Mercurial > repos > galaxytrakr > cfsan2snp2

comparison cfsan2snp-screen.xml @ 0:8e7a84e62b43 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit e734452c606dba89b6fe58c90c5f38e5ea067edd
author galaxytrakr
date Fri, 13 Mar 2026 21:22:16 +0000
parents
children e1bd0272cc59
comparison
equal deleted inserted replaced
-1:000000000000 0:8e7a84e62b43
1 <tool id="cfsan2snp-screen" name="CSP2 (Screening Mode)" version="0.9.7.7+gt_0.7">
2 <description>Screen query assemblies against reference assemblies</description>
3 <requirements>
4 <container type="docker">quay.io/galaxytrakr/csp2:0.9.7.7-galaxy_0.1</container>
5 </requirements>
6 <version_command>nextflow -version</version_command>
7 <command detect_errors="exit_code"><![CDATA[
8 mkdir -p queries references .nextflow
9 && sed "s/@CORES@/\${GALAXY_SLOTS:-1}/" $__tool_directory__/nextflow.tmpl > nextflow_gal25.config
10
11 #set readext=""
12 #for $reads in $coll
13 && ln -sf '${reads}' 'queries/${reads.element_identifier.replace(": ", ".").replace(" ", "_")}.fasta'
14 #end for
15 #for $ref in $source.reference
16 #set renamedref=$ref.element_identifier.replace(": ", ".").replace(" ", "_").replace("(","").replace(")","")
17 && ln -sf '$ref' 'references/${renamedref}.fasta'
18 #end for
19 && echo "*** Files in queries directory: ***"
20 && ls -lah queries/
21 && nextflow run /opt/csp2/CSP2.nf -c nextflow_gal25.config
22 --runmode screen
23 --fasta queries
24 --ref_fasta 'references'
25 --min_cov $opt.min_cov
26 --min_iden $opt.min_iden
27 --min_len $opt.min_len
28 --ref_edge $opt.ref_edge
29 --query_edge $opt.query_edge
30 --dwin $opt.dwin
31 --wsnps $opt.wsnps
32 --out CSP2_Screen_Output
33 --quiet
34 && echo "*** Files in output directory: ***"
35 && ls -lahR CSP2_Screen_Output
36 && tail -n +2 CSP2_Screen_Output/Isolate_Data.tsv > ${isolate_data}
37 && tail -n +2 CSP2_Screen_Output/Raw_MUMmer_Summary.tsv > ${raw_mummer}
38 && tail -n +2 CSP2_Screen_Output/Screening_Results.tsv > ${screening_results}
39 && echo "*** Nextflow log follows: ***"
40 && cat .nextflow.log
41 ]]>
42 </command>
43 <inputs>
44 <conditional name="source">
45 <param name="source_select" type="select" label="Use a curated GalaxyTrakr reference or a reference from your history">
46 <option value="curated">Use a GalaxyTrakr reference</option>
47 <option value="history">Use a reference from your history</option>
48 </param>
49 <when value="curated">
50 <param name="reference" type="select" label="Select reference fasta" multiple="true" min="1" >
51 <options from_data_table="all_fasta">
52 <filter type="sort_by" column="2"/>
53 <validator type="no_options" message="No assemblies are available for the selected input dataset"/>
54 </options>
55 </param>
56 </when>
57 <when value="history">
58 <param type="data" name="reference" format="fasta" label="Select reference FASTA" multiple="true" min="1" />
59 </when>
60 </conditional>
61 <!-- <conditional name="query">
62 <param name="query_select" type="select" label="Screen a list of paired-end reads or a list of assemblies">
63 <option value="reads">Screen a list of paired reads</option>
64 <option value="assemblies">Screen a list of assemblies</option>
65 </param>
66 <when value="reads">
67 <param label="Paired reads" name="coll" type="data_collection" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz,fastq.bz2,fastqsanger.bz2" collection_type="list:paired" />
68 </when>
69 <when value="assemblies"> -->
70 <param label="Assemblies" name="coll" type="data_collection" format="fasta" collection_type="list" />
71 <!-- </when> -->
72 <!-- </conditional> -->
73 <section name="opt" title="Advanced options...">
74 <param argument="--min_cov" name="min_cov" type="float" value="85" label="Minimum reference genome coverage to proceed with distance estimation" />
75 <param argument="--min_eden" name="min_iden" type="float" value="99" label="Minimum alignment percent identity to detect SNPs" />
76 <param argument="--min_len" name="min_len" type="integer" value="500" label="Minimum alignment length to detect SNPs" />
77 <param argument="--ref_edge" name="ref_edge" type="integer" value="150" label="Prune SNPs within this many bases of reference contig edge" />
78 <param argument="--query_edge" name="query_edge" type="integer" value="150" label="Prune SNPs within this many bases of query contig edge" />
79 <param argument="--dwin" 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)" />
80 <param argument="--wsnips" name="wsnps" type="text" value="3,2,1" label="Comma-separated list of maximum SNP counts per density window" />
81 </section>
82 </inputs>
83 <outputs>
84 <data name="raw_mummer" format="tabular" label="Raw MUMmer Output">
85 <actions>
86 <action name="column_names" type="metadata" default="SNPDiffs_File,Query_ID,Query_Assembly,Query_Contig_Count,Query_Assembly_Bases,Query_N50,Query_N90,Query_L50,Query_L90,Query_SHA256,Reference_ID,Reference_Assembly,Reference_Contig_Count,Reference_Assembly_Bases,Reference_N50,Reference_N90,Reference_L50,Reference_L90,Reference_SHA256,SNPs,Reference_Percent_Aligned,Query_Percent_Aligned,Median_Percent_Identity,Median_Alignment_Length,Kmer_Similarity,Shared_Kmers,Reference_Unique_Kmers,Query_Unique_Kmers,Reference_Breakpoints,Query_Breakpoints,Reference_Relocations,Query_Relocations,Reference_Translocations,Query_Translocations,Reference_Inversions,Query_Inversions,Reference_Insertions,Query_Insertions,Reference_Tandem,Query_Tandem,Indels,Invalid,gSNPs,gIndels" />
87 </actions>
88 </data>
89 <data name="isolate_data" format="tabular" label="Isolate Data">
90 <actions>
91 <action name="column_names" type="metadata" default="Isolate_ID,Isolate_Type,Assembly_Path,Contig_Count,Assembly_Bases,N50,N90,L50,L90,SHA256" />
92 </actions>
93 </data>
94 <data name="screening_results" format="tabular" label="Screening Results">
95 <actions>
96 <action name="column_names" type="metadata" default="Query_ID,Reference_ID,Screen_Category,CSP2_Screen_SNPs,Query_Percent_Aligned,Reference_Percent_Aligned,Query_Contigs,Query_Bases,Reference_Contigs,Reference_Bases,Raw_SNPs,Purged_Length,Purged_Identity,Purged_LengthIdentity,Purged_Invalid,Purged_Indel,Purged_Duplicate,Purged_Het,Purged_Density,Filtered_Query_Edge,Filtered_Ref_Edge,Filtered_Both_Edge,Kmer_Similarity,Shared_Kmers,Query_Unique_Kmers,Reference_Unique_Kmers,MUMmer_gSNPs,MUMmer_gIndels" />
97 </actions>
98 </data>
99 <!-- <data name="nextflow_log" format="txt" label="Nextflow Log" from_work_dir="Nextflow_Log.txt" /> -->
100 </outputs>
101 <tests>
102 <test>
103 <param name="source_select" value="history" />
104 <param name="reference" value="assemblies/Sample_A.fasta" ftype="fasta" />
105 <!-- <param name="query_select" value="assemblies" /> -->
106 <param name="coll">
107 <collection type="list">
108 <!-- <element name="Sample_A" value="assemblies/Sample_A.fasta" /> -->
109 <element name="Sample_B" value="assemblies/Sample_B.fasta" />
110 <element name="Sample_C" value="assemblies/Sample_C.fasta" />
111 <element name="Sample_D" value="assemblies/Sample_D.fasta" />
112 <element name="Sample_E" value="assemblies/Sample_E.fasta" />
113 <element name="Sample_F" value="assemblies/Sample_F.fasta" />
114 <element name="Sample_G" value="assemblies/Sample_G.fasta" />
115 <element name="Sample_H" value="assemblies/Sample_H.fasta" />
116 <element name="Sample_I" value="assemblies/Sample_I.fasta" />
117 <element name="Sample_J" value="assemblies/Sample_J.fasta" />
118 <element name="Sample_K" value="assemblies/Sample_K.fasta" />
119 <element name="Sample_L" value="assemblies/Sample_L.fasta" />
120 <element name="Sample_M" value="assemblies/Sample_M.fasta" />
121 <element name="Sample_N" value="assemblies/Sample_N.fasta" />
122 <element name="Sample_O" value="assemblies/Sample_O.fasta" />
123 </collection>
124 </param>
125
126 <output name="screening_results" value="Screening_Results.tsv" />
127 <output name="isolate_data" value="Isolate_Data.tsv" />
128 </test>
129 <test>
130 <!-- Test that spaces and parens are handled -->
131 <param name="source_select" value="history" />
132 <param name="reference" value="assemblies/Sample (A).fasta" />
133 <!-- <param name="query_select" value="assemblies" /> -->
134 <param name="coll">
135 <collection type="list">
136 <!-- <element name="Sample_A" value="assemblies/Sample_A.fasta" /> -->
137 <element name="Sample_B" value="assemblies/Sample_B.fasta" />
138 <element name="Sample_C" value="assemblies/Sample_C.fasta" />
139 <element name="Sample_D" value="assemblies/Sample_D.fasta" />
140 </collection>
141 </param>
142 <output name="isolate_data" value="Isolate_Data.tsv" compare="diff" lines_diff="17" />
143 </test>
144 <!-- <test>
145 <param name="source_select" value="history" />
146 <param name="reference" value="assemblies/Sample_A.fasta" ftype="fasta" />
147 <param name="query_select" value="reads" />
148 <param name="coll">
149 <collection type="list:paired">
150 <element name="Sample_A" >
151 <collection type="paired">
152 <element name="forward" value="reads/Week_42_Reads_1.fq.gz" ftype="fastqsanger.gz" />
153 <element name="reverse" value="reads/Week_42_Reads_2.fq.gz" ftype="fastqsanger.gz" />
154 </collection>
155 </element>
156 </collection>
157 </param>
158 <output name="screening_results" value="Screening_Results.tsv" />
159 <output name="isolate_data" value="Isolate_Data.tsv" />
160 </test> -->
161 </tests>
162 <help>
163 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.
164 </help>
165 <citations>
166 <citation type="doi">10.XXXX/placeholder.doi</citation>
167 <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}}
168 </citation>
169 </citations>
170 </tool>