|
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@4
|
10 #for $key in $input.keys()
|
|
kkonganti@4
|
11 ln -sf '$input[$key]' './cpipes-input/$key';
|
|
kkonganti@0
|
12 #end for
|
|
kkonganti@2
|
13 pwd_path=\$(pwd) &&
|
|
kkonganti@0
|
14 $__tool_directory__/0.2.1/cpipes
|
|
kkonganti@4
|
15 #if ($pipeline == "centriflaken"):
|
|
kkonganti@4
|
16 --pipeline $pipeline
|
|
kkonganti@4
|
17 --fq_single_end true
|
|
kkonganti@4
|
18 #elif ($pipeline.name == "centriflaken_hy"):
|
|
kkonganti@4
|
19 --pipeline $pipeline
|
|
kkonganti@4
|
20 #if ($reads_lib_layout == "single"):
|
|
kkonganti@4
|
21 --fq_single_end true
|
|
kkonganti@4
|
22 #else:
|
|
kkonganti@4
|
23 --fq_single_end false
|
|
kkonganti@4
|
24 #end if
|
|
kkonganti@0
|
25 #end if
|
|
kkonganti@0
|
26 --input \${pwd_path}/cpipes-input
|
|
kkonganti@0
|
27 --output \${pwd_path}/cpipes-output
|
|
kkonganti@4
|
28 --fq_suffix '${fq_suffix}'
|
|
kkonganti@0
|
29 --fq_filename_delim '${fq_filename_delim}'
|
|
kkonganti@0
|
30 --fq_filename_delim_idx $fq_filename_delim_idx
|
|
kkonganti@0
|
31 --centrifuge_extract_bug '${centrifuge_extract_bug}'
|
|
kkonganti@0
|
32 --flye_genome_size '${genome_size}'
|
|
kkonganti@4
|
33 -profile $runtime_profile
|
|
kkonganti@5
|
34 -resume
|
|
kkonganti@0
|
35 ]]></command>
|
|
kkonganti@0
|
36 <inputs>
|
|
kkonganti@3
|
37 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz,fastqsanger.gz,fastqsanger" label="Input read collection" />
|
|
kkonganti@4
|
38 <param name="pipeline" type="select" label="CPIPES Workflow name" value="centriflaken"
|
|
kkonganti@4
|
39 help="centriflaken: for short reads (paired or unpaired). centriflaken_hy: for long reads (Nanopore or PacBio). Default: centriflaken">
|
|
kkonganti@4
|
40 <option value="centriflaken">centriflaken</option>
|
|
kkonganti@4
|
41 <option value="centriflaken_hy">centriflaken_hy</option>
|
|
kkonganti@4
|
42 </param>
|
|
kkonganti@4
|
43 <param name="read_lib_layout" type="select" label="Short Read Library Layout" value="single"
|
|
kkonganti@4
|
44 help="If the pipeline is centriflaken_hy (i.e for short reads), what is the library layout? Default: Single-End">
|
|
kkonganti@4
|
45 <option value="single">Single-End</option>
|
|
kkonganti@4
|
46 <option value="paired">Paired-End</option>
|
|
kkonganti@4
|
47 </param>
|
|
kkonganti@4
|
48 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the R1 FASTQ or Unpaired FASTQ"/>
|
|
kkonganti@4
|
49 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ R2"/>
|
|
kkonganti@0
|
50 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
|
|
kkonganti@6
|
51 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@6
|
52 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
|
|
kkonganti@0
|
53 <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
|
54 <param name="genome_size" type="text" optional="true" value="5.5m" label="Estimated genome size" help="For example, 5m or 2.6g.">
|
|
kkonganti@0
|
55 <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
|
56 </param>
|
|
kkonganti@0
|
57 <param name="runtime_profile" type="select" label="Run time profile" value="kondagac">
|
|
kkonganti@0
|
58 <option value="kondagac">conda</option>
|
|
kkonganti@0
|
59 <option value="cingularitygac">singularity</option>
|
|
kkonganti@0
|
60 </param>
|
|
kkonganti@0
|
61 </inputs>
|
|
kkonganti@0
|
62 <outputs>
|
|
kkonganti@0
|
63 <data name="multiqc_report" format="html" label="MultiQC Report on ${on_string}">
|
|
kkonganti@0
|
64 <discover_datasets pattern="multiqc_report.html" assign_primary_output="true" directory="cpipes-output"/>
|
|
kkonganti@0
|
65 </data>
|
|
kkonganti@0
|
66 <data name="assembled_mags" format="fasta" label="CENTRIFLAKEN: Assembled MAGs">
|
|
kkonganti@0
|
67 <discover_datasets pattern=".*\.assembly_filtered_contigs.fasta" visible="true" directory="cpipes-output"/>
|
|
kkonganti@0
|
68 </data>
|
|
kkonganti@0
|
69 </outputs>
|
|
kkonganti@3
|
70 <tests>
|
|
kkonganti@3
|
71 <!--Test 01: long reads-->
|
|
kkonganti@3
|
72 <test expect_num_outputs="2">
|
|
kkonganti@4
|
73 <param name="input">
|
|
kkonganti@3
|
74 <collection type="list">
|
|
kkonganti@4
|
75 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
|
|
kkonganti@4
|
76 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
|
|
kkonganti@4
|
77 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
|
|
kkonganti@3
|
78 </collection>
|
|
kkonganti@3
|
79 </param>
|
|
kkonganti@3
|
80 <param name="fq_suffix" value=".fastq.gz"/>
|
|
kkonganti@3
|
81 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
|
|
kkonganti@3
|
82 <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/>
|
|
kkonganti@3
|
83 </test>
|
|
kkonganti@3
|
84 </tests>
|
|
kkonganti@0
|
85 <help><![CDATA[
|
|
kkonganti@0
|
86
|
|
kkonganti@0
|
87 .. class:: infomark
|
|
kkonganti@0
|
88
|
|
kkonganti@0
|
89 **Purpose**
|
|
kkonganti@0
|
90
|
|
kkonganti@6
|
91 Centriflaken suite of automated data analysis pipelines are based on Nextflow DSL2 developed at CFSAN, FDA. These piepelines allow rapid
|
|
kkonganti@0
|
92 and effective construction of metagenomic assembled genomes (MAGs) to enable bacterial source-tracking. It is based on methods described in our
|
|
kkonganti@0
|
93 previous publication (https://doi.org/10.1371/journal.pone.0245172).
|
|
kkonganti@0
|
94 ----
|
|
kkonganti@0
|
95
|
|
kkonganti@0
|
96 .. class:: infomark
|
|
kkonganti@0
|
97
|
|
kkonganti@0
|
98 **Testing and Validation**
|
|
kkonganti@0
|
99
|
|
kkonganti@0
|
100 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
|
101 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
|
102 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
|
103 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
|
104 and classification of STECs for each sample. We tested the pipeline with nanopore data obtained from 21 additional enriched samples from
|
|
kkonganti@0
|
105 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
|
106 done on the command line on the CFSAN Raven2 HPC Cluster.
|
|
kkonganti@0
|
107
|
|
kkonganti@0
|
108
|
|
kkonganti@0
|
109 ----
|
|
kkonganti@0
|
110
|
|
kkonganti@0
|
111 .. class:: infomark
|
|
kkonganti@0
|
112
|
|
kkonganti@0
|
113 **Outputs**
|
|
kkonganti@0
|
114
|
|
kkonganti@0
|
115 The main output files are:
|
|
kkonganti@0
|
116
|
|
kkonganti@0
|
117 ::
|
|
kkonganti@0
|
118
|
|
kkonganti@0
|
119 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
|
|
kkonganti@0
|
120 - Final assembly: contains contigs and possibly scaffolds (see below).
|
|
kkonganti@0
|
121
|
|
kkonganti@0
|
122 ]]></help>
|
|
kkonganti@0
|
123 <citations>
|
|
kkonganti@0
|
124 <citation type="bibtex">
|
|
kkonganti@0
|
125 @misc{gitlabCPIPES,
|
|
kkonganti@0
|
126 author = {Konganti, Kranti},
|
|
kkonganti@0
|
127 year = {2022},
|
|
kkonganti@0
|
128 title = {CPIPES - Centriflaken},
|
|
kkonganti@0
|
129 publisher = {GitLab},
|
|
kkonganti@0
|
130 journal = {GitLab repository},
|
|
kkonganti@0
|
131 url = {https://cfsan-git.fda.gov/Kranti.Konganti/cpipes}}
|
|
kkonganti@0
|
132 </citation>
|
|
kkonganti@0
|
133 </citations>
|
|
kkonganti@0
|
134 </tool>
|
