Mercurial > repos > galaxytrakr > hfp_bettercallsal_konda

comparison cfsan_bettercallsal.xml @ 0:0a8dda29956e draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author galaxytrakr
date Thu, 28 May 2026 20:41:10 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:0a8dda29956e
1 <tool id="hfp_bettercallsal_konda" name="bettercallsal" version="1.0.0+galaxy21">
2 <description>An automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella.</description>
3 <requirements>
4 <requirement type="package" version="24.04.3">nextflow</requirement>
5 <requirement type="package" version="1.5.8">micromamba</requirement>
6 <requirement type="package">graphviz</requirement>
7 </requirements>
8 <version_command>nextflow -version</version_command>
9 <command detect_errors="exit_code"><![CDATA[
10 input_path=\$(pwd)"/cpipes-input";
11 mkdir -p "\${input_path}" || exit 1;
12 #import re
13 #if (str($input_read_type_cond.input_read_type) == "single_long" or str($input_read_type_cond.input_read_type) == "long_long"):
14 #for _, $unpaired in enumerate($input_read_type_cond.input):
15 #set read1 = str($unpaired.name)
16 #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
17 #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
18 #set read1 = str($unpaired.name) + str('.') + $read1_ext
19 #end if
20 ln -sf '$unpaired' "\${input_path}/$read1";
21 #end for
22 #elif (str($input_read_type_cond.input_read_type) == "paired"):
23 #for _, $pair in enumerate($input_read_type_cond.input_pair)
24 #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
25 #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
26 #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
27 #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
28 #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
29 #set read_R1 = $read_R1 + str('.') + $read_R1_ext
30 #end if
31 #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
32 #set read_R2 = $read_R2 + str('.') + $read_R2_ext
33 #end if
34 ln -sf '$pair.forward' "\${input_path}/$read_R1";
35 ln -sf '$pair.reverse' "\${input_path}/$read_R2";
36 #end for
37 #end if
38 $__tool_directory__/1.0.0/cpipes
39 #if (str($input_read_type_cond.input_read_type) == "long_long"):
40 --pipeline bettercallsal_lr
41 #else
42 --pipeline bettercallsal
43 #end if
44 --input \${input_path}
45 --output cpipes-output
46 --fq_suffix '${input_read_type_cond.fq_suffix}'
47 #if (str($input_read_type_cond.input_read_type) == "long_long"):
48 --fq_single_end true
49 #elif (str($input_read_type_cond.input_read_type) == "single_long"):
50 --fq_single_end true
51 #elif (str($input_read_type_cond.input_read_type) == "paired"):
52 --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
53 #end if
54 --tuspy_n $tuspy_n
55 #if ($sourmash_cond.run == "true"):
56 --sfhpy_fcv $sourmash_cond.sfhpy_fcv
57 #end if
58 #if ($bcs_thresholds != 'relax' and str($input_read_type_cond.input_read_type) != "long_long"):
59 --kmaalign_ID $kma_id
60 #end if
61 #if ($sourmash_cond.run == "true"):
62 --sfhpy_fcv $sourmash_cond.sfhpy_fcv
63 #end if
64 --bcs_db_mode $bcs_db_mode
65 --bcs_thresholds $bcs_thresholds
66 --fq_filename_delim '${fq_filename_delim}'
67 --fq_filename_delim_idx $fq_filename_delim_idx
68 -profile kondagac;
69 #if (str($input_read_type_cond.input_read_type) == "long_long"):
70 mv './cpipes-output/bettercallsal_lr-multiqc/CPIPES-Report_multiqc_report.html' './multiqc_report.html' || exit 1;
71 #else
72 mv './cpipes-output/bettercallsal-multiqc/CPIPES-Report_multiqc_report.html' './multiqc_report.html' || exit 1;
73 #end if
74 rm -rf ./cpipes-output || exit 1;
75 rm -rf ./work || exit 1;
76 ]]></command>
77 <inputs>
78 <conditional name="input_read_type_cond">
79 <param name="input_read_type" type="select" label="Select the read collection type">
80 <option value="single_long" selected="true">Single-End short reads</option>
81 <option value="paired">Paired-End short reads</option>
82 <option value="long_long">Long reads</option>
83 </param>
84 <when value="single_long">
85 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
86 label="Dataset list of unpaired short reads" />
87 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/>
88 </when>
89 <when value="long_long">
90 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
91 label="Dataset list of long reads" />
92 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the long read FASTQ"/>
93 </when>
94 <when value="paired">
95 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
96 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"
97 help="For any data sets downloaded from NCBI into Galaxy, change this to _forward.fastq.gz suffix."/>
98 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
99 help="For any data sets downloaded from NCBI into Galaxy, change this to _reverse.fastq.gz suffix."/>
100 </when>
101 </conditional>
102 <param name="bcs_db_mode" type="select" label="Select the database mode with bettercallsal"
103 help="Refer to `Database generation` section in our manuscript: https://doi.org/10.3389/fmicb.2023.1200983">
104 <option value="snp" selected="true">per_snp_cluster</option>
105 <option value="comp">per_computed_type</option>
106 </param>
107 <param name="tuspy_n" optional="true" value="10" type="integer" label="Enter the number of top unique serotypes to retain after initial MASH screen step"
108 help="The default value of 10 is suitable for almost all scenarios."/>
109 <param name="bcs_thresholds" type="select" label="Enter the type of base quality thresholds to be set with bettercallsal"
110 help="The default value sets strictest thresholds that tends to filter out most of the false positive hits.">
111 <option value="strict" selected="true">strict</option>
112 <option value="relax">relax</option>
113 </param>
114 <param name="kma_id" optional="true" value="10.0" type="text" label="Enter the %ID threshold for KMA alignments of samples against genomes"
115 help="The default value of 10% works well for enrichment samples tested within FDA. The 'relax' preset for base quality thresholds automatically sets this value to 5%."/>
116 <conditional name="sourmash_cond">
117 <param name="run" type="select" label="Run sourmash"
118 help="Should sourmash be used for additional genome fraction filtering">
119 <option value="true" selected="true">yes</option>
120 <option value="false">no</option>
121 </param>
122 <when value="true">
123 <param name="sfhpy_fcv" type="text" value="0.1" label="Enter the minimum coverage match with sourmash before a serotype hit is considered for further processing"
124 help="The default value is set at 10% coverage threshold."/>
125 </when>
126 <when value="false">
127 <param name="sfhpy_fcv" type="select" label="Enter the minimum coverage match with sourmash before a serotype hit is considered for further processing"
128 help="THIS OPTION IS IGNORED IF SOURMASH TOOL IS NOT RUN.">
129 <option value="NA" selected="true">N/A</option>
130 </param>
131 </when>
132 </conditional>
133 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
134 help="This is the delimitor by which samples are grouped together to display in the final MultiQC report. For example, if your input data sets are mango_replicate1.fastq.gz, mango_replicate2.fastq.gz, orange_replicate1_maryland.fastq.gz, orange_replicate2_maryland.fastq.gz, then to create 2 samples mango and orange, the value for --fq_filename_delim would be _ (underscore) and the value for --fq_filename_delim_idx would be 1, since you want to group by the first word (i.e. mango or orange) after splitting the filename based on _ (underscore)."/>
135 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
136 <!-- <param name="runtime_profile" type="select" label="Run time profile">
137 <option value="kondagac" selected="true">conda</option>
138 <option value="cingularitygac">singularity</option>
139 </param> -->
140 </inputs>
141 <outputs>
142 <data name="multiqc_report" format="html" label="bettercallsal: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
143 </outputs>
144 <tests>
145 <!--Test 01: long reads-->
146 <test expect_num_outputs="2">
147 <param name="input">
148 <collection type="list">
149 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
150 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
151 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
152 </collection>
153 </param>
154 <param name="fq_suffix" value=".fastq.gz"/>
155 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
156 <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
157 </test>
158 </tests>
159 <help><![CDATA[
160
161 .. class:: infomark
162
163 **Purpose**
164
165 bettercallsal is an automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella.
166 It uses MASH to reduce the search space followed by additional genome filtering with sourmash. It then performs genome based
167 alignment with kma followed by count generation using salmon. This workflow can be used to analyze shotgun metagenomics
168 datasets, quasi-metagenomic datasets (enriched for Salmonella) and target enriched datasets (enriched with molecular baits specific for Salmonella)
169 and is especially useful in a case where a sample is of multi-serovar mixture.
170
171 It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at CFSAN.
172
173
174 ----
175
176 .. class:: infomark
177
178 **Testing and Validation**
179
180 The CPIPES - bettercallsal Nextflow pipeline has been wrapped to make it work in Galaxy. It takes in either paired or unpaired short reads list as an input
181 and generates a MultiQC report in the final step. The pipeline has been tested on 2x300 bp MiSeq and 2x150 bp NextSeq simulated reads and has been shown to call multiple
182 Salmonella serotypes with up to ~95% accuracy. The pipeline has also been tested on metagenomics data sets from Peach and Papaya outbreaks as discussed in
183 our publication (https://www.frontiersin.org/articles/10.3389/fmicb.2023.1200983/full). All the original testing and validation was
184 done on the command line on the CFSAN Raven2 HPC Cluster.
185
186
187 ----
188
189 .. class:: infomark
190
191 **Outputs**
192
193 The main output file is a:
194
195 ::
196
197 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
198 Please note that due to MultiQC customizations, the preview (eye icon) will not
199 work within Galaxy for the MultiQC report. Please download the file by clicking
200 on the floppy icon and view it in your browser on your local desktop/workstation.
201 You can export the tables and plots from the downloaded MultiQC report.
202
203 ]]></help>
204 <citations>
205 <citation type="bibtex">
206 @article{bettercallsal,
207 author = {Konganti, Kranti},
208 year = {2023},
209 month = {August},
210 title = {bettercallsal: better calling of Salmonella serotypes from enrichment cultures using shotgun metagenomic profiling and its application in an outbreak setting},
211 journal = {Frontiers in Microbiology},
212 doi = {10.3389/fmicb.2023.1200983},
213 url = {https://www.frontiersin.org/articles/10.3389/fmicb.2023.1200983/full}}
214 </citation>
215 </citations>
216 </tool>