,;U2AF1,upstream_gene_variant,,ENST00000468039,; T ENSG00000160201 ENST00000291552 Transcript missense_variant 177/945 101/723 34/240 S/Y tCt/tAt rs371769427,COSV52341059,COSV52341472 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 deleterious(0) probably_damaging(0.997) 2/8 Pfam:PF00642,Prints:PR01848,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 likely_pathogenic 0,1,1 26619011,22158538,23029227,23861105,24498085 MODERATE 1 SNV 1 1,1,1 1 . AGA . . 8.004e-06 1.766e-05 43104346 +RUNX1 861 . GRCh38 21 34792292 34792292 + Missense_Mutation SNP A A C novel TUMOR NORMAL A A c.1286T>G p.Leu429Arg p.L429R ENST00000300305 8/8 54 . 21 0 . . RUNX1,missense_variant,p.Leu402Arg,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Leu429Arg,ENST00000300305,;RUNX1,missense_variant,p.Leu429Arg,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Leu429Arg,ENST00000437180,;RUNX1,missense_variant,p.Leu338Arg,ENST00000399240,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; C ENSG00000159216 ENST00000300305 Transcript missense_variant 1731/6222 1286/1443 429/480 L/R cTg/cGg 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A deleterious(0) possibly_damaging(0.887) 8/8 PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Pfam:PF08504,Prints:PR00967 MODERATE 1 SNV 1 1 . CAG . . 34792292 +RUNX1 861 . GRCh38 21 34792478 34792478 + Missense_Mutation SNP C C T rs867474432 TUMOR NORMAL C C c.1100G>A p.Gly367Asp p.G367D ENST00000300305 8/8 901 778 123 482 482 0 RUNX1,missense_variant,p.Gly340Asp,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Gly367Asp,ENST00000300305,;RUNX1,missense_variant,p.Gly367Asp,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Gly367Asp,ENST00000437180,;RUNX1,missense_variant,p.Gly276Asp,ENST00000399240,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; T ENSG00000159216 ENST00000300305 Transcript missense_variant 1545/6222 1100/1443 367/480 G/D gGc/gAc rs867474432,COSV55867253 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A deleterious(0.01) possibly_damaging(0.568) 8/8 Low_complexity_(Seg):seg,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:4.10.770.10 0,1 MODERATE 1 SNV 1 0,1 1 . GCC . . 34792478 +RUNX1 861 . GRCh38 21 34880549 34880549 + Splice_Region SNP T T C novel TUMOR NORMAL T T c.508+8A>G ENST00000300305 504 450 54 0 . . RUNX1,splice_region_variant,,ENST00000300305,;RUNX1,splice_region_variant,,ENST00000344691,NM_001001890.3;RUNX1,splice_region_variant,,ENST00000358356,NM_001122607.2;RUNX1,splice_region_variant,,ENST00000399237,;RUNX1,splice_region_variant,,ENST00000399240,;RUNX1,splice_region_variant,,ENST00000437180,;RUNX1,splice_region_variant,,ENST00000675419,NM_001754.5;RUNX1,downstream_gene_variant,,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,splice_region_variant,,ENST00000482318,; C ENSG00000159216 ENST00000300305 Transcript splice_region_variant,intron_variant 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A 4/7 LOW 1 SNV 1 1 . ATA . . 34880549 +RUNX1 861 . GRCh38 21 34880555 34880556 + Splice_Site INS - - CCTCTT novel TUMOR NORMAL - - c.504_508+1dup p.X168_splice ENST00000300305 883 658 225 343 343 0 RUNX1,splice_donor_variant,,ENST00000300305,;RUNX1,splice_donor_variant,,ENST00000344691,NM_001001890.3;RUNX1,splice_donor_variant,,ENST00000358356,NM_001122607.2;RUNX1,splice_donor_variant,,ENST00000399237,;RUNX1,splice_donor_variant,,ENST00000399240,;RUNX1,splice_donor_variant,,ENST00000437180,;RUNX1,splice_donor_variant,,ENST00000675419,NM_001754.5;RUNX1,downstream_gene_variant,,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,splice_donor_variant,,ENST00000482318,; CCTCTT ENSG00000159216 ENST00000300305 Transcript splice_donor_variant 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A 4/7 HIGH 1 insertion 1 1 . TAC . . 34880555 +RUNX1 861 . GRCh38 21 34880595 34880595 + Missense_Mutation SNP C C T TUMOR NORMAL C C c.470G>A p.Arg157Lys p.R157K ENST00000300305 4/8 862 788 74 523 522 1 RUNX1,missense_variant,p.Arg130Lys,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Arg157Lys,ENST00000300305,;RUNX1,missense_variant,p.Arg157Lys,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Arg157Lys,ENST00000437180,;RUNX1,missense_variant,p.Arg130Lys,ENST00000358356,NM_001122607.2;RUNX1,missense_variant,p.Arg130Lys,ENST00000399240,;RUNX1,missense_variant,p.Arg145Lys,ENST00000399237,;RUNX1,downstream_gene_variant,,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; T ENSG00000159216 ENST00000300305 Transcript missense_variant 915/6222 470/1443 157/480 R/K aGa/aAa COSV55871984,COSV55885034 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A tolerated(0.16) probably_damaging(0.978) 4/8 PROSITE_profiles:PS51062,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:2.60.40.720,Pfam:PF00853,Superfamily:SSF49417,Prints:PR00967 1,1 MODERATE 1 SNV 1 1,1 1 . TCT . . 34880595 +RUNX1 861 . GRCh38 21 34880650 34880651 + Frame_Shift_Ins INS - - G novel TUMOR NORMAL - - c.414_415insC p.Asn139GlnfsTer5 p.N139Qfs*5 ENST00000300305 4/8 611 449 162 528 527 1 RUNX1,frameshift_variant,p.Asn112GlnfsTer5,ENST00000344691,NM_001001890.3;RUNX1,frameshift_variant,p.Asn139GlnfsTer5,ENST00000300305,;RUNX1,frameshift_variant,p.Asn139GlnfsTer5,ENST00000675419,NM_001754.5;RUNX1,frameshift_variant,p.Asn139GlnfsTer5,ENST00000437180,;RUNX1,frameshift_variant,p.Asn112GlnfsTer5,ENST00000358356,NM_001122607.2;RUNX1,frameshift_variant,p.Asn112GlnfsTer5,ENST00000399240,;RUNX1,frameshift_variant,p.Asn127GlnfsTer5,ENST00000399237,;RUNX1,frameshift_variant,p.Asn126GlnfsTer5,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; G ENSG00000159216 ENST00000300305 Transcript frameshift_variant 859-860/6222 414-415/1443 138-139/480 -/X -/C 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A 4/8 PROSITE_profiles:PS51062,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:2.60.40.720,Pfam:PF00853,Superfamily:SSF49417,Prints:PR00967 HIGH 1 insertion 1 1 . TTT . . 34880650 +RUNX1 861 . GRCh38 21 34886911 34886911 + Missense_Mutation SNP G G A novel TUMOR NORMAL G G c.283C>T p.Pro95Ser p.P95S ENST00000300305 3/8 51 34 17 0 . . RUNX1,missense_variant,p.Pro68Ser,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Pro95Ser,ENST00000300305,;RUNX1,missense_variant,p.Pro95Ser,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Pro95Ser,ENST00000437180,;RUNX1,missense_variant,p.Pro68Ser,ENST00000358356,NM_001122607.2;RUNX1,missense_variant,p.Pro68Ser,ENST00000399240,;RUNX1,missense_variant,p.Pro83Ser,ENST00000399237,;RUNX1,missense_variant,p.Pro82Ser,ENST00000455571,;RUNX1,downstream_gene_variant,,ENST00000475045,;AP000331.1,downstream_gene_variant,,ENST00000651798,;RUNX1,intron_variant,,ENST00000482318,;,regulatory_region_variant,,ENSR00000141768,; A ENSG00000159216 ENST00000300305 Transcript missense_variant 728/6222 283/1443 95/480 P/S Ccc/Tcc 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A deleterious(0) probably_damaging(0.997) 3/8 PROSITE_profiles:PS51062,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:2.60.40.720,Pfam:PF00853,Superfamily:SSF49417,Prints:PR00967,Prints:PR00967 MODERATE 1 SNV 1 1 . GGG . . 34886911 +SETD4 54093 . GRCh38 21 36043782 36043782 + Missense_Mutation SNP C C G novel TUMOR NORMAL C C c.901G>C p.Glu301Gln p.E301Q ENST00000399215 6/10 1140 1010 130 975 975 0 SETD4,missense_variant,p.Glu301Gln,ENST00000399215,;SETD4,missense_variant,p.Glu277Gln,ENST00000399212,NM_001286752.2;SETD4,missense_variant,p.Glu301Gln,ENST00000332131,NM_017438.5;SETD4,missense_variant,p.Gly277Arg,ENST00000399201,;SETD4,missense_variant,p.Gly277Arg,ENST00000399205,NM_001007261.2;SETD4,missense_variant,p.Gly301Arg,ENST00000399208,NM_001007259.2;SETD4,missense_variant,p.Gly301Arg,ENST00000399207,;SETD4,downstream_gene_variant,,ENST00000424303,;SETD4,downstream_gene_variant,,ENST00000429161,;SETD4,downstream_gene_variant,,ENST00000442559,;SETD4,downstream_gene_variant,,ENST00000446166,;SETD4,splice_region_variant,,ENST00000481477,;SETD4,upstream_gene_variant,,ENST00000469482,;SETD4,downstream_gene_variant,,ENST00000485865,;SETD4,upstream_gene_variant,,ENST00000487297,; G ENSG00000185917 ENST00000399215 Transcript missense_variant,splice_region_variant 2274/4272 901/1323 301/440 E/Q Gaa/Caa 1 -1 SETD4 HGNC HGNC:1258 protein_coding YES CCDS13640.1 ENSP00000382163 Q9NVD3.158 UPI000012868E deleterious(0.01) benign(0.203) 6/10 PANTHER:PTHR13271,PANTHER:PTHR13271:SF8,PIRSF:PIRSF027158 MODERATE 1 SNV 2 . CCT . . 36043782 +ERG 2078 . GRCh38 21 38383625 38383625 + Silent SNP T T C novel TUMOR NORMAL T T c.1239A>G p.Ser413= p.S413= ENST00000417133 12/12 352 329 23 0 . . ERG,synonymous_variant,p.Ser389=,ENST00000442448,NM_004449.4;ERG,synonymous_variant,p.Ser413=,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,synonymous_variant,p.Ser390=,ENST00000398910,NM_001291391.1;ERG,synonymous_variant,p.Ser389=,ENST00000398911,;ERG,synonymous_variant,p.Ser406=,ENST00000288319,NM_182918.4;ERG,synonymous_variant,p.Ser383=,ENST00000398907,;ERG,synonymous_variant,p.Ser382=,ENST00000398905,NM_001331025.2;ERG,synonymous_variant,p.Ser290=,ENST00000398897,NM_001243429.1;ERG,synonymous_variant,p.Ser413=,ENST00000398919,NM_001243428.1;ERG,synonymous_variant,p.Ser314=,ENST00000453032,NM_001136155.1; C ENSG00000157554 ENST00000417133 Transcript synonymous_variant 1425/5023 1239/1461 413/486 S tcA/tcG 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 12/12 PANTHER:PTHR11849,PANTHER:PTHR11849:SF216,Superfamily:SSF46785 LOW 1 SNV 2 1 . ATG . . 38383625 +ERG 2078 . GRCh38 21 38400597 38400597 + Missense_Mutation SNP G G A TUMOR NORMAL G G c.743C>T p.Thr248Met p.T248M ENST00000417133 8/12 1199 892 307 567 566 1 ERG,missense_variant,p.Thr248Met,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Thr248Met,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Thr241Met,ENST00000288319,NM_182918.4;ERG,missense_variant,p.Thr241Met,ENST00000398907,;ERG,missense_variant,p.Thr248Met,ENST00000398919,NM_001243428.1;ERG,missense_variant,p.Thr149Met,ENST00000453032,NM_001136155.1;ERG,missense_variant,p.Thr209Met,ENST00000429727,;ERG,intron_variant,,ENST00000398897,NM_001243429.1;ERG,intron_variant,,ENST00000398905,NM_001331025.2;ERG,intron_variant,,ENST00000398911,;ERG,intron_variant,,ENST00000442448,NM_004449.4;ERG,non_coding_transcript_exon_variant,,ENST00000492833,;ERG,intron_variant,,ENST00000481609,;ERG,downstream_gene_variant,,ENST00000473107,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,;,regulatory_region_variant,,ENSR00000662899,; A ENSG00000157554 ENST00000417133 Transcript missense_variant 929/5023 743/1461 248/486 T/M aCg/aTg COSV55741264 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 tolerated(0.19) benign(0.39) 8/12 PANTHER:PTHR11849,PANTHER:PTHR11849:SF216 1 MODERATE 1 SNV 2 1 1 . CGT . . 38400597 +ERG 2078 . GRCh38 21 38400606 38400606 + Missense_Mutation SNP G G T TUMOR NORMAL G G c.734C>A p.Pro245His p.P245H ENST00000417133 8/12 343 190 153 507 507 0 ERG,missense_variant,p.Pro245His,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Pro245His,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Pro238His,ENST00000288319,NM_182918.4;ERG,missense_variant,p.Pro238His,ENST00000398907,;ERG,missense_variant,p.Pro245His,ENST00000398919,NM_001243428.1;ERG,missense_variant,p.Pro146His,ENST00000453032,NM_001136155.1;ERG,missense_variant,p.Pro206His,ENST00000429727,;ERG,intron_variant,,ENST00000398897,NM_001243429.1;ERG,intron_variant,,ENST00000398905,NM_001331025.2;ERG,intron_variant,,ENST00000398911,;ERG,intron_variant,,ENST00000442448,NM_004449.4;ERG,non_coding_transcript_exon_variant,,ENST00000492833,;ERG,intron_variant,,ENST00000481609,;ERG,downstream_gene_variant,,ENST00000473107,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,;,regulatory_region_variant,,ENSR00000662899,; T ENSG00000157554 ENST00000417133 Transcript missense_variant 920/5023 734/1461 245/486 P/H cCt/cAt COSV55741651 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 tolerated(0.1) benign(0.227) 8/12 PANTHER:PTHR11849,PANTHER:PTHR11849:SF216 1 MODERATE 1 SNV 2 1 1 . AGG . . 38400606 +ERG 2078 . GRCh38 21 38403659 38403659 + Missense_Mutation SNP C C T novel TUMOR NORMAL C C c.460G>A p.Val154Met p.V154M ENST00000417133 6/12 287 149 138 0 . . ERG,missense_variant,p.Val154Met,ENST00000442448,NM_004449.4;ERG,missense_variant,p.Val154Met,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Val154Met,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Val154Met,ENST00000398911,;ERG,missense_variant,p.Val147Met,ENST00000288319,NM_182918.4;ERG,missense_variant,p.Val147Met,ENST00000398907,;ERG,missense_variant,p.Val147Met,ENST00000398905,NM_001331025.2;ERG,missense_variant,p.Val55Met,ENST00000398897,NM_001243429.1;ERG,missense_variant,p.Val154Met,ENST00000398919,NM_001243428.1;ERG,missense_variant,p.Val55Met,ENST00000453032,NM_001136155.1;ERG,missense_variant,p.Val115Met,ENST00000429727,;ERG,non_coding_transcript_exon_variant,,ENST00000481609,;ERG,non_coding_transcript_exon_variant,,ENST00000492833,;ERG,non_coding_transcript_exon_variant,,ENST00000473107,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,; T ENSG00000157554 ENST00000417133 Transcript missense_variant 646/5023 460/1461 154/486 V/M Gtg/Atg 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 deleterious(0.04) possibly_damaging(0.76) 6/12 Gene3D:1.10.150.50,PDB-ENSP_mappings:1sxe.A,Pfam:PF02198,PROSITE_profiles:PS51433,PANTHER:PTHR11849,PANTHER:PTHR11849:SF216,SMART:SM00251,Superfamily:SSF47769,CDD:cd08540 MODERATE 1 SNV 2 1 . ACC . . 38403659 +ERG 2078 . GRCh38 21 38575684 38575684 + Missense_Mutation SNP G G A rs201302788 TUMOR NORMAL G G c.17C>T p.Pro6Leu p.P6L ENST00000417133 3/12 191 92 99 0 . . ERG,missense_variant,p.Pro6Leu,ENST00000442448,NM_004449.4;ERG,missense_variant,p.Pro6Leu,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Pro6Leu,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Pro6Leu,ENST00000398911,;ERG,missense_variant,p.Pro6Leu,ENST00000398919,NM_001243428.1;ERG,5_prime_UTR_variant,,ENST00000398897,NM_001243429.1;ERG,5_prime_UTR_variant,,ENST00000429727,;ERG,non_coding_transcript_exon_variant,,ENST00000485493,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,; A ENSG00000157554 ENST00000417133 Transcript missense_variant 203/5023 17/1461 6/486 P/L cCg/cTg rs201302788 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 deleterious_low_confidence(0) benign(0.001) 3/12 0.0001163 MODERATE 1 SNV 2 1 . CGG . . 4.776e-05 0.0001056 38575684 +ERG 2078 . GRCh38 21 38575698 38575698 + Translation_Start_Site SNP C C T TUMOR NORMAL C C c.3G>A p.Met1? p.M1? ENST00000417133 3/12 331 223 96 449 442 0 ERG,start_lost,p.Met1?,ENST00000442448,NM_004449.4;ERG,start_lost,p.Met1?,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,start_lost,p.Met1?,ENST00000398910,NM_001291391.1;ERG,start_lost,p.Met1?,ENST00000398911,;ERG,start_lost,p.Met1?,ENST00000398919,NM_001243428.1;ERG,5_prime_UTR_variant,,ENST00000398897,NM_001243429.1;ERG,5_prime_UTR_variant,,ENST00000429727,;ERG,non_coding_transcript_exon_variant,,ENST00000485493,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,; T ENSG00000157554 ENST00000417133 Transcript start_lost 189/5023 3/1461 1/486 M/I atG/atA COSV67366082 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 deleterious_low_confidence(0.03) benign(0.38) 3/12 1 HIGH 1 SNV 2 1 1 . TCA . . 38575698 +TMPRSS2 7113 . GRCh38 21 41479183 41479183 + Frame_Shift_Del DEL T T - novel TUMOR NORMAL T T c.831del p.Lys277AsnfsTer19 p.K277Nfs*19 ENST00000679263 7/14 512 435 77 695 695 0 TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000676973,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000679054,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000678348,;TMPRSS2,frameshift_variant,p.Lys277AsnfsTer19,ENST00000679263,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000332149,NM_005656.4;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000678171,NM_001382720.1;TMPRSS2,frameshift_variant,p.Lys155AsnfsTer19,ENST00000679016,;TMPRSS2,frameshift_variant,p.Lys261AsnfsTer19,ENST00000398585,NM_001135099.1;TMPRSS2,frameshift_variant,p.Lys116AsnfsTer19,ENST00000678743,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000454499,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000458356,;TMPRSS2,frameshift_variant,p.Lys184AsnfsTer19,ENST00000424093,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000679181,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer16,ENST00000677680,;TMPRSS2,3_prime_UTR_variant,,ENST00000678959,;,regulatory_region_variant,,ENSR00001056496,; - ENSG00000184012 ENST00000679263 Transcript frameshift_variant 974/3623 831/1638 277/545 K/X aaA/aa 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 7/14 Pfam:PF15494,Gene3D:3.10.250.10,SMART:SM00202,Superfamily:SSF56487,PANTHER:PTHR24253,PANTHER:PTHR24253:SF89 HIGH 1 deletion 1 . AGTT . . 41479182 +TMPRSS2 7113 . GRCh38 21 41479219 41479219 + Silent SNP C C T novel TUMOR NORMAL C C c.795G>A p.Leu265= p.L265= ENST00000679263 7/14 1224 782 373 1044 996 0 TMPRSS2,synonymous_variant,p.Leu212=,ENST00000676973,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000679054,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000678348,;TMPRSS2,synonymous_variant,p.Leu265=,ENST00000679263,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000332149,NM_005656.4;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000678171,NM_001382720.1;TMPRSS2,synonymous_variant,p.Leu143=,ENST00000679016,;TMPRSS2,synonymous_variant,p.Leu249=,ENST00000398585,NM_001135099.1;TMPRSS2,synonymous_variant,p.Leu104=,ENST00000678743,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000454499,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000458356,;TMPRSS2,synonymous_variant,p.Leu172=,ENST00000424093,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000679181,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000677680,;TMPRSS2,3_prime_UTR_variant,,ENST00000678959,;,regulatory_region_variant,,ENSR00001056496,; T ENSG00000184012 ENST00000679263 Transcript synonymous_variant 938/3623 795/1638 265/545 L ctG/ctA 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 7/14 Pfam:PF15494,Gene3D:3.10.250.10,SMART:SM00202,Superfamily:SSF56487,PANTHER:PTHR24253,PANTHER:PTHR24253:SF89 LOW 1 SNV 1 . TCA . . 41479219 +TMPRSS2 7113 . GRCh38 21 41488494 41488494 + Missense_Mutation SNP G G T TUMOR NORMAL G G c.504C>A p.Asn168Lys p.N168K ENST00000679263 5/14 380 350 30 0 . . TMPRSS2,missense_variant,p.Asn115Lys,ENST00000676973,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000679054,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000678348,;TMPRSS2,missense_variant,p.Asn168Lys,ENST00000679263,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000332149,NM_005656.4;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000678171,NM_001382720.1;TMPRSS2,missense_variant,p.Asn152Lys,ENST00000398585,NM_001135099.1;TMPRSS2,missense_variant,p.Asn7Lys,ENST00000678743,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000454499,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000458356,;TMPRSS2,intron_variant,,ENST00000424093,;TMPRSS2,intron_variant,,ENST00000679016,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000463138,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000679181,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000677680,;TMPRSS2,3_prime_UTR_variant,,ENST00000678959,; T ENSG00000184012 ENST00000679263 Transcript missense_variant 647/3623 504/1638 168/545 N/K aaC/aaA COSV59825472 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 tolerated(0.95) benign(0.07) 5/14 CDD:cd00112,Gene3D:4.10.400.10,SMART:SM00192,Superfamily:SSF57424,PROSITE_profiles:PS50068,PANTHER:PTHR24253,PANTHER:PTHR24253:SF89 1 MODERATE 1 SNV 1 1 . AGT . . 41488494 +TMPRSS2 7113 . GRCh38 21 41494550 41494550 + Missense_Mutation SNP T T C rs774327563 TUMOR NORMAL T T c.203A>G p.Tyr68Cys p.Y68C ENST00000679263 3/14 356 260 96 781 781 0 TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000676973,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000679054,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000678348,;TMPRSS2,missense_variant,p.Tyr68Cys,ENST00000679263,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000332149,NM_005656.4;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000678171,NM_001382720.1;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000679016,;TMPRSS2,missense_variant,p.Tyr52Cys,ENST00000398585,NM_001135099.1;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000454499,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000458356,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000424093,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000455813,;TMPRSS2,intron_variant,,ENST00000678743,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,intron_variant,,ENST00000463138,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000679181,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000677680,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000678959,; C ENSG00000184012 ENST00000679263 Transcript missense_variant 346/3623 203/1638 68/545 Y/C tAt/tGt rs774327563 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 tolerated(0.06) benign(0.412) 3/14 MODERATE 1 SNV 1 . ATA . . 1.995e-05 0.0001232 5.444e-05 1.762e-05 41494550 +UMODL1 89766 . GRCh38 21 42085325 42085325 + Silent SNP C C T rs185422923 TUMOR NORMAL C C c.516C>T p.Asn172= p.N172= ENST00000408989 4/22 366 193 173 0 . . UMODL1,synonymous_variant,p.Asn100=,ENST00000400424,NM_001199528.3;UMODL1,synonymous_variant,p.Asn100=,ENST00000400427,NM_001199527.2;UMODL1,synonymous_variant,p.Asn172=,ENST00000408989,NM_173568.3;UMODL1,synonymous_variant,p.Asn172=,ENST00000408910,NM_001004416.2;UMODL1,synonymous_variant,p.Asn8=,ENST00000491559,;UMODL1,synonymous_variant,p.Asn8=,ENST00000466434,;UMODL1,synonymous_variant,p.Asn8=,ENST00000400421,;UMODL1,synonymous_variant,p.Asn8=,ENST00000468982,;UMODL1,synonymous_variant,p.Asn8=,ENST00000485357,;UMODL1,synonymous_variant,p.Asn8=,ENST00000497243,; T ENSG00000177398 ENST00000408989 Transcript synonymous_variant 516/5262 516/4341 172/1446 N aaC/aaT rs185422923 1 1 UMODL1 HGNC HGNC:12560 protein_coding YES CCDS42935.1 ENSP00000386126 Q5DID0.131 UPI0000D6254B NM_173568.3 4/22 PANTHER:PTHR14002,PANTHER:PTHR14002:SF22 0.0002 0.0008 0.0001207 LOW 1 SNV 1 . ACG . . 8.016e-06 6.457e-05 3.268e-05 42085325 +U2AF1 7307 . GRCh38 21 43093128 43093128 + Missense_Mutation SNP C C T novel TUMOR NORMAL C C c.697G>A p.Asp233Asn p.D233N ENST00000291552 8/8 454 425 29 344 344 0 U2AF1,missense_variant,p.Asp160Asn,ENST00000459639,NM_001025204.1;U2AF1,missense_variant,p.Asp233Asn,ENST00000291552,NM_006758.3;U2AF1,missense_variant,p.Asp233Asn,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000486519,;U2AF1,downstream_gene_variant,,ENST00000496462,; T ENSG00000160201 ENST00000291552 Transcript missense_variant 773/945 697/723 233/240 D/N Gat/Aat 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081.224 UPI0000000C26 NM_006758.3 tolerated(0.44) possibly_damaging(0.857) 8/8 PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,MobiDB_lite:mobidb-lite,MobiDB_lite:mobidb-lite,Low_complexity_(Seg):seg MODERATE 1 SNV 1 1 . TCT . . 43093128 +U2AF1 7307 . GRCh38 21 43104375 43104375 + Silent SNP A A G rs755067307 TUMOR NORMAL A A c.72T>C p.Ile24= p.I24= ENST00000291552 2/8 667 607 60 0 . . U2AF1,synonymous_variant,p.Ile24=,ENST00000291552,NM_006758.3;U2AF1,synonymous_variant,p.Ile24=,ENST00000380276,NM_001025203.1;U2AF1,5_prime_UTR_variant,,ENST00000459639,NM_001025204.1;AP001631.2,upstream_gene_variant,,ENST00000668861,;U2AF1,synonymous_variant,p.Ile24=,ENST00000464750,;U2AF1,synonymous_variant,p.Ile24=,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000496462,;U2AF1,non_coding_transcript_exon_variant,,ENST00000463599,;U2AF1,upstream_gene_variant,,ENST00000468039,; G ENSG00000160201 ENST00000291552 Transcript synonymous_variant 148/945 72/723 24/240 I atT/atC rs755067307 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081.224 UPI0000000C26 NM_006758.3 2/8 Pfam:PF00642,Prints:PR01848,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 LOW 1 SNV 1 1 . CAA . . 7.992e-06 2.921e-05 8.823e-06 43104375 +SIK1 150094 . GRCh38 21 43419117 43419117 + Missense_Mutation SNP C C T novel TUMOR NORMAL C C c.1366G>A p.Glu456Lys p.E456K ENST00000270162 11/14 113 . 45 0 . . SIK1,missense_variant,p.Glu456Lys,ENST00000270162,NM_173354.5;SIK1,downstream_gene_variant,,ENST00000644750,;SIK1,downstream_gene_variant,,ENST00000478426,;SIK1,downstream_gene_variant,,ENST00000644689,;SIK1,downstream_gene_variant,,ENST00000644871,; T ENSG00000142178 ENST00000270162 Transcript missense_variant 1502/4747 1366/2352 456/783 E/K Gag/Aag 1 -1 SIK1 HGNC HGNC:11142 protein_coding YES CCDS33575.1 ENSP00000270162 P57059.191 UPI0000206F2B NM_173354.5 deleterious(0.03) possibly_damaging(0.494) 11/14 PIRSF:PIRSF037014,PANTHER:PTHR24346,PANTHER:PTHR24346:SF47,MobiDB_lite:mobidb-lite MODERATE 1 SNV 1 1 . TCC . . 43419117 +ICOSLG 23308 . GRCh38 21 44235374 44235374 + Missense_Mutation SNP C C A TUMOR NORMAL C C c.595G>T p.Val199Leu p.V199L ENST00000400379 4/6 101 88 13 153 153 0 ICOSLG,missense_variant,p.Val199Leu,ENST00000407780,NM_001283052.2,NM_015259.6,NM_001365759.2;ICOSLG,missense_variant,p.Val199Leu,ENST00000400379,;ICOSLG,missense_variant,p.Val82Leu,ENST00000400377,NM_001283051.2;ICOSLG,missense_variant,p.Val199Leu,ENST00000344330,NM_001283050.2; A ENSG00000160223 ENST00000400379 Transcript missense_variant 723/4246 595/1422 199/473 V/L Gtg/Ttg COSV60266097 1 -1 ICOSLG HGNC HGNC:17087 protein_coding YES ENSP00000383230 K4DIA0.68 UPI00003E5A05 tolerated(0.06) probably_damaging(0.982) 4/6 Superfamily:SSF48726,Gene3D:2.60.40.10,PANTHER:PTHR24100,PANTHER:PTHR24100:SF55,PROSITE_profiles:PS50835 1 MODERATE 1 SNV 1 1 . ACG . . 44235374 +ICOSLG 23308 . GRCh38 21 44236903 44236903 + Missense_Mutation SNP C C T novel TUMOR NORMAL C C c.370G>A p.Glu124Lys p.E124K ENST00000400379 3/6 950 827 123 630 629 1 ICOSLG,missense_variant,p.Glu124Lys,ENST00000407780,NM_001283052.2,NM_015259.6,NM_001365759.2;ICOSLG,missense_variant,p.Glu124Lys,ENST00000400379,;ICOSLG,missense_variant,p.Glu124Lys,ENST00000344330,NM_001283050.2;ICOSLG,intron_variant,,ENST00000400377,NM_001283051.2;AP001059.2,upstream_gene_variant,,ENST00000619053,; T ENSG00000160223 ENST00000400379 Transcript missense_variant 498/4246 370/1422 124/473 E/K Gag/Aag 1 -1 ICOSLG HGNC HGNC:17087 protein_coding YES ENSP00000383230 K4DIA0.68 UPI00003E5A05 tolerated(0.37) benign(0.031) 3/6 Superfamily:SSF48726,SMART:SM00409,Pfam:PF07686,Gene3D:2.60.40.10,PANTHER:PTHR24100,PANTHER:PTHR24100:SF55,PROSITE_profiles:PS50835 MODERATE 1 SNV 1 . TCC . . 44236903 +ICOSLG 23308 . GRCh38 21 44237111 44237111 + Nonsense_Mutation SNP C C T novel TUMOR NORMAL C C c.162G>A p.Trp54Ter p.W54* ENST00000400379 3/6 944 745 199 596 596 0 ICOSLG,stop_gained,p.Trp54Ter,ENST00000407780,NM_001283052.2,NM_015259.6,NM_001365759.2;ICOSLG,stop_gained,p.Trp54Ter,ENST00000400379,;ICOSLG,stop_gained,p.Trp54Ter,ENST00000344330,NM_001283050.2;ICOSLG,intron_variant,,ENST00000400377,NM_001283051.2;AP001059.2,upstream_gene_variant,,ENST00000619053,; T ENSG00000160223 ENST00000400379 Transcript stop_gained 290/4246 162/1422 54/473 W/* tgG/tgA 1 -1 ICOSLG HGNC HGNC:17087 protein_coding YES ENSP00000383230 K4DIA0.68 UPI00003E5A05 3/6 Superfamily:SSF48726,SMART:SM00409,Pfam:PF07686,Gene3D:2.60.40.10,PANTHER:PTHR24100,PANTHER:PTHR24100:SF55,PROSITE_profiles:PS50835 HIGH 1 SNV 1 . GCC . . 44237111 diff --git a/tests/test_b38_output.more.maf b/tests/test_b38_output.more.maf index b37c3ac..420f1d1 100644 --- a/tests/test_b38_output.more.maf +++ b/tests/test_b38_output.more.maf @@ -1,6 +1,27 @@ #version 2.4 Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type Reference_Allele Tumor_Seq_Allele1 Tumor_Seq_Allele2 dbSNP_RS dbSNP_Val_Status Tumor_Sample_Barcode Matched_Norm_Sample_Barcode Match_Norm_Seq_Allele1 Match_Norm_Seq_Allele2 Tumor_Validation_Allele1 Tumor_Validation_Allele2 Match_Norm_Validation_Allele1 Match_Norm_Validation_Allele2 Verification_Status Validation_Status Mutation_Status Sequencing_Phase Sequence_Source Validation_Method Score BAM_File Sequencer Tumor_Sample_UUID Matched_Norm_Sample_UUID HGVSc HGVSp HGVSp_Short Transcript_ID Exon_Number t_depth t_ref_count t_alt_count n_depth n_ref_count n_alt_count all_effects Allele Gene Feature Feature_type Consequence cDNA_position CDS_position Protein_position Amino_acids Codons Existing_variation ALLELE_NUM DISTANCE STRAND_VEP SYMBOL SYMBOL_SOURCE HGNC_ID BIOTYPE CANONICAL CCDS ENSP SWISSPROT TREMBL UNIPARC RefSeq SIFT PolyPhen EXON INTRON DOMAINS AF AFR_AF AMR_AF ASN_AF EAS_AF EUR_AF SAS_AF AA_AF EA_AF CLIN_SIG SOMATIC PUBMED MOTIF_NAME MOTIF_POS HIGH_INF_POS MOTIF_SCORE_CHANGE IMPACT PICK VARIANT_CLASS TSL HGVS_OFFSET PHENO MINIMISED ExAC_AF ExAC_AF_AFR ExAC_AF_AMR ExAC_AF_EAS ExAC_AF_FIN ExAC_AF_NFE ExAC_AF_OTH ExAC_AF_SAS GENE_PHENO FILTER flanking_bps vcf_id vcf_qual ExAC_AF_Adj ExAC_AC_AN_Adj ExAC_AC_AN ExAC_AC_AN_AFR ExAC_AC_AN_AMR ExAC_AC_AN_EAS ExAC_AC_AN_FIN ExAC_AC_AN_NFE ExAC_AC_AN_OTH ExAC_AC_AN_SAS ExAC_FILTER gnomAD_AF gnomAD_AFR_AF gnomAD_AMR_AF gnomAD_ASJ_AF gnomAD_EAS_AF gnomAD_FIN_AF gnomAD_NFE_AF gnomAD_OTH_AF gnomAD_SAS_AF vcf_pos t_GT n_GT -U2AF1 7307 mskcc.org GRCh38 21 43094659 43094660 + In_Frame_Ins INS - - CTCATA rs1349995283 MSK_T001 MSK_N001 - - c.472_477dup p.Tyr158_Glu159dup p.Y158_E159dup ENST00000291552 6/8 20 10 10 11 11 0 U2AF1,inframe_insertion,p.Tyr85_Glu86dup,ENST00000459639,NM_001025204.1;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000291552,NM_006758.3;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,3_prime_UTR_variant,,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000496462,; CTCATA ENSG00000160201 ENST00000291552 Transcript inframe_insertion 553-554/945 477-478/723 159-160/240 -/YE -/TATGAG rs1349995283 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 6/8 Pfam:PF00642,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 MODERATE 1 insertion 1 1 . ATC . . 3.978e-06 8.795e-06 43094659 0/1 0/0 -U2AF1 7307 mskcc.org GRCh38 21 43094660 43094661 + In_Frame_Ins INS - - TCATAC novel MSK_T001 MSK_N001 - - c.472_477dup p.Tyr158_Glu159dup p.Y158_E159dup ENST00000291552 6/8 20 10 10 11 11 0 U2AF1,inframe_insertion,p.Tyr85_Glu86dup,ENST00000459639,NM_001025204.1;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000291552,NM_006758.3;U2AF1,inframe_insertion,p.Tyr158_Glu159dup,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,3_prime_UTR_variant,,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000496462,; TCATAC ENSG00000160201 ENST00000291552 Transcript inframe_insertion 552-553/945 476-477/723 159/240 E/EYE gag/gaGTATGAg 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 6/8 Pfam:PF00642,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 MODERATE 1 insertion 1 -1 1 . TCT . . 43094660 0/1 0/0 -U2AF1 7307 mskcc.org GRCh38 21 43094667 43094667 + Missense_Mutation SNP T T C rs371246226 MSK_T001 MSK_N001 T T c.470A>G p.Gln157Arg p.Q157R ENST00000291552 6/8 20 10 10 11 11 0 U2AF1,missense_variant,p.Gln84Arg,ENST00000459639,NM_001025204.1;U2AF1,missense_variant,p.Gln157Arg,ENST00000291552,NM_006758.3;U2AF1,missense_variant,p.Gln157Arg,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,3_prime_UTR_variant,,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000496462,; C ENSG00000160201 ENST00000291552 Transcript missense_variant 546/945 470/723 157/240 Q/R cAg/cGg rs371246226,COSV52341120,COSV52341147 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 deleterious(0) probably_damaging(0.971) 6/8 Pfam:PF00642,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 0.0001163 likely_pathogenic 0,1,1 22158538,23029227,23861105 MODERATE 1 SNV 1 1,1,1 1 . CTG . . 2.387e-05 6.16e-05 9.923e-05 3.519e-05 43094667 0/1 0/0 -U2AF1 7307 mskcc.org GRCh38 21 43104346 43104346 + Missense_Mutation SNP G G T rs371769427 MSK_T001 MSK_N001 G G c.101C>A p.Ser34Tyr p.S34Y ENST00000291552 2/8 20 10 10 11 11 0 U2AF1,missense_variant,p.Ser34Tyr,ENST00000291552,NM_006758.3;U2AF1,missense_variant,p.Ser34Tyr,ENST00000380276,NM_001025203.1;U2AF1,5_prime_UTR_variant,,ENST00000459639,NM_001025204.1;AP001631.2,upstream_gene_variant,,ENST00000668861,;U2AF1,missense_variant,p.Ser34Tyr,ENST00000464750,;U2AF1,missense_variant,p.Ser34Tyr,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000496462,;U2AF1,non_coding_transcript_exon_variant,,ENST00000463599,;U2AF1,upstream_gene_variant,,ENST00000468039,; T ENSG00000160201 ENST00000291552 Transcript missense_variant 177/945 101/723 34/240 S/Y tCt/tAt rs371769427,COSV52341059,COSV52341472 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081 UPI0000000C26 NM_006758.3 deleterious(0) probably_damaging(0.997) 2/8 Pfam:PF00642,Prints:PR01848,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 likely_pathogenic 0,1,1 26619011,22158538,23029227,23861105,24498085 MODERATE 1 SNV 1 1,1,1 1 . AGA . . 8.004e-06 1.766e-05 43104346 0/1 0/0 +RUNX1 861 mskcc.org GRCh38 21 34792292 34792292 + Missense_Mutation SNP A A C novel MSK_T001 MSK_N001 A A c.1286T>G p.Leu429Arg p.L429R ENST00000300305 8/8 54 . 21 0 . . RUNX1,missense_variant,p.Leu402Arg,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Leu429Arg,ENST00000300305,;RUNX1,missense_variant,p.Leu429Arg,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Leu429Arg,ENST00000437180,;RUNX1,missense_variant,p.Leu338Arg,ENST00000399240,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; C ENSG00000159216 ENST00000300305 Transcript missense_variant 1731/6222 1286/1443 429/480 L/R cTg/cGg 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A deleterious(0) possibly_damaging(0.887) 8/8 PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Pfam:PF08504,Prints:PR00967 MODERATE 1 SNV 1 1 . CAG . . 34792292 0/1 0/0 +RUNX1 861 mskcc.org GRCh38 21 34792478 34792478 + Missense_Mutation SNP C C T rs867474432 MSK_T001 MSK_N001 C C c.1100G>A p.Gly367Asp p.G367D ENST00000300305 8/8 901 778 123 482 482 0 RUNX1,missense_variant,p.Gly340Asp,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Gly367Asp,ENST00000300305,;RUNX1,missense_variant,p.Gly367Asp,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Gly367Asp,ENST00000437180,;RUNX1,missense_variant,p.Gly276Asp,ENST00000399240,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; T ENSG00000159216 ENST00000300305 Transcript missense_variant 1545/6222 1100/1443 367/480 G/D gGc/gAc rs867474432,COSV55867253 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A deleterious(0.01) possibly_damaging(0.568) 8/8 Low_complexity_(Seg):seg,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:4.10.770.10 0,1 MODERATE 1 SNV 1 0,1 1 . GCC . . 34792478 0/1 0/0 +RUNX1 861 mskcc.org GRCh38 21 34880549 34880549 + Splice_Region SNP T T C novel MSK_T001 MSK_N001 T T c.508+8A>G ENST00000300305 504 450 54 0 . . RUNX1,splice_region_variant,,ENST00000300305,;RUNX1,splice_region_variant,,ENST00000344691,NM_001001890.3;RUNX1,splice_region_variant,,ENST00000358356,NM_001122607.2;RUNX1,splice_region_variant,,ENST00000399237,;RUNX1,splice_region_variant,,ENST00000399240,;RUNX1,splice_region_variant,,ENST00000437180,;RUNX1,splice_region_variant,,ENST00000675419,NM_001754.5;RUNX1,downstream_gene_variant,,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,splice_region_variant,,ENST00000482318,; C ENSG00000159216 ENST00000300305 Transcript splice_region_variant,intron_variant 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A 4/7 LOW 1 SNV 1 1 . ATA . . 34880549 0/1 0/0 +RUNX1 861 mskcc.org GRCh38 21 34880555 34880556 + Splice_Site INS - - CCTCTT novel MSK_T001 MSK_N001 - - c.504_508+1dup p.X168_splice ENST00000300305 883 658 225 343 343 0 RUNX1,splice_donor_variant,,ENST00000300305,;RUNX1,splice_donor_variant,,ENST00000344691,NM_001001890.3;RUNX1,splice_donor_variant,,ENST00000358356,NM_001122607.2;RUNX1,splice_donor_variant,,ENST00000399237,;RUNX1,splice_donor_variant,,ENST00000399240,;RUNX1,splice_donor_variant,,ENST00000437180,;RUNX1,splice_donor_variant,,ENST00000675419,NM_001754.5;RUNX1,downstream_gene_variant,,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,splice_donor_variant,,ENST00000482318,; CCTCTT ENSG00000159216 ENST00000300305 Transcript splice_donor_variant 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A 4/7 HIGH 1 insertion 1 1 . TAC . . 34880555 0/1 0/0 +RUNX1 861 mskcc.org GRCh38 21 34880595 34880595 + Missense_Mutation SNP C C T MSK_T001 MSK_N001 C C c.470G>A p.Arg157Lys p.R157K ENST00000300305 4/8 862 788 74 523 522 1 RUNX1,missense_variant,p.Arg130Lys,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Arg157Lys,ENST00000300305,;RUNX1,missense_variant,p.Arg157Lys,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Arg157Lys,ENST00000437180,;RUNX1,missense_variant,p.Arg130Lys,ENST00000358356,NM_001122607.2;RUNX1,missense_variant,p.Arg130Lys,ENST00000399240,;RUNX1,missense_variant,p.Arg145Lys,ENST00000399237,;RUNX1,downstream_gene_variant,,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; T ENSG00000159216 ENST00000300305 Transcript missense_variant 915/6222 470/1443 157/480 R/K aGa/aAa COSV55871984,COSV55885034 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A tolerated(0.16) probably_damaging(0.978) 4/8 PROSITE_profiles:PS51062,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:2.60.40.720,Pfam:PF00853,Superfamily:SSF49417,Prints:PR00967 1,1 MODERATE 1 SNV 1 1,1 1 . TCT . . 34880595 0/1 0/0 +RUNX1 861 mskcc.org GRCh38 21 34880650 34880651 + Frame_Shift_Ins INS - - G novel MSK_T001 MSK_N001 - - c.414_415insC p.Asn139GlnfsTer5 p.N139Qfs*5 ENST00000300305 4/8 611 449 162 528 527 1 RUNX1,frameshift_variant,p.Asn112GlnfsTer5,ENST00000344691,NM_001001890.3;RUNX1,frameshift_variant,p.Asn139GlnfsTer5,ENST00000300305,;RUNX1,frameshift_variant,p.Asn139GlnfsTer5,ENST00000675419,NM_001754.5;RUNX1,frameshift_variant,p.Asn139GlnfsTer5,ENST00000437180,;RUNX1,frameshift_variant,p.Asn112GlnfsTer5,ENST00000358356,NM_001122607.2;RUNX1,frameshift_variant,p.Asn112GlnfsTer5,ENST00000399240,;RUNX1,frameshift_variant,p.Asn127GlnfsTer5,ENST00000399237,;RUNX1,frameshift_variant,p.Asn126GlnfsTer5,ENST00000455571,;AP000331.1,intron_variant,,ENST00000651798,;RUNX1,3_prime_UTR_variant,,ENST00000482318,; G ENSG00000159216 ENST00000300305 Transcript frameshift_variant 859-860/6222 414-415/1443 138-139/480 -/X -/C 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A 4/8 PROSITE_profiles:PS51062,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:2.60.40.720,Pfam:PF00853,Superfamily:SSF49417,Prints:PR00967 HIGH 1 insertion 1 1 . TTT . . 34880650 0/1 0/0 +RUNX1 861 mskcc.org GRCh38 21 34886911 34886911 + Missense_Mutation SNP G G A novel MSK_T001 MSK_N001 G G c.283C>T p.Pro95Ser p.P95S ENST00000300305 3/8 51 34 17 0 . . RUNX1,missense_variant,p.Pro68Ser,ENST00000344691,NM_001001890.3;RUNX1,missense_variant,p.Pro95Ser,ENST00000300305,;RUNX1,missense_variant,p.Pro95Ser,ENST00000675419,NM_001754.5;RUNX1,missense_variant,p.Pro95Ser,ENST00000437180,;RUNX1,missense_variant,p.Pro68Ser,ENST00000358356,NM_001122607.2;RUNX1,missense_variant,p.Pro68Ser,ENST00000399240,;RUNX1,missense_variant,p.Pro83Ser,ENST00000399237,;RUNX1,missense_variant,p.Pro82Ser,ENST00000455571,;RUNX1,downstream_gene_variant,,ENST00000475045,;AP000331.1,downstream_gene_variant,,ENST00000651798,;RUNX1,intron_variant,,ENST00000482318,;,regulatory_region_variant,,ENSR00000141768,; A ENSG00000159216 ENST00000300305 Transcript missense_variant 728/6222 283/1443 95/480 P/S Ccc/Tcc 1 -1 RUNX1 HGNC HGNC:10471 protein_coding YES CCDS13639.1 ENSP00000300305 Q01196.238 UPI000015FE6A deleterious(0) probably_damaging(0.997) 3/8 PROSITE_profiles:PS51062,PANTHER:PTHR11950:SF40,PANTHER:PTHR11950,PIRSF:PIRSF009374,Gene3D:2.60.40.720,Pfam:PF00853,Superfamily:SSF49417,Prints:PR00967,Prints:PR00967 MODERATE 1 SNV 1 1 . GGG . . 34886911 0/1 0/0 +SETD4 54093 mskcc.org GRCh38 21 36043782 36043782 + Missense_Mutation SNP C C G novel MSK_T001 MSK_N001 C C c.901G>C p.Glu301Gln p.E301Q ENST00000399215 6/10 1140 1010 130 975 975 0 SETD4,missense_variant,p.Glu301Gln,ENST00000399215,;SETD4,missense_variant,p.Glu277Gln,ENST00000399212,NM_001286752.2;SETD4,missense_variant,p.Glu301Gln,ENST00000332131,NM_017438.5;SETD4,missense_variant,p.Gly277Arg,ENST00000399201,;SETD4,missense_variant,p.Gly277Arg,ENST00000399205,NM_001007261.2;SETD4,missense_variant,p.Gly301Arg,ENST00000399208,NM_001007259.2;SETD4,missense_variant,p.Gly301Arg,ENST00000399207,;SETD4,downstream_gene_variant,,ENST00000424303,;SETD4,downstream_gene_variant,,ENST00000429161,;SETD4,downstream_gene_variant,,ENST00000442559,;SETD4,downstream_gene_variant,,ENST00000446166,;SETD4,splice_region_variant,,ENST00000481477,;SETD4,upstream_gene_variant,,ENST00000469482,;SETD4,downstream_gene_variant,,ENST00000485865,;SETD4,upstream_gene_variant,,ENST00000487297,; G ENSG00000185917 ENST00000399215 Transcript missense_variant,splice_region_variant 2274/4272 901/1323 301/440 E/Q Gaa/Caa 1 -1 SETD4 HGNC HGNC:1258 protein_coding YES CCDS13640.1 ENSP00000382163 Q9NVD3.158 UPI000012868E deleterious(0.01) benign(0.203) 6/10 PANTHER:PTHR13271,PANTHER:PTHR13271:SF8,PIRSF:PIRSF027158 MODERATE 1 SNV 2 . CCT . . 36043782 0/1 0/0 +ERG 2078 mskcc.org GRCh38 21 38383625 38383625 + Silent SNP T T C novel MSK_T001 MSK_N001 T T c.1239A>G p.Ser413= p.S413= ENST00000417133 12/12 352 329 23 0 . . ERG,synonymous_variant,p.Ser389=,ENST00000442448,NM_004449.4;ERG,synonymous_variant,p.Ser413=,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,synonymous_variant,p.Ser390=,ENST00000398910,NM_001291391.1;ERG,synonymous_variant,p.Ser389=,ENST00000398911,;ERG,synonymous_variant,p.Ser406=,ENST00000288319,NM_182918.4;ERG,synonymous_variant,p.Ser383=,ENST00000398907,;ERG,synonymous_variant,p.Ser382=,ENST00000398905,NM_001331025.2;ERG,synonymous_variant,p.Ser290=,ENST00000398897,NM_001243429.1;ERG,synonymous_variant,p.Ser413=,ENST00000398919,NM_001243428.1;ERG,synonymous_variant,p.Ser314=,ENST00000453032,NM_001136155.1; C ENSG00000157554 ENST00000417133 Transcript synonymous_variant 1425/5023 1239/1461 413/486 S tcA/tcG 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 12/12 PANTHER:PTHR11849,PANTHER:PTHR11849:SF216,Superfamily:SSF46785 LOW 1 SNV 2 1 . ATG . . 38383625 0/1 0/0 +ERG 2078 mskcc.org GRCh38 21 38400597 38400597 + Missense_Mutation SNP G G A MSK_T001 MSK_N001 G G c.743C>T p.Thr248Met p.T248M ENST00000417133 8/12 1199 892 307 567 566 1 ERG,missense_variant,p.Thr248Met,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Thr248Met,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Thr241Met,ENST00000288319,NM_182918.4;ERG,missense_variant,p.Thr241Met,ENST00000398907,;ERG,missense_variant,p.Thr248Met,ENST00000398919,NM_001243428.1;ERG,missense_variant,p.Thr149Met,ENST00000453032,NM_001136155.1;ERG,missense_variant,p.Thr209Met,ENST00000429727,;ERG,intron_variant,,ENST00000398897,NM_001243429.1;ERG,intron_variant,,ENST00000398905,NM_001331025.2;ERG,intron_variant,,ENST00000398911,;ERG,intron_variant,,ENST00000442448,NM_004449.4;ERG,non_coding_transcript_exon_variant,,ENST00000492833,;ERG,intron_variant,,ENST00000481609,;ERG,downstream_gene_variant,,ENST00000473107,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,;,regulatory_region_variant,,ENSR00000662899,; A ENSG00000157554 ENST00000417133 Transcript missense_variant 929/5023 743/1461 248/486 T/M aCg/aTg COSV55741264 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 tolerated(0.19) benign(0.39) 8/12 PANTHER:PTHR11849,PANTHER:PTHR11849:SF216 1 MODERATE 1 SNV 2 1 1 . CGT . . 38400597 0/1 0/0 +ERG 2078 mskcc.org GRCh38 21 38400606 38400606 + Missense_Mutation SNP G G T MSK_T001 MSK_N001 G G c.734C>A p.Pro245His p.P245H ENST00000417133 8/12 343 190 153 507 507 0 ERG,missense_variant,p.Pro245His,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Pro245His,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Pro238His,ENST00000288319,NM_182918.4;ERG,missense_variant,p.Pro238His,ENST00000398907,;ERG,missense_variant,p.Pro245His,ENST00000398919,NM_001243428.1;ERG,missense_variant,p.Pro146His,ENST00000453032,NM_001136155.1;ERG,missense_variant,p.Pro206His,ENST00000429727,;ERG,intron_variant,,ENST00000398897,NM_001243429.1;ERG,intron_variant,,ENST00000398905,NM_001331025.2;ERG,intron_variant,,ENST00000398911,;ERG,intron_variant,,ENST00000442448,NM_004449.4;ERG,non_coding_transcript_exon_variant,,ENST00000492833,;ERG,intron_variant,,ENST00000481609,;ERG,downstream_gene_variant,,ENST00000473107,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,;,regulatory_region_variant,,ENSR00000662899,; T ENSG00000157554 ENST00000417133 Transcript missense_variant 920/5023 734/1461 245/486 P/H cCt/cAt COSV55741651 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 tolerated(0.1) benign(0.227) 8/12 PANTHER:PTHR11849,PANTHER:PTHR11849:SF216 1 MODERATE 1 SNV 2 1 1 . AGG . . 38400606 0/1 0/0 +ERG 2078 mskcc.org GRCh38 21 38403659 38403659 + Missense_Mutation SNP C C T novel MSK_T001 MSK_N001 C C c.460G>A p.Val154Met p.V154M ENST00000417133 6/12 287 149 138 0 . . ERG,missense_variant,p.Val154Met,ENST00000442448,NM_004449.4;ERG,missense_variant,p.Val154Met,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Val154Met,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Val154Met,ENST00000398911,;ERG,missense_variant,p.Val147Met,ENST00000288319,NM_182918.4;ERG,missense_variant,p.Val147Met,ENST00000398907,;ERG,missense_variant,p.Val147Met,ENST00000398905,NM_001331025.2;ERG,missense_variant,p.Val55Met,ENST00000398897,NM_001243429.1;ERG,missense_variant,p.Val154Met,ENST00000398919,NM_001243428.1;ERG,missense_variant,p.Val55Met,ENST00000453032,NM_001136155.1;ERG,missense_variant,p.Val115Met,ENST00000429727,;ERG,non_coding_transcript_exon_variant,,ENST00000481609,;ERG,non_coding_transcript_exon_variant,,ENST00000492833,;ERG,non_coding_transcript_exon_variant,,ENST00000473107,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,; T ENSG00000157554 ENST00000417133 Transcript missense_variant 646/5023 460/1461 154/486 V/M Gtg/Atg 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 deleterious(0.04) possibly_damaging(0.76) 6/12 Gene3D:1.10.150.50,PDB-ENSP_mappings:1sxe.A,Pfam:PF02198,PROSITE_profiles:PS51433,PANTHER:PTHR11849,PANTHER:PTHR11849:SF216,SMART:SM00251,Superfamily:SSF47769,CDD:cd08540 MODERATE 1 SNV 2 1 . ACC . . 38403659 0/1 0/0 +ERG 2078 mskcc.org GRCh38 21 38575684 38575684 + Missense_Mutation SNP G G A rs201302788 MSK_T001 MSK_N001 G G c.17C>T p.Pro6Leu p.P6L ENST00000417133 3/12 191 92 99 0 . . ERG,missense_variant,p.Pro6Leu,ENST00000442448,NM_004449.4;ERG,missense_variant,p.Pro6Leu,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,missense_variant,p.Pro6Leu,ENST00000398910,NM_001291391.1;ERG,missense_variant,p.Pro6Leu,ENST00000398911,;ERG,missense_variant,p.Pro6Leu,ENST00000398919,NM_001243428.1;ERG,5_prime_UTR_variant,,ENST00000398897,NM_001243429.1;ERG,5_prime_UTR_variant,,ENST00000429727,;ERG,non_coding_transcript_exon_variant,,ENST00000485493,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,; A ENSG00000157554 ENST00000417133 Transcript missense_variant 203/5023 17/1461 6/486 P/L cCg/cTg rs201302788 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 deleterious_low_confidence(0) benign(0.001) 3/12 0.0001163 MODERATE 1 SNV 2 1 . CGG . . 4.776e-05 0.0001056 38575684 0/1 0/0 +ERG 2078 mskcc.org GRCh38 21 38575698 38575698 + Translation_Start_Site SNP C C T MSK_T001 MSK_N001 C C c.3G>A p.Met1? p.M1? ENST00000417133 3/12 331 223 96 449 442 0 ERG,start_lost,p.Met1?,ENST00000442448,NM_004449.4;ERG,start_lost,p.Met1?,ENST00000417133,NM_001243432.2,NM_001136154.1;ERG,start_lost,p.Met1?,ENST00000398910,NM_001291391.1;ERG,start_lost,p.Met1?,ENST00000398911,;ERG,start_lost,p.Met1?,ENST00000398919,NM_001243428.1;ERG,5_prime_UTR_variant,,ENST00000398897,NM_001243429.1;ERG,5_prime_UTR_variant,,ENST00000429727,;ERG,non_coding_transcript_exon_variant,,ENST00000485493,;ERG,non_coding_transcript_exon_variant,,ENST00000468474,; T ENSG00000157554 ENST00000417133 Transcript start_lost 189/5023 3/1461 1/486 M/I atG/atA COSV67366082 1 -1 ERG HGNC HGNC:3446 protein_coding YES CCDS46648.1 ENSP00000414150 P11308.209 UPI000018681C NM_001243432.2,NM_001136154.1 deleterious_low_confidence(0.03) benign(0.38) 3/12 1 HIGH 1 SNV 2 1 1 . TCA . . 38575698 0/1 0/0 +TMPRSS2 7113 mskcc.org GRCh38 21 41479183 41479183 + Frame_Shift_Del DEL T T - novel MSK_T001 MSK_N001 T T c.831del p.Lys277AsnfsTer19 p.K277Nfs*19 ENST00000679263 7/14 512 435 77 695 695 0 TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000676973,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000679054,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000678348,;TMPRSS2,frameshift_variant,p.Lys277AsnfsTer19,ENST00000679263,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000332149,NM_005656.4;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000678171,NM_001382720.1;TMPRSS2,frameshift_variant,p.Lys155AsnfsTer19,ENST00000679016,;TMPRSS2,frameshift_variant,p.Lys261AsnfsTer19,ENST00000398585,NM_001135099.1;TMPRSS2,frameshift_variant,p.Lys116AsnfsTer19,ENST00000678743,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000454499,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000458356,;TMPRSS2,frameshift_variant,p.Lys184AsnfsTer19,ENST00000424093,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer19,ENST00000679181,;TMPRSS2,frameshift_variant,p.Lys224AsnfsTer16,ENST00000677680,;TMPRSS2,3_prime_UTR_variant,,ENST00000678959,;,regulatory_region_variant,,ENSR00001056496,; - ENSG00000184012 ENST00000679263 Transcript frameshift_variant 974/3623 831/1638 277/545 K/X aaA/aa 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 7/14 Pfam:PF15494,Gene3D:3.10.250.10,SMART:SM00202,Superfamily:SSF56487,PANTHER:PTHR24253,PANTHER:PTHR24253:SF89 HIGH 1 deletion 1 . AGTT . . 41479182 0/1 0/0 +TMPRSS2 7113 mskcc.org GRCh38 21 41479219 41479219 + Silent SNP C C T novel MSK_T001 MSK_N001 C C c.795G>A p.Leu265= p.L265= ENST00000679263 7/14 1224 782 373 1044 996 0 TMPRSS2,synonymous_variant,p.Leu212=,ENST00000676973,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000679054,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000678348,;TMPRSS2,synonymous_variant,p.Leu265=,ENST00000679263,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000332149,NM_005656.4;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000678171,NM_001382720.1;TMPRSS2,synonymous_variant,p.Leu143=,ENST00000679016,;TMPRSS2,synonymous_variant,p.Leu249=,ENST00000398585,NM_001135099.1;TMPRSS2,synonymous_variant,p.Leu104=,ENST00000678743,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000454499,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000458356,;TMPRSS2,synonymous_variant,p.Leu172=,ENST00000424093,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000679181,;TMPRSS2,synonymous_variant,p.Leu212=,ENST00000677680,;TMPRSS2,3_prime_UTR_variant,,ENST00000678959,;,regulatory_region_variant,,ENSR00001056496,; T ENSG00000184012 ENST00000679263 Transcript synonymous_variant 938/3623 795/1638 265/545 L ctG/ctA 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 7/14 Pfam:PF15494,Gene3D:3.10.250.10,SMART:SM00202,Superfamily:SSF56487,PANTHER:PTHR24253,PANTHER:PTHR24253:SF89 LOW 1 SNV 1 . TCA . . 41479219 0/1 0/0 +TMPRSS2 7113 mskcc.org GRCh38 21 41488494 41488494 + Missense_Mutation SNP G G T MSK_T001 MSK_N001 G G c.504C>A p.Asn168Lys p.N168K ENST00000679263 5/14 380 350 30 0 . . TMPRSS2,missense_variant,p.Asn115Lys,ENST00000676973,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000679054,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000678348,;TMPRSS2,missense_variant,p.Asn168Lys,ENST00000679263,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000332149,NM_005656.4;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000678171,NM_001382720.1;TMPRSS2,missense_variant,p.Asn152Lys,ENST00000398585,NM_001135099.1;TMPRSS2,missense_variant,p.Asn7Lys,ENST00000678743,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000454499,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000458356,;TMPRSS2,intron_variant,,ENST00000424093,;TMPRSS2,intron_variant,,ENST00000679016,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000463138,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000679181,;TMPRSS2,missense_variant,p.Asn115Lys,ENST00000677680,;TMPRSS2,3_prime_UTR_variant,,ENST00000678959,; T ENSG00000184012 ENST00000679263 Transcript missense_variant 647/3623 504/1638 168/545 N/K aaC/aaA COSV59825472 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 tolerated(0.95) benign(0.07) 5/14 CDD:cd00112,Gene3D:4.10.400.10,SMART:SM00192,Superfamily:SSF57424,PROSITE_profiles:PS50068,PANTHER:PTHR24253,PANTHER:PTHR24253:SF89 1 MODERATE 1 SNV 1 1 . AGT . . 41488494 0/1 0/0 +TMPRSS2 7113 mskcc.org GRCh38 21 41494550 41494550 + Missense_Mutation SNP T T C rs774327563 MSK_T001 MSK_N001 T T c.203A>G p.Tyr68Cys p.Y68C ENST00000679263 3/14 356 260 96 781 781 0 TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000676973,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000679054,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000678348,;TMPRSS2,missense_variant,p.Tyr68Cys,ENST00000679263,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000332149,NM_005656.4;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000678171,NM_001382720.1;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000679016,;TMPRSS2,missense_variant,p.Tyr52Cys,ENST00000398585,NM_001135099.1;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000454499,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000458356,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000424093,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000455813,;TMPRSS2,intron_variant,,ENST00000678743,;TMPRSS2,non_coding_transcript_exon_variant,,ENST00000678617,;TMPRSS2,intron_variant,,ENST00000463138,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000679181,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000677680,;TMPRSS2,missense_variant,p.Tyr15Cys,ENST00000678959,; C ENSG00000184012 ENST00000679263 Transcript missense_variant 346/3623 203/1638 68/545 Y/C tAt/tGt rs774327563 1 -1 TMPRSS2 HGNC HGNC:11876 protein_coding YES ENSP00000504602 tolerated(0.06) benign(0.412) 3/14 MODERATE 1 SNV 1 . ATA . . 1.995e-05 0.0001232 5.444e-05 1.762e-05 41494550 0/1 0/0 +UMODL1 89766 mskcc.org GRCh38 21 42085325 42085325 + Silent SNP C C T rs185422923 MSK_T001 MSK_N001 C C c.516C>T p.Asn172= p.N172= ENST00000408989 4/22 366 193 173 0 . . UMODL1,synonymous_variant,p.Asn100=,ENST00000400424,NM_001199528.3;UMODL1,synonymous_variant,p.Asn100=,ENST00000400427,NM_001199527.2;UMODL1,synonymous_variant,p.Asn172=,ENST00000408989,NM_173568.3;UMODL1,synonymous_variant,p.Asn172=,ENST00000408910,NM_001004416.2;UMODL1,synonymous_variant,p.Asn8=,ENST00000491559,;UMODL1,synonymous_variant,p.Asn8=,ENST00000466434,;UMODL1,synonymous_variant,p.Asn8=,ENST00000400421,;UMODL1,synonymous_variant,p.Asn8=,ENST00000468982,;UMODL1,synonymous_variant,p.Asn8=,ENST00000485357,;UMODL1,synonymous_variant,p.Asn8=,ENST00000497243,; T ENSG00000177398 ENST00000408989 Transcript synonymous_variant 516/5262 516/4341 172/1446 N aaC/aaT rs185422923 1 1 UMODL1 HGNC HGNC:12560 protein_coding YES CCDS42935.1 ENSP00000386126 Q5DID0.131 UPI0000D6254B NM_173568.3 4/22 PANTHER:PTHR14002,PANTHER:PTHR14002:SF22 0.0002 0.0008 0.0001207 LOW 1 SNV 1 . ACG . . 8.016e-06 6.457e-05 3.268e-05 42085325 0/1 0/0 +U2AF1 7307 mskcc.org GRCh38 21 43093128 43093128 + Missense_Mutation SNP C C T novel MSK_T001 MSK_N001 C C c.697G>A p.Asp233Asn p.D233N ENST00000291552 8/8 454 425 29 344 344 0 U2AF1,missense_variant,p.Asp160Asn,ENST00000459639,NM_001025204.1;U2AF1,missense_variant,p.Asp233Asn,ENST00000291552,NM_006758.3;U2AF1,missense_variant,p.Asp233Asn,ENST00000380276,NM_001025203.1;U2AF1,3_prime_UTR_variant,,ENST00000464750,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000478282,;U2AF1,non_coding_transcript_exon_variant,,ENST00000471250,;U2AF1,downstream_gene_variant,,ENST00000463599,;U2AF1,downstream_gene_variant,,ENST00000486519,;U2AF1,downstream_gene_variant,,ENST00000496462,; T ENSG00000160201 ENST00000291552 Transcript missense_variant 773/945 697/723 233/240 D/N Gat/Aat 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081.224 UPI0000000C26 NM_006758.3 tolerated(0.44) possibly_damaging(0.857) 8/8 PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,MobiDB_lite:mobidb-lite,MobiDB_lite:mobidb-lite,Low_complexity_(Seg):seg MODERATE 1 SNV 1 1 . TCT . . 43093128 0/1 0/0 +U2AF1 7307 mskcc.org GRCh38 21 43104375 43104375 + Silent SNP A A G rs755067307 MSK_T001 MSK_N001 A A c.72T>C p.Ile24= p.I24= ENST00000291552 2/8 667 607 60 0 . . U2AF1,synonymous_variant,p.Ile24=,ENST00000291552,NM_006758.3;U2AF1,synonymous_variant,p.Ile24=,ENST00000380276,NM_001025203.1;U2AF1,5_prime_UTR_variant,,ENST00000459639,NM_001025204.1;AP001631.2,upstream_gene_variant,,ENST00000668861,;U2AF1,synonymous_variant,p.Ile24=,ENST00000464750,;U2AF1,synonymous_variant,p.Ile24=,ENST00000486519,;U2AF1,non_coding_transcript_exon_variant,,ENST00000475639,;U2AF1,non_coding_transcript_exon_variant,,ENST00000496462,;U2AF1,non_coding_transcript_exon_variant,,ENST00000463599,;U2AF1,upstream_gene_variant,,ENST00000468039,; G ENSG00000160201 ENST00000291552 Transcript synonymous_variant 148/945 72/723 24/240 I atT/atC rs755067307 1 -1 U2AF1 HGNC HGNC:12453 protein_coding YES CCDS13694.1 ENSP00000291552 Q01081.224 UPI0000000C26 NM_006758.3 2/8 Pfam:PF00642,Prints:PR01848,PROSITE_profiles:PS50103,PANTHER:PTHR12620,PANTHER:PTHR12620:SF11,SMART:SM00356 LOW 1 SNV 1 1 . CAA . . 7.992e-06 2.921e-05 8.823e-06 43104375 0/1 0/0 +SIK1 150094 mskcc.org GRCh38 21 43419117 43419117 + Missense_Mutation SNP C C T novel MSK_T001 MSK_N001 C C c.1366G>A p.Glu456Lys p.E456K ENST00000270162 11/14 113 . 45 0 . . SIK1,missense_variant,p.Glu456Lys,ENST00000270162,NM_173354.5;SIK1,downstream_gene_variant,,ENST00000644750,;SIK1,downstream_gene_variant,,ENST00000478426,;SIK1,downstream_gene_variant,,ENST00000644689,;SIK1,downstream_gene_variant,,ENST00000644871,; T ENSG00000142178 ENST00000270162 Transcript missense_variant 1502/4747 1366/2352 456/783 E/K Gag/Aag 1 -1 SIK1 HGNC HGNC:11142 protein_coding YES CCDS33575.1 ENSP00000270162 P57059.191 UPI0000206F2B NM_173354.5 deleterious(0.03) possibly_damaging(0.494) 11/14 PIRSF:PIRSF037014,PANTHER:PTHR24346,PANTHER:PTHR24346:SF47,MobiDB_lite:mobidb-lite MODERATE 1 SNV 1 1 . TCC . . 43419117 0/1 0/0 +ICOSLG 23308 mskcc.org GRCh38 21 44235374 44235374 + Missense_Mutation SNP C C A MSK_T001 MSK_N001 C C c.595G>T p.Val199Leu p.V199L ENST00000400379 4/6 101 88 13 153 153 0 ICOSLG,missense_variant,p.Val199Leu,ENST00000407780,NM_001283052.2,NM_015259.6,NM_001365759.2;ICOSLG,missense_variant,p.Val199Leu,ENST00000400379,;ICOSLG,missense_variant,p.Val82Leu,ENST00000400377,NM_001283051.2;ICOSLG,missense_variant,p.Val199Leu,ENST00000344330,NM_001283050.2; A ENSG00000160223 ENST00000400379 Transcript missense_variant 723/4246 595/1422 199/473 V/L Gtg/Ttg COSV60266097 1 -1 ICOSLG HGNC HGNC:17087 protein_coding YES ENSP00000383230 K4DIA0.68 UPI00003E5A05 tolerated(0.06) probably_damaging(0.982) 4/6 Superfamily:SSF48726,Gene3D:2.60.40.10,PANTHER:PTHR24100,PANTHER:PTHR24100:SF55,PROSITE_profiles:PS50835 1 MODERATE 1 SNV 1 1 . ACG . . 44235374 0/1 0/0 +ICOSLG 23308 mskcc.org GRCh38 21 44236903 44236903 + Missense_Mutation SNP C C T novel MSK_T001 MSK_N001 C C c.370G>A p.Glu124Lys p.E124K ENST00000400379 3/6 950 827 123 630 629 1 ICOSLG,missense_variant,p.Glu124Lys,ENST00000407780,NM_001283052.2,NM_015259.6,NM_001365759.2;ICOSLG,missense_variant,p.Glu124Lys,ENST00000400379,;ICOSLG,missense_variant,p.Glu124Lys,ENST00000344330,NM_001283050.2;ICOSLG,intron_variant,,ENST00000400377,NM_001283051.2;AP001059.2,upstream_gene_variant,,ENST00000619053,; T ENSG00000160223 ENST00000400379 Transcript missense_variant 498/4246 370/1422 124/473 E/K Gag/Aag 1 -1 ICOSLG HGNC HGNC:17087 protein_coding YES ENSP00000383230 K4DIA0.68 UPI00003E5A05 tolerated(0.37) benign(0.031) 3/6 Superfamily:SSF48726,SMART:SM00409,Pfam:PF07686,Gene3D:2.60.40.10,PANTHER:PTHR24100,PANTHER:PTHR24100:SF55,PROSITE_profiles:PS50835 MODERATE 1 SNV 1 . TCC . . 44236903 0/1 0/0 +ICOSLG 23308 mskcc.org GRCh38 21 44237111 44237111 + Nonsense_Mutation SNP C C T novel MSK_T001 MSK_N001 C C c.162G>A p.Trp54Ter p.W54* ENST00000400379 3/6 944 745 199 596 596 0 ICOSLG,stop_gained,p.Trp54Ter,ENST00000407780,NM_001283052.2,NM_015259.6,NM_001365759.2;ICOSLG,stop_gained,p.Trp54Ter,ENST00000400379,;ICOSLG,stop_gained,p.Trp54Ter,ENST00000344330,NM_001283050.2;ICOSLG,intron_variant,,ENST00000400377,NM_001283051.2;AP001059.2,upstream_gene_variant,,ENST00000619053,; T ENSG00000160223 ENST00000400379 Transcript stop_gained 290/4246 162/1422 54/473 W/* tgG/tgA 1 -1 ICOSLG HGNC HGNC:17087 protein_coding YES ENSP00000383230 K4DIA0.68 UPI00003E5A05 3/6 Superfamily:SSF48726,SMART:SM00409,Pfam:PF07686,Gene3D:2.60.40.10,PANTHER:PTHR24100,PANTHER:PTHR24100:SF55,PROSITE_profiles:PS50835 HIGH 1 SNV 1 . GCC . . 44237111 0/1 0/0 diff --git a/tests/vcf2maf.t b/tests/vcf2maf.t index e70f6d9..b1fb9a7 100644 --- a/tests/vcf2maf.t +++ b/tests/vcf2maf.t @@ -24,4 +24,4 @@ system( "rm -f tests/test_b38_output.new.maf" ); # Test some more options, diff, and cleanup ok( system( "docker run --rm -v $test_dir:/opt/tests vcf2maf:master perl vcf2maf.pl --inhibit-vep --vep-path /usr/local/bin --vep-data tests --vcf-tumor-id TUMOR --vcf-normal-id NORMAL --tumor-id MSK_T001 --normal-id MSK_N001 --maf-center mskcc.org --vep-forks 1 --buffer-size 50 --ncbi-build GRCh38 --input-vcf tests/test_b38.vep.vcf --output-maf tests/test_b38_output.more.new.maf --ref-fasta tests/Homo_sapiens.GRCh38.dna.chromosome.21.fa --retain-fmt GT" ) == 0 ); ok( system( "bash -c 'diff <(cut -f1-75,77- tests/test_b38_output.more.maf) <(cut -f1-75,77- tests/test_b38_output.more.new.maf)'" ) == 0 ); -system( "rm -f tests/test_b38_output.more.new.maf" ); +system( "rm -f tests/test_b38_output.more.new.maf tests/test_b38.vep.vcf" ); diff --git a/tests/vcf2vcf.t b/tests/vcf2vcf.t index e9728e8..88fc95b 100644 --- a/tests/vcf2vcf.t +++ b/tests/vcf2vcf.t @@ -12,10 +12,8 @@ chdir $script_dir; # Set the number of tests we'll run, and run them use Test::Simple tests => 4; -ok( system( "perl vcf2vcf.pl --help > /dev/null" ) == 0 ); -ok( system( "perl vcf2vcf.pl --man > /dev/null" ) == 0 ); -ok( system( "perl vcf2vcf.pl --input-vcf tests/test.vcf --output-vcf tests/test_grch38.new.vcf --remap-chain data/GRCh37_to_GRCh38.chain" ) == 0 ); -ok( system( "bash -c 'diff <(grep -v ^##fileDate tests/test_grch38.vcf) <(grep -v ^##fileDate tests/test_grch38.new.vcf)'" ) == 0 ); - -# Cleanup -system( "rm -f tests/test_grch38.new.vcf" ); +ok( system( "docker run --rm vcf2maf:master perl vcf2vcf.pl --help > /dev/null" ) == 0 ); +ok( system( "docker run --rm vcf2maf:master perl vcf2vcf.pl --man > /dev/null" ) == 0 ); +ok( system( "docker run --rm -v $test_dir:/opt/tests vcf2maf:master perl vcf2vcf.pl --input-vcf tests/test_b38.vcf --output-vcf tests/test_b37.new.vcf --remap-chain data/GRCh38_to_GRCh37.chain --ref-fasta tests/Homo_sapiens.GRCh38.dna.chromosome.21.fa" ) == 0 ); +ok( system( "bash -c 'diff <(grep -v ^##fileDate tests/test_b37.vcf) <(grep -v ^##fileDate tests/test_b37.new.vcf)'" ) == 0 ); +system( "rm -f tests/test_b37.new.vcf" ); diff --git a/vcf2maf.pl b/vcf2maf.pl index 0f5fca7..4ab7786 100644 --- a/vcf2maf.pl +++ b/vcf2maf.pl @@ -14,7 +14,7 @@ # Set any default paths and constants my ( $tumor_id, $normal_id ) = ( "TUMOR", "NORMAL" ); my ( $vep_path, $vep_data, $vep_forks, $buffer_size, $any_allele, $inhibit_vep, $online ) = ( "$ENV{HOME}/miniconda3/bin", "$ENV{HOME}/.vep", 4, 5000, 0, 0, 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, $retain_info, $retain_fmt, $min_hom_vaf, $max_filter_ac ) = ( "homo_sapiens", "GRCh37", "", ".", "", "", 0.7, 10 ); my $perl_bin = $Config{perlpath}; @@ -1152,12 +1152,12 @@ =head1 OPTIONS --any-allele When reporting co-located variants, allow mismatched variant alleles too --inhibit-vep Skip running VEP, but extract VEP annotation in VCF if found --online Use useastdb.ensembl.org instead of local cache (supports only GRCh38 VCFs listing <100 events) - --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] --filter-vcf A VCF for FILTER tag common_variant; Disabled by default [] --max-filter-ac Use tag common_variant if the filter-vcf reports a subpopulation AC higher than this [10] --species Ensembl-friendly name of species (e.g. mus_musculus for mouse) [homo_sapiens] --ncbi-build NCBI reference assembly of variants MAF (e.g. GRCm38 for mouse) [GRCh37] - --cache-version Version of offline cache to use with VEP (e.g. 75, 91, 101) [Default: Installed version] + --cache-version Version of offline cache to use with VEP (e.g. 75, 91, 102) [Default: Installed version] --maf-center Variant calling center to report in MAF [.] --retain-info Comma-delimited names of INFO fields to retain as extra columns in MAF [] --retain-fmt Comma-delimited names of FORMAT fields to retain as extra columns in MAF [] diff --git a/vcf2vcf.pl b/vcf2vcf.pl index f12d9bb..a6f5186 100644 --- a/vcf2vcf.pl +++ b/vcf2vcf.pl @@ -42,7 +42,7 @@ # Parse options and print usage if there is a syntax error, or if usage was explicitly requested my ( $man, $help, $add_filters ) = ( 0, 0, 0 ); my ( $input_vcf, $output_vcf, $new_tumor_id, $new_normal_id, $remap_chain ); -my ( $tumor_bam, $normal_bam, $ref_fasta ) = ( "", "", "$ENV{HOME}/.vep/homo_sapiens/91_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa.gz" ); +my ( $tumor_bam, $normal_bam, $ref_fasta ) = ( "", "", "$ENV{HOME}/.vep/homo_sapiens/102_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz" ); GetOptions( 'help!' => \$help, 'man!' => \$man, @@ -486,7 +486,7 @@ =head1 OPTIONS --new-normal-id Matched normal ID to use in the new VCF [--vcf-normal-id] --tumor-bam Path to tumor BAM, if provided, will add or override DP:AD:ADF:ADR in output VCF --normal-bam Path to normal BAM, if provided, will add or override DP:AD:ADF:ADR in output VCF - --ref-fasta Reference FASTA file [~/.vep/homo_sapiens/91_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa.gz] + --ref-fasta Reference FASTA file [~/.vep/homo_sapiens/102_GRCh37/Homo_sapiens.GRCh37.dna.toplevel.fa.gz] --add-header VCF-style header lines to add to the output VCF; Use "\n" to separate lines [] --add-info Comma-delimited tag=value pairs to add as INFO fields in the output VCF [] --retain-info Comma-delimited names of INFO fields to retain in output VCF [SOMATIC,SS,I16,MQSB]