Mercurial > repos > jpayne > csp2

comparison csp2-screen.xml @ 0:1c1e01265e0f draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 7f3c6fb6db52daedaa0c59d6ca7f39710778f242-dirty
author jpayne
date Mon, 11 Aug 2025 15:46:24 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:1c1e01265e0f
1 <tool id="csp2-screen" name="CSP2 (Screening Mode)" version="0.9.7.7">
2 <description>Screen query assemblies against reference assemblies</description>
3 <requirements>
4 <!-- <requirement type="package" version="24.10.1">nextflow</requirement>
5 <requirement type="package" version="1.5.8">micromamba</requirement> -->
6 <container type="docker">cfsanbiostatistics/csp2:v.0.9.7.7-galaxy</container>
7 </requirements>
8 <version_command>nextflow -version</version_command>
9 <command detect_errors="exit_code"><![CDATA[
10 mkdir -p queries references .nextflow
11 #set readext=""
12 #set renamedref=$source.reference.element_identifier.replace(": ", ".").replace(" ", "_")
13 #for $reads in $coll
14 && ln -sf '${reads}' 'queries/${reads.element_identifier.replace(": ", ".").replace(" ", "_")}.fasta'
15 #end for
16 && ln -sf '$source.reference' 'references/${renamedref}.fasta'
17 && echo "*** Files in queries directory: ***"
18 && ls -lah queries/
19 && nextflow run
20 /app/CSP2.nf -c $__tool_directory__/nextflow.config -profile standard
21 --runmode screen
22 --fasta queries
23 --ref_fasta 'references/${renamedref}.fasta'
24 --min_cov $opt.min_cov
25 --min_iden $opt.min_iden
26 --min_len $opt.min_len
27 --ref_edge $opt.ref_edge
28 --query_edge $opt.query_edge
29 --dwin $opt.dwin
30 --wsnps $opt.wsnps
31 --out CSP2_Screen_Output
32 --quiet
33 && echo "*** Files in output directory: ***"
34 && ls -lahR CSP2_Screen_Output
35 && tail -n +2 CSP2_Screen_Output/Isolate_Data.tsv > ${isolate_data}
36 && tail -n +2 CSP2_Screen_Output/Raw_MUMmer_Summary.tsv > ${raw_mummer}
37 && tail -n +2 CSP2_Screen_Output/Screening_Results.tsv > ${screening_results}
38 && echo "*** Nextflow log follows: ***"
39 && cat .nextflow.log
40 ]]>
41 </command>
42 <inputs>
43 <conditional name="source">
44 <param name="source_select" type="select" label="Use a curated GalaxyTrakr reference or a reference from your history">
45 <option value="curated">Use a GalaxyTrakr reference</option>
46 <option value="history">Use a reference from your history</option>
47 </param>
48 <when value="curated">
49 <param name="reference" type="select" label="Select reference fasta">
50 <options from_data_table="all_fasta">
51 <filter type="sort_by" column="2"/>
52 <validator type="no_options" message="No assemblies are available for the selected input dataset"/>
53 </options>
54 </param>
55 </when>
56 <when value="history">
57 <param type="data" name="reference" format="fasta" label="Select reference FASTA"/>
58 </when>
59 </conditional>
60 <!-- <conditional name="query">
61 <param name="query_select" type="select" label="Screen a list of paired-end reads or a list of assemblies">
62 <option value="reads">Screen a list of paired reads</option>
63 <option value="assemblies">Screen a list of assemblies</option>
64 </param>
65 <when value="reads">
66 <param label="Paired reads" name="coll" type="data_collection" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz,fastq.bz2,fastqsanger.bz2" collection_type="list:paired" />
67 </when>
68 <when value="assemblies"> -->
69 <param label="Assemblies" name="coll" type="data_collection" format="fasta" collection_type="list" />
70 <!-- </when> -->
71 <!-- </conditional> -->
72 <section name="opt" title="Advanced options...">
73 <param argument="--min_cov" name="min_cov" type="float" value="85" label="Minimum reference genome coverage to proceed with distance estimation" />
74 <param argument="--min_eden" name="min_iden" type="float" value="99" label="Minimum alignment percent identity to detect SNPs" />
75 <param argument="--min_len" name="min_len" type="integer" value="500" label="Minimum alignment length to detect SNPs" />
76 <param argument="--ref_edge" name="ref_edge" type="integer" value="150" label="Prune SNPs within this many bases of reference contig edge" />
77 <param argument="--query_edge" name="query_edge" type="integer" value="150" label="Prune SNPs within this many bases of query contig edge" />
78 <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)" />
79 <param argument="--wsnips" name="wsnps" type="text" value="3,2,1" label="Comma-separated list of maximum SNP counts per density window" />
80 </section>
81 </inputs>
82 <outputs>
83 <data name="raw_mummer" format="tabular" label="Raw MUMmer Output">
84 <actions>
85 <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" />
86 </actions>
87 </data>
88 <data name="isolate_data" format="tabular" label="Isolate Data">
89 <actions>
90 <action name="column_names" type="metadata" default="Isolate_ID,Isolate_Type,Assembly_Path,Contig_Count,Assembly_Bases,N50,N90,L50,L90,SHA256" />
91 </actions>
92 </data>
93 <data name="screening_results" format="tabular" label="Screening Results">
94 <actions>
95 <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" />
96 </actions>
97 </data>
98 <!-- <data name="nextflow_log" format="txt" label="Nextflow Log" from_work_dir="Nextflow_Log.txt" /> -->
99 </outputs>
100 <tests>
101 <test>
102 <param name="source_select" value="history" />
103 <param name="reference" value="assemblies/Sample_A.fasta" ftype="fasta" />
104 <!-- <param name="query_select" value="assemblies" /> -->
105 <param name="coll">
106 <collection type="list">
107 <!-- <element name="Sample_A" value="assemblies/Sample_A.fasta" /> -->
108 <element name="Sample_B" value="assemblies/Sample_B.fasta" />
109 <element name="Sample_C" value="assemblies/Sample_C.fasta" />
110 <element name="Sample_D" value="assemblies/Sample_D.fasta" />
111 <element name="Sample_E" value="assemblies/Sample_E.fasta" />
112 <element name="Sample_F" value="assemblies/Sample_F.fasta" />
113 <element name="Sample_G" value="assemblies/Sample_G.fasta" />
114 <element name="Sample_H" value="assemblies/Sample_H.fasta" />
115 <element name="Sample_I" value="assemblies/Sample_I.fasta" />
116 <element name="Sample_J" value="assemblies/Sample_J.fasta" />
117 <element name="Sample_K" value="assemblies/Sample_K.fasta" />
118 <element name="Sample_L" value="assemblies/Sample_L.fasta" />
119 <element name="Sample_M" value="assemblies/Sample_M.fasta" />
120 <element name="Sample_N" value="assemblies/Sample_N.fasta" />
121 <element name="Sample_O" value="assemblies/Sample_O.fasta" />
122 </collection>
123 </param>
124
125 <output name="screening_results" value="Screening_Results.tsv" />
126 <output name="isolate_data" value="Isolate_Data.tsv" />
127 </test>
128 <!-- <test>
129 <param name="source_select" value="history" />
130 <param name="reference" value="assemblies/Sample_A.fasta" ftype="fasta" />
131 <param name="query_select" value="reads" />
132 <param name="coll">
133 <collection type="list:paired">
134 <element name="Sample_A" >
135 <collection type="paired">
136 <element name="forward" value="reads/Week_42_Reads_1.fq.gz" ftype="fastqsanger.gz" />
137 <element name="reverse" value="reads/Week_42_Reads_2.fq.gz" ftype="fastqsanger.gz" />
138 </collection>
139 </element>
140 </collection>
141 </param>
142 <output name="screening_results" value="Screening_Results.tsv" />
143 <output name="isolate_data" value="Isolate_Data.tsv" />
144 </test> -->
145 </tests>
146 <help>
147 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.
148 </help>
149 <citations>
150 <citation type="doi">10.XXXX/placeholder.doi</citation>
151 <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}}
152 </citation>
153 </citations>
154 </tool>