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