Mercurial > repos > kkonganti > hfp_nowayout

comparison hfp_nowayout.xml @ 0:97cd2f532efe

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author kkonganti
date Mon, 31 Mar 2025 14:50:40 -0400
parents
children fa47b825716b
comparison
equal deleted inserted replaced
-1:000000000000 0:97cd2f532efe
1 <tool id="hfp_nowayout" name="nowayout" version="0.5.0+galaxy24">
2 <description>An automated workflow to identify Mitochondrial reads and classify Eukaryotes.</description>
3 <requirements>
4 <container type="docker">quay.io/biocontainers/nextflow:24.10.4--hdfd78af_0</container>
5 </requirements>
6 <version_command>nextflow -version</version_command>
7 <command detect_errors="exit_code"><![CDATA[
8 input_path=\$(pwd)"/cpipes-input";
9 mkdir -p "\${input_path}" || exit 1;
10 #import re
11 #if (str($input_read_type_cond.input_read_type) == "single_long"):
12 #for _, $unpaired in enumerate($input_read_type_cond.input):
13 #set read1 = str($unpaired.name)
14 #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
15 #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
16 #set read1 = str($unpaired.name) + str('.') + $read1_ext
17 #end if
18 ln -sf '$unpaired' "\${input_path}/$read1";
19 #end for
20 #elif (str($input_read_type_cond.input_read_type) == "paired"):
21 #for _, $pair in enumerate($input_read_type_cond.input_pair)
22 #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
23 #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
24 #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
25 #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
26 #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
27 #set read_R1 = $read_R1 + str('.') + $read_R1_ext
28 #end if
29 #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
30 #set read_R2 = $read_R2 + str('.') + $read_R2_ext
31 #end if
32 ln -sf '$pair.forward' "\${input_path}/$read_R1";
33 ln -sf '$pair.reverse' "\${input_path}/$read_R2";
34 #end for
35 #end if
36 $__tool_directory__/0.5.0/cpipes
37 --pipeline nowayout
38 --input \${input_path}
39 --output cpipes-output
40 --fq_suffix '${input_read_type_cond.fq_suffix}'
41 #if (str($input_read_type_cond.input_read_type) == "single_long"):
42 --fq_single_end true
43 #elif (str($input_read_type_cond.input_read_type) == "paired"):
44 --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
45 #end if
46 --db_mode $nowo_db_mode
47 --nowo_thresholds $nowo_thresholds
48 --fq_filename_delim '${fq_filename_delim}'
49 --fq_filename_delim_idx $fq_filename_delim_idx
50 -profile gxkubernetes;
51 mv './cpipes-output/nowayout-multiqc/multiqc_report.html' './multiqc_report.html' || exit 1;
52 mv './cpipes-output/krona_ktimporttext/CPIPES_nowayout_krona.html './CPIPES_nowayout_krona.html' || exit 1;
53 rm -rf ./cpipes-output || exit 1;
54 rm -rf ./work || exit 1;
55 ]]></command>
56 <inputs>
57 <conditional name="input_read_type_cond">
58 <param name="input_read_type" type="select" label="Select the read collection type">
59 <option value="single_long" selected="true">Single-End short reads</option>
60 <option value="paired">Paired-End short reads</option>
61 </param>
62 <when value="single_long">
63 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
64 label="Dataset list of unpaired short reads or long reads" />
65 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/>
66 </when>
67 <when value="paired">
68 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
69 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"
70 help="For any data sets downloaded from NCBI into Galaxy, change this to _forward.fastq.gz suffix."/>
71 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
72 help="For any data sets downloaded from NCBI into Galaxy, change this to _reverse.fastq.gz suffix."/>
73 </when>
74 </conditional>
75 <param name="nowo_db_mode" type="select" label="Select the database with nowayout"
76 help="Please see below about different databases.">
77 <option value="mitomine" selected="true">mitomine</option>
78 <option value="cytox1">cytox1</option>
79 <option value="voucher">voucher</option>
80 <option value="ganoderma">ganoderma</option>
81 <option value="listeria">listeria</option>
82 </param>
83 <param name="nowo_thresholds" type="select" label="Enter the type of base quality thresholds to be set with nowayout"
84 help="The default value sets strictest thresholds that tends to filter out most of the false positive hits.">
85 <option value="strict" selected="true">strict</option>
86 <option value="relax">relax</option>
87 </param>
88 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
89 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)."/>
90 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
91 </inputs>
92 <outputs>
93 <data name="krona_chart" format="html" label="nowayout: Krona Chart on ${on_string}" from_work_dir="CPIPES_nowayout_krona.html"/>
94 <data name="multiqc_report" format="html" label="nowayout: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
95 </outputs>
96 <tests>
97 <!--Test 01: long reads-->
98 <test expect_num_outputs="2">
99 <param name="input">
100 <collection type="list">
101 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
102 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
103 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
104 </collection>
105 </param>
106 <param name="fq_suffix" value=".fastq.gz"/>
107 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
108 <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
109 </test>
110 </tests>
111 <help><![CDATA[
112
113 .. class:: infomark
114
115 **Purpose**
116
117 nowayout is a mitochondrial metagenomics classifier for Eukaryotes.
118 It uses a custom kma database to identify mitochondrial reads and
119 performs read classification followed by further read classification
120 reinforcement using sourmash.
121
122 It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at HFP.
123
124
125 ----
126
127 .. class:: infomark
128
129 ** Databases **
130
131 - mitomine: Big database that works in almost all scenarios.
132 - cytox1: Collection of only non-redundant COXI genes from NCBI.
133 - voucher: Collection of only non-redundant voucher sequences from NCBI.
134 - ganoderma: Collection of only non-redundant mtDNA sequences of Ganoderma fungi.
135 - listeria: Collection of organelle sequences and other rRNA genes for Listeria.
136
137
138 ----
139
140 .. class:: infomark
141
142 **Testing and Validation**
143
144 The CPIPES - nowayout Nextflow pipeline has been wrapped to make it work in Galaxy.
145 It takes in either paired or unpaired short reads list as an input and generates a MultiQC report
146 which contains relative abundances in context of number of mitochondrial reads identified. It also
147 generates a Krona chart for each sample. The pipeline has been tested on multiple internal insect
148 mixture samples. All the original testing and validation was done on the command line on the
149 HFP Reedling HPC Cluster.
150
151
152 ----
153
154 .. class:: infomark
155
156 ** Please note **
157
158 ::
159
160 - nowayout only works on Illumina short reads (paired or unpaired).
161 - nowayout uses a custom kma database named mitomine.
162 - The custom database will be incrementally augmented and refined over time.
163 - mitomine stats:
164 Contains ~ 2.93M non-redundant mitochondrial and voucher sequences.
165 Represents ~ 717K unique species.
166 - Other databases are also available but will be seldom updated.
167
168 ----
169
170 .. class:: infomark
171
172 **Outputs**
173
174 The main output file is a:
175
176 ::
177
178 - MultiQC Report: Contains a brief summary report including individual Mitochondrial reads identified
179 per sample and relative abundances in context of the total number of Mitochondrial reads
180 identified.
181 Please note that due to MultiQC customizations, the preview (eye icon) will not
182 work within Galaxy for the MultiQC report. Please download the file by clicking
183 on the floppy icon and view it in your browser on your local desktop/workstation.
184 You can export the tables and plots from the downloaded MultiQC report.
185
186 ]]></help>
187 <citations>
188 <citation type="bibtex">
189 @article{nowayout,
190 author = {Konganti, Kranti},
191 year = {2025},
192 month = {May},
193 title = {nowayout: An automated mitrochiondrial read classifier for Eukaryotes.},
194 journal = {Manuscript in preparation},
195 doi = {10.3389/xxxxxxxxxxxxxxxxxx},
196 url = {https://xxxxxxx/articles/10.3389/xxxxxxxxxxxx/full}}
197 </citation>
198 </citations>
199 </tool>