[ { "name": "BWT2-Pic-MarkDup-GatkRealign-BCFmpileup", "docker_name": "bwt2-pic-markdup-gatkrealign-bcfmpileup", "description": "SNP calling", "version": "0.0.1", "author": "MBB", "options": [ { "name": "results_dir", "type": "output_dir", "value": "\/Results", "label": "Results directory: ", "volumes": [ { "Results": "\/Results" } ] } ], "steps_in": [ { "step_name": "indexing", "tool_name": "gatk_prepare_fasta", "rule_name": "gatk_prepare_fasta", "params": [] }, { "step_name": "mapping", "tool_name": "bowtie2", "rule_name": "bowtie2_PE", "params": [ { "input_name": "read", "origin_command": "raw_reads", "origin_name": "read", "origin_step": "input" }, { "input_name": "read2", "origin_command": "raw_reads", "origin_name": "read2", "origin_step": "input" }, { "input_name": "index", "origin_command": "raw_bowtie2_index", "origin_name": "bowtie2_index", "origin_step": "input" } ] }, { "step_name": "bam_correction", "tool_name": "Picard_MarkDuplicates", "rule_name": "Picard_MarkDuplicates", "params": [ { "input_name": "bam_in", "origin_command": "bowtie2_PE", "origin_name": "bam", "origin_step": "mapping" } ] }, { "step_name": "bam_correction_2", "tool_name": "gatk_IndelRealigner", "rule_name": "gatk_IndelRealigner", "params": [ { "input_name": "bam", "origin_command": "Picard_MarkDuplicates", "origin_name": "sorted_bam", "origin_step": "bam_correction" }, { "input_name": "genome_fasta", "origin_command": "gatk_prepare_fasta", "origin_name": "fasta", "origin_step": "indexing" }, { "input_name": "fasta_index", "origin_command": "gatk_prepare_fasta", "origin_name": "index", "origin_step": "indexing" }, { "input_name": "sequence_dict", "origin_command": "gatk_prepare_fasta", "origin_name": "fadict", "origin_step": "indexing" } ] }, { "step_name": "format_conversion", "tool_name": "bams2Dir", "rule_name": "bams2Dir", "params": [ { "input_name": "bam", "origin_command": "gatk_IndelRealigner", "origin_name": "sorted_bam", "origin_step": "bam_correction_2" } ] }, { "step_name": "variant_calling", "tool_name": "bcftools_mpileup_and_call_onbam_dir", "rule_name": "bcftools_mpileup_and_call_onbam_dir", "params": [ { "input_name": "bamDir", "origin_command": "bams2Dir", "origin_name": "bamDir", "origin_step": "format_conversion" } ] }, { "step_name": "vcf_postprocess", "tool_name": "multiSamplesvcfparser", "rule_name": "multiSamplesvcfparser", "params": [ { "input_name": "vcf", "origin_command": "bcftools_mpileup_and_call_onbam_dir", "origin_name": "vcf", "origin_step": "variant_calling" } ] } ], "steps": [ { "title": "indexing", "name": "indexing", "tools": [ "gatk_prepare_fasta" ], "default": "gatk_prepare_fasta" }, { "title": "mapping", "name": "mapping", "tools": [ "bowtie2" ], "default": "bowtie2" }, { "title": "bam_correction", "name": "bam_correction", "tools": [ "Picard_MarkDuplicates" ], "default": "Picard_MarkDuplicates" }, { "title": "bam_correction_2", "name": "bam_correction_2", "tools": [ "gatk_IndelRealigner" ], "default": "gatk_IndelRealigner" }, { "title": "format_conversion", "name": "format_conversion", "tools": [ "bams2Dir" ], "default": "bams2Dir" }, { "title": "variant_calling", "name": "variant_calling", "tools": [ "bcftools_mpileup_and_call_onbam_dir" ], "default": "bcftools_mpileup_and_call_onbam_dir" }, { "title": "vcf_postprocess", "name": "vcf_postprocess", "tools": [ "multiSamplesvcfparser" ], "default": "multiSamplesvcfparser" } ], "input": [ "raw_contigs", "raw_reads", "raw_bowtie2_index" ], "params_equals": [ { "param_A": "variant_calling__bcftools_mpileup_and_call_onbam_dir_genome_fasta", "param_B": "indexing__gatk_prepare_fasta_genome_fasta" } ], "git": "https:\/\/gitlab.mbb.univ-montp2.fr\/khalid\/bwt2-pic-markdup-gatkrealign-bcfmpileup", "json": { "class": "GraphLinksModel", "linkFromPortIdProperty": "fromPort", "linkToPortIdProperty": "toPort", "modelData": { "position": "-272.614990234375 -499" }, "nodeDataArray": [ { "name": "reads", "text": "read", "size2": "", "category": "Data", "strokeWidth": 2, "fill": "#2ecc71", "inservices": [], "outservices": [ { "name": "o1", "type": "reads", "value": "raw_reads", "description": "", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "unknown", "version": "unknown", "key": -3, "loc": "-200 -380" }, { "name": "reads", "text": "read", "size2": "", "category": "Data", "strokeWidth": 2, "fill": "#2ecc71", "inservices": [], "outservices": [ { "name": "o1", "type": "reads", "value": "raw_reads", "description": "", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "unknown", "version": "unknown", "key": -2, "loc": "-200 -290" }, { "name": "bowtie2_index", "text": "bowtie2_index", "size2": "", "category": "Data", "strokeWidth": 2, "fill": "#2ecc71", "inservices": [], "outservices": [ { "name": "o1", "type": "bowtie2_index", "value": "raw_bowtie2_index", "description": "", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "unknown", "version": "unknown", "key": -6, "loc": "-210 -150" }, { "name": "bcftools_mpileup_and_call_onbam_dir", "text": "BCFtools mpileup and call on bams dir", "size2": "340 85", "category": "Tool", "strokeWidth": 2, "fill": "#3498db", "inservices": [ { "name": "i1", "type": "bams_dir", "value": "bamDir", "description": "A directory containing Bam files one per sample", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" }, { "name": "i2", "type": "contigs", "value": "genome_fasta", "description": "Fasta reference", "ptype": "IN", "from": "parameter", "list": false, "stroke": "#000000" } ], "outservices": [ { "name": "o1", "type": "vcf", "value": "vcf", "description": "Variant file (vcf)", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" }, { "name": "o2", "type": "txt", "value": "stats", "description": "VCF file stats", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o3", "type": "link", "value": "linkOut" } ], "description": "BCFtools is a set of utilities that manipulate variant calls in the Variant Call Format (VCF) and its binary counterpart BCF.", "version": "1.9", "key": "2295692024", "loc": "1360 130" }, { "name": "bowtie2_PE", "text": "Bowtie2 PE", "size2": "130 110", "category": "Tool", "strokeWidth": 2, "fill": "#3498db", "inservices": [ { "name": "i1", "type": "reads", "value": "read", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" }, { "name": "i2", "type": "reads", "value": "read2", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" }, { "name": "i3", "type": "bowtie2_index", "value": "index", "description": "Index files for bowtie2 alignment", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" } ], "outservices": [ { "name": "o1", "type": "bams", "value": "bam", "description": "Alignment files", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "A fast and sensitive gapped read aligner", "version": "2.4.1", "key": "6899858938", "loc": "80 -300" }, { "name": "contigs", "text": "contigs", "size2": "", "category": "Data", "strokeWidth": 2, "fill": "#2ecc71", "inservices": [], "outservices": [ { "name": "o1", "type": "contigs", "value": "raw_contigs", "description": "", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "unknown", "version": "unknown", "key": -7, "loc": "-210 -60" }, { "name": "bams2Dir", "text": "bams to bam_dir", "size2": "160 60", "category": "Tool", "strokeWidth": 2, "fill": "#3498db", "inservices": [ { "name": "i1", "type": "bams", "value": "bam", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" } ], "outservices": [ { "name": "o1", "type": "bams_dir", "value": "bamDir", "description": "A dir containg links to bam files", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "Create a Dir with symlinks to bams in input", "version": "unknown", "key": "2986529221", "loc": "1070 -170" }, { "name": "multiSamplesvcfparser", "text": "multiSamplesvcfparser", "size2": "200 60", "category": "Tool", "strokeWidth": 2, "fill": "#3498db", "inservices": [ { "name": "i1", "type": "vcf", "value": "vcf", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" } ], "outservices": [ { "name": "o1", "type": "tsv", "value": "vcf_stats", "description": "VCF stats", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "Plot VCF stats", "version": "unknown", "key": "4576542430", "loc": "1630 10" }, { "name": "Picard_MarkDuplicates", "text": "Picard Mark Duplicates", "size2": "220 110", "category": "Tool", "strokeWidth": 2, "fill": "#3498db", "inservices": [ { "name": "i1", "type": [ "bams", "sam" ], "value": "bam_in", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" } ], "outservices": [ { "name": "o1", "type": "bams", "value": "sorted_bam", "description": "Sorted bam", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" }, { "name": "o2", "type": "bai", "value": "bai", "description": "Bam index", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" }, { "name": "o3", "type": "txt", "value": "metric", "description": "Metrics", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o4", "type": "link", "value": "linkOut" } ], "description": "This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.", "version": "2.20.8", "key": "8866960901", "loc": "320 -300" }, { "name": "gatk_IndelRealigner", "text": "Gatk IndelRealigner", "size2": "185 135", "category": "Tool", "strokeWidth": 2, "fill": "#3498db", "inservices": [ { "name": "i1", "type": "bams", "value": "bam", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" }, { "name": "i2", "type": "contigs", "value": "genome_fasta", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" }, { "name": "i3", "type": "fasta_index", "value": "fasta_index", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" }, { "name": "i4", "type": "sequence_dict", "value": "sequence_dict", "description": "", "ptype": "IN", "from": "", "list": false, "stroke": "#000000" } ], "outservices": [ { "name": "o1", "type": "bams", "value": "sorted_bam", "description": "Bam with indels realigned", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o2", "type": "link", "value": "linkOut" } ], "description": "The local realignment process is designed to consume one or more BAM files and to locally realign reads such that the number of mismatching bases is minimized across all the reads.", "version": "3.6-0", "key": "2009772116", "loc": "820 -170" }, { "name": "gatk_prepare_fasta", "text": "gatk prepare fasta", "size2": "195 110", "category": "Tool", "strokeWidth": 2, "fill": "#3498db", "inservices": [ { "name": "i1", "type": "contigs", "value": "genome_fasta", "description": "", "ptype": "IN", "from": "parameter", "list": false, "stroke": "#000000" } ], "outservices": [ { "name": "o1", "type": "contigs", "value": "fasta", "description": "Reference fasta", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" }, { "name": "o2", "type": "fasta_index", "value": "index", "description": "Reference index", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" }, { "name": "o3", "type": "sequence_dict", "value": "fadict", "description": "Reference dict", "ptype": "OUT", "from": "", "list": false, "stroke": "#000000" } ], "outservices2": [ { "name": "o4", "type": "link", "value": "linkOut" } ], "description": "Prepare fasta ref for GATK", "version": "unknown", "key": "2552269906", "loc": "310 -160" } ], "linkDataArray": [ { "from": -3, "to": "6899858938", "fromPort": "raw_reads", "toPort": "read", "points": [ -142.385009765625, -378.70000000000005, -132.385009765625, -378.70000000000005, -70.2647705078125, -378.70000000000005, -70.2647705078125, -321.67783203125, -8.14453125, -321.67783203125, 1.85546875, -321.67783203125 ] }, { "from": -2, "to": "6899858938", "fromPort": "raw_reads", "toPort": "read2", "points": [ -142.385009765625, -288.70000000000005, -132.385009765625, -288.70000000000005, -70.2647705078125, -288.70000000000005, -70.2647705078125, -298.6, -8.14453125, -298.6, 1.85546875, -298.6 ] }, { "from": -6, "to": "6899858938", "fromPort": "raw_bowtie2_index", "toPort": "index", "points": [ -152.385009765625, -148.7, -142.385009765625, -148.7, -75.2647705078125, -148.7, -75.2647705078125, -275.52216796874995, -8.14453125, -275.52216796874995, 1.85546875, -275.52216796874995 ] }, { "from": -7, "to": "2295692024", "fromPort": "raw_contigs", "toPort": "genome_fasta", "points": [ -152.385009765625, -55.853694661458334, -142.385009765625, -55.853694661458334, 512.2352294921875, -55.853694661458334, 512.2352294921875, 144.188916015625, 1166.85546875, 144.188916015625, 1176.85546875, 144.188916015625 ] }, { "from": "2986529221", "to": "2295692024", "fromPort": "bamDir", "toPort": "bamDir", "points": [ 1163.14453125, -166.1, 1173.14453125, -166.1, 1173.14453125, -26.25, 1166.85546875, -26.25, 1166.85546875, 121.111083984375, 1176.85546875, 121.111083984375 ] }, { "from": "2295692024", "to": "4576542430", "fromPort": "vcf", "toPort": "vcf", "points": [ 1543.14453125, 121.111083984375, 1553.14453125, 121.111083984375, 1553.14453125, 63.75, 1506.85546875, 63.75, 1506.85546875, 13.900000000000007, 1516.85546875, 13.900000000000007 ] }, { "from": "6899858938", "to": "8866960901", "fromPort": "bam", "toPort": "bam_in", "points": [ 158.14453125, -298.6, 168.14453125, -298.6, 177.5, -298.6, 177.5, -298.6, 186.85546875, -298.6, 196.85546875, -298.6 ] }, { "from": "8866960901", "to": "2009772116", "fromPort": "sorted_bam", "toPort": "bam", "points": [ 443.14453125, -321.67783203125, 453.14453125, -321.67783203125, 578.75, -321.67783203125, 578.75, -204.46674804687498, 704.35546875, -204.46674804687498, 714.35546875, -204.46674804687498 ] }, { "from": -7, "to": "2552269906", "fromPort": "raw_contigs", "toPort": "genome_fasta", "points": [ -152.385009765625, -61.546305338541664, -142.385009765625, -61.546305338541664, 23.4852294921875, -61.546305338541664, 23.4852294921875, -158.6, 189.35546875, -158.6, 199.35546875, -158.6 ] }, { "from": "2552269906", "to": "2009772116", "fromPort": "fasta", "toPort": "genome_fasta", "points": [ 420.64453125, -181.67783203125, 430.64453125, -181.67783203125, 567.5, -181.67783203125, 567.5, -181.38891601562497, 704.35546875, -181.38891601562497, 714.35546875, -181.38891601562497 ] }, { "from": "2552269906", "to": "2009772116", "fromPort": "index", "toPort": "fasta_index", "points": [ 420.64453125, -158.6, 430.64453125, -158.6, 567.5, -158.6, 567.5, -158.311083984375, 704.35546875, -158.311083984375, 714.35546875, -158.311083984375 ] }, { "from": "2552269906", "to": "2009772116", "fromPort": "fadict", "toPort": "sequence_dict", "points": [ 420.64453125, -135.52216796875, 430.64453125, -135.52216796875, 567.5, -135.52216796875, 567.5, -135.23325195312498, 704.35546875, -135.23325195312498, 714.35546875, -135.23325195312498 ] }, { "from": "2009772116", "to": "2986529221", "fromPort": "sorted_bam", "toPort": "bam", "points": [ 925.64453125, -169.85, 935.64453125, -169.85, 951.25, -169.85, 951.25, -166.1, 966.85546875, -166.1, 976.85546875, -166.1 ] } ], "version": 2 }, "yaml": "{\nname: \"BWT2-Pic-MarkDup-GatkRealign-BCFmpileup\",\ndocker_name: \"bwt2-pic-markdup-gatkrealign-bcfmpileup\",\ndescription: \"SNP calling\",\nversion: \"0.0.1\",\nauthor: \"MBB\",\noptions: [\n {\n name: \"results_dir\",\n type: \"output_dir\",\n value: \"\/Results\",\n label: \"Results directory: \",\n volumes: [Results: \"\/Results\"]\n },\n],\nsteps_in: [\n{ step_name: \"indexing\", tool_name: \"gatk_prepare_fasta\", rule_name: \"gatk_prepare_fasta\",\n params: [\n #{ input_name: genome_fasta, origin_command: raw_contigs, origin_name: contigs, origin_step: input}, # This input will be read from the params file (see documentation)\n ]\n},\n{ step_name: \"mapping\", tool_name: \"bowtie2\", rule_name: \"bowtie2_PE\",\n params: [\n { input_name: read, origin_command: raw_reads, origin_name: read, origin_step: input},\n { input_name: read2, origin_command: raw_reads, origin_name: read2, origin_step: input},\n { input_name: index, origin_command: raw_bowtie2_index, origin_name: bowtie2_index, origin_step: input},\n ]\n},\n{ step_name: \"bam_correction\", tool_name: \"Picard_MarkDuplicates\", rule_name: \"Picard_MarkDuplicates\",\n params: [\n { input_name: bam_in, origin_command: bowtie2_PE, origin_name: bam, origin_step: mapping},\n ]\n},\n{ step_name: \"bam_correction_2\", tool_name: \"gatk_IndelRealigner\", rule_name: \"gatk_IndelRealigner\",\n params: [\n { input_name: bam, origin_command: Picard_MarkDuplicates, origin_name: sorted_bam, origin_step: bam_correction},\n { input_name: genome_fasta, origin_command: gatk_prepare_fasta, origin_name: fasta, origin_step: indexing},\n { input_name: fasta_index, origin_command: gatk_prepare_fasta, origin_name: index, origin_step: indexing},\n { input_name: sequence_dict, origin_command: gatk_prepare_fasta, origin_name: fadict, origin_step: indexing},\n ]\n},\n{ step_name: \"format_conversion\", tool_name: \"bams2Dir\", rule_name: \"bams2Dir\",\n params: [\n { input_name: bam, origin_command: gatk_IndelRealigner, origin_name: sorted_bam, origin_step: bam_correction_2},\n ]\n},\n{ step_name: \"variant_calling\", tool_name: \"bcftools_mpileup_and_call_onbam_dir\", rule_name: \"bcftools_mpileup_and_call_onbam_dir\",\n params: [\n { input_name: bamDir, origin_command: bams2Dir, origin_name: bamDir, origin_step: format_conversion},\n #{ input_name: genome_fasta, origin_command: raw_contigs, origin_name: contigs, origin_step: input}, # This input will be read from the params file (see documentation)\n ]\n},\n{ step_name: \"vcf_postprocess\", tool_name: \"multiSamplesvcfparser\", rule_name: \"multiSamplesvcfparser\",\n params: [\n { input_name: vcf, origin_command: bcftools_mpileup_and_call_onbam_dir, origin_name: vcf, origin_step: variant_calling},\n ]\n},\n],\nsteps: [\n { title: \"indexing\", name: \"indexing\", tools: [gatk_prepare_fasta], default: \"gatk_prepare_fasta\" },\n { title: \"mapping\", name: \"mapping\", tools: [bowtie2], default: \"bowtie2\" },\n { title: \"bam_correction\", name: \"bam_correction\", tools: [Picard_MarkDuplicates], default: \"Picard_MarkDuplicates\" },\n { title: \"bam_correction_2\", name: \"bam_correction_2\", tools: [gatk_IndelRealigner], default: \"gatk_IndelRealigner\" },\n { title: \"format_conversion\", name: \"format_conversion\", tools: [bams2Dir], default: \"bams2Dir\" },\n { title: \"variant_calling\", name: \"variant_calling\", tools: [bcftools_mpileup_and_call_onbam_dir], default: \"bcftools_mpileup_and_call_onbam_dir\" },\n { title: \"vcf_postprocess\", name: \"vcf_postprocess\", tools: [multiSamplesvcfparser], default: \"multiSamplesvcfparser\" },\n],\ninput: [\"raw_contigs\",\"raw_reads\",\"raw_bowtie2_index\",],\nparams_equals: [\n { param_A: \"variant_calling__bcftools_mpileup_and_call_onbam_dir_genome_fasta\", param_B: \"indexing__gatk_prepare_fasta_genome_fasta\"},\n\n]\n}\n" } ]