Commit 53905977 authored by khalid's avatar khalid
Browse files

Put new WF in separate dirs

parent 12d034b9
{
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: [
#{ 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)
]
},
{ 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},
#{ 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)
]
},
{ 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"},
]
}
{"class":"GraphLinksModel","linkFromPortIdProperty":"fromPort","linkToPortIdProperty":"toPort","modelData":{"position":"-549 -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":"-390 -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":"-410 -280"},{"name":"dada2_assign_taxonomy","text":"dada2_assign_taxonomy","size2":"200 85","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"fasta_file","value":"seqs","description":"","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"tsv","value":"abundance","description":"per sample OTU abundance ","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"tsv","value":"taxa_bootstrap","description":"Bootstap support table","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"taxa_assigment","description":"Matrix with each row corresponding to an input sequence, and each column corresponding to a taxonomic level","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"2959189882","loc":"940 -250"},{"name":"dada2_Err_Derep_makeSequenceTable_PE","text":"dada2_Err_Derep_makeSequenceTable PE","size2":"265 135","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"}],"outservices":[{"name":"o1","type":"fasta_file","value":"ASVseqfile","description":"amplicon sequence variants in fasta ","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"ASVtable","description":"number of times each exact amplicon sequence was observed in each sample","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o3","type":"png","value":"errRplotF","description":"error profile plot forward","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o4","type":"png","value":"errRplotR","description":"error profile plot reverse","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o5","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"0751264220","loc":"540 -220"},{"name":"dada2_filter_trim_PE","text":"dada2_filter_trim PE","size2":"185 85","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"}],"outservices":[{"name":"o1","type":"fq.gz","value":"filtFs","description":"List of filtered forward reads","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"fq.gz","value":"filtRs","description":"List of filtered reverse reads","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"1259008530","loc":"90 -230"},{"name":"dada2_plotQualityProfile_PE","text":"dada2_plotQualityProfile PE","size2":"265 85","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"}],"outservices":[{"name":"o1","type":"png","value":"qualityF","description":"Quality plot forward","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"png","value":"qualityR","description":"Quality plot reverse","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"0700693146","loc":"50 -390"}],"linkDataArray":[{"from":-3,"to":"0700693146","fromPort":"raw_reads","toPort":"read","points":[-332.385009765625,-381.5463053385417,-322.385009765625,-381.5463053385417,-214.0147705078125,-381.5463053385417,-214.0147705078125,-398.888916015625,-105.64453125,-398.888916015625,-95.64453125,-398.888916015625]},{"from":-2,"to":"0700693146","fromPort":"raw_reads","toPort":"read2","points":[-352.385009765625,-281.5463053385417,-342.385009765625,-281.5463053385417,-224.0147705078125,-281.5463053385417,-224.0147705078125,-375.81108398437493,-105.64453125,-375.81108398437493,-95.64453125,-375.81108398437493]},{"from":-3,"to":"1259008530","fromPort":"raw_reads","toPort":"read","points":[-332.385009765625,-375.85369466145835,-322.385009765625,-375.85369466145835,-174.0147705078125,-375.85369466145835,-174.0147705078125,-238.888916015625,-25.64453125,-238.888916015625,-15.64453125,-238.888916015625]},{"from":-2,"to":"1259008530","fromPort":"raw_reads","toPort":"read2","points":[-352.385009765625,-275.85369466145835,-342.385009765625,-275.85369466145835,-184.0147705078125,-275.85369466145835,-184.0147705078125,-215.811083984375,-25.64453125,-215.811083984375,-15.64453125,-215.811083984375]},{"from":"1259008530","to":"0751264220","fromPort":"filtFs","toPort":"read","points":[195.64453125,-238.888916015625,205.64453125,-238.888916015625,295,-238.888916015625,295,-231.38891601562497,384.35546875,-231.38891601562497,394.35546875,-231.38891601562497]},{"from":"1259008530","to":"0751264220","fromPort":"filtRs","toPort":"read2","points":[195.64453125,-215.811083984375,205.64453125,-215.811083984375,295,-215.811083984375,295,-208.31108398437496,384.35546875,-208.31108398437496,394.35546875,-208.31108398437496]},{"from":"0751264220","to":"2959189882","fromPort":"ASVseqfile","toPort":"seqs","points":[685.64453125,-254.46674804687498,695.64453125,-254.46674804687498,756.25,-254.46674804687498,756.25,-258.888916015625,816.85546875,-258.888916015625,826.85546875,-258.888916015625]},{"from":"0751264220","to":"2959189882","fromPort":"ASVtable","toPort":"abundance","points":[685.64453125,-231.38891601562497,695.64453125,-231.38891601562497,756.25,-231.38891601562497,756.25,-235.81108398437496,816.85546875,-235.81108398437496,826.85546875,-235.81108398437496]}],"version":2}
\ No newline at end of file
{"class":"GraphLinksModel","linkFromPortIdProperty":"fromPort","linkToPortIdProperty":"toPort","modelData":{"position":"-549 -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":"-410 -370"},{"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":"-410 -280"},{"name":"dada2_assign_taxonomy","text":"dada2_assign_taxonomy","size2":"200 85","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"fasta_file","value":"seqs","description":"","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"tsv","value":"abundance","description":"per sample OTU abundance ","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"tsv","value":"taxa_bootstrap","description":"Bootstap support table","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"taxa_assigment","description":"Matrix with each row corresponding to an input sequence, and each column corresponding to a taxonomic level","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"2959189882","loc":"940 -250"},{"name":"dada2_Err_Derep_makeSequenceTable_PE","text":"dada2_Err_Derep_makeSequenceTable PE","size2":"265 135","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"}],"outservices":[{"name":"o1","type":"fasta_file","value":"ASVseqfile","description":"amplicon sequence variants in fasta ","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"ASVtable","description":"number of times each exact amplicon sequence was observed in each sample","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o3","type":"png","value":"errRplotF","description":"error profile plot forward","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o4","type":"png","value":"errRplotR","description":"error profile plot reverse","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o5","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"0751264220","loc":"440 -230"},{"name":"dada2_filter_trim_PE","text":"dada2_filter_trim PE","size2":"185 85","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"}],"outservices":[{"name":"o1","type":"fq.gz","value":"filtFs","description":"List of filtered forward reads","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"fq.gz","value":"filtRs","description":"List of filtered reverse reads","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"1259008530","loc":"90 -230"},{"name":"dada2_plotQualityProfile_PE","text":"dada2_plotQualityProfile PE","size2":"265 85","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"}],"outservices":[{"name":"o1","type":"png","value":"qualityF","description":"Quality plot forward","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"png","value":"qualityR","description":"Quality plot reverse","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Fast and accurate sample inference from amplicon data with single-nucleotide resolution","version":"1.16","key":"0700693146","loc":"50 -390"},{"name":"lulu","text":"lulu post clustering","size2":"195 85","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"tsv","value":"abundance_file","description":"OTU table with samples as columns and OTUs as rows, with unique OTU id's as row names","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"fasta_file","value":"sequence_file","description":"OTU sequences","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"tsv","value":"curated_table","description":"Table of retained OTUs","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"otu_map","description":"Table of information of which daughters were mapped to which parents OTUs","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"A r-package for distribution based post clustering curation of amplicon data.","version":"latest","key":"9489564170","loc":"980 -20"}],"linkDataArray":[{"from":-3,"to":"0700693146","fromPort":"raw_reads","toPort":"read","points":[-352.385009765625,-371.5463053385417,-342.385009765625,-371.5463053385417,-224.0147705078125,-371.5463053385417,-224.0147705078125,-398.888916015625,-105.64453125,-398.888916015625,-95.64453125,-398.888916015625]},{"from":-2,"to":"0700693146","fromPort":"raw_reads","toPort":"read2","points":[-352.385009765625,-281.5463053385417,-342.385009765625,-281.5463053385417,-224.0147705078125,-281.5463053385417,-224.0147705078125,-375.81108398437493,-105.64453125,-375.81108398437493,-95.64453125,-375.81108398437493]},{"from":-3,"to":"1259008530","fromPort":"raw_reads","toPort":"read","points":[-352.385009765625,-365.85369466145835,-342.385009765625,-365.85369466145835,-184.0147705078125,-365.85369466145835,-184.0147705078125,-238.888916015625,-25.64453125,-238.888916015625,-15.64453125,-238.888916015625]},{"from":-2,"to":"1259008530","fromPort":"raw_reads","toPort":"read2","points":[-352.385009765625,-275.85369466145835,-342.385009765625,-275.85369466145835,-184.0147705078125,-275.85369466145835,-184.0147705078125,-215.811083984375,-25.64453125,-215.811083984375,-15.64453125,-215.811083984375]},{"from":"1259008530","to":"0751264220","fromPort":"filtFs","toPort":"read","points":[195.64453125,-238.888916015625,205.64453125,-238.888916015625,245,-238.888916015625,245,-241.38891601562497,284.35546875,-241.38891601562497,294.35546875,-241.38891601562497]},{"from":"1259008530","to":"0751264220","fromPort":"filtRs","toPort":"read2","points":[195.64453125,-215.811083984375,205.64453125,-215.811083984375,245,-215.811083984375,245,-218.31108398437496,284.35546875,-218.31108398437496,294.35546875,-218.31108398437496]},{"from":"0751264220","to":"2959189882","fromPort":"ASVseqfile","toPort":"seqs","points":[585.64453125,-267.31305338541665,603.64453125,-267.31305338541665,710.25,-267.31305338541665,710.25,-258.888916015625,816.85546875,-258.888916015625,826.85546875,-258.888916015625]},{"from":"0751264220","to":"2959189882","fromPort":"ASVtable","toPort":"abundance","points":[585.64453125,-241.38891601562497,595.64453125,-241.38891601562497,706.25,-241.38891601562497,706.25,-235.81108398437496,816.85546875,-235.81108398437496,826.85546875,-235.81108398437496]},{"from":"2959189882","to":"9489564170","fromPort":"taxa_assigment","toPort":"abundance_file","points":[1053.14453125,-235.81108398437496,1063.14453125,-235.81108398437496,1063.14453125,-135,859.35546875,-135,859.35546875,-28.888916015625007,869.35546875,-28.888916015625007]},{"from":"0751264220","to":"9489564170","fromPort":"ASVseqfile","toPort":"sequence_file","points":[585.64453125,-261.6204427083333,595.64453125,-261.6204427083333,727.5,-261.6204427083333,727.5,-5.811083984375005,859.35546875,-5.811083984375005,869.35546875,-5.811083984375005]}],"version":2}
\ No newline at end of file
{
name: "Dada2",
docker_name: "dada2",
description: "My workflow",
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: "metabarcoding_3", tool_name: "dada2_filter_trim", rule_name: "dada2_filter_trim_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},
]
},
{ step_name: "metabarcoding_4", tool_name: "dada2_plotQualityProfile", rule_name: "dada2_plotQualityProfile_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},
]
},
{ step_name: "metabarcoding_2", tool_name: "dada2_Err_Derep_makeSequenceTable", rule_name: "dada2_Err_Derep_makeSequenceTable_PE",
params: [
{ input_name: read, origin_command: dada2_filter_trim_PE, origin_name: filtFs, origin_step: metabarcoding_3},
{ input_name: read2, origin_command: dada2_filter_trim_PE, origin_name: filtRs, origin_step: metabarcoding_3},
]
},
{ step_name: "metabarcoding", tool_name: "dada2_assign_taxonomy", rule_name: "dada2_assign_taxonomy",
params: [
{ input_name: seqs, origin_command: dada2_Err_Derep_makeSequenceTable_PE, origin_name: ASVseqfile, origin_step: metabarcoding_2},
{ input_name: abundance, origin_command: dada2_Err_Derep_makeSequenceTable_PE, origin_name: ASVtable, origin_step: metabarcoding_2},
]
},
{ step_name: "metabarcoding_5", tool_name: "lulu", rule_name: "lulu",
params: [
{ input_name: abundance_file, origin_command: dada2_assign_taxonomy, origin_name: taxa_assigment, origin_step: metabarcoding},
{ input_name: sequence_file, origin_command: dada2_Err_Derep_makeSequenceTable_PE, origin_name: ASVseqfile, origin_step: metabarcoding_2},
]
},
],
steps: [
{ title: "metabarcoding_3", name: "metabarcoding_3", tools: [dada2_filter_trim], default: "dada2_filter_trim" },
{ title: "metabarcoding_4", name: "metabarcoding_4", tools: [dada2_plotQualityProfile], default: "dada2_plotQualityProfile" },
{ title: "metabarcoding_2", name: "metabarcoding_2", tools: [dada2_Err_Derep_makeSequenceTable], default: "dada2_Err_Derep_makeSequenceTable" },
{ title: "metabarcoding", name: "metabarcoding", tools: [dada2_assign_taxonomy], default: "dada2_assign_taxonomy" },
{ title: "metabarcoding_5", name: "metabarcoding_5", tools: [lulu], default: "lulu" },
],
input: ["raw_reads",],
params_equals: [
]
}
{"class":"GraphLinksModel","linkFromPortIdProperty":"fromPort","linkToPortIdProperty":"toPort","modelData":{"position":"-891.556267729264 -808.5"},"nodeDataArray":[{"name":"FROGS_remove_chimera","text":"FROGS remove chimera","size2":"195 110","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"fasta_file","value":"sequence_file","description":"the sequences in fasta format","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"biom","value":"abundance_biom","description":"the abundance file","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"fasta_file","value":"non_chimera_fasta","description":"the non chimera sequences","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"biom","value":"abundance_file","description":"the abundance file with affiliation","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o3","type":"html","value":"summary","description":"summary","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o4","type":"link","value":"linkOut"}],"description":"Remove PCR chimera in each sample","version":"3.2.3","key":"4840997664","loc":"130 -30"},{"name":"FROGS_preprocess_PE","text":"FROGS_preprocess_PE","size2":"175 110","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"read_dir","value":"read_dir","description":"Directory containing the processed radtag reads","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"fasta_file","value":"sequence_file","description":"the dereplicated sequences : strictly identical sequence are represented only once","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"count_file","description":"the count of all unique sequences in each sample","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o3","type":"html","value":"summary","description":"summary","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o4","type":"link","value":"linkOut"}],"description":"Merging, Denoising and Dereplication","version":"3.2.3","key":"8026992436","loc":"-370 -30"},{"name":"FROGS_filter_OTU","text":"FROGS filter OTU","size2":"195 135","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"fasta_file","value":"sequence_file","description":"the sequences in fasta format","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"biom","value":"biom","description":"The abundance of each OTU in each sample","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"fasta_file","value":"filtered_sequences","description":"The sequences after filtering","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"biom","value":"abundance_file","description":"The abundance after filtering","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o3","type":"tsv","value":"excluded_file","description":"The list of the OTUs deleted by filters","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o4","type":"html","value":"summary","description":"The filters and the number of removed sequences","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o5","type":"link","value":"linkOut"}],"description":"Filters OTUs on several criteria","version":"3.2.3","key":"8724708950","loc":"220 -540"},{"name":"FROGS_cluster","text":"FROGS cluster","size2":"155 110","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"fasta_file","value":"sequence_file","description":"the sequences in fasta format","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"tsv","value":"count_file","description":"the count by sample for each sequence","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"fasta_file","value":"cluster_seeds","description":"The clusters representative sequences","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"biom","value":"abundance_file","description":"The abundance of each cluster in each sample","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o3","type":"tsv","value":"cluster_composition","description":"A text file representing the read composition of each cluster","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o4","type":"link","value":"linkOut"}],"description":"Single-linkage clustering on sequences","version":"3.2.3","key":"7214681101","loc":"-110 -30"},{"name":"FROGS_affiliation","text":"FROGS affiliation","size2":"185 85","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"fasta_file","value":"fasta","description":"the sequences in fasta format","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"biom","value":"biom","description":"the abundance of each OTU in each sample","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"biom","value":"abundance_file","description":"the abundance file with affiliation","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"html","value":"summary","description":"summary","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Adding taxonomic affiliation in abundance file","version":"3.2.3","key":"6242321927","loc":"620 -10"},{"name":"read_dir","text":"read_dir","size2":"","category":"Data","strokeWidth":2,"fill":"#2ecc71","inservices":[],"outservices":[{"name":"o1","type":"read_dir","value":"raw_read_dir","description":"","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o2","type":"link","value":"linkOut"}],"description":"unknown","version":"unknown","key":-9,"loc":"-600 -60"},{"name":"FROGS_filter_affiliation","text":"FROGS filter affiliation","size2":"220 160","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"fasta_file","value":"fasta","description":"The sequence file to filter","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"biom","value":"biom","description":"The abundance file to filter","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"biom","value":"biom_filtered","description":"the abundance file with filtered affiliation","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"fasta_file","value":"sequence_file","description":"the filtered sequences","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o3","type":"tsv","value":"impacted","description":"The list of the OTUs deleted or hidden or with updated blast affiliation","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o4","type":"tsv","value":"multihit","description":"The list of blast affiliations for multi-affiliated impacted OTU","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o5","type":"html","value":"summary","description":"summary","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o6","type":"link","value":"linkOut"}],"description":"Filters OTUs on several affiliation criteria","version":"3.2.3","key":"3993521995","loc":"920 -570"},{"name":"FROGS_phyloseq_stats","text":"FROGS_phyloseq_stats","size2":"175 110","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"biom","value":"biom_file","description":"The biom file contains the OTU's informations: abundance and taxonomy.","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"fasta_file","value":"otu_sequence_file","description":"OTU sequences in fasta format","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i3","type":"popmap","value":"popmap_file","description":"Path to tsv file with metatdata of samples conditions","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"tsv","value":"alpha_div","description":"detailed alpha diversity indices in each sample","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"wunifrac_div","description":"wunifrac distance matrix between samples","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Phyloseq to analyse abundance, diversity and structure","version":"3.2.3","key":"6413296569","loc":"1180 -330"},{"name":"popmap","text":"popmap","size2":"","category":"Data","strokeWidth":2,"fill":"#2ecc71","inservices":[],"outservices":[{"name":"o1","type":"popmap","value":"raw_popmap","description":"","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o2","type":"link","value":"linkOut"}],"description":"unknown","version":"unknown","key":-10,"loc":"910 -300"},{"name":"FROGS_biom_to_tsv","text":"FROGS biom2tsv","size2":"155 85","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"biom","value":"biom","description":"the abundance of each OTU in each sample","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"tsv","value":"abundance_file","description":"output file with the abundance and metadata (tsv)","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"lulu_abundance_file","description":"OTU abundance with samples as columns and OTUs as rows (for lulu)","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"Adding taxonomic affiliation in abundance file","version":"3.2.3","key":"2822907117","loc":"1240 -750"},{"name":"lulu","text":"lulu post clustering","size2":"195 85","category":"Tool","strokeWidth":2,"fill":"#3498db","inservices":[{"name":"i1","type":"tsv","value":"abundance_file","description":"OTU table with samples as columns and OTUs as rows, with unique OTU id's as row names","ptype":"IN","from":"","list":false,"stroke":"#000000"},{"name":"i2","type":"fasta_file","value":"sequence_file","description":"OTU sequences","ptype":"IN","from":"","list":false,"stroke":"#000000"}],"outservices":[{"name":"o1","type":"tsv","value":"curated_table","description":"Table of retained OTUs","ptype":"OUT","from":"","list":false,"stroke":"#000000"},{"name":"o2","type":"tsv","value":"otu_map","description":"Table of information of which daughters were mapped to which parents OTUs","ptype":"OUT","from":"","list":false,"stroke":"#000000"}],"outservices2":[{"name":"o3","type":"link","value":"linkOut"}],"description":"A r-package for distribution based post clustering curation of amplicon data.","version":"latest","key":"8356225461","loc":"1340 -550"}],"linkDataArray":[{"from":-9,"to":"8026992436","fromPort":"raw_read_dir","toPort":"read_dir","points":[-541.9458332061768,-58.7,-531.9458332061768,-58.7,-506.7354166507721,-58.7,-506.7354166507721,-28.600000000000005,-481.52500009536743,-28.600000000000005,-471.52500009536743,-28.600000000000005]},{"from":"8026992436","to":"7214681101","fromPort":"sequence_file","toPort":"sequence_file","points":[-268.47499990463257,-52.18166608810425,-258.47499990463257,-52.18166608810425,-235,-52.18166608810425,-235,-40.39083304405213,-211.52500009536743,-40.39083304405213,-201.52500009536743,-40.39083304405213]},{"from":"8026992436","to":"7214681101","fromPort":"count_file","toPort":"count_file","points":[-268.47499990463257,-28.600000000000005,-258.47499990463257,-28.600000000000005,-235,-28.600000000000005,-235,-16.809166955947877,-211.52500009536743,-16.809166955947877,-201.52500009536743,-16.809166955947877]},{"from":"7214681101","to":"4840997664","fromPort":"cluster_seeds","toPort":"sequence_file","points":[-18.47499990463257,-52.18166608810425,-8.474999904632568,-52.18166608810425,0,-52.18166608810425,0,-40.39083304405213,8.474999904632568,-40.39083304405213,18.47499990463257,-40.39083304405213]},{"from":"7214681101","to":"4840997664","fromPort":"abundance_file","toPort":"abundance_biom","points":[-18.47499990463257,-28.600000000000005,-8.474999904632568,-28.600000000000005,0,-28.600000000000005,0,-16.809166955947877,8.474999904632568,-16.809166955947877,18.47499990463257,-16.809166955947877]},{"from":"4840997664","to":"8724708950","fromPort":"non_chimera_fasta","toPort":"sequence_file","points":[240.64453125,-51.677832031250006,250.64453125,-51.677832031250006,250.64453125,-278.75,99.35546875,-278.75,99.35546875,-551.388916015625,109.35546875,-551.388916015625]},{"from":"4840997664","to":"8724708950","fromPort":"abundance_file","toPort":"biom","points":[240.64453125,-28.6,250.64453125,-28.6,250.64453125,-278.75,99.35546875,-278.75,99.35546875,-528.311083984375,109.35546875,-528.311083984375]},{"from":"8724708950","to":"6242321927","fromPort":"filtered_sequences","toPort":"fasta","points":[330.64453125,-571.6204427083334,340.64453125,-571.6204427083334,340,-571.6204427083334,340,-571.6204427083334,540,-571.6204427083334,540,-212,508,-212,508,-18.888916015625,504.35546875,-18.888916015625,514.35546875,-18.888916015625]},{"from":"8724708950","to":"6242321927","fromPort":"abundance_file","toPort":"biom","points":[330.64453125,-551.3889160156251,340.64453125,-551.3889160156251,340,-551.3889160156251,340,-551.3889160156251,540,-551.3889160156251,540,-212,508,-212,508,4.188916015624999,504.35546875,4.188916015624999,514.35546875,4.188916015624999]},{"from":"6242321927","to":"3993521995","fromPort":"abundance_file","toPort":"biom","points":[725.64453125,-18.888916015625,735.64453125,-18.888916015625,761.25,-18.888916015625,761.25,-559.561083984375,786.85546875,-559.561083984375,796.85546875,-559.561083984375]},{"from":"8724708950","to":"3993521995","fromPort":"filtered_sequences","toPort":"fasta","points":[330.64453125,-577.3130533854168,340.64453125,-577.3130533854168,563.75,-577.3130533854168,563.75,-582.638916015625,786.85546875,-582.638916015625,796.85546875,-582.638916015625]},{"from":"3993521995","to":"6413296569","fromPort":"sequence_file","toPort":"otu_sequence_file","points":[1043.14453125,-594.1778320312501,1053.14453125,-594.1778320312501,1061.25,-594.1778320312501,1061.25,-328.6,1069.35546875,-328.6,1079.35546875,-328.6]},{"from":"3993521995","to":"6413296569","fromPort":"biom_filtered","toPort":"biom_file","points":[1043.14453125,-617.2556640625,1053.14453125,-617.2556640625,1061.25,-617.2556640625,1061.25,-351.67783203125,1069.35546875,-351.67783203125,1079.35546875,-351.67783203125]},{"from":-10,"to":"6413296569","fromPort":"raw_popmap","toPort":"popmap_file","points":[967.614990234375,-298.70000000000005,977.614990234375,-298.70000000000005,1023.4852294921875,-298.70000000000005,1023.4852294921875,-305.52216796874995,1069.35546875,-305.52216796874995,1079.35546875,-305.52216796874995]},{"from":"3993521995","to":"2822907117","fromPort":"biom_filtered","toPort":"biom","points":[1043.14453125,-620.1019694010417,1053.14453125,-620.1019694010417,1096.25,-620.1019694010417,1096.25,-747.35,1139.35546875,-747.35,1149.35546875,-747.35]},{"from":"2822907117","fromPort":"abundance_file","toPort":"","points":[1308.26123046875,-758.888916015625,1298.26123046875,-758.888916015625,1274.8391716586266,-758.888916015625,1274.8391716586266,-721.3550391139429,1251.4171128485032,-721.3550391139429,1241.4171128485032,-721.3550391139429]},{"from":"2822907117","to":"8356225461","fromPort":"lulu_abundance_file","toPort":"abundance_file","points":[1330.64453125,-735.811083984375,1340.64453125,-735.811083984375,1340.64453125,-650,1219.35546875,-650,1219.35546875,-558.888916015625,1229.35546875,-558.888916015625]},{"from":"3993521995","to":"8356225461","fromPort":"sequence_file","toPort":"sequence_file","points":[1043.14453125,-597.0241373697918,1061.14453125,-597.0241373697918,1140.25,-597.0241373697918,1140.25,-535.811083984375,1219.35546875,-535.811083984375,1229.35546875,-535.811083984375]}],"version":2}
\ No newline at end of file
{
name: "Frogs",
docker_name: "frogs",
description: "Metabarcoding 16S with Frogs",
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: "FROGS_2", tool_name: "FROGS_preprocess", rule_name: "FROGS_preprocess_PE",
params: [
{ input_name: read_dir, origin_command: raw_read_dir, origin_name: read_dir, origin_step: input},
]
},
{ step_name: "FROGS_4", tool_name: "FROGS_cluster", rule_name: "FROGS_cluster",
params: [
{ input_name: sequence_file, origin_command: FROGS_preprocess_PE, origin_name: sequence_file, origin_step: FROGS_2},
{ input_name: count_file, origin_command: FROGS_preprocess_PE, origin_name: count_file, origin_step: FROGS_2},
]
},
{ step_name: "FROGS", tool_name: "FROGS_remove_chimera", rule_name: "FROGS_remove_chimera",
params: [
{ input_name: sequence_file, origin_command: FROGS_cluster, origin_name: cluster_seeds, origin_step: FROGS_4},
{ input_name: abundance_biom, origin_command: FROGS_cluster, origin_name: abundance_file, origin_step: FROGS_4},
]
},
{ step_name: "FROGS_3", tool_name: "FROGS_filter_OTU", rule_name: "FROGS_filter_OTU",
params: [
{ input_name: sequence_file, origin_command: FROGS_remove_chimera, origin_name: non_chimera_fasta, origin_step: FROGS},
{ input_name: biom, origin_command: FROGS_remove_chimera, origin_name: abundance_file, origin_step: FROGS},
]
},
{ step_name: "FROGS_5", tool_name: "FROGS_affiliation", rule_name: "FROGS_affiliation",
params: [
{ input_name: fasta, origin_command: FROGS_filter_OTU, origin_name: filtered_sequences, origin_step: FROGS_3},
{ input_name: biom, origin_command: FROGS_filter_OTU, origin_name: abundance_file, origin_step: FROGS_3},
]
},
{ step_name: "FROGS_6", tool_name: "FROGS_filter_affiliation", rule_name: "FROGS_filter_affiliation",
params: [
{ input_name: fasta, origin_command: FROGS_filter_OTU, origin_name: filtered_sequences, origin_step: FROGS_3},
{ input_name: biom, origin_command: FROGS_affiliation, origin_name: abundance_file, origin_step: FROGS_5},
]
},
{ step_name: "FROGS_8", tool_name: "FROGS_biom_to_tsv", rule_name: "FROGS_biom_to_tsv",
params: [
{ input_name: biom, origin_command: FROGS_filter_affiliation, origin_name: biom_filtered, origin_step: FROGS_6},
]
},
{ step_name: "FROGS_7", tool_name: "FROGS_phyloseq_stats", rule_name: "FROGS_phyloseq_stats",
params: [
{ input_name: biom_file, origin_command: FROGS_filter_affiliation, origin_name: biom_filtered, origin_step: FROGS_6},
{ input_name: otu_sequence_file, origin_command: FROGS_filter_affiliation, origin_name: sequence_file, origin_step: FROGS_6},
{ input_name: popmap_file, origin_command: raw_popmap, origin_name: popmap, origin_step: input},
]
},
{ step_name: "metabarcoding", tool_name: "lulu", rule_name: "lulu",
params: [
{ input_name: abundance_file, origin_command: FROGS_biom_to_tsv, origin_name: lulu_abundance_file, origin_step: FROGS_8},
{ input_name: sequence_file, origin_command: FROGS_filter_affiliation, origin_name: sequence_file, origin_step: FROGS_6},
]
},
],
steps: [
{ title: "FROGS_2", name: "FROGS_2", tools: [FROGS_preprocess], default: "FROGS_preprocess" },
{ title: "FROGS_4", name: "FROGS_4", tools: [FROGS_cluster], default: "FROGS_cluster" },
{ title: "FROGS", name: "FROGS", tools: [FROGS_remove_chimera], default: "FROGS_remove_chimera" },
{ title: "FROGS_3", name: "FROGS_3", tools: [FROGS_filter_OTU], default: "FROGS_filter_OTU" },
{ title: "FROGS_5", name: "FROGS_5", tools: [FROGS_affiliation], default: "FROGS_affiliation" },
{ title: "FROGS_6", name: "FROGS_6", tools: [FROGS_filter_affiliation], default: "FROGS_filter_affiliation" },
{ title: "FROGS_8", name: "FROGS_8", tools: [FROGS_biom_to_tsv], default: "FROGS_biom_to_tsv" },
{ title: "FROGS_7", name: "FROGS_7", tools: [FROGS_phyloseq_stats], default: "FROGS_phyloseq_stats" },
{ title: "metabarcoding", name: "metabarcoding", tools: [lulu], default: "lulu" },
],
input: ["raw_read_dir","raw_popmap",],
params_equals: [
]
}
{
name: "Megahit-FindMitos-Blast-Annotate-IGV",
docker_name: "megahit-findmitos-blast-annotate-igv",
description: "Find mitochondrial genome ",
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: "blast_2", tool_name: "makeblastdb", rule_name: "makeblastdb",
params: [
#{ 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)
]
},
{ step_name: "assembly", tool_name: "megahit", rule_name: "megahit_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},
]
},
{ step_name: "find_mito_scaffold", tool_name: "mitoz_findmitoscaf", rule_name: "mitoz_findmitoscaf",
params: [
{ input_name: fasta, origin_command: megahit_PE, origin_name: contigs, origin_step: assembly},
]
},
{ step_name: "annotation", tool_name: "mitoz_annotate", rule_name: "mitoz_annotate_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: fasta, origin_command: mitoz_findmitoscaf, origin_name: mitogenome, origin_step: find_mito_scaffold},
]
},
{ step_name: "blast", tool_name: "blastn", rule_name: "blastn",
params: [
{ input_name: query, origin_command: mitoz_findmitoscaf, origin_name: mitogenome, origin_step: find_mito_scaffold},
{ input_name: blastdb, origin_command: makeblastdb, origin_name: database, origin_step: blast_2},
]
},
{ step_name: "visualization", tool_name: "igv_visualize", rule_name: "igv_visualize",
params: [
{ input_name: genome, origin_command: mitoz_findmitoscaf, origin_name: mitogenome, origin_step: find_mito_scaffold},
{ input_name: circos_bam, origin_command: mitoz_annotate_PE, origin_name: circos_bam, origin_step: annotation},
]
},
],
steps: [
{ title: "blast_2", name: "blast_2", tools: [makeblastdb], default: "makeblastdb" },
{ title: "assembly", name: "assembly", tools: [megahit], default: "megahit" },
{ title: "find_mito_scaffold", name: "find_mito_scaffold", tools: [mitoz_findmitoscaf], default: "mitoz_findmitoscaf" },
{ title: "annotation", name: "annotation", tools: [mitoz_annotate], default: "mitoz_annotate" },
{ title: "blast", name: "blast", tools: [blastn], default: "blastn" },
{ title: "visualization", name: "visualization", tools: [igv_visualize], default: "igv_visualize" },
],
input: ["raw_contigs","raw_reads",],
params_equals: [
{ remove: blast__blastn_query},
{ remove: blast__blastn_blastdb},
]
}
{
name: "RnaSeq-Fatsp-Hisat2-Htseq-Deseq.json",
docker_name: "rnaseq-fatsp-hisat2-htseq-deseq.json",
description: "Rnaseq differential expression ",
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: "hisat2_index", rule_name: "hisat2_index",
params: [
#{ 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)
]
},
{ step_name: "quality", tool_name: "fastp", rule_name: "fastp_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},
]
},
{ step_name: "quality_2", tool_name: "fastqc", rule_name: "fastqc_PE",
params: [
{ input_name: read, origin_command: fastp_PE, origin_name: read_preprocessed, origin_step: quality},
{ input_name: read2, origin_command: fastp_PE, origin_name: read2_preprocessed, origin_step: quality},
]
},
{ step_name: "mapping", tool_name: "hisat2", rule_name: "hisat2_PE",
params: [
{ input_name: read, origin_command: fastp_PE, origin_name: read_preprocessed, origin_step: quality},
{ input_name: read2, origin_command: fastp_PE, origin_name: read_preprocessed, origin_step: quality},
{ input_name: index, origin_command: hisat2_index, origin_name: index, origin_step: indexing},
]
},
{ step_name: "quantification", tool_name: "htseq_count", rule_name: "htseq_count",
params: [
{ input_name: bam, origin_command: hisat2_PE, origin_name: bam, origin_step: mapping},
{ input_name: gff_file, origin_command: raw_gff3, origin_name: gff3, origin_step: input},
]
},
{ step_name: "differential_expression", tool_name: "deseq2", rule_name: "deseq2",
params: [
{ input_name: counts, origin_command: htseq_count, origin_name: stats, origin_step: quantification},
{ input_name: popmap_file, origin_command: raw_popmap, origin_name: popmap, origin_step: input},
]
},
],
steps: [
{ title: "indexing", name: "indexing", tools: [hisat2_index], default: "hisat2_index" },
{ title: "quality", name: "quality", tools: [fastp], default: "fastp" },
{ title: "quality_2", name: "quality_2", tools: [fastqc], default: "fastqc" },
{ title: "mapping", name: "mapping", tools: [hisat2], default: "hisat2" },
{ title: "quantification", name: "quantification", tools: [htseq_count], default: "htseq_count" },
{ title: "differential_expression", name: "differential_expression", tools: [deseq2], default: "deseq2" },
],
input: ["raw_contigs","raw_reads","raw_gff3","raw_popmap",],
params_equals: [
]
}
{
name: "Smudgplot-jellyfish",
docker_name: "smudgplot-jellyfish",
description: "Genome profiling from unassembled reads",
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: "quantification_2", tool_name: "jellyfish_count", rule_name: "jellyfish_count",
params: [
{ input_name: read, origin_command: raw_reads, origin_name: read, origin_step: input},
]
},
{ step_name: "visualization", tool_name: "jellyfish_histo", rule_name: "jellyfish_histo",
params: [
{ input_name: kmer_counts, origin_command: jellyfish_count, origin_name: kmer_counts, origin_step: quantification_2},
]
},
{ step_name: "quality", tool_name: "genomescope", rule_name: "genomescope",
params: [
{ input_name: kmer_histo, origin_command: jellyfish_histo, origin_name: kmer_histo, origin_step: visualization},
]
},
{ step_name: "quantification", tool_name: "smudgeplotJelly", rule_name: "smudgeplotJelly",
params: [
{ input_name: kmer_histo, origin_command: jellyfish_histo, origin_name: kmer_histo, origin_step: visualization},
{ input_name: jelly_db, origin_command: jellyfish_count, origin_name: kmer_counts, origin_step: quantification_2},
]
},
],
steps: [
{ title: "quantification_2", name: "quantification_2", tools: [jellyfish_count], default: "jellyfish_count" },
{ title: "visualization", name: "visualization", tools: [jellyfish_histo], default: "jellyfish_histo" },
{ title: "quality", name: "quality", tools: [genomescope], default: "genomescope" },
{ title: "quantification", name: "quantification", tools: [smudgeplotJelly], default: "smudgeplotJelly" },
],
input: ["raw_reads",],
params_equals: [
]
}
{
name: "Stacks-refMap",
docker_name: "stacks-refmap",
description: "Stacks on reference geneome",
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: "stacks_3", tool_name: "process_radtags", rule_name: "process_radtags_SE",
params: [
{ input_name: reads_dir, origin_command: raw_read_dir, origin_name: read_dir, origin_step: input},
{ input_name: tags, origin_command: raw_tsv, origin_name: tsv, origin_step: input},
]
},
{ step_name: "mapping", tool_name: "bowtie", rule_name: "bowtie_SE",
params: [
{ input_name: read, origin_command: process_radtags_SE, origin_name: reads_demultiplexed, origin_step: stacks_3},
{ input_name: index, origin_command: raw_bowtie_index, origin_name: bowtie_index, origin_step: input},
]
},