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

Changeset 0:3b1e7c170b10 (2019-10-10)
Next changeset 1:eee2da03d1f5 (2021-05-22)
Commit message:
"planemo upload for repository https://github.com/COMBAT-TB/tb_variant_filter commit 36771827ae3d5dc06df488b3faffb392f77e672e"
added:
tb_variant_filter.xml
test-data/test_input1.vcf
test-data/test_input2.vcf
test-data/test_output1.vcf
test-data/test_output2.vcf
test-data/test_output3.vcf
test-data/test_output4.vcf
test-data/test_output5.vcf
test-data/test_output6.vcf
b
diff -r 000000000000 -r 3b1e7c170b10 tb_variant_filter.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tb_variant_filter.xml Thu Oct 10 17:59:02 2019 -0400
[
b'@@ -0,0 +1,160 @@\n+<tool id="tb_variant_filter" name="TB Variant Filter" version="@TOOL_VERSION@+galaxy0" profile="16.04">\n+    <description>M. tuberculosis H37Rv VCF filter</description>\n+    <macros>\n+        <token name="@TOOL_VERSION@">0.1.3</token>\n+    </macros>\n+    <requirements>\n+        <requirement type="package" version="@TOOL_VERSION@">tb_variant_filter</requirement>\n+    </requirements>\n+    <command detect_errors="exit_code"><![CDATA[\n+        tb_variant_filter\n+        #if "region_filter" in str($filters).split(\',\')\n+            #if str($filter_options.show_filter_options) == "yes":\n+                --region_filter $filter_options.region_filter\n+            #else\n+                --region_filter pe_ppe,uvp\n+            #end if\n+        #end if\n+        #if "close_to_indel_filter" in str($filters).split(\',\')\n+            --close_to_indel_filter\n+            #if str($filter_options.show_filter_options) == "yes":\n+                --indel_window_size $filter_options.indel_window_size\n+            #end if\n+        #end if\n+        #if "min_percentage_alt_filter" in str($filters).split(\',\') \n+            --min_percentage_alt_filter \n+            #if str($filter_options.show_filter_options) == "yes":\n+                --min_percentage_alt $filter_options.min_percentage_alt\n+            #end if\n+        #end if\n+        #if "min_depth_filter" in str($filters).split(\',\') \n+            --min_depth_filter \n+            #if str($filter_options.show_filter_options) == "yes":\n+                --min_depth $filter_options.min_depth\n+            #end if\n+        #end if\n+        #if "snv_only_filter" in str($filters).split(\',\'):\n+            --snv_only_filter\n+        #end if\n+        \'$input1\' \'$output1\'\n+    ]]></command>\n+    <inputs>\n+        <param type="data" name="input1" label="VCF file to be filter"  format="vcf"/>\n+\n+        <param type="select" name="filters" multiple="true" label="Filters to apply">\n+            <option value="region_filter" selected="true">Filter out variants by regions</option>\n+            <option value="close_to_indel_filter">Filter variants close to indels</option>\n+            <option value="min_percentage_alt_filter">Filter variants by percentage alt allele</option>\n+            <option value="min_depth_filter">Filter sites by read alignment depth</option>\n+            <option value="snv_only_filter">Only accept SNVs</option>\n+        </param>\n+\n+        <conditional name="filter_options">\n+            <param type="select" name="show_filter_options" label="Show options for the filters">\n+                <option value="yes">Yes</option>\n+                <option value="no" selected="true">No</option>\n+            </param>\n+            <when value="yes">\n+                <param argument="--region_filter" type="select" multiple="true" label="Region filters to enable">\n+                    <!-- if these are changed the code above needs to change to keep the defaults in line with those that are default here -->\n+                    <option value="pe_ppe" selected="true">PE/PPE</option>\n+                    <option value="tbprofiler">TBProfiler antibiotic resistant genes</option>\n+                    <option value="mtbseq">MTBseq antibiotic resistant genes</option>\n+                    <option value="uvp" selected="true">UVP repeat / insertion sequence sites</option>\n+                </param>\n+                <param argument="--indel_window_size" type="integer" value="5" label="Window to mask around indels"/>\n+                <param argument="--min_percentage_alt" type="float" value="90"\n+                    label="Minimum alternate allele percentage to accept"/>\n+                <param argument="--min_depth" type="integer" value="30" label="Minimum read depth (coverage)"/>\n+            </when>\n+            <when value="no"></when>\n+\n+        </conditional>\n+    </inputs>\n+    <outputs>\n+        <data name="output1" format="vcf"/>\n+    </outputs>\n+    <tests>\n+        <test>\n+            <param name'..b'region_filter" />\n+            <conditional name="filter_options">\n+                <param name="show_filter_options" value="yes" />\n+                <param name="region_filter" value="pe_ppe,tbprofiler,uvp" />\n+            </conditional>\n+            <output name="output1" file="test_output1.vcf" ftype="vcf" />\n+        </test>\n+        <test>\n+            <param name="input1" value="test_input1.vcf" ftype="vcf" />\n+            <param name="filters" value="close_to_indel_filter" />\n+            <conditional name="filter_options">\n+                <param name="show_filter_options" value="yes" />\n+                <param name="indel_window_size" value="5" />\n+            </conditional>\n+            <output name="output1" file="test_output2.vcf" ftype="vcf" />\n+        </test>\n+        <test>\n+            <param name="input1" value="test_input1.vcf" ftype="vcf" />\n+            <param name="filters" value="min_percentage_alt_filter" />\n+            <conditional name="filter_options">\n+                <param name="show_filter_options" value="yes" />\n+                <param name="min_percentage_alt" value="95.0" />\n+            </conditional>\n+            <output name="output1" file="test_output3.vcf" ftype="vcf" />\n+        </test>\n+        <test>\n+            <param name="input1" value="test_input2.vcf" ftype="vcf" />\n+            <param name="filters" value="min_percentage_alt_filter" />\n+            <conditional name="filter_options">\n+                <param name="show_filter_options" value="yes" />\n+                <param name="min_percentage_alt" value="30.0" />\n+            </conditional>\n+            <output name="output1" file="test_output4.vcf" ftype="vcf" />\n+        </test>\n+        <test>\n+            <param name="input1" value="test_input1.vcf" ftype="vcf" />\n+            <param name="filters" value="min_depth_filter" />\n+            <conditional name="filter_options">\n+                <param name="show_filter_options" value="yes" />\n+                <param name="min_depth" value="30" />\n+            </conditional>\n+            <output name="output1" file="test_output5.vcf" ftype="vcf" />\n+        </test>\n+        <test>\n+            <param name="input1" value="test_input1.vcf" ftype="vcf" />\n+            <param name="filters" value="snv_only_filter" />\n+            <output name="output1" file="test_output6.vcf" ftype="vcf" />\n+        </test>\n+    </tests>\n+    <help><![CDATA[\n+This tool offers multiple options for filtering variants (in\n+VCF files, relative to M. tuberculosis H37Rv).\n+\n+It currently has 5 main modes:\n+\n+1. Filter by region. Mask out variants in certain regions. Region lists available as:\n+    1.  PE/PPE genes from `Fishbein et al 2015 <https://onlinelibrary.wiley.com/doi/full/10.1111/mmi.12981>`_\n+    2. `TBProfiler <http://tbdr.lshtm.ac.uk/>`_ list of antibiotic resistant genes\n+    3. `MTBseq <https://github.com/ngs-fzb/MTBseq_source>`_ list of antibiotic resistant genes\n+    4. `UVP <https://github.com/CPTR-ReSeqTB/UVP>`_ list of repetitive loci in M. tuberculosis genome\n+2. Filter by window around indels. Masks out variants within a certain distance (by default 5 bases) of an insertion or deletion site.\n+3. Filter by percentage of alternate allele bases. Mask out variants with less than a minimum percentage (by default 90%) alternative alleles.\n+4. Filter by depth of aligned reads.\n+5. Filter out all variants that are not SNV (single nucleotide variants).\n+\n+When used together the effects of the filters are added (i.e. a variant is masked out if it is masked by any of the filters).\n+    ]]></help>\n+    <citations>\n+        <citation type="bibtex"><![CDATA[\n+@misc{vanHeusden2019,\n+  author = {van Heusden, P.},\n+  title = {tb_variant_filter},\n+  year = {2019},\n+  publisher = {GitHub},\n+  journal = {GitHub repository},\n+  howpublished = {\\url{https://github.com/pvanheus/tb_variant_filter}},\n+  commit = {4a9b2a4a85ddbfbb0d713a02373c8aa0aa159a6c}\n+}\n+        ]]></citation>\n+    </citations>\n+</tool>\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_input1.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_input1.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,102 @@\n+##fileformat=VCFv4.2\n+##FILTER=<ID=PASS,Description="All filters passed">\n+##fileDate=20190323\n+##source=freeBayes v1.2.0-dirty\n+##reference=reference/ref.fa\n+##contig=<ID=Chromosome,length=4411532>\n+##phasing=none\n+##commandline="freebayes -p 2 -P 0 -C 10 --min-repeat-entropy 1.5 --strict-vcf -q 13 -m 60 --min-coverage 10 -F 0.05 -f reference/ref.fa snps.bam --region Chromosome:0-1495044"\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Count of full observations of the reference haplotype.">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Count of full observations of this alternate haplotype.">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">\n+##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count">\n+##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations">\n+##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count">\n+##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations">\n+##bcftools_viewVersion=1.9+htslib-1.9\n+##bcftools_viewCommand=view --include \'FMT/GT="1/1" && QUAL>=100.0 && FMT/DP>=10 && (FMT/AO)/(FMT/DP)>=0.9\' snps.raw.vcf; Date=Sat Mar 23 06:45:26 2019\n+##bcftools_annotateVersion=1.9+htslib-1.9\n+##bcftools_annotateCommand=annotate --remove ^INFO/TYPE,^INFO/DP,^INFO/RO,^INFO/AO,^INFO/AB,^FORMAT/GT,^FORMAT/DP,^FORMAT/RO,^FORMAT/AO,^FORMAT/QR,^FORMAT/QA,^FORMAT/GL; Date=Sat Mar 23 06:45:26 2019\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tout\n+Chromosome\t1849\t.\tC\tA\t3412.24\t.\tAB=0;AO=110;DP=110;QA=3850;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:0:0:110:3850:-346.644,-33.1133,0\n+Chromosome\t1977\t.\tA\tG\t3234.43\t.\tAB=0;AO=106;DP=106;QA=3704;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3704:-333.508,-31.9092,0\n+Chromosome\t4013\t.\tT\tC\t3965.91\t.\tAB=0;AO=125;DP=125;QA=4448;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:125:0:0:125:4448:-400.411,-37.6288,0\n+Chromosome\t7362\t.\tG\tC\t4009.71\t.\tAB=0;AO=126;DP=126;QA=4518;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4518:-406.711,-37.9298,0\n+Chromosome\t9304\t.\tG\tA\t4222.23\t.\tAB=0;AO=136;DP=136;QA=4764;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:136:0:0:136:4764:-428.865,-40.9401,0\n+Chromosome\t11820\t.\tC\tG\t2252.54\t.\tAB=0;AO=74;DP=74;QA=2662;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:74:0:0:74:2662:-239.791,-22.2762,0\n+Chromosome\t11879\t.\tA\tG\t1815.99\t.\tAB=0;AO=63;DP=63;QA=2212;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:63:0:0:63:2212:-199.306,-18.9649,0\n+Chromosome\t14785\t.\tT\tC\t4342.4\t.\tAB=0;AO=139;DP=139;QA=4874;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:139:0:0:139:4874:-438.763,-41.8432,0\n+Chromosome\t14861\t.\tG\tT\t4237.79\t.\tAB=0;AO=133;DP=135;QA=4758;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:135:0:0:133:4758:-427.969,-40.037,0\n+Chromosome\t15117\t.\tC\tG\t3298.26\t.\tAB=0;AO=106;DP=106;QA=3708;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3708:-333.903,-31.9092,0\n+Chromosome\t15890\t.\tG\tA\t3349.13\t.\tAB=0;AO=116;DP=117;QA=3770;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:117:0:0:1'..b'GL\t1/1:78:0:0:78:2358:-212.453,-23.4803,0\n+Chromosome\t105139\t.\tC\tA\t3418.74\t.\tAB=0;AO=109;DP=110;QA=3888;QR=38;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:1:38:109:3888:-346.257,-29.316,0\n+Chromosome\t105736\t.\tT\tC\t1805.18\t.\tAB=0;AO=61;DP=61;QA=2101;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:61:0:0:61:2101:-189.335,-18.3628,0\n+Chromosome\t116000\t.\tT\tG\t3196.37\t.\tAB=0;AO=105;DP=105;QA=3605;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3605:-324.628,-31.6082,0\n+Chromosome\t122109\t.\tA\tG\t3324.29\t.\tAB=0;AO=111;DP=111;QA=3735;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:111:0:0:111:3735:-336.329,-33.4143,0\n+Chromosome\t123454\t.\tC\tT\t4362.28\t.\tAB=0;AO=136;DP=137;QA=4894;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:136:4894:-440.321,-40.9401,0\n+Chromosome\t123520\t.\tT\tC\t3793.13\t.\tAB=0;AO=121;DP=121;QA=4262;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:121:0:0:121:4262:-383.682,-36.4246,0\n+Chromosome\t125711\t.\tGGTT\tG\t3140.7\t.\tAB=0;AO=105;DP=105;QA=3531;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3531:-317.98,-31.6082,0\n+Chromosome\t125830\t.\tG\tGA\t2079.98\t.\tAB=0;AO=69;DP=72;QA=2347;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:69:2347:-211.164,-20.7711,0\n+Chromosome\t131174\t.\tT\tTG\t2854.04\t.\tAB=0;AO=97;DP=99;QA=3213;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:99:0:0:97:3213:-288.972,-29.1999,0\n+Chromosome\t133839\t.\tC\tT\t2457.55\t.\tAB=0;AO=78;DP=78;QA=2802;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2802:-252.374,-23.4803,0\n+Chromosome\t134024\t.\tT\tC\t2242.53\t.\tAB=0;AO=72;DP=72;QA=2543;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2543:-229.099,-21.6742,0\n+Chromosome\t138419\t.\tG\tA\t4166.36\t.\tAB=0;AO=132;DP=132;QA=4683;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:132:0:0:132:4683:-421.582,-39.736,0\n+Chromosome\t139297\t.\tG\tT\t3706.81\t.\tAB=0;AO=120;DP=120;QA=4165;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:120:0:0:120:4165:-374.978,-36.1236,0\n+Chromosome\t143207\t.\tT\tC\t2180.95\t.\tAB=0;AO=72;DP=72;QA=2523;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2523:-227.3,-21.6742,0\n+Chromosome\t146087\t.\tT\tC\t4315.28\t.\tAB=0;AO=137;DP=137;QA=4844;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:137:4844:-436.07,-41.2411,0\n+Chromosome\t147262\t.\tG\tT\t3766.49\t.\tAB=0;AO=122;DP=122;QA=4228;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:122:0:0:122:4228:-380.649,-36.7257,0\n+Chromosome\t154283\t.\tT\tC\t4403.08\t.\tAB=0;AO=141;DP=141;QA=4941;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:141:0:0:141:4941:-444.791,-42.4452,0\n+Chromosome\t154990\t.\tG\tT\t4207.92\t.\tAB=0;AO=142;DP=143;QA=4724;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:143:0:0:142:4724:-424.969,-42.7463,0\n+Chromosome\t162151\t.\tGT\tG\t2208.67\t.\tAB=0;AO=81;DP=84;QA=2524;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:84:0:0:81:2524:-226.95,-24.3834,0\n+Chromosome\t163940\t.\tA\tG\t2507.97\t.\tAB=0;AO=80;DP=80;QA=2839;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:80:0:0:80:2839:-255.719,-24.0824,0\n+Chromosome\t166253\t.\tA\tC\t3141.13\t.\tAB=0;AO=102;DP=102;QA=3586;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:102:0:0:102:3586:-322.902,-30.7051,0\n+Chromosome\t177857\t.\tG\tA\t2984.02\t.\tAB=0;AO=98;DP=98;QA=3389;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:98:0:0:98:3389:-305.192,-29.5009,0\n+Chromosome\t188800\t.\tT\tC\t1887.67\t.\tAB=0;AO=64;DP=64;QA=2217;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:64:0:0:64:2217:-199.772,-19.2659,0\n+Chromosome\t190816\t.\tA\tC\t1715.49\t.\tAB=0;AO=57;DP=57;QA=2026;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:57:0:0:57:2026:-182.579,-17.1587,0\n+Chromosome\t194305\t.\tC\tCGG\t1602.78\t.\tAB=0;AO=58;DP=59;QA=1889;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:59:0:0:58:1889:-169.924,-17.4597,0\n+Chromosome\t2738274\t.\tA\tC\t511.15\t.\tAB=0;AO=18;DP=19;QA=633;QR=35;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:19:1:35:18:633:-53.7923,-2.22094,0\n+Chromosome\t3750185\t.\tCGAC\tGGTG\t1102.73\t.\tAB=0;AO=36;DP=36;QA=1255;QR=0;RO=0;TYPE=complex\tGT:DP:RO:QR:AO:QA:GL\t1/1:36:0:0:36:1255:-113.24,-10.8371,0\n+Chromosome\t3750193\t.\tG\tA\t1198.75\t.\tAB=0;AO=40;DP=40;QA=1367;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:40:0:0:40:1367:-123.307,-12.0412,0\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_input2.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_input2.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,60 @@\n+##fileformat=VCFv4.1\n+##fileDate=20150301\n+##source=freeBayes v0.9.20-16-g3e35e72\n+##reference=reference.fasta\n+##phasing=none\n+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=DPB,Number=1,Type=Float,Description="Total read depth per bp at the locus; bases in reads overlapping / bases in haplotype">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Estimated allele frequency in the range (0,1]">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count, with partial observations recorded fractionally">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observations, with partial observations recorded fractionally">\n+##INFO=<ID=PRO,Number=1,Type=Float,Description="Reference allele observation count, with partial observations recorded fractionally">\n+##INFO=<ID=PAO,Number=A,Type=Float,Description="Alternate allele observations, with partial observations recorded fractionally">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=PQR,Number=1,Type=Float,Description="Reference allele quality sum in phred for partial observations">\n+##INFO=<ID=PQA,Number=A,Type=Float,Description="Alternate allele quality sum in phred for partial observations">\n+##INFO=<ID=SRF,Number=1,Type=Integer,Description="Number of reference observations on the forward strand">\n+##INFO=<ID=SRR,Number=1,Type=Integer,Description="Number of reference observations on the reverse strand">\n+##INFO=<ID=SAF,Number=A,Type=Integer,Description="Number of alternate observations on the forward strand">\n+##INFO=<ID=SAR,Number=A,Type=Integer,Description="Number of alternate observations on the reverse strand">\n+##INFO=<ID=SRP,Number=1,Type=Float,Description="Strand balance probability for the reference allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SRF and SRR given E(SRF/SRR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=SAP,Number=A,Type=Float,Description="Strand balance probability for the alternate allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SAF and SAR given E(SAF/SAR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=ABP,Number=A,Type=Float,Description="Allele balance probability at heterozygous sites: Phred-scaled upper-bounds estimate of the probability of observing the deviation between ABR and ABA given E(ABR/ABA) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=RUN,Number=A,Type=Integer,Description="Run length: the number of consecutive repeats of the alternate allele in the reference genome">\n+##INFO=<ID=RPP,Number=A,Type=Float,Description="Read Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=RPPR,Number=1,Type=Float,Description="Read Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=RPL,Number=A,Type=Float,Description="Reads Placed Left: number of reads supporting the alternate balanced to the left (5\') of the alternate allele">\n+##INFO=<ID=RPR,Numbe'..b':0:0:82:2334:-866.31,-24.6845,0\t0/1:27:14:431:13:389:-131.174,0,-142.961\t1/1:68:0:0:68:2019:-725.97,-20.47,0\t1/1:16:0:0:16:493:-172.669,-4.81648,0\t0/1:57:2:58:55:1716:-577.549,0,-4.35015\t1/1:34:0:0:34:1117:-372.828,-10.235,0\t0/1:25:9:295:16:540:-169.396,0,-91.3433\t0/1:53:26:837:27:880:-279.548,0,-267.677\t1/1:33:0:0:33:1063:-359.964,-9.93399,0\t0/1:21:12:397:9:297:-92.7309,0,-125.728\t0/1:107:50:1484:57:1738:-580.482,0,-501.622\t1/1:9:0:0:9:282:-97.6869,-2.70927,0\t1/1:22:0:0:22:711:-240.294,-6.62266,0\t0/1:130:57:1814:72:2337:-747.579,0,-580.516\t0/0:151:150:4800:1:31:0,-34.3561,-1621.09\t1/1:26:0:0:26:813:-281.46,-7.82678,0\t.\t1/1:7:0:0:7:223:-76.3831,-2.10721,0\t1/1:13:0:0:13:425:-142.565,-3.91339,0\t0/0:127:127:4112:0:0:0,-38.2308,-1386.3\t0/1:21:12:387:9:297:-92.7307,0,-124.822\t0/1:31:21:677:10:338:-101.416,0,-219.904\n+E2_L101\t189\t.\tGT\tGA,AA\t79493.6\t.\tAB=0.530648,0.564103;ABP=12.3275,4.40227;AC=27,1;AF=0.364865,0.0135135;AN=74;AO=711,22;CIGAR=1M1X,2X;DP=1947;DPB=1947;DPRA=1.2223,0.775155;EPP=1546.93,50.7827;EPPR=2623.98;GTI=0;LEN=1,2;MEANALT=1.2,2;MQM=59.9536,60;MQMR=59.9528;NS=37;NUMALT=2;ODDS=8.57375;PAIRED=1,1;PAIREDR=1;PAO=0,0;PQA=0,0;PQR=0;PRO=0;QA=26768,823;QR=45917;RO=1207;RPL=711,22;RPP=1546.93,50.7827;RPPR=2623.98;RPR=0,0;RUN=1,1;SAF=0,0;SAP=1546.93,50.7827;SAR=711,22;SRF=0;SRP=2623.98;SRR=1207;TYPE=snp,mnp;technology.Illumina=1,1\tGT:DP:RO:QR:AO:QA:GL\t0/1:63:29:1128:33,0:1297,0:-362.019,0,-314.829,-370.749,-324.763,-695.435\t0/1:279:136:5023:143,0:5199,0:-1527.93,0,-1456.1,-1568.87,-1499.14,-3067.65\t0/0:18:18:720:0,0:0,0:0,-5.41854,-209.126,-5.41854,-209.126,-209.126\t0/0:50:50:1802:0,0:0,0:0,-15.0515,-562.43,-15.0515,-562.43,-562.43\t.\t0/0:140:140:5188:0,0:0,0:0,-42.1442,-1586.93,-42.1442,-1586.93,-1586.93\t0/0:15:15:612:0,0:0,0:0,-4.51545,-175.417,-4.51545,-175.417,-175.417\t0/1:63:14:556:49,0:1902,0:-544.414,0,-143.417,-548.629,-158.168,-706.402\t0/0:7:7:255:0,0:0,0:0,-2.10721,-79.294,-2.10721,-79.294,-79.294\t1/1:13:0:0:13,0:486,0:-148.079,-3.91339,0,-148.079,-3.91339,-148.079\t0/1:21:10:377:11,0:413,0:-119.194,0,-107.957,-122.204,-111.268,-233.097\t0/1:33:7:283:26,0:969,0:-285.557,0,-71.9094,-287.664,-79.7362,-367.003\t.\t0/1:26:19:720:7,0:270,0:-72.8033,0,-209.291,-78.5229,-211.398,-289.538\t0/0:45:45:1610:0,0:0,0:0,-13.5463,-505.167,-13.5463,-505.167,-505.167\t1/2:39:0:0:17,22:633,823:-431.573,-243.764,-238.646,-188.182,0,-181.559\t0/1:49:16:571:33,0:1209,0:-358.342,0,-164.964,-363.158,-174.898,-537.697\t0/0:14:14:515:0,0:0,0:0,-4.21442,-158.684,-4.21442,-158.684,-158.684\t0/1:82:37:1340:45,0:1616,0:-481.016,0,-392.198,-492.154,-405.744,-897.538\t0/1:27:14:522:13,0:489,0:-140.222,0,-151.186,-144.436,-155.1,-299.162\t1/1:69:0:0:69,0:2506,0:-777.734,-20.7711,0,-777.734,-20.7711,-777.734\t0/1:17:10:355:7,0:270,0:-75.5457,0,-107.162,-78.556,-109.269,-187.452\t0/1:58:33:1252:25,0:989,0:-271.846,0,-359.488,-281.78,-367.013,-648.405\t0/1:35:19:755:16,0:627,0:-174.228,0,-209.735,-179.947,-214.551,-394.104\t0/1:26:9:351:17,0:680,0:-189.701,0,-96.1193,-192.41,-101.237,-293.254\t0/0:53:53:2059:0,0:0,0:0,-15.9546,-609.511,-15.9546,-609.511,-609.511\t0/0:33:32:1269:0,0:0,0:0,-9.63296,-370.162,-9.63296,-370.162,-370.162\t0/1:21:12:477:9,0:365,0:-98.8929,0,-132.958,-102.505,-135.668,-237.771\t0/1:107:52:1896:55,0:2071,0:-594.399,0,-554.667,-610.053,-571.224,-1180.91\t0/1:9:7:281:2,0:50,0:-18.0366,0,-78.9529,-20.1438,-79.555,-99.4154\t1/1:22:0:0:22,0:864,0:-254.067,-6.62266,0,-254.067,-6.62266,-254.067\t0/1:131:57:2263:72,0:2808,0:-789.722,0,-620.658,-806.881,-642.332,-1449.1\t0/0:152:150:5887:1,0:38,0:0,-34.038,-1717.85,-45.1545,-1718.15,-1729.26\t0/1:27:14:534:13,0:512,0:-142.297,0,-152.267,-146.511,-156.181,-302.304\t.\t0/1:7:3:113:4,0:158,0:-44.4921,0,-32.4297,-45.3952,-33.6338,-78.6449\t0/0:14:14:544:0,0:0,0:0,-4.21442,-161.298,-4.21442,-161.298,-161.298\t0/0:129:127:4963:0,0:0,0:0,-38.2308,-1462.3,-38.2308,-1462.3,-1462.3\t0/1:22:13:480:9,0:347,0:-96.9577,0,-140.907,-100.871,-143.616,-244.109\t0/0:31:31:1216:0,0:0,0:0,-9.33193,-357.713,-9.33193,-357.713,-357.713\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_output1.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_output1.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,94 @@\n+##fileformat=VCFv4.2\n+##FILTER=<ID=PASS,Description="All filters passed">\n+##fileDate=20190323\n+##source=freeBayes v1.2.0-dirty\n+##reference=reference/ref.fa\n+##contig=<ID=Chromosome,length=4411532>\n+##phasing=none\n+##commandline="freebayes -p 2 -P 0 -C 10 --min-repeat-entropy 1.5 --strict-vcf -q 13 -m 60 --min-coverage 10 -F 0.05 -f reference/ref.fa snps.bam --region Chromosome:0-1495044"\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Count of full observations of the reference haplotype.">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Count of full observations of this alternate haplotype.">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">\n+##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count">\n+##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations">\n+##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count">\n+##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations">\n+##bcftools_viewVersion=1.9+htslib-1.9\n+##bcftools_viewCommand=view --include \'FMT/GT="1/1" && QUAL>=100.0 && FMT/DP>=10 && (FMT/AO)/(FMT/DP)>=0.9\' snps.raw.vcf; Date=Sat Mar 23 06:45:26 2019\n+##bcftools_annotateVersion=1.9+htslib-1.9\n+##bcftools_annotateCommand=annotate --remove ^INFO/TYPE,^INFO/DP,^INFO/RO,^INFO/AO,^INFO/AB,^FORMAT/GT,^FORMAT/DP,^FORMAT/RO,^FORMAT/AO,^FORMAT/QR,^FORMAT/QA,^FORMAT/GL; Date=Sat Mar 23 06:45:26 2019\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tout\n+Chromosome\t1849\t.\tC\tA\t3412.24\t.\tAB=0.0;AO=110;DP=110;QA=3850;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:0:0:110:3850:-346.644,-33.1133,0.0\n+Chromosome\t1977\t.\tA\tG\t3234.43\t.\tAB=0.0;AO=106;DP=106;QA=3704;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3704:-333.508,-31.9092,0.0\n+Chromosome\t4013\t.\tT\tC\t3965.91\t.\tAB=0.0;AO=125;DP=125;QA=4448;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:125:0:0:125:4448:-400.411,-37.6288,0.0\n+Chromosome\t11820\t.\tC\tG\t2252.54\t.\tAB=0.0;AO=74;DP=74;QA=2662;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:74:0:0:74:2662:-239.791,-22.2762,0.0\n+Chromosome\t11879\t.\tA\tG\t1815.99\t.\tAB=0.0;AO=63;DP=63;QA=2212;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:63:0:0:63:2212:-199.306,-18.9649,0.0\n+Chromosome\t14785\t.\tT\tC\t4342.4\t.\tAB=0.0;AO=139;DP=139;QA=4874;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:139:0:0:139:4874:-438.763,-41.8432,0.0\n+Chromosome\t14861\t.\tG\tT\t4237.79\t.\tAB=0.0;AO=133;DP=135;QA=4758;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:135:0:0:133:4758:-427.969,-40.037,0.0\n+Chromosome\t15117\t.\tC\tG\t3298.26\t.\tAB=0.0;AO=106;DP=106;QA=3708;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3708:-333.903,-31.9092,0.0\n+Chromosome\t15890\t.\tG\tA\t3349.13\t.\tAB=0.0;AO=116;DP=117;QA=3770;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:117:0:0:116:3770:-339.321,-34.9195,0.0\n+Chromosome\t16119\t.\tC\tA\t3794.09\t.\tAB=0.0;AO=124;DP=125;QA=4268;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:125:0:0:124:4268:-383.905,-37.3277,0.0\n+Chromosome\t21795\t.\tG\tA\t768.571\t.\tAB=0.0;AO=28;DP=28;QA=892;QR=0;RO=0;TYP'..b'172;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:64:0:0:64:2172:-195.723,-19.2659,0.0\n+Chromosome\t75940\t.\tG\tC\t2674.83\t.\tAB=0.0;AO=89;DP=89;QA=3048;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:89:0:0:89:3048:-274.519,-26.7917,0.0\n+Chromosome\t87468\t.\tC\tT\t4061.4\t.\tAB=0.0;AO=126;DP=126;QA=4584;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4584:-412.628,-37.9298,0.0\n+Chromosome\t92199\t.\tT\tG\t686.38\t.\tAB=0.0;AO=23;DP=23;QA=799;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:23:0:0:23:799:-72.2155,-6.92369,0.0\n+Chromosome\t94388\t.\tG\tA\t2922.87\t.\tAB=0.0;AO=95;DP=95;QA=3292;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:95:0:0:95:3292:-296.486,-28.5979,0.0\n+Chromosome\t99162\t.\tTCGGTGTGCG\tT\t2040.99\t.\tAB=0.0;AO=78;DP=78;QA=2358;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2358:-212.453,-23.4803,0.0\n+Chromosome\t116000\t.\tT\tG\t3196.37\t.\tAB=0.0;AO=105;DP=105;QA=3605;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3605:-324.628,-31.6082,0.0\n+Chromosome\t122109\t.\tA\tG\t3324.29\t.\tAB=0.0;AO=111;DP=111;QA=3735;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:111:0:0:111:3735:-336.329,-33.4143,0.0\n+Chromosome\t123454\t.\tC\tT\t4362.28\t.\tAB=0.0;AO=136;DP=137;QA=4894;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:136:4894:-440.321,-40.9401,0.0\n+Chromosome\t123520\t.\tT\tC\t3793.13\t.\tAB=0.0;AO=121;DP=121;QA=4262;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:121:0:0:121:4262:-383.682,-36.4246,0.0\n+Chromosome\t125711\t.\tGGTT\tG\t3140.7\t.\tAB=0.0;AO=105;DP=105;QA=3531;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3531:-317.98,-31.6082,0.0\n+Chromosome\t125830\t.\tG\tGA\t2079.98\t.\tAB=0.0;AO=69;DP=72;QA=2347;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:69:2347:-211.164,-20.7711,0.0\n+Chromosome\t131174\t.\tT\tTG\t2854.04\t.\tAB=0.0;AO=97;DP=99;QA=3213;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:99:0:0:97:3213:-288.972,-29.1999,0.0\n+Chromosome\t133839\t.\tC\tT\t2457.55\t.\tAB=0.0;AO=78;DP=78;QA=2802;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2802:-252.374,-23.4803,0.0\n+Chromosome\t134024\t.\tT\tC\t2242.53\t.\tAB=0.0;AO=72;DP=72;QA=2543;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2543:-229.099,-21.6742,0.0\n+Chromosome\t138419\t.\tG\tA\t4166.36\t.\tAB=0.0;AO=132;DP=132;QA=4683;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:132:0:0:132:4683:-421.582,-39.736,0.0\n+Chromosome\t139297\t.\tG\tT\t3706.81\t.\tAB=0.0;AO=120;DP=120;QA=4165;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:120:0:0:120:4165:-374.978,-36.1236,0.0\n+Chromosome\t143207\t.\tT\tC\t2180.95\t.\tAB=0.0;AO=72;DP=72;QA=2523;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2523:-227.3,-21.6742,0.0\n+Chromosome\t146087\t.\tT\tC\t4315.28\t.\tAB=0.0;AO=137;DP=137;QA=4844;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:137:4844:-436.07,-41.2411,0.0\n+Chromosome\t147262\t.\tG\tT\t3766.49\t.\tAB=0.0;AO=122;DP=122;QA=4228;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:122:0:0:122:4228:-380.649,-36.7257,0.0\n+Chromosome\t154283\t.\tT\tC\t4403.08\t.\tAB=0.0;AO=141;DP=141;QA=4941;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:141:0:0:141:4941:-444.791,-42.4452,0.0\n+Chromosome\t154990\t.\tG\tT\t4207.92\t.\tAB=0.0;AO=142;DP=143;QA=4724;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:143:0:0:142:4724:-424.969,-42.7463,0.0\n+Chromosome\t162151\t.\tGT\tG\t2208.67\t.\tAB=0.0;AO=81;DP=84;QA=2524;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:84:0:0:81:2524:-226.95,-24.3834,0.0\n+Chromosome\t163940\t.\tA\tG\t2507.97\t.\tAB=0.0;AO=80;DP=80;QA=2839;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:80:0:0:80:2839:-255.719,-24.0824,0.0\n+Chromosome\t166253\t.\tA\tC\t3141.13\t.\tAB=0.0;AO=102;DP=102;QA=3586;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:102:0:0:102:3586:-322.902,-30.7051,0.0\n+Chromosome\t190816\t.\tA\tC\t1715.49\t.\tAB=0.0;AO=57;DP=57;QA=2026;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:57:0:0:57:2026:-182.579,-17.1587,0.0\n+Chromosome\t194305\t.\tC\tCGG\t1602.78\t.\tAB=0.0;AO=58;DP=59;QA=1889;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:59:0:0:58:1889:-169.924,-17.4597,0.0\n+Chromosome\t2738274\t.\tA\tC\t511.15\t.\tAB=0.0;AO=18;DP=19;QA=633;QR=35;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:19:1:35:18:633:-53.7923,-2.22094,0.0\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_output2.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_output2.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,101 @@\n+##fileformat=VCFv4.2\n+##FILTER=<ID=PASS,Description="All filters passed">\n+##fileDate=20190323\n+##source=freeBayes v1.2.0-dirty\n+##reference=reference/ref.fa\n+##contig=<ID=Chromosome,length=4411532>\n+##phasing=none\n+##commandline="freebayes -p 2 -P 0 -C 10 --min-repeat-entropy 1.5 --strict-vcf -q 13 -m 60 --min-coverage 10 -F 0.05 -f reference/ref.fa snps.bam --region Chromosome:0-1495044"\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Count of full observations of the reference haplotype.">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Count of full observations of this alternate haplotype.">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">\n+##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count">\n+##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations">\n+##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count">\n+##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations">\n+##bcftools_viewVersion=1.9+htslib-1.9\n+##bcftools_viewCommand=view --include \'FMT/GT="1/1" && QUAL>=100.0 && FMT/DP>=10 && (FMT/AO)/(FMT/DP)>=0.9\' snps.raw.vcf; Date=Sat Mar 23 06:45:26 2019\n+##bcftools_annotateVersion=1.9+htslib-1.9\n+##bcftools_annotateCommand=annotate --remove ^INFO/TYPE,^INFO/DP,^INFO/RO,^INFO/AO,^INFO/AB,^FORMAT/GT,^FORMAT/DP,^FORMAT/RO,^FORMAT/AO,^FORMAT/QR,^FORMAT/QA,^FORMAT/GL; Date=Sat Mar 23 06:45:26 2019\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tout\n+Chromosome\t1849\t.\tC\tA\t3412.24\t.\tAB=0.0;AO=110;DP=110;QA=3850;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:0:0:110:3850:-346.644,-33.1133,0.0\n+Chromosome\t1977\t.\tA\tG\t3234.43\t.\tAB=0.0;AO=106;DP=106;QA=3704;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3704:-333.508,-31.9092,0.0\n+Chromosome\t4013\t.\tT\tC\t3965.91\t.\tAB=0.0;AO=125;DP=125;QA=4448;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:125:0:0:125:4448:-400.411,-37.6288,0.0\n+Chromosome\t7362\t.\tG\tC\t4009.71\t.\tAB=0.0;AO=126;DP=126;QA=4518;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4518:-406.711,-37.9298,0.0\n+Chromosome\t9304\t.\tG\tA\t4222.23\t.\tAB=0.0;AO=136;DP=136;QA=4764;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:136:0:0:136:4764:-428.865,-40.9401,0.0\n+Chromosome\t11820\t.\tC\tG\t2252.54\t.\tAB=0.0;AO=74;DP=74;QA=2662;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:74:0:0:74:2662:-239.791,-22.2762,0.0\n+Chromosome\t11879\t.\tA\tG\t1815.99\t.\tAB=0.0;AO=63;DP=63;QA=2212;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:63:0:0:63:2212:-199.306,-18.9649,0.0\n+Chromosome\t14785\t.\tT\tC\t4342.4\t.\tAB=0.0;AO=139;DP=139;QA=4874;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:139:0:0:139:4874:-438.763,-41.8432,0.0\n+Chromosome\t14861\t.\tG\tT\t4237.79\t.\tAB=0.0;AO=133;DP=135;QA=4758;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:135:0:0:133:4758:-427.969,-40.037,0.0\n+Chromosome\t15117\t.\tC\tG\t3298.26\t.\tAB=0.0;AO=106;DP=106;QA=3708;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3708:-333.903,-31.9092,0.0\n+Chromosome\t15890\t.\tG\tA\t3349.13\t.\tAB=0.0;AO=116;DP=117;QA=3770;QR=0;RO=0;T'..b'=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2358:-212.453,-23.4803,0.0\n+Chromosome\t105139\t.\tC\tA\t3418.74\t.\tAB=0.0;AO=109;DP=110;QA=3888;QR=38;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:1:38:109:3888:-346.257,-29.316,0.0\n+Chromosome\t105736\t.\tT\tC\t1805.18\t.\tAB=0.0;AO=61;DP=61;QA=2101;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:61:0:0:61:2101:-189.335,-18.3628,0.0\n+Chromosome\t116000\t.\tT\tG\t3196.37\t.\tAB=0.0;AO=105;DP=105;QA=3605;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3605:-324.628,-31.6082,0.0\n+Chromosome\t122109\t.\tA\tG\t3324.29\t.\tAB=0.0;AO=111;DP=111;QA=3735;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:111:0:0:111:3735:-336.329,-33.4143,0.0\n+Chromosome\t123454\t.\tC\tT\t4362.28\t.\tAB=0.0;AO=136;DP=137;QA=4894;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:136:4894:-440.321,-40.9401,0.0\n+Chromosome\t123520\t.\tT\tC\t3793.13\t.\tAB=0.0;AO=121;DP=121;QA=4262;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:121:0:0:121:4262:-383.682,-36.4246,0.0\n+Chromosome\t125711\t.\tGGTT\tG\t3140.7\t.\tAB=0.0;AO=105;DP=105;QA=3531;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3531:-317.98,-31.6082,0.0\n+Chromosome\t125830\t.\tG\tGA\t2079.98\t.\tAB=0.0;AO=69;DP=72;QA=2347;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:69:2347:-211.164,-20.7711,0.0\n+Chromosome\t131174\t.\tT\tTG\t2854.04\t.\tAB=0.0;AO=97;DP=99;QA=3213;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:99:0:0:97:3213:-288.972,-29.1999,0.0\n+Chromosome\t133839\t.\tC\tT\t2457.55\t.\tAB=0.0;AO=78;DP=78;QA=2802;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2802:-252.374,-23.4803,0.0\n+Chromosome\t134024\t.\tT\tC\t2242.53\t.\tAB=0.0;AO=72;DP=72;QA=2543;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2543:-229.099,-21.6742,0.0\n+Chromosome\t138419\t.\tG\tA\t4166.36\t.\tAB=0.0;AO=132;DP=132;QA=4683;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:132:0:0:132:4683:-421.582,-39.736,0.0\n+Chromosome\t139297\t.\tG\tT\t3706.81\t.\tAB=0.0;AO=120;DP=120;QA=4165;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:120:0:0:120:4165:-374.978,-36.1236,0.0\n+Chromosome\t143207\t.\tT\tC\t2180.95\t.\tAB=0.0;AO=72;DP=72;QA=2523;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2523:-227.3,-21.6742,0.0\n+Chromosome\t146087\t.\tT\tC\t4315.28\t.\tAB=0.0;AO=137;DP=137;QA=4844;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:137:4844:-436.07,-41.2411,0.0\n+Chromosome\t147262\t.\tG\tT\t3766.49\t.\tAB=0.0;AO=122;DP=122;QA=4228;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:122:0:0:122:4228:-380.649,-36.7257,0.0\n+Chromosome\t154283\t.\tT\tC\t4403.08\t.\tAB=0.0;AO=141;DP=141;QA=4941;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:141:0:0:141:4941:-444.791,-42.4452,0.0\n+Chromosome\t154990\t.\tG\tT\t4207.92\t.\tAB=0.0;AO=142;DP=143;QA=4724;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:143:0:0:142:4724:-424.969,-42.7463,0.0\n+Chromosome\t162151\t.\tGT\tG\t2208.67\t.\tAB=0.0;AO=81;DP=84;QA=2524;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:84:0:0:81:2524:-226.95,-24.3834,0.0\n+Chromosome\t163940\t.\tA\tG\t2507.97\t.\tAB=0.0;AO=80;DP=80;QA=2839;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:80:0:0:80:2839:-255.719,-24.0824,0.0\n+Chromosome\t166253\t.\tA\tC\t3141.13\t.\tAB=0.0;AO=102;DP=102;QA=3586;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:102:0:0:102:3586:-322.902,-30.7051,0.0\n+Chromosome\t177857\t.\tG\tA\t2984.02\t.\tAB=0.0;AO=98;DP=98;QA=3389;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:98:0:0:98:3389:-305.192,-29.5009,0.0\n+Chromosome\t188800\t.\tT\tC\t1887.67\t.\tAB=0.0;AO=64;DP=64;QA=2217;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:64:0:0:64:2217:-199.772,-19.2659,0.0\n+Chromosome\t190816\t.\tA\tC\t1715.49\t.\tAB=0.0;AO=57;DP=57;QA=2026;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:57:0:0:57:2026:-182.579,-17.1587,0.0\n+Chromosome\t194305\t.\tC\tCGG\t1602.78\t.\tAB=0.0;AO=58;DP=59;QA=1889;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:59:0:0:58:1889:-169.924,-17.4597,0.0\n+Chromosome\t2738274\t.\tA\tC\t511.15\t.\tAB=0.0;AO=18;DP=19;QA=633;QR=35;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:19:1:35:18:633:-53.7923,-2.22094,0.0\n+Chromosome\t3750185\t.\tCGAC\tGGTG\t1102.73\t.\tAB=0.0;AO=36;DP=36;QA=1255;QR=0;RO=0;TYPE=complex\tGT:DP:RO:QR:AO:QA:GL\t1/1:36:0:0:36:1255:-113.24,-10.8371,0.0\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_output3.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_output3.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,101 @@\n+##fileformat=VCFv4.2\n+##FILTER=<ID=PASS,Description="All filters passed">\n+##fileDate=20190323\n+##source=freeBayes v1.2.0-dirty\n+##reference=reference/ref.fa\n+##contig=<ID=Chromosome,length=4411532>\n+##phasing=none\n+##commandline="freebayes -p 2 -P 0 -C 10 --min-repeat-entropy 1.5 --strict-vcf -q 13 -m 60 --min-coverage 10 -F 0.05 -f reference/ref.fa snps.bam --region Chromosome:0-1495044"\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Count of full observations of the reference haplotype.">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Count of full observations of this alternate haplotype.">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">\n+##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count">\n+##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations">\n+##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count">\n+##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations">\n+##bcftools_viewVersion=1.9+htslib-1.9\n+##bcftools_viewCommand=view --include \'FMT/GT="1/1" && QUAL>=100.0 && FMT/DP>=10 && (FMT/AO)/(FMT/DP)>=0.9\' snps.raw.vcf; Date=Sat Mar 23 06:45:26 2019\n+##bcftools_annotateVersion=1.9+htslib-1.9\n+##bcftools_annotateCommand=annotate --remove ^INFO/TYPE,^INFO/DP,^INFO/RO,^INFO/AO,^INFO/AB,^FORMAT/GT,^FORMAT/DP,^FORMAT/RO,^FORMAT/AO,^FORMAT/QR,^FORMAT/QA,^FORMAT/GL; Date=Sat Mar 23 06:45:26 2019\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tout\n+Chromosome\t1849\t.\tC\tA\t3412.24\t.\tAB=0.0;AO=110;DP=110;QA=3850;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:0:0:110:3850:-346.644,-33.1133,0.0\n+Chromosome\t1977\t.\tA\tG\t3234.43\t.\tAB=0.0;AO=106;DP=106;QA=3704;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3704:-333.508,-31.9092,0.0\n+Chromosome\t4013\t.\tT\tC\t3965.91\t.\tAB=0.0;AO=125;DP=125;QA=4448;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:125:0:0:125:4448:-400.411,-37.6288,0.0\n+Chromosome\t7362\t.\tG\tC\t4009.71\t.\tAB=0.0;AO=126;DP=126;QA=4518;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4518:-406.711,-37.9298,0.0\n+Chromosome\t9304\t.\tG\tA\t4222.23\t.\tAB=0.0;AO=136;DP=136;QA=4764;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:136:0:0:136:4764:-428.865,-40.9401,0.0\n+Chromosome\t11820\t.\tC\tG\t2252.54\t.\tAB=0.0;AO=74;DP=74;QA=2662;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:74:0:0:74:2662:-239.791,-22.2762,0.0\n+Chromosome\t11879\t.\tA\tG\t1815.99\t.\tAB=0.0;AO=63;DP=63;QA=2212;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:63:0:0:63:2212:-199.306,-18.9649,0.0\n+Chromosome\t14785\t.\tT\tC\t4342.4\t.\tAB=0.0;AO=139;DP=139;QA=4874;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:139:0:0:139:4874:-438.763,-41.8432,0.0\n+Chromosome\t14861\t.\tG\tT\t4237.79\t.\tAB=0.0;AO=133;DP=135;QA=4758;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:135:0:0:133:4758:-427.969,-40.037,0.0\n+Chromosome\t15117\t.\tC\tG\t3298.26\t.\tAB=0.0;AO=106;DP=106;QA=3708;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3708:-333.903,-31.9092,0.0\n+Chromosome\t15890\t.\tG\tA\t3349.13\t.\tAB=0.0;AO=116;DP=117;QA=3770;QR=0;RO=0;T'..b'0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2358:-212.453,-23.4803,0.0\n+Chromosome\t105139\t.\tC\tA\t3418.74\t.\tAB=0.0;AO=109;DP=110;QA=3888;QR=38;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:1:38:109:3888:-346.257,-29.316,0.0\n+Chromosome\t105736\t.\tT\tC\t1805.18\t.\tAB=0.0;AO=61;DP=61;QA=2101;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:61:0:0:61:2101:-189.335,-18.3628,0.0\n+Chromosome\t116000\t.\tT\tG\t3196.37\t.\tAB=0.0;AO=105;DP=105;QA=3605;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3605:-324.628,-31.6082,0.0\n+Chromosome\t122109\t.\tA\tG\t3324.29\t.\tAB=0.0;AO=111;DP=111;QA=3735;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:111:0:0:111:3735:-336.329,-33.4143,0.0\n+Chromosome\t123454\t.\tC\tT\t4362.28\t.\tAB=0.0;AO=136;DP=137;QA=4894;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:136:4894:-440.321,-40.9401,0.0\n+Chromosome\t123520\t.\tT\tC\t3793.13\t.\tAB=0.0;AO=121;DP=121;QA=4262;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:121:0:0:121:4262:-383.682,-36.4246,0.0\n+Chromosome\t125711\t.\tGGTT\tG\t3140.7\t.\tAB=0.0;AO=105;DP=105;QA=3531;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3531:-317.98,-31.6082,0.0\n+Chromosome\t125830\t.\tG\tGA\t2079.98\t.\tAB=0.0;AO=69;DP=72;QA=2347;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:69:2347:-211.164,-20.7711,0.0\n+Chromosome\t131174\t.\tT\tTG\t2854.04\t.\tAB=0.0;AO=97;DP=99;QA=3213;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:99:0:0:97:3213:-288.972,-29.1999,0.0\n+Chromosome\t133839\t.\tC\tT\t2457.55\t.\tAB=0.0;AO=78;DP=78;QA=2802;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2802:-252.374,-23.4803,0.0\n+Chromosome\t134024\t.\tT\tC\t2242.53\t.\tAB=0.0;AO=72;DP=72;QA=2543;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2543:-229.099,-21.6742,0.0\n+Chromosome\t138419\t.\tG\tA\t4166.36\t.\tAB=0.0;AO=132;DP=132;QA=4683;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:132:0:0:132:4683:-421.582,-39.736,0.0\n+Chromosome\t139297\t.\tG\tT\t3706.81\t.\tAB=0.0;AO=120;DP=120;QA=4165;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:120:0:0:120:4165:-374.978,-36.1236,0.0\n+Chromosome\t143207\t.\tT\tC\t2180.95\t.\tAB=0.0;AO=72;DP=72;QA=2523;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2523:-227.3,-21.6742,0.0\n+Chromosome\t146087\t.\tT\tC\t4315.28\t.\tAB=0.0;AO=137;DP=137;QA=4844;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:137:4844:-436.07,-41.2411,0.0\n+Chromosome\t147262\t.\tG\tT\t3766.49\t.\tAB=0.0;AO=122;DP=122;QA=4228;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:122:0:0:122:4228:-380.649,-36.7257,0.0\n+Chromosome\t154283\t.\tT\tC\t4403.08\t.\tAB=0.0;AO=141;DP=141;QA=4941;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:141:0:0:141:4941:-444.791,-42.4452,0.0\n+Chromosome\t154990\t.\tG\tT\t4207.92\t.\tAB=0.0;AO=142;DP=143;QA=4724;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:143:0:0:142:4724:-424.969,-42.7463,0.0\n+Chromosome\t162151\t.\tGT\tG\t2208.67\t.\tAB=0.0;AO=81;DP=84;QA=2524;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:84:0:0:81:2524:-226.95,-24.3834,0.0\n+Chromosome\t163940\t.\tA\tG\t2507.97\t.\tAB=0.0;AO=80;DP=80;QA=2839;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:80:0:0:80:2839:-255.719,-24.0824,0.0\n+Chromosome\t166253\t.\tA\tC\t3141.13\t.\tAB=0.0;AO=102;DP=102;QA=3586;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:102:0:0:102:3586:-322.902,-30.7051,0.0\n+Chromosome\t177857\t.\tG\tA\t2984.02\t.\tAB=0.0;AO=98;DP=98;QA=3389;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:98:0:0:98:3389:-305.192,-29.5009,0.0\n+Chromosome\t188800\t.\tT\tC\t1887.67\t.\tAB=0.0;AO=64;DP=64;QA=2217;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:64:0:0:64:2217:-199.772,-19.2659,0.0\n+Chromosome\t190816\t.\tA\tC\t1715.49\t.\tAB=0.0;AO=57;DP=57;QA=2026;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:57:0:0:57:2026:-182.579,-17.1587,0.0\n+Chromosome\t194305\t.\tC\tCGG\t1602.78\t.\tAB=0.0;AO=58;DP=59;QA=1889;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:59:0:0:58:1889:-169.924,-17.4597,0.0\n+Chromosome\t3750185\t.\tCGAC\tGGTG\t1102.73\t.\tAB=0.0;AO=36;DP=36;QA=1255;QR=0;RO=0;TYPE=complex\tGT:DP:RO:QR:AO:QA:GL\t1/1:36:0:0:36:1255:-113.24,-10.8371,0.0\n+Chromosome\t3750193\t.\tG\tA\t1198.75\t.\tAB=0.0;AO=40;DP=40;QA=1367;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:40:0:0:40:1367:-123.307,-12.0412,0.0\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_output4.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_output4.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,58 @@\n+##fileformat=VCFv4.1\n+##fileDate=20150301\n+##source=freeBayes v0.9.20-16-g3e35e72\n+##reference=reference.fasta\n+##phasing=none\n+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=DPB,Number=1,Type=Float,Description="Total read depth per bp at the locus; bases in reads overlapping / bases in haplotype">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Estimated allele frequency in the range (0,1]">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count, with partial observations recorded fractionally">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observations, with partial observations recorded fractionally">\n+##INFO=<ID=PRO,Number=1,Type=Float,Description="Reference allele observation count, with partial observations recorded fractionally">\n+##INFO=<ID=PAO,Number=A,Type=Float,Description="Alternate allele observations, with partial observations recorded fractionally">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=PQR,Number=1,Type=Float,Description="Reference allele quality sum in phred for partial observations">\n+##INFO=<ID=PQA,Number=A,Type=Float,Description="Alternate allele quality sum in phred for partial observations">\n+##INFO=<ID=SRF,Number=1,Type=Integer,Description="Number of reference observations on the forward strand">\n+##INFO=<ID=SRR,Number=1,Type=Integer,Description="Number of reference observations on the reverse strand">\n+##INFO=<ID=SAF,Number=A,Type=Integer,Description="Number of alternate observations on the forward strand">\n+##INFO=<ID=SAR,Number=A,Type=Integer,Description="Number of alternate observations on the reverse strand">\n+##INFO=<ID=SRP,Number=1,Type=Float,Description="Strand balance probability for the reference allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SRF and SRR given E(SRF/SRR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=SAP,Number=A,Type=Float,Description="Strand balance probability for the alternate allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SAF and SAR given E(SAF/SAR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=ABP,Number=A,Type=Float,Description="Allele balance probability at heterozygous sites: Phred-scaled upper-bounds estimate of the probability of observing the deviation between ABR and ABA given E(ABR/ABA) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=RUN,Number=A,Type=Integer,Description="Run length: the number of consecutive repeats of the alternate allele in the reference genome">\n+##INFO=<ID=RPP,Number=A,Type=Float,Description="Read Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=RPPR,Number=1,Type=Float,Description="Read Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding\'s inequality">\n+##INFO=<ID=RPL,Number=A,Type=Float,Description="Reads Placed Left: number of reads supporting the alternate balanced to the left (5\') of the alternate allele">\n+##INFO=<ID=RPR,Numbe'..b'/1:68:0:0:68:2019:-725.97,-20.47,0.0\t1/1:16:0:0:16:493:-172.669,-4.81648,0.0\t0/1:57:2:58:55:1716:-577.549,0.0,-4.35015\t1/1:34:0:0:34:1117:-372.828,-10.235,0.0\t0/1:25:9:295:16:540:-169.396,0.0,-91.3433\t0/1:53:26:837:27:880:-279.548,0.0,-267.677\t1/1:33:0:0:33:1063:-359.964,-9.93399,0.0\t0/1:21:12:397:9:297:-92.7309,0.0,-125.728\t0/1:107:50:1484:57:1738:-580.482,0.0,-501.622\t1/1:9:0:0:9:282:-97.6869,-2.70927,0.0\t1/1:22:0:0:22:711:-240.294,-6.62266,0.0\t0/1:130:57:1814:72:2337:-747.579,0.0,-580.516\t0/0:151:150:4800:1:31:0.0,-34.3561,-1621.09\t1/1:26:0:0:26:813:-281.46,-7.82678,0.0\t.:.:.:.:.:.:.\t1/1:7:0:0:7:223:-76.3831,-2.10721,0.0\t1/1:13:0:0:13:425:-142.565,-3.91339,0.0\t0/0:127:127:4112:0:0:0.0,-38.2308,-1386.3\t0/1:21:12:387:9:297:-92.7307,0.0,-124.822\t0/1:31:21:677:10:338:-101.416,0.0,-219.904\n+E2_L101\t189\t.\tGT\tGA\t79493.6\t.\tAB=0.530648;ABP=12.3275;AC=27;AF=0.364865;AN=74;AO=711;CIGAR=1M1X;DP=1947;DPB=1947.0;DPRA=1.2223;EPP=1546.93;EPPR=2623.98;GTI=0;LEN=1;MEANALT=1.2;MQM=59.9536;MQMR=59.9528;NS=37;NUMALT=2;ODDS=8.57375;PAIRED=1.0;PAIREDR=1.0;PAO=0.0;PQA=0.0;PQR=0.0;PRO=0.0;QA=26768;QR=45917;RO=1207;RPL=711.0;RPP=1546.93;RPPR=2623.98;RPR=0.0;RUN=1;SAF=0;SAP=1546.93;SAR=711;SRF=0;SRP=2623.98;SRR=1207;TYPE=snp;technology.Illumina=1.0\tGT:DP:RO:QR:AO:QA:GL\t0/1:63:29:1128:33,0:1297,0:-362.019,0.0,-314.829,-370.749,-324.763,-695.435\t0/1:279:136:5023:143,0:5199,0:-1527.93,0.0,-1456.1,-1568.87,-1499.14,-3067.65\t0/0:18:18:720:0,0:0,0:0.0,-5.41854,-209.126,-5.41854,-209.126,-209.126\t0/0:50:50:1802:0,0:0,0:0.0,-15.0515,-562.43,-15.0515,-562.43,-562.43\t.:.:.:.:.:.:.\t0/0:140:140:5188:0,0:0,0:0.0,-42.1442,-1586.93,-42.1442,-1586.93,-1586.93\t0/0:15:15:612:0,0:0,0:0.0,-4.51545,-175.417,-4.51545,-175.417,-175.417\t0/1:63:14:556:49,0:1902,0:-544.414,0.0,-143.417,-548.629,-158.168,-706.402\t0/0:7:7:255:0,0:0,0:0.0,-2.10721,-79.294,-2.10721,-79.294,-79.294\t1/1:13:0:0:13,0:486,0:-148.079,-3.91339,0.0,-148.079,-3.91339,-148.079\t0/1:21:10:377:11,0:413,0:-119.194,0.0,-107.957,-122.204,-111.268,-233.097\t0/1:33:7:283:26,0:969,0:-285.557,0.0,-71.9094,-287.664,-79.7362,-367.003\t.:.:.:.:.:.:.\t0/1:26:19:720:7,0:270,0:-72.8033,0.0,-209.291,-78.5229,-211.398,-289.538\t0/0:45:45:1610:0,0:0,0:0.0,-13.5463,-505.167,-13.5463,-505.167,-505.167\t1/2:39:0:0:17,22:633,823:-431.573,-243.764,-238.646,-188.182,0.0,-181.559\t0/1:49:16:571:33,0:1209,0:-358.342,0.0,-164.964,-363.158,-174.898,-537.697\t0/0:14:14:515:0,0:0,0:0.0,-4.21442,-158.684,-4.21442,-158.684,-158.684\t0/1:82:37:1340:45,0:1616,0:-481.016,0.0,-392.198,-492.154,-405.744,-897.538\t0/1:27:14:522:13,0:489,0:-140.222,0.0,-151.186,-144.436,-155.1,-299.162\t1/1:69:0:0:69,0:2506,0:-777.734,-20.7711,0.0,-777.734,-20.7711,-777.734\t0/1:17:10:355:7,0:270,0:-75.5457,0.0,-107.162,-78.556,-109.269,-187.452\t0/1:58:33:1252:25,0:989,0:-271.846,0.0,-359.488,-281.78,-367.013,-648.405\t0/1:35:19:755:16,0:627,0:-174.228,0.0,-209.735,-179.947,-214.551,-394.104\t0/1:26:9:351:17,0:680,0:-189.701,0.0,-96.1193,-192.41,-101.237,-293.254\t0/0:53:53:2059:0,0:0,0:0.0,-15.9546,-609.511,-15.9546,-609.511,-609.511\t0/0:33:32:1269:0,0:0,0:0.0,-9.63296,-370.162,-9.63296,-370.162,-370.162\t0/1:21:12:477:9,0:365,0:-98.8929,0.0,-132.958,-102.505,-135.668,-237.771\t0/1:107:52:1896:55,0:2071,0:-594.399,0.0,-554.667,-610.053,-571.224,-1180.91\t0/1:9:7:281:2,0:50,0:-18.0366,0.0,-78.9529,-20.1438,-79.555,-99.4154\t1/1:22:0:0:22,0:864,0:-254.067,-6.62266,0.0,-254.067,-6.62266,-254.067\t0/1:131:57:2263:72,0:2808,0:-789.722,0.0,-620.658,-806.881,-642.332,-1449.1\t0/0:152:150:5887:1,0:38,0:0.0,-34.038,-1717.85,-45.1545,-1718.15,-1729.26\t0/1:27:14:534:13,0:512,0:-142.297,0.0,-152.267,-146.511,-156.181,-302.304\t.:.:.:.:.:.:.\t0/1:7:3:113:4,0:158,0:-44.4921,0.0,-32.4297,-45.3952,-33.6338,-78.6449\t0/0:14:14:544:0,0:0,0:0.0,-4.21442,-161.298,-4.21442,-161.298,-161.298\t0/0:129:127:4963:0,0:0,0:0.0,-38.2308,-1462.3,-38.2308,-1462.3,-1462.3\t0/1:22:13:480:9,0:347,0:-96.9577,0.0,-140.907,-100.871,-143.616,-244.109\t0/0:31:31:1216:0,0:0,0:0.0,-9.33193,-357.713,-9.33193,-357.713,-357.713\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_output5.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_output5.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,98 @@\n+##fileformat=VCFv4.2\n+##FILTER=<ID=PASS,Description="All filters passed">\n+##fileDate=20190323\n+##source=freeBayes v1.2.0-dirty\n+##reference=reference/ref.fa\n+##contig=<ID=Chromosome,length=4411532>\n+##phasing=none\n+##commandline="freebayes -p 2 -P 0 -C 10 --min-repeat-entropy 1.5 --strict-vcf -q 13 -m 60 --min-coverage 10 -F 0.05 -f reference/ref.fa snps.bam --region Chromosome:0-1495044"\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Count of full observations of the reference haplotype.">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Count of full observations of this alternate haplotype.">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">\n+##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count">\n+##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations">\n+##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count">\n+##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations">\n+##bcftools_viewVersion=1.9+htslib-1.9\n+##bcftools_viewCommand=view --include \'FMT/GT="1/1" && QUAL>=100.0 && FMT/DP>=10 && (FMT/AO)/(FMT/DP)>=0.9\' snps.raw.vcf; Date=Sat Mar 23 06:45:26 2019\n+##bcftools_annotateVersion=1.9+htslib-1.9\n+##bcftools_annotateCommand=annotate --remove ^INFO/TYPE,^INFO/DP,^INFO/RO,^INFO/AO,^INFO/AB,^FORMAT/GT,^FORMAT/DP,^FORMAT/RO,^FORMAT/AO,^FORMAT/QR,^FORMAT/QA,^FORMAT/GL; Date=Sat Mar 23 06:45:26 2019\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tout\n+Chromosome\t1849\t.\tC\tA\t3412.24\t.\tAB=0.0;AO=110;DP=110;QA=3850;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:0:0:110:3850:-346.644,-33.1133,0.0\n+Chromosome\t1977\t.\tA\tG\t3234.43\t.\tAB=0.0;AO=106;DP=106;QA=3704;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3704:-333.508,-31.9092,0.0\n+Chromosome\t4013\t.\tT\tC\t3965.91\t.\tAB=0.0;AO=125;DP=125;QA=4448;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:125:0:0:125:4448:-400.411,-37.6288,0.0\n+Chromosome\t7362\t.\tG\tC\t4009.71\t.\tAB=0.0;AO=126;DP=126;QA=4518;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4518:-406.711,-37.9298,0.0\n+Chromosome\t9304\t.\tG\tA\t4222.23\t.\tAB=0.0;AO=136;DP=136;QA=4764;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:136:0:0:136:4764:-428.865,-40.9401,0.0\n+Chromosome\t11820\t.\tC\tG\t2252.54\t.\tAB=0.0;AO=74;DP=74;QA=2662;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:74:0:0:74:2662:-239.791,-22.2762,0.0\n+Chromosome\t11879\t.\tA\tG\t1815.99\t.\tAB=0.0;AO=63;DP=63;QA=2212;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:63:0:0:63:2212:-199.306,-18.9649,0.0\n+Chromosome\t14785\t.\tT\tC\t4342.4\t.\tAB=0.0;AO=139;DP=139;QA=4874;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:139:0:0:139:4874:-438.763,-41.8432,0.0\n+Chromosome\t14861\t.\tG\tT\t4237.79\t.\tAB=0.0;AO=133;DP=135;QA=4758;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:135:0:0:133:4758:-427.969,-40.037,0.0\n+Chromosome\t15117\t.\tC\tG\t3298.26\t.\tAB=0.0;AO=106;DP=106;QA=3708;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3708:-333.903,-31.9092,0.0\n+Chromosome\t15890\t.\tG\tA\t3349.13\t.\tAB=0.0;AO=116;DP=117;QA=3770;QR=0;RO=0;TY'..b'0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2358:-212.453,-23.4803,0.0\n+Chromosome\t105139\t.\tC\tA\t3418.74\t.\tAB=0.0;AO=109;DP=110;QA=3888;QR=38;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:1:38:109:3888:-346.257,-29.316,0.0\n+Chromosome\t105736\t.\tT\tC\t1805.18\t.\tAB=0.0;AO=61;DP=61;QA=2101;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:61:0:0:61:2101:-189.335,-18.3628,0.0\n+Chromosome\t116000\t.\tT\tG\t3196.37\t.\tAB=0.0;AO=105;DP=105;QA=3605;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3605:-324.628,-31.6082,0.0\n+Chromosome\t122109\t.\tA\tG\t3324.29\t.\tAB=0.0;AO=111;DP=111;QA=3735;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:111:0:0:111:3735:-336.329,-33.4143,0.0\n+Chromosome\t123454\t.\tC\tT\t4362.28\t.\tAB=0.0;AO=136;DP=137;QA=4894;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:136:4894:-440.321,-40.9401,0.0\n+Chromosome\t123520\t.\tT\tC\t3793.13\t.\tAB=0.0;AO=121;DP=121;QA=4262;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:121:0:0:121:4262:-383.682,-36.4246,0.0\n+Chromosome\t125711\t.\tGGTT\tG\t3140.7\t.\tAB=0.0;AO=105;DP=105;QA=3531;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3531:-317.98,-31.6082,0.0\n+Chromosome\t125830\t.\tG\tGA\t2079.98\t.\tAB=0.0;AO=69;DP=72;QA=2347;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:69:2347:-211.164,-20.7711,0.0\n+Chromosome\t131174\t.\tT\tTG\t2854.04\t.\tAB=0.0;AO=97;DP=99;QA=3213;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:99:0:0:97:3213:-288.972,-29.1999,0.0\n+Chromosome\t133839\t.\tC\tT\t2457.55\t.\tAB=0.0;AO=78;DP=78;QA=2802;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2802:-252.374,-23.4803,0.0\n+Chromosome\t134024\t.\tT\tC\t2242.53\t.\tAB=0.0;AO=72;DP=72;QA=2543;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2543:-229.099,-21.6742,0.0\n+Chromosome\t138419\t.\tG\tA\t4166.36\t.\tAB=0.0;AO=132;DP=132;QA=4683;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:132:0:0:132:4683:-421.582,-39.736,0.0\n+Chromosome\t139297\t.\tG\tT\t3706.81\t.\tAB=0.0;AO=120;DP=120;QA=4165;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:120:0:0:120:4165:-374.978,-36.1236,0.0\n+Chromosome\t143207\t.\tT\tC\t2180.95\t.\tAB=0.0;AO=72;DP=72;QA=2523;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2523:-227.3,-21.6742,0.0\n+Chromosome\t146087\t.\tT\tC\t4315.28\t.\tAB=0.0;AO=137;DP=137;QA=4844;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:137:4844:-436.07,-41.2411,0.0\n+Chromosome\t147262\t.\tG\tT\t3766.49\t.\tAB=0.0;AO=122;DP=122;QA=4228;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:122:0:0:122:4228:-380.649,-36.7257,0.0\n+Chromosome\t154283\t.\tT\tC\t4403.08\t.\tAB=0.0;AO=141;DP=141;QA=4941;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:141:0:0:141:4941:-444.791,-42.4452,0.0\n+Chromosome\t154990\t.\tG\tT\t4207.92\t.\tAB=0.0;AO=142;DP=143;QA=4724;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:143:0:0:142:4724:-424.969,-42.7463,0.0\n+Chromosome\t162151\t.\tGT\tG\t2208.67\t.\tAB=0.0;AO=81;DP=84;QA=2524;QR=0;RO=0;TYPE=del\tGT:DP:RO:QR:AO:QA:GL\t1/1:84:0:0:81:2524:-226.95,-24.3834,0.0\n+Chromosome\t163940\t.\tA\tG\t2507.97\t.\tAB=0.0;AO=80;DP=80;QA=2839;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:80:0:0:80:2839:-255.719,-24.0824,0.0\n+Chromosome\t166253\t.\tA\tC\t3141.13\t.\tAB=0.0;AO=102;DP=102;QA=3586;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:102:0:0:102:3586:-322.902,-30.7051,0.0\n+Chromosome\t177857\t.\tG\tA\t2984.02\t.\tAB=0.0;AO=98;DP=98;QA=3389;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:98:0:0:98:3389:-305.192,-29.5009,0.0\n+Chromosome\t188800\t.\tT\tC\t1887.67\t.\tAB=0.0;AO=64;DP=64;QA=2217;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:64:0:0:64:2217:-199.772,-19.2659,0.0\n+Chromosome\t190816\t.\tA\tC\t1715.49\t.\tAB=0.0;AO=57;DP=57;QA=2026;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:57:0:0:57:2026:-182.579,-17.1587,0.0\n+Chromosome\t194305\t.\tC\tCGG\t1602.78\t.\tAB=0.0;AO=58;DP=59;QA=1889;QR=0;RO=0;TYPE=ins\tGT:DP:RO:QR:AO:QA:GL\t1/1:59:0:0:58:1889:-169.924,-17.4597,0.0\n+Chromosome\t3750185\t.\tCGAC\tGGTG\t1102.73\t.\tAB=0.0;AO=36;DP=36;QA=1255;QR=0;RO=0;TYPE=complex\tGT:DP:RO:QR:AO:QA:GL\t1/1:36:0:0:36:1255:-113.24,-10.8371,0.0\n+Chromosome\t3750193\t.\tG\tA\t1198.75\t.\tAB=0.0;AO=40;DP=40;QA=1367;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:40:0:0:40:1367:-123.307,-12.0412,0.0\n'
b
diff -r 000000000000 -r 3b1e7c170b10 test-data/test_output6.vcf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test_output6.vcf Thu Oct 10 17:59:02 2019 -0400
b
b'@@ -0,0 +1,92 @@\n+##fileformat=VCFv4.2\n+##FILTER=<ID=PASS,Description="All filters passed">\n+##fileDate=20190323\n+##source=freeBayes v1.2.0-dirty\n+##reference=reference/ref.fa\n+##contig=<ID=Chromosome,length=4411532>\n+##phasing=none\n+##commandline="freebayes -p 2 -P 0 -C 10 --min-repeat-entropy 1.5 --strict-vcf -q 13 -m 60 --min-coverage 10 -F 0.05 -f reference/ref.fa snps.bam --region Chromosome:0-1495044"\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus">\n+##INFO=<ID=RO,Number=1,Type=Integer,Description="Count of full observations of the reference haplotype.">\n+##INFO=<ID=AO,Number=A,Type=Integer,Description="Count of full observations of this alternate haplotype.">\n+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">\n+##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred">\n+##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">\n+##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">\n+##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count">\n+##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations">\n+##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count">\n+##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations">\n+##bcftools_viewVersion=1.9+htslib-1.9\n+##bcftools_viewCommand=view --include \'FMT/GT="1/1" && QUAL>=100.0 && FMT/DP>=10 && (FMT/AO)/(FMT/DP)>=0.9\' snps.raw.vcf; Date=Sat Mar 23 06:45:26 2019\n+##bcftools_annotateVersion=1.9+htslib-1.9\n+##bcftools_annotateCommand=annotate --remove ^INFO/TYPE,^INFO/DP,^INFO/RO,^INFO/AO,^INFO/AB,^FORMAT/GT,^FORMAT/DP,^FORMAT/RO,^FORMAT/AO,^FORMAT/QR,^FORMAT/QA,^FORMAT/GL; Date=Sat Mar 23 06:45:26 2019\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tout\n+Chromosome\t1849\t.\tC\tA\t3412.24\t.\tAB=0.0;AO=110;DP=110;QA=3850;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:0:0:110:3850:-346.644,-33.1133,0.0\n+Chromosome\t1977\t.\tA\tG\t3234.43\t.\tAB=0.0;AO=106;DP=106;QA=3704;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3704:-333.508,-31.9092,0.0\n+Chromosome\t4013\t.\tT\tC\t3965.91\t.\tAB=0.0;AO=125;DP=125;QA=4448;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:125:0:0:125:4448:-400.411,-37.6288,0.0\n+Chromosome\t7362\t.\tG\tC\t4009.71\t.\tAB=0.0;AO=126;DP=126;QA=4518;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4518:-406.711,-37.9298,0.0\n+Chromosome\t9304\t.\tG\tA\t4222.23\t.\tAB=0.0;AO=136;DP=136;QA=4764;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:136:0:0:136:4764:-428.865,-40.9401,0.0\n+Chromosome\t11820\t.\tC\tG\t2252.54\t.\tAB=0.0;AO=74;DP=74;QA=2662;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:74:0:0:74:2662:-239.791,-22.2762,0.0\n+Chromosome\t11879\t.\tA\tG\t1815.99\t.\tAB=0.0;AO=63;DP=63;QA=2212;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:63:0:0:63:2212:-199.306,-18.9649,0.0\n+Chromosome\t14785\t.\tT\tC\t4342.4\t.\tAB=0.0;AO=139;DP=139;QA=4874;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:139:0:0:139:4874:-438.763,-41.8432,0.0\n+Chromosome\t14861\t.\tG\tT\t4237.79\t.\tAB=0.0;AO=133;DP=135;QA=4758;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:135:0:0:133:4758:-427.969,-40.037,0.0\n+Chromosome\t15117\t.\tC\tG\t3298.26\t.\tAB=0.0;AO=106;DP=106;QA=3708;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:106:0:0:106:3708:-333.903,-31.9092,0.0\n+Chromosome\t15890\t.\tG\tA\t3349.13\t.\tAB=0.0;AO=116;DP=117;QA=3770;QR=0;RO=0;TY'..b'P=126;QA=4382;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4382:-394.523,-37.9298,0.0\n+Chromosome\t75233\t.\tC\tA\t1903.61\t.\tAB=0.0;AO=64;DP=64;QA=2172;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:64:0:0:64:2172:-195.723,-19.2659,0.0\n+Chromosome\t75940\t.\tG\tC\t2674.83\t.\tAB=0.0;AO=89;DP=89;QA=3048;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:89:0:0:89:3048:-274.519,-26.7917,0.0\n+Chromosome\t87468\t.\tC\tT\t4061.4\t.\tAB=0.0;AO=126;DP=126;QA=4584;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:126:0:0:126:4584:-412.628,-37.9298,0.0\n+Chromosome\t92199\t.\tT\tG\t686.38\t.\tAB=0.0;AO=23;DP=23;QA=799;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:23:0:0:23:799:-72.2155,-6.92369,0.0\n+Chromosome\t94388\t.\tG\tA\t2922.87\t.\tAB=0.0;AO=95;DP=95;QA=3292;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:95:0:0:95:3292:-296.486,-28.5979,0.0\n+Chromosome\t105139\t.\tC\tA\t3418.74\t.\tAB=0.0;AO=109;DP=110;QA=3888;QR=38;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:110:1:38:109:3888:-346.257,-29.316,0.0\n+Chromosome\t105736\t.\tT\tC\t1805.18\t.\tAB=0.0;AO=61;DP=61;QA=2101;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:61:0:0:61:2101:-189.335,-18.3628,0.0\n+Chromosome\t116000\t.\tT\tG\t3196.37\t.\tAB=0.0;AO=105;DP=105;QA=3605;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:105:0:0:105:3605:-324.628,-31.6082,0.0\n+Chromosome\t122109\t.\tA\tG\t3324.29\t.\tAB=0.0;AO=111;DP=111;QA=3735;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:111:0:0:111:3735:-336.329,-33.4143,0.0\n+Chromosome\t123454\t.\tC\tT\t4362.28\t.\tAB=0.0;AO=136;DP=137;QA=4894;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:136:4894:-440.321,-40.9401,0.0\n+Chromosome\t123520\t.\tT\tC\t3793.13\t.\tAB=0.0;AO=121;DP=121;QA=4262;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:121:0:0:121:4262:-383.682,-36.4246,0.0\n+Chromosome\t133839\t.\tC\tT\t2457.55\t.\tAB=0.0;AO=78;DP=78;QA=2802;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:78:0:0:78:2802:-252.374,-23.4803,0.0\n+Chromosome\t134024\t.\tT\tC\t2242.53\t.\tAB=0.0;AO=72;DP=72;QA=2543;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2543:-229.099,-21.6742,0.0\n+Chromosome\t138419\t.\tG\tA\t4166.36\t.\tAB=0.0;AO=132;DP=132;QA=4683;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:132:0:0:132:4683:-421.582,-39.736,0.0\n+Chromosome\t139297\t.\tG\tT\t3706.81\t.\tAB=0.0;AO=120;DP=120;QA=4165;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:120:0:0:120:4165:-374.978,-36.1236,0.0\n+Chromosome\t143207\t.\tT\tC\t2180.95\t.\tAB=0.0;AO=72;DP=72;QA=2523;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:72:0:0:72:2523:-227.3,-21.6742,0.0\n+Chromosome\t146087\t.\tT\tC\t4315.28\t.\tAB=0.0;AO=137;DP=137;QA=4844;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:137:0:0:137:4844:-436.07,-41.2411,0.0\n+Chromosome\t147262\t.\tG\tT\t3766.49\t.\tAB=0.0;AO=122;DP=122;QA=4228;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:122:0:0:122:4228:-380.649,-36.7257,0.0\n+Chromosome\t154283\t.\tT\tC\t4403.08\t.\tAB=0.0;AO=141;DP=141;QA=4941;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:141:0:0:141:4941:-444.791,-42.4452,0.0\n+Chromosome\t154990\t.\tG\tT\t4207.92\t.\tAB=0.0;AO=142;DP=143;QA=4724;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:143:0:0:142:4724:-424.969,-42.7463,0.0\n+Chromosome\t163940\t.\tA\tG\t2507.97\t.\tAB=0.0;AO=80;DP=80;QA=2839;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:80:0:0:80:2839:-255.719,-24.0824,0.0\n+Chromosome\t166253\t.\tA\tC\t3141.13\t.\tAB=0.0;AO=102;DP=102;QA=3586;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:102:0:0:102:3586:-322.902,-30.7051,0.0\n+Chromosome\t177857\t.\tG\tA\t2984.02\t.\tAB=0.0;AO=98;DP=98;QA=3389;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:98:0:0:98:3389:-305.192,-29.5009,0.0\n+Chromosome\t188800\t.\tT\tC\t1887.67\t.\tAB=0.0;AO=64;DP=64;QA=2217;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:64:0:0:64:2217:-199.772,-19.2659,0.0\n+Chromosome\t190816\t.\tA\tC\t1715.49\t.\tAB=0.0;AO=57;DP=57;QA=2026;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:57:0:0:57:2026:-182.579,-17.1587,0.0\n+Chromosome\t2738274\t.\tA\tC\t511.15\t.\tAB=0.0;AO=18;DP=19;QA=633;QR=35;RO=1;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:19:1:35:18:633:-53.7923,-2.22094,0.0\n+Chromosome\t3750193\t.\tG\tA\t1198.75\t.\tAB=0.0;AO=40;DP=40;QA=1367;QR=0;RO=0;TYPE=snp\tGT:DP:RO:QR:AO:QA:GL\t1/1:40:0:0:40:1367:-123.307,-12.0412,0.0\n'