|
kkonganti@1
|
1 <tool id="cfsan_bettercallsal" name="bettercallsal" version="0.2.0+galaxy0">
|
|
kkonganti@1
|
2 <description>An automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella.</description>
|
|
kkonganti@0
|
3 <requirements>
|
|
kkonganti@1
|
4 <requirement type="package" version="22.10">nextflow</requirement>
|
|
kkonganti@1
|
5 <requirement type="package" version="1.0.0">micromamba</requirement>
|
|
kkonganti@0
|
6 <requirement type="package">graphviz</requirement>
|
|
kkonganti@0
|
7 </requirements>
|
|
kkonganti@0
|
8 <version_command>nextflow -version</version_command>
|
|
kkonganti@0
|
9 <command detect_errors="exit_code"><![CDATA[
|
|
kkonganti@0
|
10 mkdir -p cpipes-input || exit 1;
|
|
kkonganti@0
|
11 pwd_path=\$(pwd);
|
|
kkonganti@0
|
12 #import re
|
|
kkonganti@0
|
13 #if (str($input_read_type_cond.input_read_type) == "single_long"):
|
|
kkonganti@0
|
14 #for _, $unpaired in enumerate($input_read_type_cond.input):
|
|
kkonganti@0
|
15 #set read1 = str($unpaired.name)
|
|
kkonganti@0
|
16 #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
|
|
kkonganti@0
|
17 #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
|
|
kkonganti@0
|
18 #set read1 = str($unpaired.name) + str('.') + $read1_ext
|
|
kkonganti@0
|
19 #end if
|
|
kkonganti@0
|
20 ln -sf '$unpaired' './cpipes-input/$read1';
|
|
kkonganti@0
|
21 #end for
|
|
kkonganti@0
|
22 #elif (str($input_read_type_cond.input_read_type) == "paired"):
|
|
kkonganti@0
|
23 #for _, $pair in enumerate($input_read_type_cond.input_pair)
|
|
kkonganti@0
|
24 #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
|
|
kkonganti@0
|
25 #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
|
|
kkonganti@0
|
26 #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
|
|
kkonganti@0
|
27 #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
|
|
kkonganti@0
|
28 #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
|
|
kkonganti@0
|
29 #set read_R1 = $read_R1 + str('.') + $read_R1_ext
|
|
kkonganti@0
|
30 #end if
|
|
kkonganti@0
|
31 #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
|
|
kkonganti@0
|
32 #set read_R2 = $read_R2 + str('.') + $read_R2_ext
|
|
kkonganti@0
|
33 #end if
|
|
kkonganti@0
|
34 ln -sf '$pair.forward' './cpipes-input/$read_R1';
|
|
kkonganti@0
|
35 ln -sf '$pair.reverse' './cpipes-input/$read_R2';
|
|
kkonganti@0
|
36 #end for
|
|
kkonganti@0
|
37 #end if
|
|
kkonganti@1
|
38 $__tool_directory__/0.5.0/cpipes
|
|
kkonganti@2
|
39 --pipeline bettercallsal
|
|
kkonganti@1
|
40 --input \${pwd_path}/cpipes-input
|
|
kkonganti@0
|
41 --output \${pwd_path}/cpipes-output
|
|
kkonganti@0
|
42 --fq_suffix '${input_read_type_cond.fq_suffix}'
|
|
kkonganti@1
|
43 #if (str($input_read_type_cond.input_read_type) == "single_long"):
|
|
kkonganti@1
|
44 --fq_single_end true
|
|
kkonganti@1
|
45 #elif (str($input_read_type_cond.input_read_type) == "paired"):
|
|
kkonganti@1
|
46 --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
|
|
kkonganti@0
|
47 #end if
|
|
kkonganti@1
|
48 --tuspy_n $tuspy_n
|
|
kkonganti@3
|
49 #if ($sourmash_cond.run == "true"):
|
|
kkonganti@4
|
50 --sfhpy_fcv $sourmash_cond.sfhpy_fcv
|
|
kkonganti@1
|
51 #end if
|
|
kkonganti@1
|
52 --bcs_thresholds $bcs_thresholds
|
|
kkonganti@0
|
53 --fq_filename_delim '${fq_filename_delim}'
|
|
kkonganti@0
|
54 --fq_filename_delim_idx $fq_filename_delim_idx
|
|
kkonganti@0
|
55 -profile kondagac;
|
|
kkonganti@2
|
56 mv './cpipes-output/bettercallsal-multiqc/multiqc_report.html' './multiqc_report.html' > /dev/null 2>&1 || exit 1;
|
|
kkonganti@0
|
57 rm -rf ./cpipes-output > /dev/null 2>&1 || exit 1;
|
|
kkonganti@0
|
58 rm -rf ./work > /dev/null 2>&1 || exit 1
|
|
kkonganti@0
|
59 ]]></command>
|
|
kkonganti@0
|
60 <inputs>
|
|
kkonganti@0
|
61 <conditional name="input_read_type_cond">
|
|
kkonganti@0
|
62 <param name="input_read_type" type="select" label="Select the read collection type">
|
|
kkonganti@1
|
63 <option value="single_long" selected="true">Single-End short reads</option>
|
|
kkonganti@1
|
64 <option value="paired">Paired-End short reads</option>
|
|
kkonganti@0
|
65 </param>
|
|
kkonganti@0
|
66 <when value="single_long">
|
|
kkonganti@0
|
67 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
|
|
kkonganti@0
|
68 label="Dataset list of unpaired short reads or long reads" />
|
|
kkonganti@1
|
69 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/>
|
|
kkonganti@0
|
70 </when>
|
|
kkonganti@0
|
71 <when value="paired">
|
|
kkonganti@0
|
72 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
|
|
kkonganti@5
|
73 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"
|
|
kkonganti@5
|
74 help="For any data sets downloaded from NCBI into Galaxy, change this to _forward.fastq.gz suffix."/>
|
|
kkonganti@5
|
75 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
|
|
kkonganti@6
|
76 help="For any data sets downloaded from NCBI into Galaxy, change this to _reverse.fastq.gz suffix."/>
|
|
kkonganti@0
|
77 </when>
|
|
kkonganti@0
|
78 </conditional>
|
|
kkonganti@2
|
79 <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"
|
|
kkonganti@1
|
80 help="The default value of 10 is suitable for almost all scenarios."/>
|
|
kkonganti@2
|
81 <param name="bcs_thresholds" type="select" label="Enter the type of base quality thresholds to be set with bettercallsal"
|
|
kkonganti@1
|
82 help="The default value sets strictest thresholds that tends to filter out most of the false positive hits.">
|
|
kkonganti@1
|
83 <option value="strict" selected="true">strict</option>
|
|
kkonganti@1
|
84 <option value="relax">relax</option>
|
|
kkonganti@1
|
85 </param>
|
|
kkonganti@1
|
86 <conditional name="sourmash_cond">
|
|
kkonganti@1
|
87 <param name="run" type="select" label="Run sourmash"
|
|
kkonganti@2
|
88 help="Should sourmash be used for additional genome fraction filtering">
|
|
kkonganti@1
|
89 <option value="true" selected="true">yes</option>
|
|
kkonganti@1
|
90 <option value="false">no</option>
|
|
kkonganti@1
|
91 </param>
|
|
kkonganti@1
|
92 <when value="true">
|
|
kkonganti@2
|
93 <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"
|
|
kkonganti@1
|
94 help="The default value is set at 10% coverage threshold."/>
|
|
kkonganti@1
|
95 </when>
|
|
kkonganti@1
|
96 <when value="false">
|
|
kkonganti@2
|
97 <param name="sfhpy_fcv" type="select" label="Enter the minimum coverage match with sourmash before a serotype hit is considered for further processing"
|
|
kkonganti@8
|
98 help="THIS OPTION IS IGNORED IF SOURMASH TOOL IS NOT RUN.">
|
|
kkonganti@1
|
99 <option value="NA" selected="true">N/A</option>
|
|
kkonganti@1
|
100 </param>
|
|
kkonganti@1
|
101 </when>
|
|
kkonganti@1
|
102 </conditional>
|
|
kkonganti@0
|
103 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
|
|
kkonganti@0
|
104 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)."/>
|
|
kkonganti@0
|
105 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
|
|
kkonganti@0
|
106 <!-- <param name="runtime_profile" type="select" label="Run time profile">
|
|
kkonganti@0
|
107 <option value="kondagac" selected="true">conda</option>
|
|
kkonganti@0
|
108 <option value="cingularitygac">singularity</option>
|
|
kkonganti@0
|
109 </param> -->
|
|
kkonganti@0
|
110 </inputs>
|
|
kkonganti@0
|
111 <outputs>
|
|
kkonganti@2
|
112 <data name="multiqc_report" format="html" label="bettercallsal: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
|
|
kkonganti@0
|
113 </outputs>
|
|
kkonganti@0
|
114 <tests>
|
|
kkonganti@0
|
115 <!--Test 01: long reads-->
|
|
kkonganti@0
|
116 <test expect_num_outputs="2">
|
|
kkonganti@0
|
117 <param name="input">
|
|
kkonganti@0
|
118 <collection type="list">
|
|
kkonganti@0
|
119 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
|
|
kkonganti@0
|
120 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
|
|
kkonganti@0
|
121 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
|
|
kkonganti@0
|
122 </collection>
|
|
kkonganti@0
|
123 </param>
|
|
kkonganti@0
|
124 <param name="fq_suffix" value=".fastq.gz"/>
|
|
kkonganti@0
|
125 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
|
|
kkonganti@0
|
126 <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
|
|
kkonganti@0
|
127 </test>
|
|
kkonganti@0
|
128 </tests>
|
|
kkonganti@0
|
129 <help><![CDATA[
|
|
kkonganti@0
|
130
|
|
kkonganti@0
|
131 .. class:: infomark
|
|
kkonganti@0
|
132
|
|
kkonganti@0
|
133 **Purpose**
|
|
kkonganti@0
|
134
|
|
kkonganti@1
|
135 bettercallsal is an automated workflow to assign Salmonella serotype based on NCBI Pathogen Detection Project for Salmonella.
|
|
kkonganti@1
|
136 It uses MASH to reduce the search space followed by additional genome filtering with sourmash. It then performs genome based
|
|
kkonganti@1
|
137 alignment with kma followed by count generation using salmon. This workflow can be used to analyze shotgun metagenomics
|
|
kkonganti@1
|
138 datasets, quasi-metagenomic datasets (enriched for Salmonella) and target enriched datasets (enriched with molecular baits specific for Salmonella)
|
|
kkonganti@1
|
139 and is especially useful in a case where a sample is of multi-serovar mixture.
|
|
kkonganti@1
|
140
|
|
kkonganti@1
|
141 It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at CFSAN.
|
|
kkonganti@1
|
142
|
|
kkonganti@0
|
143
|
|
kkonganti@0
|
144 ----
|
|
kkonganti@0
|
145
|
|
kkonganti@0
|
146 .. class:: infomark
|
|
kkonganti@0
|
147
|
|
kkonganti@0
|
148 **Testing and Validation**
|
|
kkonganti@0
|
149
|
|
kkonganti@1
|
150 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
|
|
kkonganti@10
|
151 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
|
|
kkonganti@1
|
152 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
|
|
kkonganti@1
|
153 our preprint (https://www.biorxiv.org/content/10.1101/2023.04.06.535929v1.full). All the original testing and validation was
|
|
kkonganti@0
|
154 done on the command line on the CFSAN Raven2 HPC Cluster.
|
|
kkonganti@0
|
155
|
|
kkonganti@0
|
156
|
|
kkonganti@0
|
157 ----
|
|
kkonganti@0
|
158
|
|
kkonganti@0
|
159 .. class:: infomark
|
|
kkonganti@0
|
160
|
|
kkonganti@0
|
161 **Outputs**
|
|
kkonganti@0
|
162
|
|
kkonganti@7
|
163 The main output file is a:
|
|
kkonganti@0
|
164
|
|
kkonganti@0
|
165 ::
|
|
kkonganti@0
|
166
|
|
kkonganti@0
|
167 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
|
|
kkonganti@0
|
168 Please note that due to MultiQC customizations, the preview (eye icon) will not
|
|
kkonganti@0
|
169 work within Galaxy for the MultiQC report. Please download the file by clicking
|
|
kkonganti@0
|
170 on the floppy icon and view it in your browser on your local desktop/workstation.
|
|
kkonganti@1
|
171 You can export the tables and plots from the downloaded MultiQC report.
|
|
kkonganti@0
|
172
|
|
kkonganti@0
|
173 ]]></help>
|
|
kkonganti@0
|
174 <citations>
|
|
kkonganti@0
|
175 <citation type="bibtex">
|
|
kkonganti@1
|
176 @misc{bettercallsal,
|
|
kkonganti@0
|
177 author = {Konganti, Kranti},
|
|
kkonganti@1
|
178 year = {2023},
|
|
kkonganti@1
|
179 title = {bettercallsal: better calling of Salmonella serotypes from enrichment cultures using shotgun metagenomic profiling and its application in an outbreak setting},
|
|
kkonganti@1
|
180 publisher = {Cold Spring Harbor Laboratory},
|
|
kkonganti@1
|
181 journal = {bioRxiv},
|
|
kkonganti@1
|
182 url = {https://www.biorxiv.org/content/10.1101/2023.04.06.535929v1.full}}
|
|
kkonganti@0
|
183 </citation>
|
|
kkonganti@0
|
184 </citations>
|
|
kkonganti@0
|
185 </tool>
|
