Mercurial > repos > kkonganti > cfsan_centriflaken

comparison cfsan_centriflaken.xml @ 0:77494b0fa3c7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload"
author kkonganti
date Mon, 27 Jun 2022 15:55:37 -0400
parents
children e0d902b50cff
comparison
equal deleted inserted replaced
-1:000000000000 0:77494b0fa3c7
1 <tool id="cfsan_centriflaken" name="Centriflaken" version="0.2.0+galaxy0">
2 <description>An automated pipeline to generate a MAG of interest (E.coli or Salmonella) and perform serotyping.</description>
3 <requirements>
4 <requirement type="package" version="22.04">nextflow</requirement>
5 <requirement type="package">graphviz</requirement>
6 </requirements>
7 <version_command>nextflow -version</version_command>
8 <command detect_errors="exit_code"><![CDATA[
9 mkdir -p cpipes-input
10 #for $input in $LIST
11 ln -sf '$input' './cpipes-input/${input.element_identifier}';
12 #end for
13 pwd_path=\$(pwd)
14 $__tool_directory__/0.2.1/cpipes
15 #if (reads.type == "long"):
16 --pipeline $pipeline
17 #else:
18 --pipeline $pipeline
19 #end if
20 --input \${pwd_path}/cpipes-input
21 --output \${pwd_path}/cpipes-output
22 #if ($reads_lib.paired_end == "true"):
23 --fq_single_end false
24 --fq_suffix '${fq_suffix}'
25 --fq2_suffix '${fq2_suffix}'
26 #else:
27 --fq_single_end true
28 --fq_suffix '${fq_suffix}'
29 #end if
30 --fq_filename_delim '${fq_filename_delim}'
31 --fq_filename_delim_idx $fq_filename_delim_idx
32 --centrifuge_extract_bug '${centrifuge_extract_bug}'
33 --flye_genome_size '${genome_size}'
34 -profile $profile
35 ]]></command>
36 <inputs>
37 <param name="input" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastqsanger" label="Input reads" />
38 <conditional name="reads">
39 <param name="type" type="select" label="Sequencing Read Library Type" value="long">
40 <option value="long">Long reads</option>
41 <option value="short">Short reads</option>
42 </param>
43 <when value="short">
44 <conditional name="reads_lib">
45 <param name="paired_end" type="select" label="Sequencing Read Library Layout" value="false">
46 <option value="false">Short read Single-End or Long reads</option>
47 <option value="true">Short read Paired-End</option>
48 </param>
49 <when value="true">
50 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the FASTQ R1 file of Paired-End reads."/>
51 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the FASTQ R2 file of Paired-End reads."/>
52 </when>
53 <when value="false">
54 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the FASTQ R1 file of Paired-End reads."/>
55 </when>
56 </conditional>
57 </when>
58 <when value="long">
59 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the FASTQ file of Long reads."/>
60 </when>
61 </conditional>
62 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
63 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_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)"/>
64 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delimitor_idx)" />
65 <param name="centrifuge_extract_bug" type="text" value="Escherichia coli" label="Reads belonging to this taxa are extracted and a MAG is generated to allow for serotyping"/>
66 <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g.">
67 <validator type="regex" message="Genome size must be a float or integer, optionally followed by the a unit prefix (kmg)">^([0-9]*[.])?[0-9]+[kmg]?$</validator>
68 </param>
69 <param name="runtime_profile" type="select" label="Run time profile" value="kondagac">
70 <option value="kondagac">conda</option>
71 <option value="cingularitygac">singularity</option>
72 </param>
73 </inputs>
74 <outputs>
75 <data name="multiqc_report" format="html" label="MultiQC Report on ${on_string}">
76 <discover_datasets pattern="multiqc_report.html" assign_primary_output="true" directory="cpipes-output"/>
77 </data>
78 <data name="assembled_mags" format="fasta" label="CENTRIFLAKEN: Assembled MAGs">
79 <discover_datasets pattern=".*\.assembly_filtered_contigs.fasta" visible="true" directory="cpipes-output"/>
80 </data>
81 </outputs>
82 <help><![CDATA[
83
84 .. class:: infomark
85
86 **Purpose**
87
88 Centriflaken suite of automated data analysis pipelines based on Nextflow DSL2 developed at CFSAN, FDA. Thess piepelines allow rapid
89 and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our
90 previous publication (https://doi.org/10.1371/journal.pone.0245172).
91 ----
92
93 .. class:: infomark
94
95 **Testing and Validation**
96
97 The pipeline has been wrapped to make it work in Galaxy. It takes in either paired or unpaired short reads or long reads, generates MAGs and performs
98 in silico-based analysis (i.e., virulence gene finding). Additionally, AMR gene finding analysis is also included in Centriflaken and performed on MAGs
99 of interest. The final summary plots and tables can be downloaded from the provided MultiQC HTML report generated as part of the pipeline.
100 The Centriflaken pipeline was validated with data from our previously published method (Maguire et al, 2021) and was able to replicate the detection
101 and classification of STECs for each sample. We tested the pipeline with nanopore data obtained from 21 additional enriched samples from
102 irrigation water and was able to perform the entire precision metagenomics analysis in less than 5 hours for all of them. All the original testing and validation was
103 done on the command line on the CFSAN Raven2 HPC Cluster.
104
105
106 ----
107
108 .. class:: infomark
109
110 **Outputs**
111
112 The main output files are:
113
114 ::
115
116 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
117 - Final assembly: contains contigs and possibly scaffolds (see below).
118
119 ]]></help>
120 <citations>
121 <citation type="bibtex">
122 @misc{gitlabCPIPES,
123 author = {Konganti, Kranti},
124 year = {2022},
125 title = {CPIPES - Centriflaken},
126 publisher = {GitLab},
127 journal = {GitLab repository},
128 url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}}
129 </citation>
130 </citations>
131 </tool>