|
0
|
1 <tool id="hfp_cronology_awsbatch" name="cronology" version="0.2.0+awsbatch">
|
|
|
2 <description>An automated workflow for Cronobacter isolate assembly, sequence typing and traceback.</description>
|
|
|
3 <requirements>
|
|
|
4 <container type="docker">quay.io/galaxytrakr/mulled-v2-ebd88135862aa647eeae73d4d8e6ea8ec81245cd:v5.0</container>
|
|
|
5 </requirements>
|
|
|
6 <version_command>nextflow -version</version_command>
|
|
|
7 <command detect_errors="exit_code"><![CDATA[
|
|
|
8 export MAMBA_ROOT_PREFIX="/server/galaxy/data/nextflow-micromamba-cache";
|
|
|
9 export NXF_HOME=\$(pwd)"/.nextflow-home";
|
|
|
10 mkdir -p cpipes-input || exit 1;
|
|
|
11 echo -e 'We attempted to create a tree and upload to microreact.org. The following is the log of that attempt\nand contains the URL if it was successful.\n\n' > upload_to_microreact.txt || exit 1;
|
|
|
12 pwd_path=\$(pwd);
|
|
|
13 #import re
|
|
|
14 #if (str($input_read_type_cond.input_read_type) == "single_long"):
|
|
|
15 #for _, $unpaired in enumerate($input_read_type_cond.input):
|
|
|
16 #set read1 = str($unpaired.name)
|
|
|
17 #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
|
|
|
18 #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
|
|
|
19 #set read1 = str($unpaired.name) + str('.') + $read1_ext
|
|
|
20 #end if
|
|
|
21 ln -sf '$unpaired' './cpipes-input/$read1';
|
|
|
22 #end for
|
|
|
23 #elif (str($input_read_type_cond.input_read_type) == "paired"):
|
|
|
24 #for _, $pair in enumerate($input_read_type_cond.input_pair)
|
|
|
25 #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
|
|
|
26 #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
|
|
|
27 #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
|
|
|
28 #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
|
|
|
29 #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
|
|
|
30 #set read_R1 = $read_R1 + str('.') + $read_R1_ext
|
|
|
31 #end if
|
|
|
32 #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
|
|
|
33 #set read_R2 = $read_R2 + str('.') + $read_R2_ext
|
|
|
34 #end if
|
|
|
35 ln -sf '$pair.forward' './cpipes-input/$read_R1';
|
|
|
36 ln -sf '$pair.reverse' './cpipes-input/$read_R2';
|
|
|
37 #end for
|
|
|
38 #end if
|
|
|
39 $__tool_directory__/0.2.0/cpipes
|
|
|
40 --pipeline cronology
|
|
|
41 --input \${pwd_path}/cpipes-input
|
|
|
42 --output \${pwd_path}/cpipes-output
|
|
|
43 --fq_suffix '${input_read_type_cond.fq_suffix}'
|
|
|
44 #if (str($input_read_type_cond.input_read_type) == "single_long"):
|
|
|
45 --fq_single_end true
|
|
|
46 #elif (str($input_read_type_cond.input_read_type) == "paired"):
|
|
|
47 --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
|
|
|
48 #end if
|
|
|
49 --ref_acc $refgenome
|
|
|
50 --tuspy_n $tuspy_n
|
|
|
51 --fq_filename_delim '${fq_filename_delim}'
|
|
|
52 --fq_filename_delim_idx $fq_filename_delim_idx
|
|
|
53 -profile stdkondagac;
|
|
|
54 mv './cpipes-output/cronology-multiqc/multiqc_report.html' './multiqc_report.html' || exit 1;
|
|
|
55 mv './cpipes-output/mashtree/hitsTree.dnd' './hitsTree.newick' || exit 1;
|
|
|
56 cat ./cpipes-output/upload_microreact/microreact_url.txt >> upload_to_microreact.txt || exit 1;
|
|
|
57 ]]></command>
|
|
|
58 <inputs>
|
|
|
59 <conditional name="input_read_type_cond">
|
|
|
60 <param name="input_read_type" type="select" label="Select the read collection type">
|
|
|
61 <option value="single_long" selected="true">Single-End short reads</option>
|
|
|
62 <option value="paired">Paired-End short reads</option>
|
|
|
63 </param>
|
|
|
64 <when value="single_long">
|
|
|
65 <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
|
|
|
66 label="Dataset list of unpaired short reads or long reads" />
|
|
|
67 <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/>
|
|
|
68 </when>
|
|
|
69 <when value="paired">
|
|
|
70 <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
|
|
|
71 <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"
|
|
|
72 help="For any data sets downloaded from NCBI into Galaxy, change this to _forward.fastq.gz suffix."/>
|
|
|
73 <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
|
|
|
74 help="For any data sets downloaded from NCBI into Galaxy, change this to _reverse.fastq.gz suffix."/>
|
|
|
75 </when>
|
|
|
76 </conditional>
|
|
|
77 <param name="refgenome" optional="true" value="GCF_003516125" type="text"
|
|
|
78 label="NCBI reference genome accession"
|
|
|
79 help="Is the reference genome other than Cronobacter sakazakii? Reference genome FASTA is used as a model for gene prediction. DO NOT ENTER THE DECIMAL PART (Ex: GCF_003516125.1)." />
|
|
|
80 <param name="tuspy_n" optional="true" value="5" type="integer" label="Enter the number of top unique hits to retain after initial MASH screen step"
|
|
|
81 help="These hits will be used to build a genome distance based tree for your experiment run. Default value of 2 is suitable for almost all scenarios."/>
|
|
|
82 <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)"
|
|
|
83 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)."/>
|
|
|
84 <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
|
|
|
85 </inputs>
|
|
|
86 <outputs>
|
|
|
87 <data name="multiqc_report" format="html" label="cronology: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
|
|
|
88 <data name="mashtree" format="nhx" label="cronology: Genome distance based tree on ${on_string}" from_work_dir="hitsTree.newick"/>
|
|
|
89 <data name="microreact" format="txt" label="cronology: Tree result from microreact.org ${on_string}" from_work_dir="upload_to_microreact.txt"/>
|
|
|
90 <collection name="itol_metadata" type="list" label="cronology: iTOL Metadata: ${on_string}">
|
|
|
91 <discover_datasets pattern="(?P<name>.*)\.txt" ext="txt" directory="./cpipes-output/cat_unique" match_relative_path="true" />
|
|
|
92 </collection>
|
|
|
93 <collection name="gene_models" type="list" label="cronology: Predicted gene models: ${on_string}">
|
|
|
94 <discover_datasets pattern=".*\/(?P<name>.*)\.gff" ext="gff" directory="./cpipes-output/prokka" recurse="true" match_relative_path="true" />
|
|
|
95 </collection>
|
|
|
96 <collection name="assemblies" type="list" label="cronology: Polished genome assemblies: ${on_string}">
|
|
|
97 <discover_datasets pattern="(?P<name>.*)\.fa" ext="fa" directory="./cpipes-output/polypolish" match_relative_path="true" />
|
|
|
98 </collection>
|
|
|
99 </outputs>
|
|
|
100 <tests>
|
|
|
101 <!--Test 01: long reads-->
|
|
|
102 <test expect_num_outputs="2">
|
|
|
103 <param name="input">
|
|
|
104 <collection type="list">
|
|
|
105 <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
|
|
|
106 <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
|
|
|
107 <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
|
|
|
108 </collection>
|
|
|
109 </param>
|
|
|
110 <param name="fq_suffix" value=".fastq.gz"/>
|
|
|
111 <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
|
|
|
112 <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
|
|
|
113 </test>
|
|
|
114 </tests>
|
|
|
115 <help><![CDATA[
|
|
|
116
|
|
|
117 .. class:: infomark
|
|
|
118
|
|
|
119 **Purpose**
|
|
|
120
|
|
|
121 cronology is an automated workflow for Cronobacter isolate assembly,
|
|
|
122 sequencing typing and traceback. The workflow version 0.1.0 takes in single-end
|
|
|
123 or paired-end Illumina short read data, performs QC using fastp, assembly and polish using shovill and polypolish
|
|
|
124 and whole genome distance based clustering using mashtree based on NCBI Pathogen Detection DB for Cronobacter.
|
|
|
125
|
|
|
126 It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at CFSAN.
|
|
|
127
|
|
|
128
|
|
|
129 ----
|
|
|
130
|
|
|
131 .. class:: infomark
|
|
|
132
|
|
|
133 **Testing and Validation**
|
|
|
134
|
|
|
135 The CPIPES - cronology Nextflow pipeline has been wrapped to make it work in Galaxy.
|
|
|
136 All the testing has been done on the command line on the CFSAN Raven2 HPC Cluster.
|
|
|
137
|
|
|
138
|
|
|
139 ----
|
|
|
140
|
|
|
141 .. class:: infomark
|
|
|
142
|
|
|
143 **Outputs**
|
|
|
144
|
|
|
145 The main output files are:
|
|
|
146
|
|
|
147 ::
|
|
|
148
|
|
|
149 - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
|
|
|
150 Please note that due to MultiQC customizations, the preview (eye icon) will not
|
|
|
151 work within Galaxy for the MultiQC report. Please download the file by clicking
|
|
|
152 on the floppy icon and view it in your browser on your local desktop/workstation.
|
|
|
153 You can export the tables and plots from the downloaded MultiQC report.
|
|
|
154 - Polished de novo assemblies (FASTA) for each sample.
|
|
|
155 - Genome annotations (GFF) for each sample.
|
|
|
156 - Whole genome distance based clustering tree (Newick).
|
|
|
157 - Additional metadata useful for uploading the Newick tree into iTOL.
|
|
|
158 - A https://microreact.org URL stored in a TXT file. An attempt will be made to upload the tree (Newick)
|
|
|
159 to https://microreact.org and if successful, the URL will be retrieved and stored in this TXT file.
|
|
|
160
|
|
|
161 ]]></help>
|
|
|
162 <citations>
|
|
|
163 <citation type="bibtex">
|
|
|
164 @article{cronology,
|
|
|
165 author = {Konganti, Kranti},
|
|
|
166 year = {2024},
|
|
|
167 month = {May},
|
|
|
168 title = {cronology: An automated workflow for Cronobacter isolate assembly, sequence typing and traceback},
|
|
|
169 journal = {Unpublished},
|
|
|
170 doi = {xx.xxxx/xxxxx.2024.xxxxxxxxxx},
|
|
|
171 url = {https://github.com/CFSAN-Biostatistics/cronology}}
|
|
|
172 </citation>
|
|
|
173 </citations>
|
|
|
174 </tool>
|
