Repository 'gemini_comp_hets'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/gemini_comp_hets

Changeset 4:62647e2637f6 (2018-12-14)
Previous changeset 3:7cf9bc210044 (2018-10-17)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gemini commit 283362494058ed64143b1f27afb447b8a1cb4313
modified:
gemini_comp_hets.xml
gemini_macros.xml
repository_dependencies.xml
test-data/anno.bed
test-data/gemini_amend_input.db
test-data/gemini_comphets_input.db
test-data/gemini_de_novo_input.db
test-data/gemini_is_somatic_result.db
tool_data_table_conf.xml.sample
added:
test-data/gemini_amend.ped
test-data/gemini_amend.vcf
test-data/gemini_annotate_result.db
test-data/gemini_auto_dom_input.db
test-data/gemini_auto_rec_input.db
test-data/gemini_burden_calpha_template.tabular
test-data/gemini_burden_count_highimpact_result.tabular
test-data/gemini_burden_count_nonsynonymous_result.tabular
test-data/gemini_load_result1.db
test-data/gemini_load_result2.db
test-data/gemini_versioned_databases.loc
test-data/gemini_windower_template.tabular
test-data/test-cache/gemini-config.yaml
test-data/test-cache/gemini/data/29way_pi_lods_elements_12mers.chr_specific.fdr_0.1_with_scores.txt.hg19.merged.bed.gz
test-data/test-cache/gemini/data/29way_pi_lods_elements_12mers.chr_specific.fdr_0.1_with_scores.txt.hg19.merged.bed.gz.tbi
test-data/test-cache/gemini/data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz
test-data/test-cache/gemini/data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz.tbi
test-data/test-cache/gemini/data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz
test-data/test-cache/gemini/data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz.tbi
test-data/test-cache/gemini/data/ExAC.r0.3.sites.vep.tidy.vcf.gz
test-data/test-cache/gemini/data/ExAC.r0.3.sites.vep.tidy.vcf.gz.tbi
test-data/test-cache/gemini/data/GRC_patch_regions.bed.gz
test-data/test-cache/gemini/data/GRC_patch_regions.bed.gz.tbi
test-data/test-cache/gemini/data/GRCh37-gms-mappability.vcf.gz
test-data/test-cache/gemini/data/GRCh37-gms-mappability.vcf.gz.tbi
test-data/test-cache/gemini/data/cancer_gene_census.20140120.tsv
test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz
test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz.tbi
test-data/test-cache/gemini/data/cosmic-v68-GRCh37.tidy.vcf.gz
test-data/test-cache/gemini/data/cosmic-v68-GRCh37.tidy.vcf.gz.tbi
test-data/test-cache/gemini/data/cse-hiseq-8_4-2013-02-20.bed.gz
test-data/test-cache/gemini/data/cse-hiseq-8_4-2013-02-20.bed.gz.tbi
test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz
test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz.tbi
test-data/test-cache/gemini/data/detailed_gene_table_v75
test-data/test-cache/gemini/data/encode.6celltypes.consensus.bedg.gz
test-data/test-cache/gemini/data/encode.6celltypes.consensus.bedg.gz.tbi
test-data/test-cache/gemini/data/genetic_map_HapMapII_GRCh37.gz
test-data/test-cache/gemini/data/genetic_map_HapMapII_GRCh37.gz.tbi
test-data/test-cache/gemini/data/geno2mp.variants.tidy.vcf.gz
test-data/test-cache/gemini/data/geno2mp.variants.tidy.vcf.gz.tbi
test-data/test-cache/gemini/data/hg19.CpG.bed.gz
test-data/test-cache/gemini/data/hg19.CpG.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.cytoband.bed.gz
test-data/test-cache/gemini/data/hg19.cytoband.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.dgv.bed.gz
test-data/test-cache/gemini/data/hg19.dgv.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.gerp.elements.bed.gz
test-data/test-cache/gemini/data/hg19.gerp.elements.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.gwas.bed.gz
test-data/test-cache/gemini/data/hg19.gwas.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.pfam.ucscgenes.bed.gz
test-data/test-cache/gemini/data/hg19.pfam.ucscgenes.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.rmsk.bed.gz
test-data/test-cache/gemini/data/hg19.rmsk.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.segdup.bed.gz
test-data/test-cache/gemini/data/hg19.segdup.bed.gz.tbi
test-data/test-cache/gemini/data/hg19.vista.enhancers.20131108.bed.gz
test-data/test-cache/gemini/data/hg19.vista.enhancers.20131108.bed.gz.tbi
test-data/test-cache/gemini/data/hg19_fitcons_fc-i6-0_V1-01.bed.gz
test-data/test-cache/gemini/data/hg19_fitcons_fc-i6-0_V1-01.bed.gz.tbi
test-data/test-cache/gemini/data/hprd_interaction_edges.gz
test-data/test-cache/gemini/data/kegg_pathways_ensembl66
test-data/test-cache/gemini/data/kegg_pathways_ensembl67
test-data/test-cache/gemini/data/kegg_pathways_ensembl68
test-data/test-cache/gemini/data/kegg_pathways_ensembl69
test-data/test-cache/gemini/data/kegg_pathways_ensembl70
test-data/test-cache/gemini/data/kegg_pathways_ensembl71
test-data/test-cache/gemini/data/stam.125cells.dnaseI.hg19.bed.gz
test-data/test-cache/gemini/data/stam.125cells.dnaseI.hg19.bed.gz.tbi
test-data/test-cache/gemini/data/summary_gene_table_v75
test-data/test-cache/gemini/data/wgEncodeRegTfbsClusteredV2.cell_count.20130213.bed.gz
test-data/test-cache/gemini/data/wgEncodeRegTfbsClusteredV2.cell_count.20130213.bed.gz.tbi
test-data/util/README.rst
test-data/util/build-data/anno.bed
test-data/util/build-data/anno.bed.gz
test-data/util/build-data/anno.bed.gz.tbi
test-data/util/build-data/gemini_load_input.vcf
test-data/util/build-data/test.auto_dom.ped
test-data/util/build-data/test.auto_dom.vcf
test-data/util/build-data/test.auto_rec.ped
test-data/util/build-data/test.auto_rec.vcf
test-data/util/build-data/test.comp_het.ped
test-data/util/build-data/test.comp_het.vcf
test-data/util/build-data/test.de_novo.ped
test-data/util/build-data/test.de_novo.vcf
test-data/util/build-gemini-testdata.sh
test-data/util/shrink_simple_tab.py
test-data/util/shrink_tabix.py
tool-data/gemini_versioned_databases.loc.sample
tool_data_table_conf.xml.test
removed:
test-data/gemini_amend_input.ped
test-data/gemini_amend_result.db
test-data/gemini_annotate_input.db
test-data/gemini_annotate_result.tabular
test-data/gemini_autosomal_dominant_result.tabular
test-data/gemini_autosomal_input.db
test-data/gemini_autosomal_recessive.tabular
test-data/gemini_burden_input.db
test-data/gemini_burden_result.tabular
test-data/gemini_comphets_result.tabular
test-data/gemini_dbinfo_result.tabular
test-data/gemini_de_novo_result.tabular
test-data/gemini_dump_result.tabular
test-data/gemini_gene_wise_result.tabular
test-data/gemini_interactions_result.tabular
test-data/gemini_load_result.db
test-data/gemini_lofsieve_result.tabular
test-data/gemini_mendel_errors_result.tabular
test-data/gemini_pathways_result.tabular
test-data/gemini_qc_result.tabular
test-data/gemini_query_result.tabular
test-data/gemini_region_result.tabular
test-data/gemini_roh_result.tabular
test-data/gemini_stats_result.tabular
test-data/gemini_windower_input.db
tool-data/gemini_databases.loc.sample
tool_dependencies.xml
b
diff -r 7cf9bc210044 -r 62647e2637f6 gemini_comp_hets.xml
--- a/gemini_comp_hets.xml Wed Oct 17 13:30:12 2018 -0400
+++ b/gemini_comp_hets.xml Fri Dec 14 12:49:22 2018 -0500
b
@@ -1,4 +1,4 @@
-<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.0">
+<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.1">
     <description>Identifying potential compound heterozygotes</description>
     <macros>
         <import>gemini_macros.xml</import>
@@ -62,11 +62,17 @@
     <tests>
         <test>
             <param name="infile" value="gemini_comphets_input.db" ftype="gemini.sqlite" />
-            <param name="report_selector" value="column_filter" />
-            <param name="columns" value="chrom,start,end,ref,alt,gene,impact" />
+            <conditional name="report">
+                <param name="report_selector" value="column_filter" />
+                <param name="columns" value="chrom,start,end,ref,alt,gene,impact" />
+            </conditional>
             <param name="allow_unaffected" value="True" />
             <param name="max_priority" value="3" />
-            <output name="outfile" file="gemini_comphets_result.tabular" />
+            <output name="outfile">
+                <assert_contents>
+                    <has_line_matching expression="chrom&#009;start&#009;end&#009;.*gene.*" />
+                </assert_contents>
+            </output>
         </test>
     </tests>
     <help>
b
diff -r 7cf9bc210044 -r 62647e2637f6 gemini_macros.xml
--- a/gemini_macros.xml Wed Oct 17 13:30:12 2018 -0400
+++ b/gemini_macros.xml Fri Dec 14 12:49:22 2018 -0500
[
@@ -1,7 +1,12 @@
 <macros>
+    <!-- gemini version to be used -->
+    <token name="@VERSION@">0.18.1</token>
+    <!-- minimal annotation files version required by this version of gemini -->
+    <token name="@DB_VERSION@">181</token>
+
     <xml name="requirements">
         <requirements>
-            <requirement type="package" version="0.18.1">gemini</requirement>
+            <requirement type="package" version="@VERSION@">gemini</requirement>
             <requirement type="package" version="0.2.6">tabix</requirement>
             <!-- for conda useage -->
             <!--requirement type="package" version="1.3.1">htslib</requirement-->
@@ -23,9 +28,10 @@
     </xml>
 
     <xml name="annotation_dir">
-        <param name="annotation_databases" type="select" optional="True" label="Choose a gemini annotation database">
-            <options from_data_table="gemini_databases">
+        <param name="annotation_databases" type="select" label="Choose a gemini annotation source">
+            <options from_data_table="gemini_versioned_databases">
                 <filter type="sort_by" column="0" />
+                <filter type="static_value" column="2" value="@DB_VERSION@" />
             </options>
         </param>
     </xml>
@@ -97,6 +103,12 @@
        </sanitizer>
     </xml>
 
+    <token name="@PROVIDE_ANNO_DATA@"><![CDATA[
+        mkdir gemini &&
+        ln -s "${annotation_databases.fields.path}/gemini/data" gemini/data &&
+        export GEMINI_CONFIG="${annotation_databases.fields.path}" &&
+    ]]></token>
+
     <token name="@MULTILN_SQL_EXPR_TO_CMDLN@">
         #set $sql_expr = str($multiline_sql_expr).strip()
         #if str($sql_expr):
@@ -153,7 +165,6 @@
     <xml name="gt_pl_max">
         <param name="gt_pl_max" type="integer" value="-1" min="-1" label="The maximum phred-scaled genotype likelihod (PL) allowed for each sample in a family" help="default: -1 (not set) (--gt-pl-max)" />
     </xml>
-    <token name="@VERSION@">0.18.1</token>
 
     <xml name="citations">
         <citations>
b
diff -r 7cf9bc210044 -r 62647e2637f6 repository_dependencies.xml
--- a/repository_dependencies.xml Wed Oct 17 13:30:12 2018 -0400
+++ b/repository_dependencies.xml Fri Dec 14 12:49:22 2018 -0500
b
@@ -1,4 +1,4 @@
-<?xml version="1.0"?>
+<?xml version="1.0" ?>
 <repositories description="This requires the GEMINI data manager definition to install all required annotation databases.">
-    <repository changeset_revision="172815da3d41" name="data_manager_gemini_database_downloader" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
-</repositories>
+    <repository changeset_revision="fe5a9a7d95b0" name="data_manager_gemini_database_downloader" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"/>
+</repositories>
\ No newline at end of file
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/anno.bed
--- a/test-data/anno.bed Wed Oct 17 13:30:12 2018 -0400
+++ b/test-data/anno.bed Fri Dec 14 12:49:22 2018 -0500
b
@@ -1,3 +1,3 @@
-chr1 30547 30548
-chr1 30920 30925
-chr1 30922 30923
+chr3 187000000 187150000
+chr3 187150000 187300000
+chr3 187300000 187450000
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_amend.ped
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gemini_amend.ped Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,10 @@
+#family_id sample_id paternal_id maternal_id sex phenotype
+1 1_dad 0 0 -1 1
+1 1_mom 0 0 -1 1
+1 1_kid 1_dad 1_mom -1 2
+2 2_dad 0 0 -1 1
+2 2_mom 0 0 -1 1
+2 2_kid 2_dad 2_mom -1 2
+3 3_dad 0 0 -1 1
+3 3_mom 0 0 -1 1
+3 3_kid 3_dad 3_mom -1 2
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_amend.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gemini_amend.vcf Fri Dec 14 12:49:22 2018 -0500
[
b'@@ -0,0 +1,127 @@\n+##fileformat=VCFv4.1\n+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">\n+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">\n+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">\n+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">\n+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher\'s exact test to detect strand bias">\n+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">\n+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">\n+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">\n+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">\n+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">\n+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">\n+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">\n+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">\n+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[bam/M10478.conc.on.pos.realigned.bam, bam/M10475.conc.on.pos.realigned.bam, bam/M10500.conc.on.pos.realigned.bam, bam/M128215.conc.on.pos.realigned.bam] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null interval_set_rule=UNION interval_merging=ALL reference_sequence=/m/cphg-quinlan/cphg-quinlan/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa rodBind=[] nonDeterministicRandomSeed=false downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=10 num_cpu_threads=null num_io_threads=null num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_VARIANTS_ONLY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 computeSLOD=false alleles=(RodBinding name= source=UNBOUND) min_base_quality_score=17 max_deletion_fraction=0.05 multiallelic=false max_alternate_alleles=5 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 indelHaplotypeSize=80 bandedIndel=false indelDebug=false ignoreSNPAlleles=false dbsnp=(RodBinding name='..b'29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n+chr10\t135336656\t.\tG\tA\t38.34\t.\tAC=4;AF=1.00;AN=4;DP=2;Dels=0.00;FS=0.000;HRun=4;HaplotypeScore=0.0000;MQ=37.00;MQ0=0;QD=19.17;CSQ=upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000418356|||,intron_variant&nc_transcript_variant|||ENSG00000214279||ENST00000488261|||,intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541261|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000421586|||,intron_variant|||ENSG00000130649|CYP2E1|ENST00000463117|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000252945|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541080|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000477500|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000480558|||,intron_variant|||ENSG00000214279||ENST00000356567|||;EFF=INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),INTRON(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000463117|),INTRON(MODIFIER||||693|RP11-108K14.4.1|protein_coding|CODING|ENST00000356567|),INTRON(MODIFIER|||||RP11-108K14.4.1|retained_intron|CODING|ENST00000488261|),UPSTREAM(MODIFIER||||305|CYP2E1|protein_coding|CODING|ENST00000418356|),UPSTREAM(MODIFIER||||355|CYP2E1|protein_coding|CODING|ENST00000421586|),UPSTREAM(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000252945|),UPSTREAM(MODIFIER||||85|CYP2E1|protein_coding|CODING|ENST00000541261|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000477500|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000480558|)\tGT:AD:DP:GQ:PL\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n+chr10\t135369532\t.\tT\tC\t122.62\t.\tAC=2;AF=0.25;AN=8;BaseQRankSum=2.118;DP=239;Dels=0.00;FS=5.194;HRun=2;HaplotypeScore=5.7141;MQ=36.02;MQ0=0;MQRankSum=0.082;QD=2.31;ReadPosRankSum=-0.695;CSQ=missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000303903|9/13|benign(0.001)|tolerated(1),missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000432597|10/14|benign(0)|tolerated(1),downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000460441|||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000343131|9/13|benign(0.001)|tolerated(1),intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000171772|SYCE1|ENST00000479535|6/10||,downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000482127|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000130649|CYP2E1|ENST00000368520|6/6||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000368517|9/13|benign(0)|tolerated(1);EFF=DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000460441|),DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000482127|),EXON(MODIFIER|||||CYP2E1|retained_intron|CODING|ENST00000368520|),EXON(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000479535|),INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000368517|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000432597|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|318|SYCE1|protein_coding|CODING|ENST00000303903|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|351|SYCE1|protein_coding|CODING|ENST00000343131|exon_10_135369485_135369551)\tGT:AD:DP:GQ:PL\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t1/1:0,24:24:66.14:729,66,0\n\\ No newline at end of file\n'
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_amend_input.db
b
Binary file test-data/gemini_amend_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_amend_input.ped
--- a/test-data/gemini_amend_input.ped Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,5 +0,0 @@
-#family_id name paternal_id maternal_id sex phenotype ethnicity hair_color
-1 M10475    None None  1    1    None brown
-1 M10478     M10475  M10500    2    2    None red
-1 M10500     None    None    2    2    None
-1 M128215    M10475  M10500    1    1    None green
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_amend_result.db
b
Binary file test-data/gemini_amend_result.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_annotate_input.db
b
Binary file test-data/gemini_annotate_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_annotate_result.db
b
Binary file test-data/gemini_annotate_result.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_annotate_result.tabular
--- a/test-data/gemini_annotate_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,1 +0,0 @@
-updated 10 variants
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_auto_dom_input.db
b
Binary file test-data/gemini_auto_dom_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_auto_rec_input.db
b
Binary file test-data/gemini_auto_rec_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_autosomal_dominant_result.tabular
--- a/test-data/gemini_autosomal_dominant_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,9 +0,0 @@
-gene chrom impact variant_id family_id family_members family_genotypes samples family_count
-ASAH2C chr10 missense_variant 3 3 3_dad(3_dad;affected),3_mom(3_mom;unknown),3_kid(3_kid;affected) C/T,C/C,C/T 3_dad,3_kid 2
-ASAH2C chr10 missense_variant 3 2 2_dad(2_dad;unaffected),2_mom(2_mom;affected),2_kid(2_kid;affected) C/C,C/T,C/T 2_mom,2_kid 2
-ASAH2C chr10 missense_variant 4 3 3_dad(3_dad;affected),3_mom(3_mom;unknown),3_kid(3_kid;affected) C/T,C/C,C/T 3_dad,3_kid 2
-ASAH2C chr10 missense_variant 4 2 2_dad(2_dad;unaffected),2_mom(2_mom;affected),2_kid(2_kid;affected) C/C,C/T,C/T 2_mom,2_kid 2
-SPRN chr10 intron_variant 5 3 3_dad(3_dad;affected),3_mom(3_mom;unknown),3_kid(3_kid;affected) G/A,G/G,G/A 3_dad,3_kid 1
-WDR37 chr10 stop_lost 1 3 3_dad(3_dad;affected),3_mom(3_mom;unknown),3_kid(3_kid;affected) T/C,T/T,T/C 3_dad,3_kid 2
-WDR37 chr10 stop_lost 1 2 2_dad(2_dad;unaffected),2_mom(2_mom;affected),2_kid(2_kid;affected) T/T,T/C,T/C 2_mom,2_kid 2
-WDR37 chr10 stop_lost 2 3 3_dad(3_dad;affected),3_mom(3_mom;unknown),3_kid(3_kid;affected) T/C,T/C,T/C 3_dad,3_kid 2
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_autosomal_input.db
b
Binary file test-data/gemini_autosomal_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_autosomal_recessive.tabular
--- a/test-data/gemini_autosomal_recessive.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,2 +0,0 @@
-gene chrom impact variant_id family_id family_members family_genotypes samples family_count
-WDR37 chr10 stop_lost 2 1 1_dad(1_dad;unaffected),1_mom(1_mom;unaffected),1_kid(1_kid;affected) T/C,T/C,C/C 1_kid 1
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_burden_calpha_template.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gemini_burden_calpha_template.tabular Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,4 @@
+gene T c Z p_value
+SYCE1 .+ .+ .+ .+
+WDR37 .+ .+ .+ .+
+ASAH2C .+ .+ .+ .+
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_burden_count_highimpact_result.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gemini_burden_count_highimpact_result.tabular Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,2 @@
+gene 1_kid 3_kid
+WDR37 1 2
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_burden_count_nonsynonymous_result.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gemini_burden_count_nonsynonymous_result.tabular Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,5 @@
+gene 1_dad 1_kid 1_mom 2_dad 2_kid 2_mom 3_dad 3_kid 3_mom
+SYCE1 0 1 0 0 1 0 0 1 0
+SPRN 0 1 0 0 1 0 1 1 1
+WDR37 0 1 0 0 0 0 0 2 0
+ASAH2C 2 3 2 1 3 1 1 2 1
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_burden_input.db
b
Binary file test-data/gemini_burden_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_burden_result.tabular
--- a/test-data/gemini_burden_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,6 +0,0 @@
-gene T c Z p_value
-SYCE1 -0.5 0.25 -1.0 0.00699300699301
-DHODH 0.0 0.0 nan nan
-WDR37 -1.0 1.5 -0.816496580928 0.00699300699301
-ASAH2C -0.5 0.75 -0.57735026919 0.00699300699301
-CTBP2 0.0 0.0 nan nan
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_comphets_input.db
b
Binary file test-data/gemini_comphets_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_comphets_result.tabular
--- a/test-data/gemini_comphets_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,3 +0,0 @@
-chrom start end ref alt gene impact variant_id family_id family_members family_genotypes samples family_count comp_het_id priority
-chr1 17362 17366 TTCT T WASH7P splice_acceptor_variant 3 4 child_4(child_4;affected;male),dad_4(dad_4;unaffected;male),mom_4(mom_4;unaffected;female) TTCT|T,TTCT/T,TTCT/TTCT child_4 1 1_3_7 3
-chr1 17729 17730 C A WASH7P splice_acceptor_variant 7 4 child_4(child_4;affected;male),dad_4(dad_4;unaffected;male),mom_4(mom_4;unaffected;female) C/A,C/A,C/A child_4 1 1_3_7 3
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_dbinfo_result.tabular
--- a/test-data/gemini_dbinfo_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,209 +0,0 @@
-table_name column_name type
-variants chrom text
-variants start integer
-variants end integer
-variants vcf_id text
-variants variant_id integer
-variants anno_id integer
-variants ref text
-variants alt text
-variants qual float
-variants filter text
-variants type text
-variants sub_type text
-variants gts blob
-variants gt_types blob
-variants gt_phases blob
-variants gt_depths blob
-variants gt_ref_depths blob
-variants gt_alt_depths blob
-variants gt_quals blob
-variants gt_copy_numbers blob
-variants gt_phred_ll_homref blob
-variants gt_phred_ll_het blob
-variants gt_phred_ll_homalt blob
-variants call_rate float
-variants in_dbsnp bool
-variants rs_ids text
-variants sv_cipos_start_left integer
-variants sv_cipos_end_left integer
-variants sv_cipos_start_right integer
-variants sv_cipos_end_right integer
-variants sv_length integer
-variants sv_is_precise bool
-variants sv_tool text
-variants sv_evidence_type text
-variants sv_event_id text
-variants sv_mate_id text
-variants sv_strand text
-variants in_omim bool
-variants clinvar_sig text
-variants clinvar_disease_name text
-variants clinvar_dbsource text
-variants clinvar_dbsource_id text
-variants clinvar_origin text
-variants clinvar_dsdb text
-variants clinvar_dsdbid text
-variants clinvar_disease_acc text
-variants clinvar_in_locus_spec_db bool
-variants clinvar_on_diag_assay bool
-variants clinvar_causal_allele text
-variants pfam_domain text
-variants cyto_band text
-variants rmsk text
-variants in_cpg_island bool
-variants in_segdup bool
-variants is_conserved bool
-variants gerp_bp_score float
-variants gerp_element_pval float
-variants num_hom_ref integer
-variants num_het integer
-variants num_hom_alt integer
-variants num_unknown integer
-variants aaf real
-variants hwe decimal(2,7)
-variants inbreeding_coeff decimal(2,7)
-variants pi decimal(2,7)
-variants recomb_rate decimal(2,7)
-variants gene text
-variants transcript text
-variants is_exonic bool
-variants is_coding bool
-variants is_splicing bool
-variants is_lof bool
-variants exon text
-variants codon_change text
-variants aa_change text
-variants aa_length text
-variants biotype text
-variants impact text
-variants impact_so text
-variants impact_severity text
-variants polyphen_pred text
-variants polyphen_score float
-variants sift_pred text
-variants sift_score float
-variants anc_allele text
-variants rms_bq float
-variants cigar text
-variants depth integer
-variants strand_bias float
-variants rms_map_qual float
-variants in_hom_run integer
-variants num_mapq_zero integer
-variants num_alleles integer
-variants num_reads_w_dels float
-variants haplotype_score float
-variants qual_depth float
-variants allele_count integer
-variants allele_bal float
-variants in_hm2 bool
-variants in_hm3 bool
-variants is_somatic bool
-variants somatic_score float
-variants in_esp bool
-variants aaf_esp_ea decimal(2,7)
-variants aaf_esp_aa decimal(2,7)
-variants aaf_esp_all decimal(2,7)
-variants exome_chip bool
-variants in_1kg bool
-variants aaf_1kg_amr decimal(2,7)
-variants aaf_1kg_eas decimal(2,7)
-variants aaf_1kg_sas decimal(2,7)
-variants aaf_1kg_afr decimal(2,7)
-variants aaf_1kg_eur decimal(2,7)
-variants aaf_1kg_all decimal(2,7)
-variants grc text
-variants gms_illumina float
-variants gms_solid float
-variants gms_iontorrent float
-variants in_cse bool
-variants encode_tfbs text
-variants encode_dnaseI_cell_count integer
-variants encode_dnaseI_cell_list text
-variants encode_consensus_gm12878 text
-variants encode_consensus_h1hesc text
-variants encode_consensus_helas3 text
-variants encode_consensus_hepg2 text
-variants encode_consensus_huvec text
-variants encode_consensus_k562 text
-variants vista_enhancers text
-variants cosmic_ids text
-variants info blob
-variants cadd_raw float
-variants cadd_scaled float
-variants fitcons float
-variants in_exac bool
-variants aaf_exac_all decimal(2,7)
-variants aaf_adj_exac_all decimal(2,7)
-variants aaf_adj_exac_afr decimal(2,7)
-variants aaf_adj_exac_amr decimal(2,7)
-variants aaf_adj_exac_eas decimal(2,7)
-variants aaf_adj_exac_fin decimal(2,7)
-variants aaf_adj_exac_nfe decimal(2,7)
-variants aaf_adj_exac_oth decimal(2,7)
-variants aaf_adj_exac_sas decimal(2,7)
-variants exac_num_het int
-variants exac_num_hom_alt int
-variants exac_num_chroms int
-variants max_aaf_all REAL
-variant_impacts variant_id integer
-variant_impacts anno_id integer
-variant_impacts gene text
-variant_impacts transcript text
-variant_impacts is_exonic bool
-variant_impacts is_coding bool
-variant_impacts is_splicing bool
-variant_impacts is_lof bool
-variant_impacts exon text
-variant_impacts codon_change text
-variant_impacts aa_change text
-variant_impacts aa_length text
-variant_impacts biotype text
-variant_impacts impact text
-variant_impacts impact_so text
-variant_impacts impact_severity text
-variant_impacts polyphen_pred text
-variant_impacts polyphen_score float
-variant_impacts sift_pred text
-variant_impacts sift_score float
-samples sample_id integer
-samples family_id text
-samples name text
-samples paternal_id text
-samples maternal_id text
-samples sex text
-samples phenotype text
-samples ethnicity text
-gene_detailed uid integer
-gene_detailed chrom text
-gene_detailed gene text
-gene_detailed is_hgnc bool
-gene_detailed ensembl_gene_id text
-gene_detailed transcript text
-gene_detailed biotype text
-gene_detailed transcript_status text
-gene_detailed ccds_id text
-gene_detailed hgnc_id text
-gene_detailed entrez_id text
-gene_detailed cds_length text
-gene_detailed protein_length text
-gene_detailed transcript_start text
-gene_detailed transcript_end text
-gene_detailed strand text
-gene_detailed synonym text
-gene_detailed rvis_pct float
-gene_detailed mam_phenotype_id text
-gene_summary uid integer
-gene_summary chrom text
-gene_summary gene text
-gene_summary is_hgnc bool
-gene_summary ensembl_gene_id text
-gene_summary hgnc_id text
-gene_summary transcript_min_start text
-gene_summary transcript_max_end text
-gene_summary strand text
-gene_summary synonym text
-gene_summary rvis_pct float
-gene_summary mam_phenotype_id text
-gene_summary in_cosmic_census bool
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_de_novo_input.db
b
Binary file test-data/gemini_de_novo_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_de_novo_result.tabular
--- a/test-data/gemini_de_novo_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
[
b"@@ -1,9 +0,0 @@\n-chrom\tstart\tend\tvcf_id\tvariant_id\tanno_id\tref\talt\tqual\tfilter\ttype\tsub_type\tcall_rate\tin_dbsnp\trs_ids\tsv_cipos_start_left\tsv_cipos_end_left\tsv_cipos_start_right\tsv_cipos_end_right\tsv_length\tsv_is_precise\tsv_tool\tsv_evidence_type\tsv_event_id\tsv_mate_id\tsv_strand\tin_omim\tclinvar_sig\tclinvar_disease_name\tclinvar_dbsource\tclinvar_dbsource_id\tclinvar_origin\tclinvar_dsdb\tclinvar_dsdbid\tclinvar_disease_acc\tclinvar_in_locus_spec_db\tclinvar_on_diag_assay\tclinvar_causal_allele\tpfam_domain\tcyto_band\trmsk\tin_cpg_island\tin_segdup\tis_conserved\tgerp_bp_score\tgerp_element_pval\tnum_hom_ref\tnum_het\tnum_hom_alt\tnum_unknown\taaf\thwe\tinbreeding_coeff\tpi\trecomb_rate\tgene\ttranscript\tis_exonic\tis_coding\tis_splicing\tis_lof\texon\tcodon_change\taa_change\taa_length\tbiotype\timpact\timpact_so\timpact_severity\tpolyphen_pred\tpolyphen_score\tsift_pred\tsift_score\tanc_allele\trms_bq\tcigar\tdepth\tstrand_bias\trms_map_qual\tin_hom_run\tnum_mapq_zero\tnum_alleles\tnum_reads_w_dels\thaplotype_score\tqual_depth\tallele_count\tallele_bal\tin_hm2\tin_hm3\tis_somatic\tsomatic_score\tin_esp\taaf_esp_ea\taaf_esp_aa\taaf_esp_all\texome_chip\tin_1kg\taaf_1kg_amr\taaf_1kg_eas\taaf_1kg_sas\taaf_1kg_afr\taaf_1kg_eur\taaf_1kg_all\tgrc\tgms_illumina\tgms_solid\tgms_iontorrent\tin_cse\tencode_tfbs\tencode_dnaseI_cell_count\tencode_dnaseI_cell_list\tencode_consensus_gm12878\tencode_consensus_h1hesc\tencode_consensus_helas3\tencode_consensus_hepg2\tencode_consensus_huvec\tencode_consensus_k562\tvista_enhancers\tcosmic_ids\tinfo\tcadd_raw\tcadd_scaled\tfitcons\tin_exac\taaf_exac_all\taaf_adj_exac_all\taaf_adj_exac_afr\taaf_adj_exac_amr\taaf_adj_exac_eas\taaf_adj_exac_fin\taaf_adj_exac_nfe\taaf_adj_exac_oth\taaf_adj_exac_sas\texac_num_het\texac_num_hom_alt\texac_num_chroms\tmax_aaf_all\tgts\tgt_types\tgt_phases\tgt_depths\tgt_ref_depths\tgt_alt_depths\tgt_quals\tgt_copy_numbers\tgt_phred_ll_homref\tgt_phred_ll_het\tgt_phred_ll_homalt\tfamily_id\tfamily_members\tfamily_genotypes\tsamples\tfamily_count\n-chr10\t48003991\t48003992\tNone\t2\t1\tC\tT\t1047.86999512\tNone\tsnp\tts\t1.0\t1\trs142685947,rs3739968\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10q11.22\tNone\t0\t1\t1\tNone\t3.10871e-42\t2\t6\t1\t0\t0.444444444444\t0.29371811258\t-0.35\t0.522875816993\t1.718591\tASAH2C\tENST00000420079\t1\t1\t0\t0\texon_10_48003968_48004056\ttGt/tAt\tC540Y\t610\tprotein_coding\tmissense_variant\tmissense_variant\tMED\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t165\tNone\t20.9400005341\t0\t0\t8\t0.0\t4.382999897\t9.52999973297\t4\tNone\tNone\tNone\tNone\tNone\t0\tNone\tNone\tNone\t0\t1\t0.3112\t0.4573\t0.3855\t0.1241\t0.5149\t0.346645\tgrc_fix\t73.3\t40.3\t92.8\t0\tNone\tNone\tNone\tR\tR\tR\tR\tR\tR\tNone\tNone\tNone\tNone\tNone\t0.553676\t1\t0.443\t0.448537771896\t0.288974151858\t0.281426746944\t0.543088975937\t0.524984286612\t0.478147713207\t0.463529411765\t0.418641164716\t17495\t15317\t107302\t0.543088975937\t['C/T' 'C/T' 'T/T' 'C/C' 'C/C' 'C/T' 'C/T' 'C/T' 'C/T']\t[1 1 3 0 0 1 1 1 1]\t[False False False False False False False False False]\t[38 29 23 38 29 23 38 29 23]\t[1 0 0 1 0 0 1 0 0]\t[37 29 23 37 29 23 37 29 23]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t2\t2_dad(2_dad;unaffected),2_mom(2_mom;unaffected),2_kid(2_kid;affected)\tC/C,C/C,C/T\t2_kid\t2\n-chr10\t48004991\t48004992\tNone\t3\t1\tC\tT\t1047.86999512\tNone\tsnp\tts\t1.0\t0\tNone\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10q11.22\tNone\t0\t1\t0\tNone\tNone\t2\t6\t1\t0\t0.444444444444\t0.29371811258\t-0.35\t0.522875816993\t1.718591\tASAH2C\tENST00000420079\t1\t1\t0\t0\texon_10_48003968_48004056\ttGt/tAt\tC540Y\t610\tprotein_coding\tmissense_variant\tmissense_variant\tMED\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t165\tNone\t20.9400005341\t0\t0\t8\t0.0\t4.382999897\t9.52999973297\t4\tNone\tNone\tNone\tNone\tNone\t0\tNone\tNone\tNone\t0\t0\tNone\tNone\tNone\tNone\tNone\tNone\tgrc_fix\tNone\tNone\tNone\t0\tNone\tNone\tNone\tR\tR\tR\tR\tR\tR\tNone\tNone\tNone\tNone\tNone\t0.061011\t0\tNone\tNone\tNone\t"..b"\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10q26.3\tNone\t0\t0\t1\tNone\t3.86096e-59\t6\t3\t0\t0\t0.166666666667\t0.548506235587\t-0.2\t0.294117647059\t0.022013\tSYCE1\tENST00000368517\t1\t1\t0\t0\texon_10_135369485_135369551\taAg/aGg\tK147R\t282\tprotein_coding\tmissense_variant\tmissense_variant\tMED\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t239\tNone\t36.0200004578\t2\t0\t8\t0.0\t5.71409988403\t2.30999994278\t2\tNone\tNone\tNone\tNone\tNone\t1\t0.0938372093023\t0.163867453473\t0.117561125634\t1\t1\t0.1844\t0.2698\t0.2188\t0.1997\t0.1093\t0.197284\tNone\tNone\tNone\tNone\t0\tNone\tNone\tNone\tR\tR\tR\tR\tR\tR\tNone\tNone\tNone\tNone\tNone\t0.487112\t1\t0.134\t0.134286610119\t0.184985563041\t0.164938655607\t0.256026889198\t0.122313048744\t0.0919761054243\t0.113686534216\t0.194096927001\t13825\t1225\t121196\t0.2698\t['T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C']\t[0 0 1 0 0 1 0 0 1]\t[False False False False False False False False False]\t[38 29 22 38 29 21 38 29 24]\t[1 0 0 1 0 0 1 0 0]\t[37 29 22 37 29 21 37 29 24]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t3\t3_dad(3_dad;unaffected),3_mom(3_mom;unaffected),3_kid(3_kid;affected)\tT/T,T/T,T/C\t3_kid\t3\n-chr10\t135369531\t135369532\tNone\t5\t6\tT\tC\t122.620002747\tNone\tsnp\tts\t1.0\t1\trs3747881,rs386585367\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10q26.3\tNone\t0\t0\t1\tNone\t3.86096e-59\t6\t3\t0\t0\t0.166666666667\t0.548506235587\t-0.2\t0.294117647059\t0.022013\tSYCE1\tENST00000368517\t1\t1\t0\t0\texon_10_135369485_135369551\taAg/aGg\tK147R\t282\tprotein_coding\tmissense_variant\tmissense_variant\tMED\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t239\tNone\t36.0200004578\t2\t0\t8\t0.0\t5.71409988403\t2.30999994278\t2\tNone\tNone\tNone\tNone\tNone\t1\t0.0938372093023\t0.163867453473\t0.117561125634\t1\t1\t0.1844\t0.2698\t0.2188\t0.1997\t0.1093\t0.197284\tNone\tNone\tNone\tNone\t0\tNone\tNone\tNone\tR\tR\tR\tR\tR\tR\tNone\tNone\tNone\tNone\tNone\t0.487112\t1\t0.134\t0.134286610119\t0.184985563041\t0.164938655607\t0.256026889198\t0.122313048744\t0.0919761054243\t0.113686534216\t0.194096927001\t13825\t1225\t121196\t0.2698\t['T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C']\t[0 0 1 0 0 1 0 0 1]\t[False False False False False False False False False]\t[38 29 22 38 29 21 38 29 24]\t[1 0 0 1 0 0 1 0 0]\t[37 29 22 37 29 21 37 29 24]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t2\t2_dad(2_dad;unaffected),2_mom(2_mom;unaffected),2_kid(2_kid;affected)\tT/T,T/T,T/C\t2_kid\t3\n-chr10\t1142207\t1142208\tNone\t1\t4\tT\tC\t3404.30004883\tNone\tsnp\tts\t1.0\t1\trs10794716\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10p15.3\tNone\t0\t0\t0\tNone\tNone\t7\t1\t1\t0\t0.166666666667\t0.0718606383197\t0.6\t0.294117647059\t0.200924\tWDR37\tENST00000381329\t1\t1\t0\t1\texon_10_1142110_1142566\tTga/Cga\t*250R\t249\tprotein_coding\tstop_lost\tstop_lost\tHIGH\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t122\tNone\t36.0\t0\t0\t8\t0.0\t2.67470002174\t27.8999996185\t8\tNone\tNone\tNone\tNone\tNone\t1\t0.999534883721\t0.975034044485\t0.991234814701\t0\t1\t0.9942\t1\t1\t0.9561\t1\t0.98762\tNone\tNone\tNone\tNone\t0\tNone\t2\tOsteobl;Progfib\tT\tT\tT\tT\tT\tT\tNone\tNone\tNone\tNone\tNone\t0.156188\t1\t0.997\t0.997067786838\t0.970305592927\t0.998358956642\t1\t1\t0.999595432887\t0.998898678414\t1\t346\t60354\t121410\t1.0\t['T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/T' 'T/T' 'T/T' 'C/C']\t[0 0 1 0 0 0 0 0 3]\t[False False False False False False False False False]\t[38 29 23 38 29 22 38 29 24]\t[1 0 0 1 0 0 1 0 0]\t[37 29 23 37 29 22 37 29 24]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t1\t1_dad(1_dad;unaffected),1_mom(1_mom;unaffected),1_kid(1_kid;affected)\tT/T,T/T,T/C\t1_kid\t1\n"
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_dump_result.tabular
--- a/test-data/gemini_dump_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,97 +0,0 @@
-chrom start end ref alt type sub_type aaf in_dbsnp gene sample genotype
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 child_1 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 child_2 G/G
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 dad_2 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 mom_2 G/G
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 dad_1 G/G
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 mom_1 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 child_3 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 dad_3 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 mom_3 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 child_4 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 dad_4 G/A
-chr1 16976 16977 G A snp ts 0.375 0 DDX11L1 mom_4 G/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 child_1 A/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 child_2 A/G
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 dad_2 A/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 mom_2 A/G
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 dad_1 A/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 mom_1 A/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 child_3 A/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 dad_3 A/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 mom_3 A/G
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 child_4 A/G
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 dad_4 A/A
-chr1 17221 17222 A G snp ts 0.166666666667 1 DDX11L1 mom_4 A/A
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P child_1 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P child_2 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P dad_2 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P mom_2 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P dad_1 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P mom_1 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P child_3 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P dad_3 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P mom_3 TTCT/TTCT
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P child_4 TTCT/T
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P dad_4 TTCT/T
-chr1 17362 17366 TTCT T indel del 0.0833333333333 0 WASH7P mom_4 TTCT/TTCT
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 child_1 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 child_2 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 dad_2 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 mom_2 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 dad_1 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 mom_1 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 child_3 G/A
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 dad_3 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 mom_3 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 child_4 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 dad_4 G/G
-chr1 17562 17563 G A snp ts 0.0416666666667 0 DDX11L1 mom_4 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 child_1 G/C
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 child_2 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 dad_2 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 mom_2 G/C
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 dad_1 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 mom_1 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 child_3 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 dad_3 G/C
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 mom_3 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 child_4 G/C
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 dad_4 G/G
-chr1 17696 17697 G C snp tv 0.166666666667 1 DDX11L1 mom_4 G/G
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 child_1 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 child_2 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 dad_2 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 mom_2 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 dad_1 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 mom_1 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 child_3 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 dad_3 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 mom_3 A/A
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 child_4 A/G
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 dad_4 A/G
-chr1 17721 17722 A G snp ts 0.125 1 DDX11L1 mom_4 A/G
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P child_1 C/C
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P child_2 C/C
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P dad_2 C/C
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P mom_2 C/C
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P dad_1 C/A
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P mom_1 C/C
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P child_3 C/A
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P dad_3 C/C
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P mom_3 C/C
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P child_4 C/A
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P dad_4 C/A
-chr1 17729 17730 C A snp tv 0.208333333333 0 WASH7P mom_4 C/A
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 child_1 A/A
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 child_2 A/A
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 dad_2 A/A
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 mom_2 A/A
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 dad_1 A/G
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 mom_1 A/G
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 child_3 A/G
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 dad_3 A/G
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 mom_3 A/G
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 child_4 A/G
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 dad_4 A/G
-chr1 17745 17746 A G snp ts 0.333333333333 1 DDX11L1 mom_4 A/G
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_gene_wise_result.tabular
--- a/test-data/gemini_gene_wise_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,6 +0,0 @@
-chrom start end gene impact impact_severity max_aaf_all variant_filters n_gene_variants gene_filters
-chr10 48003991 48003992 ASAH2C missense_variant MED 0.543088975937 1 1 1
-chr10 126678091 126678092 CTBP2 stop_gained HIGH 0.0904917363803 1 1 1
-chr10 135369531 135369532 SYCE1 missense_variant MED 0.2698 1 1 1
-chr10 1142207 1142208 WDR37 stop_lost HIGH 1.0 1 1 1
-chr16 72057434 72057435 DHODH missense_variant MED 0.000432002764818 1 1 1
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_interactions_result.tabular
--- a/test-data/gemini_interactions_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,25 +0,0 @@
-sample gene order_of_interaction interacting_gene
-M10475 CTBP2 0_order: none
-M10475 CTBP2 1_order: none
-M10475 CTBP2 2_order: none
-M10475 CTBP2 3_order: none
-M10475 CTBP2 4_order: WDR37
-M10475 CTBP2 5_order: none
-M128215 CTBP2 0_order: CTBP2
-M128215 CTBP2 1_order: none
-M128215 CTBP2 2_order: none
-M128215 CTBP2 3_order: none
-M128215 CTBP2 4_order: WDR37
-M128215 CTBP2 5_order: none
-M10478 CTBP2 0_order: none
-M10478 CTBP2 1_order: none
-M10478 CTBP2 2_order: none
-M10478 CTBP2 3_order: none
-M10478 CTBP2 4_order: WDR37
-M10478 CTBP2 5_order: MTG1
-M10500 CTBP2 0_order: none
-M10500 CTBP2 1_order: none
-M10500 CTBP2 2_order: none
-M10500 CTBP2 3_order: none
-M10500 CTBP2 4_order: WDR37
-M10500 CTBP2 5_order: MTG1
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_is_somatic_result.db
b
Binary file test-data/gemini_is_somatic_result.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_load_result.db
b
Binary file test-data/gemini_load_result.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_load_result1.db
b
Binary file test-data/gemini_load_result1.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_load_result2.db
b
Binary file test-data/gemini_load_result2.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_lofsieve_result.tabular
--- a/test-data/gemini_lofsieve_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,11 +0,0 @@
-chrom start end ref alt highest_impact aa_change var_trans_pos trans_aa_length var_trans_pct sample genotype gene transcript trans_type
-chr10 1142207 1142208 T C stop_lost */R 250 250/249 1.00401606426 M10475 C/C WDR37 ENST00000381329 protein_coding
-chr10 1142207 1142208 T C stop_lost */R 250 250/249 1.00401606426 M10478 C/C WDR37 ENST00000381329 protein_coding
-chr10 1142207 1142208 T C stop_lost */R 250 250/249 1.00401606426 M10500 C/C WDR37 ENST00000381329 protein_coding
-chr10 1142207 1142208 T C stop_lost */R 250 250/249 1.00401606426 M128215 C/C WDR37 ENST00000381329 protein_coding
-chr10 126678091 126678092 G A stop_gained Q/* 445 445/445 1.0 M128215 G/A CTBP2 ENST00000531469 protein_coding
-chr10 126678091 126678092 G A stop_gained Q/* 445 445/445 1.0 M128215 G/A CTBP2 ENST00000309035 protein_coding
-chr10 126678091 126678092 G A stop_gained Q/* 445 445/445 1.0 M128215 G/A CTBP2 ENST00000494626 protein_coding
-chr10 126678091 126678092 G A stop_gained Q/* 445 445/445 1.0 M128215 G/A CTBP2 ENST00000337195 protein_coding
-chr10 126678091 126678092 G A stop_gained Q/* 445 445/445 1.0 M128215 G/A CTBP2 ENST00000334808 protein_coding
-chr10 126678091 126678092 G A stop_gained Q/* 445 445/445 1.0 M128215 G/A CTBP2 ENST00000411419 protein_coding
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_mendel_errors_result.tabular
--- a/test-data/gemini_mendel_errors_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
[
b"@@ -1,10 +0,0 @@\n-chrom\tstart\tend\tvcf_id\tvariant_id\tanno_id\tref\talt\tqual\tfilter\ttype\tsub_type\tcall_rate\tin_dbsnp\trs_ids\tsv_cipos_start_left\tsv_cipos_end_left\tsv_cipos_start_right\tsv_cipos_end_right\tsv_length\tsv_is_precise\tsv_tool\tsv_evidence_type\tsv_event_id\tsv_mate_id\tsv_strand\tin_omim\tclinvar_sig\tclinvar_disease_name\tclinvar_dbsource\tclinvar_dbsource_id\tclinvar_origin\tclinvar_dsdb\tclinvar_dsdbid\tclinvar_disease_acc\tclinvar_in_locus_spec_db\tclinvar_on_diag_assay\tclinvar_causal_allele\tpfam_domain\tcyto_band\trmsk\tin_cpg_island\tin_segdup\tis_conserved\tgerp_bp_score\tgerp_element_pval\tnum_hom_ref\tnum_het\tnum_hom_alt\tnum_unknown\taaf\thwe\tinbreeding_coeff\tpi\trecomb_rate\tgene\ttranscript\tis_exonic\tis_coding\tis_splicing\tis_lof\texon\tcodon_change\taa_change\taa_length\tbiotype\timpact\timpact_so\timpact_severity\tpolyphen_pred\tpolyphen_score\tsift_pred\tsift_score\tanc_allele\trms_bq\tcigar\tdepth\tstrand_bias\trms_map_qual\tin_hom_run\tnum_mapq_zero\tnum_alleles\tnum_reads_w_dels\thaplotype_score\tqual_depth\tallele_count\tallele_bal\tin_hm2\tin_hm3\tis_somatic\tsomatic_score\tin_esp\taaf_esp_ea\taaf_esp_aa\taaf_esp_all\texome_chip\tin_1kg\taaf_1kg_amr\taaf_1kg_eas\taaf_1kg_sas\taaf_1kg_afr\taaf_1kg_eur\taaf_1kg_all\tgrc\tgms_illumina\tgms_solid\tgms_iontorrent\tin_cse\tencode_tfbs\tencode_dnaseI_cell_count\tencode_dnaseI_cell_list\tencode_consensus_gm12878\tencode_consensus_h1hesc\tencode_consensus_helas3\tencode_consensus_hepg2\tencode_consensus_huvec\tencode_consensus_k562\tvista_enhancers\tcosmic_ids\tinfo\tcadd_raw\tcadd_scaled\tfitcons\tin_exac\taaf_exac_all\taaf_adj_exac_all\taaf_adj_exac_afr\taaf_adj_exac_amr\taaf_adj_exac_eas\taaf_adj_exac_fin\taaf_adj_exac_nfe\taaf_adj_exac_oth\taaf_adj_exac_sas\texac_num_het\texac_num_hom_alt\texac_num_chroms\tmax_aaf_all\tgts\tgt_types\tgt_phases\tgt_depths\tgt_ref_depths\tgt_alt_depths\tgt_quals\tgt_copy_numbers\tgt_phred_ll_homref\tgt_phred_ll_het\tgt_phred_ll_homalt\tfamily_id\tfamily_members\tfamily_genotypes\tsamples\tfamily_count\tviolation\tviolation_prob\n-chr10\t1142207\t1142208\tNone\t1\t4\tT\tC\t3404.30004883\tNone\tsnp\tts\t1.0\t1\trs10794716\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10p15.3\tNone\t0\t0\t0\tNone\tNone\t7\t1\t1\t0\t0.166666666667\t0.0718606383197\t0.6\t0.294117647059\t0.200924\tWDR37\tENST00000381329\t1\t1\t0\t1\texon_10_1142110_1142566\tTga/Cga\t*250R\t249\tprotein_coding\tstop_lost\tstop_lost\tHIGH\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t122\tNone\t36.0\t0\t0\t8\t0.0\t2.67470002174\t27.8999996185\t8\tNone\tNone\tNone\tNone\tNone\t1\t0.999534883721\t0.975034044485\t0.991234814701\t0\t1\t0.9942\t1\t1\t0.9561\t1\t0.98762\tNone\tNone\tNone\tNone\t0\tNone\t2\tOsteobl;Progfib\tT\tT\tT\tT\tT\tT\tNone\tNone\tNone\tNone\tNone\t0.156188\t1\t0.997\t0.997067786838\t0.970305592927\t0.998358956642\t1\t1\t0.999595432887\t0.998898678414\t1\t346\t60354\t121410\t1.0\t['T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/T' 'T/T' 'T/T' 'C/C']\t[0 0 1 0 0 0 0 0 3]\t[False False False False False False False False False]\t[38 29 23 38 29 22 38 29 24]\t[1 0 0 1 0 0 1 0 0]\t[37 29 23 37 29 22 37 29 24]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t1\t1_dad(1_dad;unaffected),1_mom(1_mom;unaffected),1_kid(1_kid;affected)\tT/T,T/T,T/C\t1_kid\t2\tplausible de novo;implausible de novo\t0.00000\n-chr10\t1142207\t1142208\tNone\t1\t4\tT\tC\t3404.30004883\tNone\tsnp\tts\t1.0\t1\trs10794716\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10p15.3\tNone\t0\t0\t0\tNone\tNone\t7\t1\t1\t0\t0.166666666667\t0.0718606383197\t0.6\t0.294117647059\t0.200924\tWDR37\tENST00000381329\t1\t1\t0\t1\texon_10_1142110_1142566\tTga/Cga\t*250R\t249\tprotein_coding\tstop_lost\tstop_lost\tHIGH\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t122\tNone\t36.0\t0\t0\t8\t0.0\t2.67470002174\t27.8999996185\t8\tNone\tNone\tNone\tNone\tNone\t1\t0.999534883721\t0.975034044485\t0.991234814701\t0\t1\t0.9942\t1\t1\t0.9561\t1\t0.98762\tNone\tNone\tNone\tNone\t0\tNone\t2\tOsteobl;Progfib\tT\tT\tT\tT\tT\tT\tNone\tNone\tNone\tNone\tNone\t0.156188\t1\t0.997\t0"..b"e_variant\tMED\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t239\tNone\t36.0200004578\t2\t0\t8\t0.0\t5.71409988403\t2.30999994278\t2\tNone\tNone\tNone\tNone\tNone\t1\t0.0938372093023\t0.163867453473\t0.117561125634\t1\t1\t0.1844\t0.2698\t0.2188\t0.1997\t0.1093\t0.197284\tNone\tNone\tNone\tNone\t0\tNone\tNone\tNone\tR\tR\tR\tR\tR\tR\tNone\tNone\tNone\tNone\tNone\t0.487112\t1\t0.134\t0.134286610119\t0.184985563041\t0.164938655607\t0.256026889198\t0.122313048744\t0.0919761054243\t0.113686534216\t0.194096927001\t13825\t1225\t121196\t0.2698\t['T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C']\t[0 0 1 0 0 1 0 0 1]\t[False False False False False False False False False]\t[38 29 22 38 29 21 38 29 24]\t[1 0 0 1 0 0 1 0 0]\t[37 29 22 37 29 21 37 29 24]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t1\t1_dad(1_dad;unaffected),1_mom(1_mom;unaffected),1_kid(1_kid;affected)\tT/T,T/T,T/C\t1_kid\t3\tplausible de novo;plausible de novo;plausible de novo\t0.00000\n-chr10\t135369531\t135369532\tNone\t5\t6\tT\tC\t122.620002747\tNone\tsnp\tts\t1.0\t1\trs3747881,rs386585367\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10q26.3\tNone\t0\t0\t1\tNone\t3.86096e-59\t6\t3\t0\t0\t0.166666666667\t0.548506235587\t-0.2\t0.294117647059\t0.022013\tSYCE1\tENST00000368517\t1\t1\t0\t0\texon_10_135369485_135369551\taAg/aGg\tK147R\t282\tprotein_coding\tmissense_variant\tmissense_variant\tMED\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t239\tNone\t36.0200004578\t2\t0\t8\t0.0\t5.71409988403\t2.30999994278\t2\tNone\tNone\tNone\tNone\tNone\t1\t0.0938372093023\t0.163867453473\t0.117561125634\t1\t1\t0.1844\t0.2698\t0.2188\t0.1997\t0.1093\t0.197284\tNone\tNone\tNone\tNone\t0\tNone\tNone\tNone\tR\tR\tR\tR\tR\tR\tNone\tNone\tNone\tNone\tNone\t0.487112\t1\t0.134\t0.134286610119\t0.184985563041\t0.164938655607\t0.256026889198\t0.122313048744\t0.0919761054243\t0.113686534216\t0.194096927001\t13825\t1225\t121196\t0.2698\t['T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C']\t[0 0 1 0 0 1 0 0 1]\t[False False False False False False False False False]\t[38 29 22 38 29 21 38 29 24]\t[1 0 0 1 0 0 1 0 0]\t[37 29 22 37 29 21 37 29 24]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t3\t3_dad(3_dad;unaffected),3_mom(3_mom;unaffected),3_kid(3_kid;affected)\tT/T,T/T,T/C\t3_kid\t3\tplausible de novo;plausible de novo;plausible de novo\t0.00000\n-chr10\t135369531\t135369532\tNone\t5\t6\tT\tC\t122.620002747\tNone\tsnp\tts\t1.0\t1\trs3747881,rs386585367\tNone\tNone\tNone\tNone\tNone\t1\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tNone\tchr10q26.3\tNone\t0\t0\t1\tNone\t3.86096e-59\t6\t3\t0\t0\t0.166666666667\t0.548506235587\t-0.2\t0.294117647059\t0.022013\tSYCE1\tENST00000368517\t1\t1\t0\t0\texon_10_135369485_135369551\taAg/aGg\tK147R\t282\tprotein_coding\tmissense_variant\tmissense_variant\tMED\tNone\tNone\tNone\tNone\tNone\tNone\tNone\t239\tNone\t36.0200004578\t2\t0\t8\t0.0\t5.71409988403\t2.30999994278\t2\tNone\tNone\tNone\tNone\tNone\t1\t0.0938372093023\t0.163867453473\t0.117561125634\t1\t1\t0.1844\t0.2698\t0.2188\t0.1997\t0.1093\t0.197284\tNone\tNone\tNone\tNone\t0\tNone\tNone\tNone\tR\tR\tR\tR\tR\tR\tNone\tNone\tNone\tNone\tNone\t0.487112\t1\t0.134\t0.134286610119\t0.184985563041\t0.164938655607\t0.256026889198\t0.122313048744\t0.0919761054243\t0.113686534216\t0.194096927001\t13825\t1225\t121196\t0.2698\t['T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C' 'T/T' 'T/T' 'T/C']\t[0 0 1 0 0 1 0 0 1]\t[False False False False False False False False False]\t[38 29 22 38 29 21 38 29 24]\t[1 0 0 1 0 0 1 0 0]\t[37 29 22 37 29 21 37 29 24]\t[ 87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939  87.16000366  78.19999695  66.13999939]\tNone\t[940 899 729 940 899 729 940 899 729]\t[87 78 66 87 78 66 87 78 66]\t[0 0 0 0 0 0 0 0 0]\t2\t2_dad(2_dad;unaffected),2_mom(2_mom;unaffected),2_kid(2_kid;affected)\tT/T,T/T,T/C\t2_kid\t3\tplausible de novo;plausible de novo;plausible de novo\t0.00000\n"
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_pathways_result.tabular
--- a/test-data/gemini_pathways_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,17 +0,0 @@
-chrom start end ref alt impact sample genotype gene transcript pathway
-chr10 52004314 52004315 T C intron_variant M10500 C/C ASAH2 ENST00000329428 hsa00600:Sphingolipid_metabolism,hsa01100:Metabolic_pathways
-chr10 52004314 52004315 T C intron_variant M128215 C/C ASAH2 ENST00000329428 hsa00600:Sphingolipid_metabolism,hsa01100:Metabolic_pathways
-chr10 52004314 52004315 T C intron_variant M10500 C/C ASAH2 ENST00000447815 hsa00600:Sphingolipid_metabolism,hsa01100:Metabolic_pathways
-chr10 52004314 52004315 T C intron_variant M128215 C/C ASAH2 ENST00000447815 hsa00600:Sphingolipid_metabolism,hsa01100:Metabolic_pathways
-chr10 52004314 52004315 T C intron_variant M10500 C/C ASAH2 ENST00000395526 hsa00600:Sphingolipid_metabolism,hsa01100:Metabolic_pathways
-chr10 52004314 52004315 T C intron_variant M128215 C/C ASAH2 ENST00000395526 hsa00600:Sphingolipid_metabolism,hsa01100:Metabolic_pathways
-chr10 126678091 126678092 G A stop_gained M128215 G/A CTBP2 ENST00000531469 hsa05220:Chronic_myeloid_leukemia,hsa04310:Wnt_signaling_pathway,hsa04330:Notch_signaling_pathway,hsa05200:Pathways_in_cancer
-chr10 126678091 126678092 G A stop_gained M128215 G/A CTBP2 ENST00000309035 hsa05220:Chronic_myeloid_leukemia,hsa04310:Wnt_signaling_pathway,hsa04330:Notch_signaling_pathway,hsa05200:Pathways_in_cancer
-chr10 126678091 126678092 G A stop_gained M128215 G/A CTBP2 ENST00000494626 hsa05220:Chronic_myeloid_leukemia,hsa04310:Wnt_signaling_pathway,hsa04330:Notch_signaling_pathway,hsa05200:Pathways_in_cancer
-chr10 126678091 126678092 G A stop_gained M128215 G/A CTBP2 ENST00000337195 hsa05220:Chronic_myeloid_leukemia,hsa04310:Wnt_signaling_pathway,hsa04330:Notch_signaling_pathway,hsa05200:Pathways_in_cancer
-chr10 126678091 126678092 G A stop_gained M128215 G/A CTBP2 ENST00000411419 hsa05220:Chronic_myeloid_leukemia,hsa04310:Wnt_signaling_pathway,hsa04330:Notch_signaling_pathway,hsa05200:Pathways_in_cancer
-chr10 135336655 135336656 G A intron_variant M10478 A/A CYP2E1 ENST00000463117 hsa00982:Drug_metabolism_cytochrome_P450,hsa01100:Metabolic_pathways,hsa00590:Arachidonic_acid_metabolism,hsa00980:Metabolism_of_xenobiotics_by_cytochrome_P450,hsa00591:Linoleic_acid_metabolism
-chr10 135336655 135336656 G A intron_variant M128215 A/A CYP2E1 ENST00000463117 hsa00982:Drug_metabolism_cytochrome_P450,hsa01100:Metabolic_pathways,hsa00590:Arachidonic_acid_metabolism,hsa00980:Metabolism_of_xenobiotics_by_cytochrome_P450,hsa00591:Linoleic_acid_metabolism
-chr10 135336655 135336656 G A upstream_gene_variant M10478 A/A CYP2E1 ENST00000252945 hsa00982:Drug_metabolism_cytochrome_P450,hsa01100:Metabolic_pathways,hsa00590:Arachidonic_acid_metabolism,hsa00980:Metabolism_of_xenobiotics_by_cytochrome_P450,hsa00591:Linoleic_acid_metabolism
-chr10 135336655 135336656 G A upstream_gene_variant M128215 A/A CYP2E1 ENST00000252945 hsa00982:Drug_metabolism_cytochrome_P450,hsa01100:Metabolic_pathways,hsa00590:Arachidonic_acid_metabolism,hsa00980:Metabolism_of_xenobiotics_by_cytochrome_P450,hsa00591:Linoleic_acid_metabolism
-chr16 72057434 72057435 C T missense_variant M10475 C/T DHODH ENST00000219240 hsa01100:Metabolic_pathways,hsa00240:Pyrimidine_metabolism
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_qc_result.tabular
--- a/test-data/gemini_qc_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,5 +0,0 @@
-sample sex chrX_homref chrX_het chrX_homalt chrX_unknown
-M10475 male 0 0 0 0
-M10478 female 0 0 0 0
-M10500 female 0 0 0 0
-M128215 male 0 0 0 0
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_query_result.tabular
--- a/test-data/gemini_query_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,10 +0,0 @@
-10582
-10610
-13301
-13326
-13956
-13979
-30922
-46401
-47189
-51475
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_region_result.tabular
--- a/test-data/gemini_region_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,1 +0,0 @@
-chr10 48003991 48003992 None 2 1 C T 1047.86999512 None snp ts 1.0 1 rs142685947,rs3739968 None None None None None 1 None None None None None None None None None None None None None None None None None None chr10q11.22 None 0 1 1 None 3.10871e-42 1 2 1 0 0.5 1 0 0.571428571429 1.718591 ASAH2C ENST00000420079 1 1 0 0 16/17 tGt/tAt C/Y 542/612 protein_coding missense_variant missense_variant MED benign 0.0 tolerated 1.0 None None None 165 None 20.9400005341 0 0 8 0.0 4.382999897 9.52999973297 4 None None None None None 0 None None None 0 1 0.3112 0.4573 0.3855 0.1241 0.5149 0.346645 grc_fix 73.3 40.3 92.8 0 None None None R R R R R R None None None None None 0.553676 1 0.443 0.448537771896 0.288974151858 0.281426746944 0.543088975937 0.524984286612 0.478147713207 0.463529411765 0.418641164716 17495 15317 107302 1 0.543088975937
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_roh_result.tabular
--- a/test-data/gemini_roh_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,7 +0,0 @@
-chrom start end sample num_of_snps density_per_kb run_length_in_bp
-chr10 1142208 135369532 M10475 5 0.0 134227324
-chr10 1142208 135210791 M10500 5 0.0001 134068583
-chr10 1142208 135210791 M10478 5 0.0001 134068583
-chr10 1142208 135336656 M10478 4 0.0 134194448
-chr10 1142208 135336656 M128215 6 0.0001 134194448
-chr10 1142208 135369532 M128215 5 0.0 134227324
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_stats_result.tabular
--- a/test-data/gemini_stats_result.tabular Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,5 +0,0 @@
-sample total
-M10475 3
-M10478 6
-M10500 6
-M128215 4
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_versioned_databases.loc
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gemini_versioned_databases.loc Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,3 @@
+## GEMINI versioned databases
+#DownloadDate dbkey DBversion Description Path
+1999-01-01 hg19 181 GEMINI annotations (test snapshot) ${__HERE__}/test-cache
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_windower_input.db
b
Binary file test-data/gemini_windower_input.db has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/gemini_windower_template.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gemini_windower_template.tabular Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,142 @@
+chr1 0 50000 .
+chr1 50000000 50050000 .
+chr1 100000000 100050000 .
+chr1 150000000 150050000 .
+chr1 200000000 200050000 .
+chr10 0 50000 .
+chr10 50000000 50050000 .
+chr10 100000000 100050000 .
+chr11 0 50000 .
+chr11 50000000 50050000 .
+chr11 100000000 100050000 .
+chr11_gl000202_random 0 40103 .
+chr12 0 50000 .
+chr12 50000000 50050000 .
+chr12 100000000 100050000 .
+chr13 0 50000 .
+chr13 50000000 50050000 .
+chr13 100000000 100050000 .
+chr14 0 50000 .
+chr14 50000000 50050000 .
+chr14 100000000 100050000 .
+chr15 0 50000 .
+chr15 50000000 50050000 .
+chr15 100000000 100050000 .
+chr16 0 50000 .
+chr16 50000000 50050000 .
+chr17 0 50000 .
+chr17 50000000 50050000 .
+chr17_ctg5_hap1 0 50000 .
+chr17_gl000203_random 0 37498 .
+chr17_gl000204_random 0 50000 .
+chr17_gl000205_random 0 50000 .
+chr17_gl000206_random 0 41001 .
+chr18 0 50000 .
+chr18 50000000 50050000 .
+chr18_gl000207_random 0 4262 .
+chr19 0 50000 .
+chr19 50000000 50050000 .
+chr19_gl000208_random 0 50000 .
+chr19_gl000209_random 0 50000 .
+chr1_gl000191_random 0 50000 .
+chr1_gl000192_random 0 50000 .
+chr2 0 50000 .
+chr2 50000000 50050000 .
+chr2 100000000 100050000 .
+chr2 150000000 150050000 .
+chr2 200000000 200050000 .
+chr20 0 50000 .
+chr20 50000000 50050000 .
+chr21 0 50000 .
+chr21_gl000210_random 0 27682 .
+chr22 0 50000 .
+chr22 50000000 50050000 .
+chr3 0 50000 .
+chr3 50000000 50050000 .
+chr3 100000000 100050000 .
+chr3 150000000 150050000 .
+chr4 0 50000 .
+chr4 50000000 50050000 .
+chr4 100000000 100050000 .
+chr4 150000000 150050000 .
+chr4_ctg9_hap1 0 50000 .
+chr4_gl000193_random 0 50000 .
+chr4_gl000194_random 0 50000 .
+chr5 0 50000 .
+chr5 50000000 50050000 .
+chr5 100000000 100050000 .
+chr5 150000000 150050000 .
+chr6 0 50000 .
+chr6 50000000 50050000 .
+chr6 100000000 100050000 .
+chr6 150000000 150050000 .
+chr6_apd_hap1 0 50000 .
+chr6_cox_hap2 0 50000 .
+chr6_dbb_hap3 0 50000 .
+chr6_mann_hap4 0 50000 .
+chr6_mcf_hap5 0 50000 .
+chr6_qbl_hap6 0 50000 .
+chr6_ssto_hap7 0 50000 .
+chr7 0 50000 .
+chr7 50000000 50050000 .
+chr7 100000000 100050000 .
+chr7 150000000 150050000 .
+chr7_gl000195_random 0 50000 .
+chr8 0 50000 .
+chr8 50000000 50050000 .
+chr8 100000000 100050000 .
+chr8_gl000196_random 0 38914 .
+chr8_gl000197_random 0 37175 .
+chr9 0 50000 .
+chr9 50000000 50050000 .
+chr9 100000000 100050000 .
+chr9_gl000198_random 0 50000 .
+chr9_gl000199_random 0 50000 .
+chr9_gl000200_random 0 50000 .
+chr9_gl000201_random 0 36148 .
+chrM 0 16571 .
+chrUn_gl000211 0 50000 .
+chrUn_gl000212 0 50000 .
+chrUn_gl000213 0 50000 .
+chrUn_gl000214 0 50000 .
+chrUn_gl000215 0 50000 .
+chrUn_gl000216 0 50000 .
+chrUn_gl000217 0 50000 .
+chrUn_gl000218 0 50000 .
+chrUn_gl000219 0 50000 .
+chrUn_gl000220 0 50000 .
+chrUn_gl000221 0 50000 .
+chrUn_gl000222 0 50000 .
+chrUn_gl000223 0 50000 .
+chrUn_gl000224 0 50000 .
+chrUn_gl000225 0 50000 .
+chrUn_gl000226 0 15008 .
+chrUn_gl000227 0 50000 .
+chrUn_gl000228 0 50000 .
+chrUn_gl000229 0 19913 .
+chrUn_gl000230 0 43691 .
+chrUn_gl000231 0 27386 .
+chrUn_gl000232 0 40652 .
+chrUn_gl000233 0 45941 .
+chrUn_gl000234 0 40531 .
+chrUn_gl000235 0 34474 .
+chrUn_gl000236 0 41934 .
+chrUn_gl000237 0 45867 .
+chrUn_gl000238 0 39939 .
+chrUn_gl000239 0 33824 .
+chrUn_gl000240 0 41933 .
+chrUn_gl000241 0 42152 .
+chrUn_gl000242 0 43523 .
+chrUn_gl000243 0 43341 .
+chrUn_gl000244 0 39929 .
+chrUn_gl000245 0 36651 .
+chrUn_gl000246 0 38154 .
+chrUn_gl000247 0 36422 .
+chrUn_gl000248 0 39786 .
+chrUn_gl000249 0 38502 .
+chrX 0 50000 .
+chrX 50000000 50050000 .
+chrX 100000000 100050000 .
+chrX 150000000 150050000 .
+chrY 0 50000 .
+chrY 50000000 50050000 .
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini-config.yaml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini-config.yaml Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,13 @@
+annotation_dir: gemini/data
+versions:
+  ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz: 4
+  ESP6500SI.all.snps_indels.tidy.v2.vcf.gz: 2
+  ExAC.r0.3.sites.vep.tidy.vcf.gz: 3
+  GRCh37-gms-mappability.vcf.gz: 2
+  clinvar_20160203.tidy.vcf.gz: 5
+  cosmic-v68-GRCh37.tidy.vcf.gz: 3
+  dbsnp.b141.20140813.hg19.tidy.vcf.gz: 4
+  detailed_gene_table_v75: 2
+  geno2mp.variants.tidy.vcf.gz: 1
+  hg19.rmsk.bed.gz: 2
+  summary_gene_table_v75: 2
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/29way_pi_lods_elements_12mers.chr_specific.fdr_0.1_with_scores.txt.hg19.merged.bed.gz
b
Binary file test-data/test-cache/gemini/data/29way_pi_lods_elements_12mers.chr_specific.fdr_0.1_with_scores.txt.hg19.merged.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/29way_pi_lods_elements_12mers.chr_specific.fdr_0.1_with_scores.txt.hg19.merged.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/29way_pi_lods_elements_12mers.chr_specific.fdr_0.1_with_scores.txt.hg19.merged.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz
b
Binary file test-data/test-cache/gemini/data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz
b
Binary file test-data/test-cache/gemini/data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/ExAC.r0.3.sites.vep.tidy.vcf.gz
b
Binary file test-data/test-cache/gemini/data/ExAC.r0.3.sites.vep.tidy.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/ExAC.r0.3.sites.vep.tidy.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/ExAC.r0.3.sites.vep.tidy.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/GRC_patch_regions.bed.gz
b
Binary file test-data/test-cache/gemini/data/GRC_patch_regions.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/GRC_patch_regions.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/GRC_patch_regions.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/GRCh37-gms-mappability.vcf.gz
b
Binary file test-data/test-cache/gemini/data/GRCh37-gms-mappability.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/GRCh37-gms-mappability.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/GRCh37-gms-mappability.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/cancer_gene_census.20140120.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/cancer_gene_census.20140120.tsv Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,19 @@
+ARHH "RAS homolog gene family, member H (TTF)" 399 4 4p13  yes NHL L Dom T BCL6
+BCL5 B-cell CLL/lymphoma 5 603 17 17q22  yes CLL L Dom T MYC
+BCL6 B-cell CLL/lymphoma 6 604 3 3q27  yes "NHL, CLL" L Dom "T, Mis" "IG loci, ZNFN1A1, LCP1, PIM1, TFRC, CIITA, NACA, HSPCB, HSPCA, HIST1H4I, IL21R,  POU2AF1, ARHH, EIF4A2, SFRS3"
+BCOR BCL6 corepressor 54880 X Xp11.4 yes "retinoblastoma, AML, APL (translocation)" Rec "F, N, S, T" RARA yes oculo-facio-cardio-dental genetic
+CIITA "class II, major histocompatibility complex, transactivator" 4261 16 16p13 yes "PMBL, Hodgkin lymphoma" L Dom T "FLJ27352, CD274, CD273, RALGDS, RUNDC2A, C16orf75, BCL6"
+EIF4A2 "eukaryotic translation initiation factor 4A, isoform 2" 1974 3 3q27.3 yes NHL L Dom T BCL6
+HIST1H4I "histone 1, H4i (H4FM)" 8294 6 6p21.3  yes NHL L Dom T BCL6
+HSPCA "heat shock 90kDa protein 1, alpha" 3320 14 14q32.31 yes NHL L Dom T BCL6
+HSPCB "heat shock 90kDa protein 1, beta" 3326 6 6p12 yes NHL L Dom T BCL6
+IGH@ immunoglobulin heavy locus 3492 14 14q32.33 yes "MM, Burkitt lymphoma, NHL, CLL, B-ALL, MALT, MLCLS" L Dom T "MYC, FGFR3,PAX5, IRTA1, IRF4, CCND1, BCL9, BCL8, BCL6, BCL2, BCL3, BCL10, BCL11A. LHX4, DDX6, NFKB2, PAFAH1B2, PCSK7, CRLF2"
+IKZF1 IKAROS family zinc finger 1 10320 7 7p12.2 yes "ALL, DLBCL" L "Rec,Dom" "D,T" BCL6
+IL21R interleukin 21 receptor 50615 16 16p11  yes NHL L Dom T BCL6
+LCP1 lymphocyte cytosolic protein 1 (L-plastin) 3936 13  13q14.1-q14.3  yes NHL  L Dom T BCL6
+MYC v-myc myelocytomatosis viral oncogene homolog (avian) 4609 8 8q24.12-q24.13  yes "Burkitt lymphoma, amplified in other cancers, B-CLL" "L, E" Dom "A, T" "IGK@, BCL5, BCL7A , BTG1, TRA@, IGH@"
+NACA nascent-polypeptide-associated complex alpha polypeptide 4666 12 12q23-q24.1  yes NHL L Dom T BCL6
+PIM1 pim-1 oncogene 5292 6 6p21.2  yes NHL L Dom T BCL6
+POU2AF1 "POU domain, class 2, associating factor 1 (OBF1)" 5450 11 11q23.1  yes NHL L Dom T BCL6
+SFRS3 "splicing factor, arginine/serine-rich 3" 6428 6 6p21 yes follicular lymphoma L Dom T BCL6
+TFRC "transferrin receptor (p90, CD71)" 7037 3 3q29  yes NHL L Dom T BCL6
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz
b
Binary file test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/cosmic-v68-GRCh37.tidy.vcf.gz
b
Binary file test-data/test-cache/gemini/data/cosmic-v68-GRCh37.tidy.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/cosmic-v68-GRCh37.tidy.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/cosmic-v68-GRCh37.tidy.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/cse-hiseq-8_4-2013-02-20.bed.gz
b
Binary file test-data/test-cache/gemini/data/cse-hiseq-8_4-2013-02-20.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/cse-hiseq-8_4-2013-02-20.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/cse-hiseq-8_4-2013-02-20.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz
b
Binary file test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/detailed_gene_table_v75
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/detailed_gene_table_v75 Fri Dec 14 12:49:22 2018 -0500
b
b'@@ -0,0 +1,114 @@\n+Chromosome\tGene_name\tIs_hgnc\tEnsembl_gene_id\tEnsembl_transcript_id\tBiotype\tTranscript_status\tCCDS_id\tHGNC_id\tCDS_length\tProtein_length\tTranscript_start\tTranscript_end\tstrand\tSynonyms\tRvis_pct\tentrez_gene_id\tmammalian_phenotype_id\n+chr3\tNone\t0\tENSG00000239093\tENST00000459452\tsnoRNA\tKNOWN\tNone\tNone\tNone\tNone\t187141103\t187141207\t1\tNone\tNone\tNone\tNone\n+chr3\tNone\t0\tENSG00000228952\tENST00000440726\tlincRNA\tKNOWN\tNone\tNone\tNone\tNone\t187166633\t187167238\t1\tNone\tNone\tNone\tNone\n+chr3\tNone\t0\tENSG00000223401\tENST00000450760\tlincRNA\tKNOWN\tNone\tNone\tNone\tNone\t187461474\t187463208\t1\tNone\tNone\tNone\tNone\n+chr3\tMASP\t0\tENSG00000127241\tENST00000337774\tprotein_coding\tKNOWN\tCCDS33907\tNone\t2100\t699\t186935942\t187009810\t-1\tPRSS5,MASP1,CRARF\t16.8141071\t5648\tNone\n+chr3\tPRSS5\t0\tENSG00000127241\tENST00000337774\tprotein_coding\tKNOWN\tCCDS33907\tNone\t2100\t699\t186935942\t187009810\t-1\tMASP1,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP1\t1\tENSG00000127241\tENST00000337774\tprotein_coding\tKNOWN\tCCDS33907\t6901\t2100\t699\t186935942\t187009810\t-1\tPRSS5,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tCRARF\t0\tENSG00000127241\tENST00000337774\tprotein_coding\tKNOWN\tCCDS33907\tNone\t2100\t699\t186935942\t187009810\t-1\tPRSS5,MASP1,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP\t0\tENSG00000127241\tENST00000296280\tprotein_coding\tKNOWN\tCCDS33908\tNone\t2187\t728\t186951870\t187009646\t-1\tPRSS5,MASP1,CRARF\t16.8141071\t5648\tNone\n+chr3\tPRSS5\t0\tENSG00000127241\tENST00000296280\tprotein_coding\tKNOWN\tCCDS33908\tNone\t2187\t728\t186951870\t187009646\t-1\tMASP1,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP1\t1\tENSG00000127241\tENST00000296280\tprotein_coding\tKNOWN\tCCDS33908\t6901\t2187\t728\t186951870\t187009646\t-1\tPRSS5,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tCRARF\t0\tENSG00000127241\tENST00000296280\tprotein_coding\tKNOWN\tCCDS33908\tNone\t2187\t728\t186951870\t187009646\t-1\tPRSS5,MASP1,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP\t0\tENSG00000127241\tENST00000392472\tprotein_coding\tPUTATIVE\tNone\tNone\t1848\t615\t186951872\t187009765\t-1\tPRSS5,MASP1,CRARF\t16.8141071\t5648\tNone\n+chr3\tPRSS5\t0\tENSG00000127241\tENST00000392472\tprotein_coding\tPUTATIVE\tNone\tNone\t1848\t615\t186951872\t187009765\t-1\tMASP1,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP1\t1\tENSG00000127241\tENST00000392472\tprotein_coding\tPUTATIVE\tNone\t6901\t1848\t615\t186951872\t187009765\t-1\tPRSS5,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tCRARF\t0\tENSG00000127241\tENST00000392472\tprotein_coding\tPUTATIVE\tNone\tNone\t1848\t615\t186951872\t187009765\t-1\tPRSS5,MASP1,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP\t0\tENSG00000127241\tENST00000495249\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t186953655\t187009542\t-1\tPRSS5,MASP1,CRARF\t16.8141071\t5648\tNone\n+chr3\tPRSS5\t0\tENSG00000127241\tENST00000495249\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t186953655\t187009542\t-1\tMASP1,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP1\t1\tENSG00000127241\tENST00000495249\tprocessed_transcript\tPUTATIVE\tNone\t6901\tNone\tNone\t186953655\t187009542\t-1\tPRSS5,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tCRARF\t0\tENSG00000127241\tENST00000495249\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t186953655\t187009542\t-1\tPRSS5,MASP1,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP\t0\tENSG00000127241\tENST00000169293\tprotein_coding\tKNOWN\tCCDS33909\tNone\t1143\t380\t186964149\t187009745\t-1\tPRSS5,MASP1,CRARF\t16.8141071\t5648\tNone\n+chr3\tPRSS5\t0\tENSG00000127241\tENST00000169293\tprotein_coding\tKNOWN\tCCDS33909\tNone\t1143\t380\t186964149\t187009745\t-1\tMASP1,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP1\t1\tENSG00000127241\tENST00000169293\tprotein_coding\tKNOWN\tCCDS33909\t6901\t1143\t380\t186964149\t187009745\t-1\tPRSS5,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tCRARF\t0\tENSG00000127241\tENST00000169293\tprotein_coding\tKNOWN\tCCDS33909\tNone\t1143\t380\t186964149\t187009745\t-1\tPRSS5,MASP1,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP\t0\tENSG00000127241\tENST00000392470\tprotein_coding\tPUTATIVE\tNone\tNone\t1065\t354\t186964947\t187009670\t-1\tPRSS5,MASP1,CRARF\t16.8141071\t5648\tNone\n+chr3\tPRSS5\t0\tENSG00000127241\tENST00000392470\tprotein_coding\tPUTATIVE\tNone\tNone\t1065\t354\t186964947\t187009670\t-1\tMASP1,CRARF,MASP\t16.8141071\t5648\tNone\n+chr3\tMASP1\t1\tENSG00000127241\tENST00'..b'otein_coding\tKNOWN\tNone\t1001\t312\t103\t187449568\t187455732\t-1\tLAZ3,ZNF51,ZBTB27,BCL5,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tZBTB27\t0\tENSG00000113916\tENST00000438077\tprotein_coding\tKNOWN\tNone\tNone\t312\t103\t187449568\t187455732\t-1\tLAZ3,ZNF51,BCL6,BCL5,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tZNF51\t0\tENSG00000113916\tENST00000470319\tretained_intron\tKNOWN\tNone\tNone\tNone\tNone\t187452233\t187463260\t-1\tLAZ3,BCL5,BCL6,ZBTB27,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tLAZ3\t0\tENSG00000113916\tENST00000470319\tretained_intron\tKNOWN\tNone\tNone\tNone\tNone\t187452233\t187463260\t-1\tBCL5,ZNF51,BCL6,ZBTB27,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tBCL5\t0\tENSG00000113916\tENST00000470319\tretained_intron\tKNOWN\tNone\tNone\tNone\tNone\t187452233\t187463260\t-1\tLAZ3,ZNF51,BCL6,ZBTB27,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tBCL6A\t0\tENSG00000113916\tENST00000470319\tretained_intron\tKNOWN\tNone\tNone\tNone\tNone\t187452233\t187463260\t-1\tLAZ3,ZNF51,BCL6,BCL5,ZBTB27\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tBCL6\t1\tENSG00000113916\tENST00000470319\tretained_intron\tKNOWN\tNone\t1001\tNone\tNone\t187452233\t187463260\t-1\tLAZ3,ZNF51,ZBTB27,BCL5,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tZBTB27\t0\tENSG00000113916\tENST00000470319\tretained_intron\tKNOWN\tNone\tNone\tNone\tNone\t187452233\t187463260\t-1\tLAZ3,ZNF51,BCL6,BCL5,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tZNF51\t0\tENSG00000113916\tENST00000496823\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t187453975\t187463247\t-1\tLAZ3,BCL5,BCL6,ZBTB27,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tLAZ3\t0\tENSG00000113916\tENST00000496823\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t187453975\t187463247\t-1\tBCL5,ZNF51,BCL6,ZBTB27,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tBCL5\t0\tENSG00000113916\tENST00000496823\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t187453975\t187463247\t-1\tLAZ3,ZNF51,BCL6,ZBTB27,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tBCL6A\t0\tENSG00000113916\tENST00000496823\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t187453975\t187463247\t-1\tLAZ3,ZNF51,BCL6,BCL5,ZBTB27\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tBCL6\t1\tENSG00000113916\tENST00000496823\tprocessed_transcript\tPUTATIVE\tNone\t1001\tNone\tNone\t187453975\t187463247\t-1\tLAZ3,ZNF51,ZBTB27,BCL5,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n+chr3\tZBTB27\t0\tENSG00000113916\tENST00000496823\tprocessed_transcript\tPUTATIVE\tNone\tNone\tNone\tNone\t187453975\t187463247\t-1\tLAZ3,ZNF51,BCL6,BCL5,BCL6A\t23.5727766\t604\tMP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387\n'
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/encode.6celltypes.consensus.bedg.gz
b
Binary file test-data/test-cache/gemini/data/encode.6celltypes.consensus.bedg.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/encode.6celltypes.consensus.bedg.gz.tbi
b
Binary file test-data/test-cache/gemini/data/encode.6celltypes.consensus.bedg.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/genetic_map_HapMapII_GRCh37.gz
b
Binary file test-data/test-cache/gemini/data/genetic_map_HapMapII_GRCh37.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/genetic_map_HapMapII_GRCh37.gz.tbi
b
Binary file test-data/test-cache/gemini/data/genetic_map_HapMapII_GRCh37.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/geno2mp.variants.tidy.vcf.gz
b
Binary file test-data/test-cache/gemini/data/geno2mp.variants.tidy.vcf.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/geno2mp.variants.tidy.vcf.gz.tbi
b
Binary file test-data/test-cache/gemini/data/geno2mp.variants.tidy.vcf.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.CpG.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.CpG.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.CpG.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.CpG.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.cytoband.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.cytoband.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.cytoband.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.cytoband.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.dgv.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.dgv.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.dgv.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.dgv.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.gerp.elements.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.gerp.elements.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.gerp.elements.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.gerp.elements.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.gwas.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.gwas.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.gwas.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.gwas.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.pfam.ucscgenes.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.pfam.ucscgenes.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.pfam.ucscgenes.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.pfam.ucscgenes.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.rmsk.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.rmsk.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.rmsk.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.rmsk.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.segdup.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.segdup.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.segdup.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.segdup.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.vista.enhancers.20131108.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19.vista.enhancers.20131108.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19.vista.enhancers.20131108.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19.vista.enhancers.20131108.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19_fitcons_fc-i6-0_V1-01.bed.gz
b
Binary file test-data/test-cache/gemini/data/hg19_fitcons_fc-i6-0_V1-01.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hg19_fitcons_fc-i6-0_V1-01.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/hg19_fitcons_fc-i6-0_V1-01.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/hprd_interaction_edges.gz
b
Binary file test-data/test-cache/gemini/data/hprd_interaction_edges.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/kegg_pathways_ensembl66
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/kegg_pathways_ensembl66 Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,30 @@
+B8PSA7 BCL6 BCL6 ENSG00000113916 ENST00000450123 None None
+C9J1C7 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JCS5 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JCS5 BCL6 BCL6 ENSG00000113916 ENST00000450123 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000438077 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000450123 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000169293 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000296280 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000425937 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JMA2 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+F5H2J0 MASP1 MASP1 ENSG00000127241 ENST00000541896 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000169293 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000232014 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000406870 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04080;Neuroactive_ligand_receptor_interaction
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04971;Gastric_acid_secretion
+Q5HYM1 MASP1 MASP1 ENSG00000127241 ENST00000541896 None None
+Q5QGT7 RTP2 RTP2 ENSG00000198471 ENST00000358241 hsa:344892 None
+Q96DX8 RTP4 RTP4 ENSG00000136514 ENST00000259030 hsa:64108 None
+Q9NSY8 MASP1 MASP1 ENSG00000127241 ENST00000296280 None None
+Q9NSY8 MASP1 MASP1 ENSG00000127241 ENST00000392472 None None
+Q9NSY8 MASP1 MASP1 ENSG00000127241 ENST00000541811 None None
+none BCL6 BCL6 ENSG00000113916 ENST00000419510 None None
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/kegg_pathways_ensembl67
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/kegg_pathways_ensembl67 Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,30 @@
+B8PSA7 BCL6 BCL6 ENSG00000113916 ENST00000450123 None None
+C9J1C7 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JCS5 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JCS5 BCL6 BCL6 ENSG00000113916 ENST00000450123 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000438077 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000450123 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000169293 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000296280 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000425937 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JMA2 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+F5H2J0 MASP1 MASP1 ENSG00000127241 ENST00000541896 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000169293 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000232014 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000406870 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04080;Neuroactive_ligand_receptor_interaction
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04971;Gastric_acid_secretion
+Q5HYM1 MASP1 MASP1 ENSG00000127241 ENST00000541896 None None
+Q5QGT7 RTP2 RTP2 ENSG00000198471 ENST00000358241 hsa:344892 None
+Q96DX8 RTP4 RTP4 ENSG00000136514 ENST00000259030 hsa:64108 None
+Q9NSY8 MASP1 MASP1 ENSG00000127241 ENST00000296280 None None
+Q9NSY8 MASP1 MASP1 ENSG00000127241 ENST00000392472 None None
+Q9NSY8 MASP1 MASP1 ENSG00000127241 ENST00000541811 None None
+none BCL6 BCL6 ENSG00000113916 ENST00000419510 None None
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/kegg_pathways_ensembl68
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/kegg_pathways_ensembl68 Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,26 @@
+C9J1C7 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JCS5 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000438077 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000425937 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JMA2 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000232014 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000406870 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000450123 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04080;Neuroactive_ligand_receptor_interaction
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04971;Gastric_acid_secretion
+Q5QGT7 RTP2 RTP2 ENSG00000198471 ENST00000358241 hsa:344892 None
+Q96DX8 RTP4 RTP4 ENSG00000136514 ENST00000259030 hsa:64108 None
+none BCL6 BCL6 ENSG00000113916 ENST00000419510 None None
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/kegg_pathways_ensembl69
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/kegg_pathways_ensembl69 Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,26 @@
+C9J1C7 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JCS5 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000438077 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000425937 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JMA2 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000232014 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000406870 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000450123 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04080;Neuroactive_ligand_receptor_interaction
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04971;Gastric_acid_secretion
+Q5QGT7 RTP2 RTP2 ENSG00000198471 ENST00000358241 hsa:344892 None
+Q96DX8 RTP4 RTP4 ENSG00000136514 ENST00000259030 hsa:64108 None
+none BCL6 BCL6 ENSG00000113916 ENST00000419510 None None
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/kegg_pathways_ensembl70
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/kegg_pathways_ensembl70 Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,25 @@
+C9J1C7 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000438077 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000425937 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JMA2 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000232014 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000406870 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000450123 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04080;Neuroactive_ligand_receptor_interaction
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04971;Gastric_acid_secretion
+Q5QGT7 RTP2 RTP2 ENSG00000198471 ENST00000358241 hsa:344892 None
+Q96DX8 RTP4 RTP4 ENSG00000136514 ENST00000259030 hsa:64108 None
+none BCL6 BCL6 ENSG00000113916 ENST00000419510 None None
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/kegg_pathways_ensembl71
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/kegg_pathways_ensembl71 Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,26 @@
+C9J1C7 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JCS5 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000430339 None None
+C9JL16 BCL6 BCL6 ENSG00000113916 ENST00000438077 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000425937 None None
+C9JLU5 MASP1 MASP1 ENSG00000127241 ENST00000439271 None None
+C9JMA2 MASP1 MASP1 ENSG00000127241 ENST00000392475 None None
+F8W876 MASP1 MASP1 ENSG00000127241 ENST00000392470 None None
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000232014 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000406870 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P41182 BCL6 BCL6 ENSG00000113916 ENST00000450123 hsa:604 path:hsa05202;Transcriptional_misregulation_in_cancer
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000169293 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000296280 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000337774 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa04610;Complement_and_coagulation_cascades
+P48740 MASP1 MASP1 ENSG00000127241 ENST00000392472 hsa:5648 path:hsa05150;Staphylococcus_aureus_infection
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04080;Neuroactive_ligand_receptor_interaction
+P61278 SST SST ENSG00000157005 ENST00000287641 hsa:6750 path:hsa04971;Gastric_acid_secretion
+Q5QGT7 RTP2 RTP2 ENSG00000198471 ENST00000358241 hsa:344892 None
+Q96DX8 RTP4 RTP4 ENSG00000136514 ENST00000259030 hsa:64108 None
+none BCL6 BCL6 ENSG00000113916 ENST00000419510 None None
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/stam.125cells.dnaseI.hg19.bed.gz
b
Binary file test-data/test-cache/gemini/data/stam.125cells.dnaseI.hg19.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/stam.125cells.dnaseI.hg19.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/stam.125cells.dnaseI.hg19.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/summary_gene_table_v75
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test-cache/gemini/data/summary_gene_table_v75 Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,23 @@
+Chromosome Gene_name Is_hgnc Ensembl_gene_id HGNC_id Synonyms Rvis_pct Strand Transcript_min_start Transcript_max_end Mammalian_phenotype_id
+chr3 None 0 ENSG00000239093 None None None 1 187141103 187141207 None
+chr3 None 0 ENSG00000228952 None None None 1 187166633 187167238 None
+chr3 None 0 ENSG00000223401 None None None 1 187461474 187463208 None
+chr3 MASP 0 ENSG00000127241 None PRSS5,MASP1,CRARF 16.8141071 -1 186935942 187009810 None
+chr3 PRSS5 0 ENSG00000127241 None MASP1,CRARF,MASP 16.8141071 -1 186935942 187009810 None
+chr3 MASP1 1 ENSG00000127241 6901 PRSS5,CRARF,MASP 16.8141071 -1 186935942 187009810 None
+chr3 CRARF 0 ENSG00000127241 None PRSS5,MASP1,MASP 16.8141071 -1 186935942 187009810 None
+chr3 IFRG28 0 ENSG00000136514 None RTP4,Z3CXXC4 94.35008257 1 187086120 187089864 None
+chr3 RTP4 1 ENSG00000136514 23992 IFRG28,Z3CXXC4 94.35008257 1 187086120 187089864 None
+chr3 Z3CXXC4 0 ENSG00000136514 None IFRG28,RTP4 94.35008257 1 187086120 187089864 None
+chr3 SST 1 ENSG00000157005 11329 SMST 78.16112291 -1 187386694 187388187 MP:0002873,MP:0005386,MP:0005376,MP:0005381,MP:0003631,MP:0005378
+chr3 SMST 0 ENSG00000157005 None SST 78.16112291 -1 187386694 187388187 MP:0002873,MP:0005386,MP:0005376,MP:0005381,MP:0003631,MP:0005378
+chr3 Z3CXXC2 0 ENSG00000198471 None RTP2,MGC78665 69.20853975 -1 187416047 187420345 MP:0005389
+chr3 RTP2 1 ENSG00000198471 32486 Z3CXXC2,MGC78665 69.20853975 -1 187416047 187420345 MP:0005389
+chr3 MGC78665 0 ENSG00000198471 None Z3CXXC2,RTP2 69.20853975 -1 187416047 187420345 MP:0005389
+chr3 None 0 ENSG00000228804 None None None 1 187420101 187451637 None
+chr3 ZNF51 0 ENSG00000113916 None LAZ3,BCL5,BCL6,ZBTB27,BCL6A 23.5727766 -1 187439165 187463515 MP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387
+chr3 LAZ3 0 ENSG00000113916 None BCL5,ZNF51,BCL6,ZBTB27,BCL6A 23.5727766 -1 187439165 187463515 MP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387
+chr3 BCL5 0 ENSG00000113916 None LAZ3,ZNF51,BCL6,ZBTB27,BCL6A 23.5727766 -1 187439165 187463515 MP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387
+chr3 BCL6A 0 ENSG00000113916 None LAZ3,ZNF51,BCL6,BCL5,ZBTB27 23.5727766 -1 187439165 187463515 MP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387
+chr3 BCL6 1 ENSG00000113916 1001 LAZ3,ZNF51,ZBTB27,BCL5,BCL6A 23.5727766 -1 187439165 187463515 MP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387
+chr3 ZBTB27 0 ENSG00000113916 None LAZ3,ZNF51,BCL6,BCL5,BCL6A 23.5727766 -1 187439165 187463515 MP:0005369,MP:0005384,MP:0005376,MP:0005388,MP:0005370,MP:0010768,MP:0002873,MP:0005389,MP:0005378,MP:0005397,MP:0005385,MP:0005387
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/wgEncodeRegTfbsClusteredV2.cell_count.20130213.bed.gz
b
Binary file test-data/test-cache/gemini/data/wgEncodeRegTfbsClusteredV2.cell_count.20130213.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/test-cache/gemini/data/wgEncodeRegTfbsClusteredV2.cell_count.20130213.bed.gz.tbi
b
Binary file test-data/test-cache/gemini/data/wgEncodeRegTfbsClusteredV2.cell_count.20130213.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/README.rst
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/README.rst Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,25 @@
+Prepare Gemini annotation files and test databases for tool tests
+=================================================================
+
+Each version of GEMINI is tied to a particular set of annotation files and
+database version.
+
+The ``build-gemini-testdata.sh`` script in this folder should be used to
+regenerate the annotation files and the test databases whenever the GEMINI
+version required by the tool wrappers gets upgraded.
+
+The script requires a working GEMINI installation at the targeted version and
+a folder with GEMINI's original annotation files, and can be executed with::
+
+  sh build-gemini-testdata.sh path/to/gemini/annotation/files
+  
+It will regenerate the annotation files inside test-data/test-cache/gemini/data
+and rebuild the *.db files in test-data.
+
+.. Note::
+
+   If the version of GEMINI that you are upgrading to uses a gemini-config.yaml
+   file that is different from the one found in test-data/test-cache you will
+   have to upgrade this file manually (make sure you leave the line
+   ``annotation_dir: gemini/data`` unchanged in the process).
+
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/anno.bed
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/anno.bed Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,3 @@
+chr3 187000000 187150000
+chr3 187150000 187300000
+chr3 187300000 187450000
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/anno.bed.gz
b
Binary file test-data/util/build-data/anno.bed.gz has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/anno.bed.gz.tbi
b
Binary file test-data/util/build-data/anno.bed.gz.tbi has changed
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/gemini_load_input.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/gemini_load_input.vcf Fri Dec 14 12:49:22 2018 -0500
[
b'@@ -0,0 +1,70 @@\n+##fileformat=VCFv4.1\n+##INFO=<ID=LDAF,Number=1,Type=Float,Description="MLE Allele Frequency Accounting for LD">\n+##INFO=<ID=AVGPOST,Number=1,Type=Float,Description="Average posterior probability from MaCH/Thunder">\n+##INFO=<ID=RSQ,Number=1,Type=Float,Description="Genotype imputation quality from MaCH/Thunder">\n+##INFO=<ID=ERATE,Number=1,Type=Float,Description="Per-marker Mutation rate from MaCH/Thunder">\n+##INFO=<ID=THETA,Number=1,Type=Float,Description="Per-marker Transition rate from MaCH/Thunder">\n+##INFO=<ID=CIEND,Number=2,Type=Integer,Description="Confidence interval around END for imprecise variants">\n+##INFO=<ID=CIPOS,Number=2,Type=Integer,Description="Confidence interval around POS for imprecise variants">\n+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">\n+##INFO=<ID=HOMLEN,Number=.,Type=Integer,Description="Length of base pair identical micro-homology at event breakpoints">\n+##INFO=<ID=HOMSEQ,Number=.,Type=String,Description="Sequence of base pair identical micro-homology at event breakpoints">\n+##INFO=<ID=SVLEN,Number=1,Type=Integer,Description="Difference in length between REF and ALT alleles">\n+##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">\n+##INFO=<ID=AC,Number=.,Type=Integer,Description="Alternate Allele Count">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total Allele Count">\n+##ALT=<ID=DEL,Description="Deletion">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=DS,Number=1,Type=Float,Description="Genotype dosage from MaCH/Thunder">\n+##FORMAT=<ID=GL,Number=.,Type=Float,Description="Genotype Likelihoods">\n+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele, ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/pilot_data/technical/reference/ancestral_alignments/README">\n+##INFO=<ID=AF,Number=1,Type=Float,Description="Global Allele Frequency based on AC/AN">\n+##INFO=<ID=AMR_AF,Number=1,Type=Float,Description="Allele Frequency for samples from AMR based on AC/AN">\n+##INFO=<ID=ASN_AF,Number=1,Type=Float,Description="Allele Frequency for samples from ASN based on AC/AN">\n+##INFO=<ID=AFR_AF,Number=1,Type=Float,Description="Allele Frequency for samples from AFR based on AC/AN">\n+##INFO=<ID=EUR_AF,Number=1,Type=Float,Description="Allele Frequency for samples from EUR based on AC/AN">\n+##INFO=<ID=VT,Number=1,Type=String,Description="indicates what type of variant the line represents">\n+##INFO=<ID=SNPSOURCE,Number=.,Type=String,Description="indicates if a snp was called when analysing the low coverage or exome alignment data">\n+##reference=GRCh37\n+##SnpEffVersion="SnpEff 3.0f (build 2012-08-23), by Pablo Cingolani"\n+##SnpEffCmd="SnpEff  GRCh37.66 -i vcf -o vcf -c /Users/arq5x/src/other/snpEff_3_0/snpEff.config ALL.wgs.integrated_phase1_v3.20101123.snps_indels_sv.sites.vcf.gz "\n+##INFO=<ID=EFF,Number=.,Type=String,Description="Predicted effects for this variant.Format: \'Effect ( Effect_Impact | Functional_Class | Codon_Change | Amino_Acid_change| Amino_Acid_length | Gene_Name | Gene_BioType | Coding | Transcript | Exon [ | ERRORS | WARNINGS ] )\' ">\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\n+1\t10583\trs58108140\tG\tA\t100.0\tPASS\tAVGPOST=0.7707;RSQ=0.4319;LDAF=0.2327;ERATE=0.0161;AN=2184;VT=SNP;AA=.;THETA=0.0046;AC=314;SNPSOURCE=LOWCOV;AF=0.14;ASN_AF=0.13;AMR_AF=0.17;AFR_AF=0.04;EUR_AF=0.21;EFF=DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|),UPSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328|),UPSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305|),UPSTREAM(MODIFIER||'..b'=0.9844;LDAF=0.0146;ERATE=0.0058;AF=0.01;ASN_AF=0.01;AMR_AF=0.0028;AFR_AF=0.02;EUR_AF=0.0013;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t54421\trs146477069\tA\tG\t100.0\tPASS\tERATE=0.0013;AN=2184;AC=220;VT=SNP;RSQ=0.7869;AVGPOST=0.9461;AA=A;THETA=0.0025;SNPSOURCE=LOWCOV;LDAF=0.1190;AF=0.10;ASN_AF=0.25;AMR_AF=0.12;AFR_AF=0.03;EUR_AF=0.02;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t54490\trs141149254\tG\tA\t100.0\tPASS\tERATE=0.0004;THETA=0.0074;AA=G;AN=2184;VT=SNP;RSQ=0.8366;AVGPOST=0.9646;AC=175;SNPSOURCE=LOWCOV;LDAF=0.0929;AF=0.08;ASN_AF=0.0035;AMR_AF=0.12;AFR_AF=0.03;EUR_AF=0.15;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t54676\trs2462492\tC\tT\t100.0\tPASS\tLDAF=0.1528;RSQ=0.6989;AA=T;AN=2184;AC=267;VT=SNP;AVGPOST=0.8998;SNPSOURCE=LOWCOV;THETA=0.0110;ERATE=0.0037;AF=0.12;ASN_AF=0.02;AMR_AF=0.20;AFR_AF=0.09;EUR_AF=0.18;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t54753\trs143174675\tT\tG\t100.0\tPASS\tAA=T;AN=2184;RSQ=0.6820;AC=65;VT=SNP;THETA=0.0080;ERATE=0.0016;SNPSOURCE=LOWCOV;AVGPOST=0.9697;LDAF=0.0399;AF=0.03;AMR_AF=0.04;AFR_AF=0.07;EUR_AF=0.03;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55164\trs3091274\tC\tA\t100.0\tPASS\tAN=2184;VT=SNP;ERATE=0.0045;AA=A;THETA=0.0162;SNPSOURCE=LOWCOV;AC=1955;RSQ=0.6373;AVGPOST=0.8686;LDAF=0.8489;AF=0.90;ASN_AF=0.99;AMR_AF=0.94;AFR_AF=0.65;EUR_AF=0.96;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55249\t.\tC\tCTATGG\t443.0\tPASS\tAA=C;AVGPOST=0.9073;ERATE=0.0063;RSQ=0.5891;AN=2184;THETA=0.0038;VT=INDEL;AC=151;LDAF=0.0968;AF=0.07;ASN_AF=0.16;AMR_AF=0.08;AFR_AF=0.03;EUR_AF=0.02;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55299\trs10399749\tC\tT\t100.0\tPASS\tRSQ=0.7602;LDAF=0.2954;AN=2184;VT=SNP;ERATE=0.0051;AA=c;AC=554;SNPSOURCE=LOWCOV;AVGPOST=0.8845;THETA=0.0070;AF=0.25;ASN_AF=0.33;AMR_AF=0.21;AFR_AF=0.39;EUR_AF=0.13;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55313\trs182462964\tA\tT\t100.0\tPASS\tERATE=0.0004;RSQ=0.6112;AVGPOST=0.9994;AN=2184;VT=SNP;THETA=0.0057;AA=A;SNPSOURCE=LOWCOV;AC=1;LDAF=0.0008;AF=0.0005;AFR_AF=0.0020;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55326\trs3107975\tT\tC\t100.0\tPASS\tAA=C;ERATE=0.0074;AN=2184;THETA=0.0085;VT=SNP;SNPSOURCE=LOWCOV;AVGPOST=0.9622;AC=90;RSQ=0.6901;LDAF=0.0562;AF=0.04;ASN_AF=0.07;AMR_AF=0.02;AFR_AF=0.07;EUR_AF=0.01;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55330\trs185215913\tG\tA\t100.0\tPASS\tERATE=0.0005;AA=G;AN=2184;VT=SNP;THETA=0.0086;AVGPOST=0.9988;LDAF=0.0011;SNPSOURCE=LOWCOV;AC=1;RSQ=0.4701;AF=0.0005;AFR_AF=0.0020;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55367\trs190850374\tG\tA\t100.0\tPASS\tERATE=0.0004;THETA=0.0044;AA=G;AN=2184;VT=SNP;LDAF=0.0029;RSQ=0.3860;SNPSOURCE=LOWCOV;AVGPOST=0.9961;AC=2;AF=0.0009;AMR_AF=0.01;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55388\trs182711216\tC\tT\t100.0\tPASS\tTHETA=0.0102;ERATE=0.0005;AA=C;AVGPOST=0.9983;AN=2184;LDAF=0.0010;VT=SNP;RSQ=0.2348;SNPSOURCE=LOWCOV;AC=1;AF=0.0005;ASN_AF=0.0017;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55394\trs2949420\tT\tA\t100.0\tPASS\tAC=18;AN=2184;VT=SNP;AA=A;RSQ=0.4995;AVGPOST=0.9784;LDAF=0.0171;SNPSOURCE=LOWCOV;ERATE=0.0012;THETA=0.0063;AF=0.01;AMR_AF=0.01;AFR_AF=0.0041;EUR_AF=0.02;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55416\trs193242050\tG\tA\t100.0\tPASS\tAA=G;AN=2184;AVGPOST=0.9944;VT=SNP;LDAF=0.0064;AC=9;THETA=0.0019;RSQ=0.6553;SNPSOURCE=LOWCOV;ERATE=0.0006;AF=0.0041;AFR_AF=0.02;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55427\trs183189405\tT\tC\t100.0\tPASS\tTHETA=0.0054;AA=T;AN=2184;VT=SNP;AVGPOST=0.9969;LDAF=0.0020;SNPSOURCE=LOWCOV;AC=1;RSQ=0.2759;ERATE=0.0007;AF=0.0005;AFR_AF=0.0020;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55816\trs187434873\tG\tA\t100.0\tPASS\tAN=2184;THETA=0.0119;VT=SNP;AC=10;RSQ=0.4578;AA=A;SNPSOURCE=LOWCOV;AVGPOST=0.9844;LDAF=0.0108;ERATE=0.0007;AF=0.0046;AMR_AF=0.01;EUR_AF=0.01;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55850\trs191890754\tC\tG\t100.0\tPASS\tAVGPOST=0.9921;AA=G;AN=2184;VT=SNP;RSQ=0.4083;THETA=0.0045;LDAF=0.0056;AC=5;SNPSOURCE=LOWCOV;ERATE=0.0006;AF=0.0023;EUR_AF=0.01;EFF=INTERGENIC(MODIFIER|||||||||)\n+1\t55852\trs184233019\tG\tC\t100.0\tPASS\tTHETA=0.0137;AA=G;AN=2184;RSQ=0.5433;ERATE=0.0009;LDAF=0.0046;VT=SNP;AVGPOST=0.9953;AC=5;SNPSOURCE=LOWCOV;AF=0.0023;AMR_AF=0.01;EUR_AF=0.0013;EFF=INTERGENIC(MODIFIER|||||||||)\n'
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.auto_dom.ped
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.auto_dom.ped Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,9 @@
+1 1_dad 0 0 -1 1
+1 1_mom 0 0 -1 1
+1 1_kid 1_dad 1_mom -1 2
+2 2_dad 0 0 -1 1
+2 2_mom 0 0 -1 2
+2 2_kid 2_dad 2_mom -1 2
+3 3_dad 0 0 -1 2
+3 3_mom 0 0 -1 -9
+3 3_kid 3_dad 3_mom -1 2
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.auto_dom.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.auto_dom.vcf Fri Dec 14 12:49:22 2018 -0500
[
b'@@ -0,0 +1,127 @@\n+##fileformat=VCFv4.1\n+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">\n+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">\n+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">\n+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">\n+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher\'s exact test to detect strand bias">\n+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">\n+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">\n+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">\n+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">\n+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">\n+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">\n+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">\n+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">\n+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[bam/M10478.conc.on.pos.realigned.bam, bam/M10475.conc.on.pos.realigned.bam, bam/M10500.conc.on.pos.realigned.bam, bam/M128215.conc.on.pos.realigned.bam] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null interval_set_rule=UNION interval_merging=ALL reference_sequence=/m/cphg-quinlan/cphg-quinlan/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa rodBind=[] nonDeterministicRandomSeed=false downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=10 num_cpu_threads=null num_io_threads=null num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_VARIANTS_ONLY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 computeSLOD=false alleles=(RodBinding name= source=UNBOUND) min_base_quality_score=17 max_deletion_fraction=0.05 multiallelic=false max_alternate_alleles=5 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 indelHaplotypeSize=80 bandedIndel=false indelDebug=false ignoreSNPAlleles=false dbsnp=(RodBinding name='..b'IGH|MISSENSE|Tga/Cga|*250R|249|WDR37|protein_coding|CODING|ENST00000381329|exon_10_1142110_1142566)\tGT:AD:DP:GQ:PL\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t1/1:0,24:24:66.14:729,66,0\t0/1:1,37:59:87.16:940,87,0\t0/1:0,29:49:78.20:899,78,0\t1/1:0,24:64:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n+chr10\t48003992\t.\tC\tT\t1047.87\t.\tAC=4;AF=0.50;AN=8;BaseQRankSum=-0.053;DP=165;Dels=0.00;FS=6.377;HRun=0;HaplotypeScore=4.3830;MQ=20.94;MQ0=0;MQRankSum=-0.368;QD=9.53;ReadPosRankSum=1.346;CSQ=missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000420079|16/17|benign(0)|tolerated(1),missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000426610|17/18|benign(0)|tolerated(1);EFF=NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C540Y|610|ASAH2C|protein_coding|CODING|ENST00000420079|exon_10_48003968_48004056),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C552Y|622|ASAH2C|protein_coding|CODING|ENST00000426610|exon_10_48003968_48004056)\tGT:AD:DP:GQ:PL\t0/0:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/0:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:97.16:940,87,0\t0/0:0,29:29:98.20:899,78,0\t0/1:0,24:24:96.14:729,66,0\n+chr10\t48004992\t.\tC\tT\t1047.87\t.\tAC=4;AF=0.50;AN=8;BaseQRankSum=-0.053;DP=165;Dels=0.00;FS=6.377;HRun=0;HaplotypeScore=4.3830;MQ=20.94;MQ0=0;MQRankSum=-0.368;QD=9.53;ReadPosRankSum=1.346;CSQ=missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000420079|16/17|benign(0)|tolerated(1),missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000426610|17/18|benign(0)|tolerated(1);EFF=NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C540Y|610|ASAH2C|protein_coding|CODING|ENST00000420079|exon_10_48003968_48004056),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C552Y|622|ASAH2C|protein_coding|CODING|ENST00000426610|exon_10_48003968_48004056)\tGT:AD:DP:GQ:PL\t0/0:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/0:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n+chr10\t135336656\t.\tG\tA\t38.34\t.\tAC=4;AF=1.00;AN=4;DP=2;Dels=0.00;FS=0.000;HRun=4;HaplotypeScore=0.0000;MQ=37.00;MQ0=0;QD=19.17;CSQ=upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000418356|||,intron_variant&nc_transcript_variant|||ENSG00000214279||ENST00000488261|||,intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541261|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000421586|||,intron_variant|||ENSG00000130649|CYP2E1|ENST00000463117|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000252945|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541080|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000477500|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000480558|||,intron_variant|||ENSG00000214279||ENST00000356567|||;EFF=INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),INTRON(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000463117|),INTRON(MODIFIER||||693|RP11-108K14.4.1|protein_coding|CODING|ENST00000356567|),INTRON(MODIFIER|||||RP11-108K14.4.1|retained_intron|CODING|ENST00000488261|),UPSTREAM(MODIFIER||||305|CYP2E1|protein_coding|CODING|ENST00000418356|),UPSTREAM(MODIFIER||||355|CYP2E1|protein_coding|CODING|ENST00000421586|),UPSTREAM(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000252945|),UPSTREAM(MODIFIER||||85|CYP2E1|protein_coding|CODING|ENST00000541261|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000477500|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000480558|)\tGT:AD:DP:GQ:PL\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n'
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.auto_rec.ped
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.auto_rec.ped Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,10 @@
+#family_id sample_id paternal_id maternal_id sex phenotype
+1 1_dad 0 0 -1 1
+1 1_mom 0 0 -1 1
+1 1_kid 1_dad 1_mom -1 2
+2 2_dad 0 0 -1 1
+2 2_mom 0 0 -1 1
+2 2_kid 2_dad 2_mom -1 2
+3 3_dad 0 0 -1 1
+3 3_mom 0 0 -1 1
+3 3_kid 3_dad 3_mom -1 2
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.auto_rec.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.auto_rec.vcf Fri Dec 14 12:49:22 2018 -0500
[
b'@@ -0,0 +1,127 @@\n+##fileformat=VCFv4.1\n+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">\n+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">\n+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">\n+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">\n+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher\'s exact test to detect strand bias">\n+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">\n+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">\n+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">\n+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">\n+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">\n+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">\n+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">\n+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">\n+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[bam/M10478.conc.on.pos.realigned.bam, bam/M10475.conc.on.pos.realigned.bam, bam/M10500.conc.on.pos.realigned.bam, bam/M128215.conc.on.pos.realigned.bam] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null interval_set_rule=UNION interval_merging=ALL reference_sequence=/m/cphg-quinlan/cphg-quinlan/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa rodBind=[] nonDeterministicRandomSeed=false downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=10 num_cpu_threads=null num_io_threads=null num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_VARIANTS_ONLY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 computeSLOD=false alleles=(RodBinding name= source=UNBOUND) min_base_quality_score=17 max_deletion_fraction=0.05 multiallelic=false max_alternate_alleles=5 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 indelHaplotypeSize=80 bandedIndel=false indelDebug=false ignoreSNPAlleles=false dbsnp=(RodBinding name='..b'29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n+chr10\t135336656\t.\tG\tA\t38.34\t.\tAC=4;AF=1.00;AN=4;DP=2;Dels=0.00;FS=0.000;HRun=4;HaplotypeScore=0.0000;MQ=37.00;MQ0=0;QD=19.17;CSQ=upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000418356|||,intron_variant&nc_transcript_variant|||ENSG00000214279||ENST00000488261|||,intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541261|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000421586|||,intron_variant|||ENSG00000130649|CYP2E1|ENST00000463117|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000252945|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541080|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000477500|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000480558|||,intron_variant|||ENSG00000214279||ENST00000356567|||;EFF=INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),INTRON(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000463117|),INTRON(MODIFIER||||693|RP11-108K14.4.1|protein_coding|CODING|ENST00000356567|),INTRON(MODIFIER|||||RP11-108K14.4.1|retained_intron|CODING|ENST00000488261|),UPSTREAM(MODIFIER||||305|CYP2E1|protein_coding|CODING|ENST00000418356|),UPSTREAM(MODIFIER||||355|CYP2E1|protein_coding|CODING|ENST00000421586|),UPSTREAM(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000252945|),UPSTREAM(MODIFIER||||85|CYP2E1|protein_coding|CODING|ENST00000541261|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000477500|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000480558|)\tGT:AD:DP:GQ:PL\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n+chr10\t135369532\t.\tT\tC\t122.62\t.\tAC=2;AF=0.25;AN=8;BaseQRankSum=2.118;DP=239;Dels=0.00;FS=5.194;HRun=2;HaplotypeScore=5.7141;MQ=36.02;MQ0=0;MQRankSum=0.082;QD=2.31;ReadPosRankSum=-0.695;CSQ=missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000303903|9/13|benign(0.001)|tolerated(1),missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000432597|10/14|benign(0)|tolerated(1),downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000460441|||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000343131|9/13|benign(0.001)|tolerated(1),intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000171772|SYCE1|ENST00000479535|6/10||,downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000482127|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000130649|CYP2E1|ENST00000368520|6/6||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000368517|9/13|benign(0)|tolerated(1);EFF=DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000460441|),DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000482127|),EXON(MODIFIER|||||CYP2E1|retained_intron|CODING|ENST00000368520|),EXON(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000479535|),INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000368517|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000432597|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|318|SYCE1|protein_coding|CODING|ENST00000303903|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|351|SYCE1|protein_coding|CODING|ENST00000343131|exon_10_135369485_135369551)\tGT:AD:DP:GQ:PL\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t1/1:0,24:24:66.14:729,66,0\n\\ No newline at end of file\n'
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.comp_het.ped
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.comp_het.ped Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,13 @@
+#Family_ID Individual_ID Paternal_ID Maternal_ID Sex Phenotype ethnicity
+1 child_1 dad_1 mom_1 1 2 caucasian
+2 child_2 dad_2 mom_2 1 2 caucasian
+2 dad_2 -9 -9 1 1 caucasian
+2 mom_2 -9 -9 2 1 caucasian
+1 dad_1 -9 -9 1 1 caucasian
+1 mom_1 -9 -9 2 1 caucasian
+3 child_3 dad_3 mom_3 1 2 caucasian
+3 dad_3 -9 -9 1 1 caucasian
+3 mom_3 -9 -9 2 1 caucasian
+4 child_4 dad_4 mom_4 1 2 caucasianNEuropean
+4 dad_4 -9 -9 1 1 caucasianNEuropean
+4 mom_4 -9 -9 2 1 caucasianNEuropean
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.comp_het.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.comp_het.vcf Fri Dec 14 12:49:22 2018 -0500
[
b'@@ -0,0 +1,120 @@\n+##fileformat=VCFv4.1\n+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">\n+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">\n+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">\n+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">\n+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher\'s exact test to detect strand bias">\n+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">\n+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">\n+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">\n+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">\n+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">\n+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">\n+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">\n+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">\n+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[bam/all.bam] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null interval_set_rule=UNION interval_merging=ALL reference_sequence=/home/arq5x/cphg-home/shared/genomes/hg19/bwa/gatk/human_g1k_v37.fasta rodBind=[] nonDeterministicRandomSeed=false downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=20 num_cpu_threads=null num_io_threads=null num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_VARIANTS_ONLY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 computeSLOD=false alleles=(RodBinding name= source=UNBOUND) min_base_quality_score=17 max_deletion_fraction=0.05 multiallelic=false max_alternate_alleles=5 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 indelHaplotypeSize=80 bandedIndel=false indelDebug=false ignoreSNPAlleles=false dbsnp=(RodBinding name= source=UNBOUND) out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sit'..b'e|NON_CODING|ENST00000423562|4|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|7|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|5|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|5|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|4|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|5|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|4|1)\tGT:AD:DP:GQ:PL\t0/0:247,3:250:51.15:0,51,628\t0/0:250,0:250:60.18:0,60,746\t0/0:250,0:250:54.17:0,54,685\t0/0:249,1:250:54.15:0,54,644\t0/0:233,0:233:81.25:0,81,1014\t0/0:235,4:239:45.13:0,45,549\t0/0:249,0:250:45.13:0,45,514\t0/0:249,1:250:78.20:0,78,853\t0/0:247,0:247:90.24:0,90,1012\t0/1:227,17:244:0.06:0,0,670\t0/1:214,11:225:4.62:5,0,542\t0/1:236,13:249:71.41:71,0,448\n+1\t17730\t.\tC\tA\t102.87\t.\tAC=5;AF=0.208;AN=24;BaseQRankSum=-11.508;DP=2968;DS;Dels=0.00;FS=0.000;HRun=0;HaplotypeScore=1.0610;InbreedingCoeff=-0.2498;MQ=13.12;MQ0=24;MQRankSum=-4.433;QD=0.08;ReadPosRankSum=1.952;EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328||1),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305||1),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242||1),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655||1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|4|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|5|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|5|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|4|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|5|1),EXON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|4|1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|6|1),SPLICE_SITE_ACCEPTOR(HIGH|||||WASH7P|protein_coding|NON_CODING|ENST00000430492|7|1)\tGT:AD:DP:GQ:PL\t0/0:246,4:250:36.11:0,36,464\t0/0:244,5:249:57.17:0,57,727\t0/0:244,6:250:48.15:0,48,628\t0/0:247,3:250:51.13:0,51,621\t0/1:242,8:250:26.26:26,0,830\t0/0:246,4:250:48.14:0,48,601\t0/1:238,11:250:48.54:49,0,386\t0/0:244,5:249:42.12:0,42,491\t0/0:239,3:243:23.74:0,24,609\t0/1:221,13:234:13.85:14,0,482\t0/1:232,11:243:7:7,0,501\t0/1:238,12:250:73.18:73,0,368\n+1\t17746\t.\tA\tG\t607.7\t.\tAC=8;AF=0.333;AN=24;BaseQRankSum=13.191;DP=2993;DS;Dels=0.00;FS=0.000;HRun=1;HaplotypeScore=0.4155;InbreedingCoeff=-0.5280;MQ=11.87;MQ0=5;MQRankSum=-4.672;QD=0.30;ReadPosRankSum=3.574;EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328||1),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305||1),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242||1),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655||1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|3|1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|5|1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|4|1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|4|1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|3|1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|4|1),INTRON(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|3|1)\tGT:AD:DP:GQ:PL\t0/0:206,44:250:7.45:0,7,373\t0/0:221,29:250:5.12:0,5,468\t0/0:224,26:250:3.61:0,4,382\t0/0:216,34:250:9.49:0,9,405\t0/1:243,7:250:43.06:43,0,781\t0/1:195,55:250:99:113,0,232\t0/1:218,32:250:44.30:44,0,212\t0/1:219,31:250:0.03:0,0,330\t0/1:211,39:250:74.42:74,0,236\t0/1:209,34:243:68.40:68,0,298\t0/1:172,77:249:99:193,0,137\t0/1:219,30:250:99:137,0,197\n'
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.de_novo.ped
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.de_novo.ped Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,9 @@
+1 1_dad 0 0 -1 1
+1 1_mom 0 0 -1 1
+1 1_kid 1_dad 1_mom -1 2
+2 2_dad 0 0 -1 1
+2 2_mom 0 0 -1 1
+2 2_kid 2_dad 2_mom -1 2
+3 3_dad 0 0 -1 1
+3 3_mom 0 0 -1 1
+3 3_kid 3_dad 3_mom -1 2
\ No newline at end of file
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-data/test.de_novo.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-data/test.de_novo.vcf Fri Dec 14 12:49:22 2018 -0500
[
b'@@ -0,0 +1,127 @@\n+##fileformat=VCFv4.1\n+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">\n+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">\n+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">\n+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">\n+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher\'s exact test to detect strand bias">\n+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">\n+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">\n+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">\n+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">\n+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">\n+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">\n+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">\n+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">\n+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[bam/M10478.conc.on.pos.realigned.bam, bam/M10475.conc.on.pos.realigned.bam, bam/M10500.conc.on.pos.realigned.bam, bam/M128215.conc.on.pos.realigned.bam] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null interval_set_rule=UNION interval_merging=ALL reference_sequence=/m/cphg-quinlan/cphg-quinlan/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa rodBind=[] nonDeterministicRandomSeed=false downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=10 num_cpu_threads=null num_io_threads=null num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_VARIANTS_ONLY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 computeSLOD=false alleles=(RodBinding name= source=UNBOUND) min_base_quality_score=17 max_deletion_fraction=0.05 multiallelic=false max_alternate_alleles=5 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 indelHaplotypeSize=80 bandedIndel=false indelDebug=false ignoreSNPAlleles=false dbsnp=(RodBinding name='..b':39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,23:24:66.14:729,66,0\n+chr10\t135336656\t.\tG\tA\t38.34\t.\tAC=4;AF=1.00;AN=4;DP=2;Dels=0.00;FS=0.000;HRun=4;HaplotypeScore=0.0000;MQ=37.00;MQ0=0;QD=19.17;CSQ=upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000418356|||,intron_variant&nc_transcript_variant|||ENSG00000214279||ENST00000488261|||,intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541261|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000421586|||,intron_variant|||ENSG00000130649|CYP2E1|ENST00000463117|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000252945|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541080|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000477500|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000480558|||,intron_variant|||ENSG00000214279||ENST00000356567|||;EFF=INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),INTRON(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000463117|),INTRON(MODIFIER||||693|RP11-108K14.4.1|protein_coding|CODING|ENST00000356567|),INTRON(MODIFIER|||||RP11-108K14.4.1|retained_intron|CODING|ENST00000488261|),UPSTREAM(MODIFIER||||305|CYP2E1|protein_coding|CODING|ENST00000418356|),UPSTREAM(MODIFIER||||355|CYP2E1|protein_coding|CODING|ENST00000421586|),UPSTREAM(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000252945|),UPSTREAM(MODIFIER||||85|CYP2E1|protein_coding|CODING|ENST00000541261|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000477500|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000480558|)\tGT:AD:DP:GQ:PL\t0/0:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/0:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\t0/1:1,37:39:87.16:940,87,0\t0/1:0,29:29:78.20:899,78,0\t0/1:0,24:24:66.14:729,66,0\n+chr10\t135369532\t.\tT\tC\t122.62\t.\tAC=2;AF=0.25;AN=8;BaseQRankSum=2.118;DP=239;Dels=0.00;FS=5.194;HRun=2;HaplotypeScore=5.7141;MQ=36.02;MQ0=0;MQRankSum=0.082;QD=2.31;ReadPosRankSum=-0.695;CSQ=missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000303903|9/13|benign(0.001)|tolerated(1),missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000432597|10/14|benign(0)|tolerated(1),downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000460441|||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000343131|9/13|benign(0.001)|tolerated(1),intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000171772|SYCE1|ENST00000479535|6/10||,downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000482127|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000130649|CYP2E1|ENST00000368520|6/6||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000368517|9/13|benign(0)|tolerated(1);EFF=DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000460441|),DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000482127|),EXON(MODIFIER|||||CYP2E1|retained_intron|CODING|ENST00000368520|),EXON(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000479535|),INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000368517|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000432597|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|318|SYCE1|protein_coding|CODING|ENST00000303903|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|351|SYCE1|protein_coding|CODING|ENST00000343131|exon_10_135369485_135369551)\tGT:AD:DP:GQ:PL\t0/0:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,22:24:66.14:729,66,0\t0/0:1,37:39:87.16:940,87,0\t0/0:0,29:29:78.20:899,78,0\t0/1:0,21:24:66.14:729,66,0\t0/0:1,37:50:87.16:940,87,0\t0/0:0,29:50:78.20:899,78,0\t0/1:0,24:50:66.14:729,66,0\n'
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/build-gemini-testdata.sh
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/build-gemini-testdata.sh Fri Dec 14 12:49:22 2018 -0500
[
@@ -0,0 +1,72 @@
+cd "$(dirname "$0")"
+
+export GEMINI_CONFIG=../test-cache
+OUT_PTH=$GEMINI_CONFIG/gemini/data
+GENOMIC_REGION=3:187000000-187500000
+
+
+if [ -n "$1" ]; then
+
+IN_PTH="$1"
+# downsample all vcf and bed annotation files to the region of interest and reindex
+for vcf in `ls $IN_PTH/*.gz | grep -v hprd_interaction_edges.gz -`
+do
+    python ./shrink_tabix.py $vcf -r $GENOMIC_REGION -o $OUT_PTH/`basename $vcf`
+done
+
+# downsample gene_table files to the region of interest
+echo "$IN_PTH/summary_gene_table_v75 -> $OUT_PTH/summary_gene_table_v75"
+python ./shrink_simple_tab.py $IN_PTH/summary_gene_table_v75 -r chr$GENOMIC_REGION -c 0 8 9 -n 1 -o $OUT_PTH/summary_gene_table_v75
+
+echo "$IN_PTH/detailed_gene_table_v75 -> $OUT_PTH/detailed_gene_table_v75"
+python ./shrink_simple_tab.py $IN_PTH/detailed_gene_table_v75 -r chr$GENOMIC_REGION -c 0 11 12 -n 1 -o $OUT_PTH/detailed_gene_table_v75
+
+# filter kegg_pathway files to retain only records of the genes listed
+# in the downsampled summary_gene_table
+for kegg in `ls $IN_PTH/kegg_pathways_*`
+do
+    echo "$kegg -> $OUT_PTH/`basename $kegg`"
+    cut -f2 $OUT_PTH/summary_gene_table_v75 | grep -Fv None | grep -Fwf - $kegg > $OUT_PTH/`basename $kegg`
+done
+
+# filter hprd_interaction file to retain only records of the genes listed
+# in the downsampled summary_gene_table
+echo "$IN_PTH/hprd_interaction_edges.gz -> $OUT_PTH/hprd_interaction_edges.gz"
+bgzip -dc $IN_PTH/hprd_interaction_edges.gz > $OUT_PTH/hprd_interaction_edges
+cut -f2 $OUT_PTH/summary_gene_table_v75 | grep -Fv None | grep -Ff - $OUT_PTH/hprd_interaction_edges | bgzip > $OUT_PTH/hprd_interaction_edges.gz
+rm $OUT_PTH/hprd_interaction_edges
+
+# filter cancer_gene_census file to retain only records of the genes listed
+# in the downsampled summary_gene_table;
+# TO DO: make the filter stricter by looking for matches only in the first
+# column of the cancer_gene_census file (but the file is relatively small anyway)
+echo "$IN_PTH/cancer_gene_census.20140120.tsv -> $OUT_PTH/cancer_gene_census.20140120.tsv"
+cut -f2 $OUT_PTH/summary_gene_table_v75 | grep -Fv None | grep -Fwf - $IN_PTH/cancer_gene_census.20140120.tsv > $OUT_PTH/cancer_gene_census.20140120.tsv
+
+else
+    echo "no path to gemini annotation files provided - only building test databases"
+fi
+
+
+# now use gemini load to build the test databases
+echo "Building gemini test databases"
+echo "Test databases for gemini_load"
+gemini --annotation-dir $OUT_PTH load --skip-cadd --skip-gerp-bp -v build-data/gemini_load_input.vcf -t snpEff ../gemini_load_result1.db
+gemini --annotation-dir $OUT_PTH load --skip-cadd --skip-gerp-bp -v build-data/gemini_load_input.vcf -t snpEff --skip-gene-tables --no-load-genotypes ../gemini_load_result2.db
+echo "Test database for gemini_amend"
+gemini --annotation-dir $OUT_PTH load --skip-cadd --skip-gerp-bp -v build-data/test.auto_rec.vcf -t snpEff ../gemini_amend_input.db
+echo "Test database for gemini_annotate"
+bgzip -c build-data anno.bed > build-data/anno.bed.gz
+tabix --force -p bed build-data/anno.bed.gz
+cp ../gemini_load_result1.db ../gemini_annotate_result.db
+gemini --annotation-dir $OUT_PTH annotate -f build-data/anno.bed.gz -c anno5 -a count ../gemini_annotate_result.db
+echo "Test database for gemini_set_somatic"
+cp ../gemini_load_result1.db ../gemini_is_somatic_result.db
+gemini set_somatic --min-somatic-score 5.65 ../gemini_is_somatic_result.db
+echo "Test database for gemini_de_novo and gemini_mendel_errors"
+gemini --annotation-dir $OUT_PTH load --skip-cadd --skip-gerp-bp -v build-data/test.de_novo.vcf -p build-data/test.de_novo.ped -t snpEff ../gemini_de_novo_input.db
+echo "Test database for gemini_comp_hets"
+gemini --annotation-dir $OUT_PTH load --skip-cadd --skip-gerp-bp -v build-data/test.comp_het.vcf -p build-data/test.comp_het.ped -t snpEff ../gemini_comphets_input.db
+echo "Test databases for gemini_autosomal"
+gemini --annotation-dir $OUT_PTH load --skip-cadd --skip-gerp-bp -v build-data/test.auto_rec.vcf -p build-data/test.auto_rec.ped -t snpEff ../gemini_auto_rec_input.db
+gemini --annotation-dir $OUT_PTH load --skip-cadd --skip-gerp-bp -v build-data/test.auto_dom.vcf -p build-data/test.auto_dom.ped -t snpEff ../gemini_auto_dom_input.db
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/shrink_simple_tab.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/shrink_simple_tab.py Fri Dec 14 12:49:22 2018 -0500
[
@@ -0,0 +1,61 @@
+from __future__ import print_function
+
+import argparse
+from functools import partial
+
+
+def keep_line(line, pos_cols, region):
+    fields = line.rstrip().split(b'\t')
+    if fields[pos_cols[0]] == region[0]:  # same chromosome
+        if (
+            region[1] < int(fields[pos_cols[1]]) < region[2]
+        ) or (
+            region[1] < int(fields[pos_cols[2]]) < region[2]
+        ):
+            return True
+
+
+def main(infile, ofile, num_header_lines):
+    print(infile, '->', ofile)
+    with open(infile, 'rb') as i:
+        with open(ofile, 'wb') as o:
+            # copy header lines
+            for c in range(num_header_lines):
+                o.write(next(i))
+            for line in i:
+                if keep_line(line):
+                    o.write(line)
+
+
+if __name__ == '__main__':
+    p = argparse.ArgumentParser()
+    p.add_argument('infile')
+    p.add_argument(
+        '-r', '--region',
+        required=True,
+        help='the region of the input file to rewrite'
+    )
+    p.add_argument(
+        '-o', '--ofile',
+        required=True,
+        help="the name of the output file"
+    )
+    p.add_argument(
+        '-c', '--cols',
+        nargs=3, type=int, required=True,
+        help="the columns of the input file specifying chrom, start and stop, "
+             "respectively"
+    )
+    p.add_argument(
+        '-n', '--num-header-lines',
+        type=int, default=0,
+        help='the number of header lines present in the input; These will '
+             'always be copied over to the new file.'
+    )
+    args = vars(p.parse_args())
+
+    chrom, reg = args['region'].split(':')
+    region = [chrom.encode()] + [int(x) for x in reg.split('-')]
+    keep_line = partial(keep_line, pos_cols=args['cols'], region=region)
+
+    main(args['infile'], args['ofile'], args['num_header_lines'])
b
diff -r 7cf9bc210044 -r 62647e2637f6 test-data/util/shrink_tabix.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/util/shrink_tabix.py Fri Dec 14 12:49:22 2018 -0500
[
@@ -0,0 +1,42 @@
+from __future__ import print_function
+
+import argparse
+
+import pysam
+
+
+def main(infile, ofile, region):
+    print(infile, '->', ofile)
+    with pysam.Tabixfile(infile) as i:
+        fformat = i.format.lower()
+        if fformat == 'sam':
+            fformat = 'bed'
+        if ofile[-3:] == '.gz':
+            ofile = ofile[:-3]
+        with open(ofile, 'w') as o:
+            try:
+                region_it = i.fetch(region=region)
+            except ValueError:
+                region_it = i.fetch(region='chr' + region)
+            for line in i.header:
+                o.write(line + '\n')
+            for line in region_it:
+                o.write(str(line) + '\n')
+    pysam.tabix_index(ofile, preset=fformat, force=True)
+
+
+if __name__ == '__main__':
+    p = argparse.ArgumentParser()
+    p.add_argument('infile')
+    p.add_argument(
+        '-r', '--region',
+        required=True,
+        help='the region of the input file to rewrite'
+    )
+    p.add_argument(
+        '-o', '--ofile',
+        required=True,
+        help="the name of the output file"
+    )
+    args = vars(p.parse_args())
+    main(**args)
b
diff -r 7cf9bc210044 -r 62647e2637f6 tool-data/gemini_databases.loc.sample
--- a/tool-data/gemini_databases.loc.sample Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,3 +0,0 @@
-## GEMINI databases
-#Version dbkey Description Path
-#08_08_2014 hg19 Database (08-08-2014) /path/to/data
b
diff -r 7cf9bc210044 -r 62647e2637f6 tool-data/gemini_versioned_databases.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/gemini_versioned_databases.loc.sample Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,3 @@
+## GEMINI versioned databases
+#DownloadDate dbkey DBversion Description Path
+#2018-07-08 hg19 181 GEMINI annotations (2018-07-08 snapshot) /path/to/data
b
diff -r 7cf9bc210044 -r 62647e2637f6 tool_data_table_conf.xml.sample
--- a/tool_data_table_conf.xml.sample Wed Oct 17 13:30:12 2018 -0400
+++ b/tool_data_table_conf.xml.sample Fri Dec 14 12:49:22 2018 -0500
b
@@ -1,7 +1,7 @@
 <tables>
-    <table name="gemini_databases" comment_char="#" allow_duplicate_entries="False">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/gemini_databases.loc" />
+    <table name="gemini_versioned_databases" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, version, name, path</columns>
+        <file path="tool-data/gemini_versioned_databases.loc" />
     </table>
 </tables>
 
b
diff -r 7cf9bc210044 -r 62647e2637f6 tool_data_table_conf.xml.test
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.test Fri Dec 14 12:49:22 2018 -0500
b
@@ -0,0 +1,8 @@
+<tables>
+    <!-- Location of gemini annotation files for testing -->
+    <table name="gemini_versioned_databases" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, version, name, path</columns>
+        <file path="${__HERE__}/test-data/gemini_versioned_databases.loc" />
+    </table>
+</tables>
+
b
diff -r 7cf9bc210044 -r 62647e2637f6 tool_dependencies.xml
--- a/tool_dependencies.xml Wed Oct 17 13:30:12 2018 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,9 +0,0 @@
-<?xml version="1.0"?>
-<tool_dependency>
-    <package name="gemini" version="0.18.1">
-        <repository changeset_revision="49de32b47548" name="package_gemini_0_18_1" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-    <package name="tabix" version="0.2.6">
-        <repository changeset_revision="389d2376b60b" name="package_tabix_0_2_6" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-</tool_dependency>