|
rliterman@29
|
1 <tool id="csp2-snp" name="CSP2 (SNP Pipeline Mode)" version="0.9.7_Dev21">
|
|
rliterman@29
|
2 <description>Run SNP Pipeline analysis on isolates using one or more references.</description>
|
|
rliterman@29
|
3 <requirements>
|
|
rliterman@29
|
4 <requirement type="package" version="24.10.1">nextflow</requirement>
|
|
rliterman@29
|
5 <requirement type="package" version="1.5.8">micromamba</requirement>
|
|
rliterman@29
|
6 </requirements>
|
|
rliterman@29
|
7 <version_command>nextflow -version</version_command>
|
|
rliterman@29
|
8 <command detect_errors="aggressive"><![CDATA[
|
|
rliterman@51
|
9 mkdir ./queries ./references;
|
|
rliterman@29
|
10
|
|
rliterman@29
|
11 if [ -n "$query_fasta" ] && [ "$query_fasta" != "None" ]; then
|
|
rliterman@29
|
12 #for query in $query_fasta:
|
|
rliterman@51
|
13 ln -sf ${query} ./queries/${query.element_identifier};
|
|
rliterman@29
|
14 #end for
|
|
rliterman@51
|
15 export QUERY_FASTA_ARG="--fasta ./queries";
|
|
rliterman@29
|
16 else
|
|
rliterman@29
|
17 export QUERY_FASTA_ARG="";
|
|
rliterman@29
|
18 fi;
|
|
rliterman@29
|
19
|
|
rliterman@29
|
20 if [ -n "$query_reads" ] && [ "$query_reads" != "None" ]; then
|
|
rliterman@29
|
21 #for query in $query_reads:
|
|
rliterman@51
|
22 ln -sf ${query} ./queries/${query.element_identifier};
|
|
rliterman@29
|
23 #end for
|
|
rliterman@51
|
24 export QUERY_READS_ARG="--reads ./queries";
|
|
rliterman@29
|
25 else
|
|
rliterman@29
|
26 export QUERY_READS_ARG="";
|
|
rliterman@29
|
27 fi;
|
|
rliterman@29
|
28
|
|
rliterman@29
|
29 if [ -n "$ref_fasta" ] && [ "$ref_fasta" != "None" ]; then
|
|
rliterman@29
|
30 #for ref in $ref_fasta:
|
|
rliterman@51
|
31 ln -sf ${ref} ./references/${ref.element_identifier};
|
|
rliterman@29
|
32 #end for
|
|
rliterman@51
|
33 export REF_FASTA_ARG="--ref_fasta ./references";
|
|
rliterman@29
|
34 else
|
|
rliterman@29
|
35 export REF_FASTA_ARG="";
|
|
rliterman@29
|
36 fi;
|
|
rliterman@29
|
37
|
|
rliterman@29
|
38 if [ -n "$ref_reads" ] && [ "$ref_reads" != "None" ]; then
|
|
rliterman@29
|
39 #for ref in $ref_reads:
|
|
rliterman@51
|
40 ln -sf ${ref} ./references/${ref.element_identifier};
|
|
rliterman@29
|
41 #end for
|
|
rliterman@51
|
42 export REF_READS_ARG="--ref_reads ./references";
|
|
rliterman@29
|
43 else
|
|
rliterman@29
|
44 export REF_READS_ARG="";
|
|
rliterman@29
|
45 fi;
|
|
rliterman@29
|
46
|
|
rliterman@29
|
47 if [ -n "$trim_name" ] && [ "$trim_name" != "None" ]; then
|
|
rliterman@29
|
48 export TRIM_ARG="--trim_name $trim_name";
|
|
rliterman@29
|
49 else
|
|
rliterman@29
|
50 export TRIM_ARG="";
|
|
rliterman@29
|
51 fi;
|
|
rliterman@29
|
52
|
|
rliterman@29
|
53 if [[ "$rescue" == "true" ]]; then
|
|
rliterman@29
|
54 export RESCUE_ARG="--rescue";
|
|
rliterman@29
|
55 else
|
|
rliterman@29
|
56 export RESCUE_ARG="";
|
|
rliterman@29
|
57 fi;
|
|
rliterman@29
|
58
|
|
rliterman@52
|
59 nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy --runmode snp \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_ARG \$TRIM_ARG \$RESCUE_ARG --readext $readext --forward $forward --reverse $reverse --ref_readext $readext --ref_forward $forward --ref_reverse $reverse --min_cov $min_cov --min_iden $min_iden --min_len $min_len --ref_edge $ref_edge --query_edge $query_edge --dwin $dwin --wsnps $wsnps --max_missing $max_missing --n_ref $n_ref --out ./CSP2_SNP_Output > Nextflow_Log.txt 2>&1 &&
|
|
rliterman@51
|
60 ls -la CSP2_SNP_Output/SNP_Analysis/* &&
|
|
rliterman@51
|
61 mkdir CSP2_Output &&
|
|
rliterman@51
|
62 cat CSP2_SNP_Output/logs/Reference_IDs.txt | while read line; do cp 'CSP2_SNP_Output/SNP_Analysis/'\$line'/CSP2_SNP_Pipeline.log' 'CSP2_Output/'\$line'_CSP2_SNP_Pipeline.log'; cp 'CSP2_SNP_Output/SNP_Analysis/'\$line'/Reference_Screening.tsv' 'CSP2_Output/'\$line'_Reference_Screening.tsv'; cp 'CSP2_SNP_Output/SNP_Analysis/'\$line'/snp_distance_matrix_preserved.tsv' 'CSP2_Output/'\$line'_snp_distance_matrix_preserved.tsv'; cp 'CSP2_SNP_Output/SNP_Analysis/'\$line'/snp_distance_pairwise_preserved.tsv' 'CSP2_Output/'\$line'_snp_distance_pairwise_preserved.tsv'; cp 'CSP2_SNP_Output/SNP_Analysis/'\$line'/snpma_preserved.fasta' 'CSP2_Output/'\$line'_snpma_preserved.fasta';done &&
|
|
rliterman@51
|
63 ls -la CSP2_Output;
|
|
rliterman@33
|
64
|
|
rliterman@34
|
65 ]]>
|
|
rliterman@29
|
66 </command>
|
|
rliterman@29
|
67 <inputs>
|
|
rliterman@29
|
68 <param name="query_fasta" type="data" format="fasta" value="" label="Query assemblies" multiple="true" optional="true" />
|
|
rliterman@29
|
69 <param name="ref_fasta" type="data" format="fasta" value="" label="Reference assemblies" multiple="true" optional="true" />
|
|
rliterman@29
|
70 <param name="query_reads" type="data" format="fastq,fastq.gz" value="" label="Query reads" multiple="true" optional="true" />
|
|
rliterman@29
|
71 <param name="ref_reads" type="data" format="fastq,fastq.gz" value="" label="Reference reads" multiple="true" optional="true" />
|
|
rliterman@29
|
72 <param name="min_cov" type="float" value="85" label="Minimum reference genome coverage to proceed with distance estimation" optional="true" />
|
|
rliterman@29
|
73 <param name="min_iden" type="float" value="99" label="Minimum alignment percent identity to detect SNPs" optional="true" />
|
|
rliterman@29
|
74 <param name="min_len" type="integer" value="500" label="Minimum alignment length to detect SNPs" optional="true" />
|
|
rliterman@29
|
75 <param name="ref_edge" type="integer" value="150" label="Prune SNPs within this many bases of reference contig edge" optional="true" />
|
|
rliterman@29
|
76 <param name="query_edge" type="integer" value="150" label="Prune SNPs within this many bases of query contig edge" optional="true" />
|
|
rliterman@29
|
77 <param name="dwin" type="text" value="1000,125,15" label="Comma-separated set of window sizes for SNP density filtration (Set to 0 to disable density filtration)" optional="true" />
|
|
rliterman@29
|
78 <param name="wsnps" type="text" value="3,2,1" label="Comma-separated list of maximum SNP counts per density window" optional="true" />
|
|
rliterman@29
|
79 <param name="readext" type="text" value="fastq.gz" label="Read extension format (e.g., fastq.gz)" optional="true" />
|
|
rliterman@29
|
80 <param name="forward" type="text" value="_1.fastq.gz" label="Forward read suffix (e.g. _1.fastq.gz)" optional="true" />
|
|
rliterman@29
|
81 <param name="reverse" type="text" value="_2.fastq.gz" label="Forward read suffix (e.g. _2.fastq.gz)" optional="true" />
|
|
rliterman@29
|
82 <param name="trim_name" type="text" value="" label="Text to remove from all file names (e.g., _contigs_skesa)" optional="true" />
|
|
rliterman@29
|
83 <param name="rescue" type="boolean" value="false" label="Enable SNP edge rescue mode" optional="true" />
|
|
rliterman@29
|
84 <param name="max_missing" type="float" value="50" label="Maximum percent of isolates allowed to have missing data to retain a SNP" optional="true" />
|
|
rliterman@52
|
85 <param name="n_ref" type="integer" value="1" label="Number of reference genomes to select" optional="true" />
|
|
rliterman@52
|
86
|
|
rliterman@29
|
87 </inputs>
|
|
rliterman@29
|
88 <outputs>
|
|
rliterman@34
|
89 <data name="isolate_data" format="tabular" label="Isolate Data" from_work_dir="CSP2_SNP_Output/Isolate_Data.tsv" />
|
|
rliterman@29
|
90 <data name="raw_mummer" format="tabular" label="Raw MUMmer Output" from_work_dir="CSP2_SNP_Output/Raw_MUMmer_Summary.tsv" />
|
|
rliterman@51
|
91
|
|
rliterman@51
|
92 <collection name="csp2_logs" type='list' label="CSP2 Log">
|
|
rliterman@51
|
93 <discover_datasets pattern="(?P<designation>.+)_CSP2_SNP_Pipeline\.log" directory="CSP2_Output" format='txt'/>
|
|
rliterman@51
|
94 </collection>
|
|
rliterman@51
|
95 <collection name="csp2_alignments" type='list' label="CSP2 Alignment">
|
|
rliterman@51
|
96 <discover_datasets pattern="(?P<designation>.+)_snpma_preserved\.fasta" directory="CSP2_Output" format='fasta'/>
|
|
rliterman@51
|
97 </collection>
|
|
rliterman@51
|
98 <collection name="csp2_matrices" type='list' label="CSP2 Matrices">
|
|
rliterman@51
|
99 <discover_datasets pattern="(?P<designation>.+)_snp_distance_matrix_preserved\.tsv" directory="CSP2_Output" format='tabular'/>
|
|
rliterman@51
|
100 </collection>
|
|
rliterman@51
|
101 <collection name="csp2_pairwise" type='list' label="CSP2 Pairwise Distances">
|
|
rliterman@51
|
102 <discover_datasets pattern="(?P<designation>.+)_snp_distance_pairwise_preserved\.tsv" directory="CSP2_Output" format='tabular'/>
|
|
rliterman@51
|
103 </collection>
|
|
rliterman@51
|
104 <collection name="csp2_ref_screening" type='list' label="CSP2 Reference Screening">
|
|
rliterman@51
|
105 <discover_datasets pattern="(?P<designation>.+)_Reference_Screening\.tsv" directory="CSP2_Output" format='tabular'/>
|
|
rliterman@37
|
106 </collection>
|
|
rliterman@29
|
107 </outputs>
|
|
rliterman@29
|
108 <tests>
|
|
rliterman@29
|
109 <test>
|
|
rliterman@29
|
110 <param name="query_fasta">
|
|
rliterman@29
|
111 <collection type="list">
|
|
rliterman@29
|
112 <element name="Sample_A" value="assemblies/Sample_A.fasta" />
|
|
rliterman@29
|
113 <element name="Sample_B" value="assemblies/Sample_B.fasta" />
|
|
rliterman@29
|
114 <element name="Sample_C" value="assemblies/Sample_C.fasta" />
|
|
rliterman@29
|
115 <element name="Sample_D" value="assemblies/Sample_D.fasta" />
|
|
rliterman@29
|
116 <element name="Sample_E" value="assemblies/Sample_E.fasta" />
|
|
rliterman@29
|
117 <element name="Sample_F" value="assemblies/Sample_F.fasta" />
|
|
rliterman@29
|
118 <element name="Sample_G" value="assemblies/Sample_G.fasta" />
|
|
rliterman@29
|
119 <element name="Sample_H" value="assemblies/Sample_H.fasta" />
|
|
rliterman@29
|
120 <element name="Sample_I" value="assemblies/Sample_I.fasta" />
|
|
rliterman@29
|
121 <element name="Sample_J" value="assemblies/Sample_J.fasta" />
|
|
rliterman@29
|
122 <element name="Sample_K" value="assemblies/Sample_K.fasta" />
|
|
rliterman@29
|
123 <element name="Sample_L" value="assemblies/Sample_L.fasta" />
|
|
rliterman@29
|
124 <element name="Sample_M" value="assemblies/Sample_M.fasta" />
|
|
rliterman@29
|
125 <element name="Sample_N" value="assemblies/Sample_N.fasta" />
|
|
rliterman@29
|
126 <element name="Sample_O" value="assemblies/Sample_O.fasta" />
|
|
rliterman@29
|
127 </collection>
|
|
rliterman@29
|
128 </param>
|
|
rliterman@29
|
129 <param name="query_reads">
|
|
rliterman@29
|
130 <collection type="list">
|
|
rliterman@29
|
131 <element name="Forward" value="reads/Week_42_Reads_1.fq.gz" />
|
|
rliterman@29
|
132 <element name="Reverse" value="reads/Week_42_Reads_2.fq.gz" />
|
|
rliterman@29
|
133 </collection>
|
|
rliterman@29
|
134 </param>
|
|
rliterman@29
|
135
|
|
rliterman@29
|
136 <param name="ref_id" value="Sample_A,Sample_B" />
|
|
rliterman@29
|
137 <param name="readext" value="fq.gz" />
|
|
rliterman@29
|
138 <param name="forward" value="_1.fq.gz" />
|
|
rliterman@29
|
139 <param name="reverse" value="_2.fq.gz" />
|
|
rliterman@29
|
140
|
|
rliterman@29
|
141 <output name="isolate_data" value="Isolate_Data.tsv" />
|
|
rliterman@29
|
142 </test>
|
|
rliterman@29
|
143 </tests>
|
|
rliterman@29
|
144 <help>
|
|
rliterman@29
|
145 This tool takes query assemblies and reference assemblies and calculates the pairwise distance between each query/reference combination. If no reference is provided, all queries are compared to all other queries.
|
|
rliterman@29
|
146 </help>
|
|
rliterman@29
|
147 <citations>
|
|
rliterman@29
|
148 <citation type="doi">10.XXXX/placeholder.doi</citation>
|
|
rliterman@29
|
149 <citation type="bibtex">@article{example2024,title={CFSAN SNP Pipeline 2 (CSP2): a pipeline for fast and accurate SNP distance estimation from bacterial genome assemblies.},author={Doe, John and Smith, Jane},journal={Submitted},year={2024}}
|
|
rliterman@29
|
150 </citation>
|
|
rliterman@29
|
151 </citations>
|
|
rliterman@29
|
152 </tool>
|
|
rliterman@29
|
153
|
