annotate run_galaxy.xml @ 4:1389cfeefb76 draft

Uploaded
author pedro_araujo
date Fri, 29 Jan 2021 16:04:58 +0000
parents e4b3fc88efe0
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
1 <tool id="run_galaxy" name="PhageHostPrediction" version="0.1.0" python_template_version="3.5">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
2 <description>prediction of phage-bacteria interactions</description>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
3 <requirements>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
4 <requirement type="package">biopython</requirement>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
5 <requirement type="package">scikit-learn</requirement>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
6 <requirement type="package">numpy</requirement>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
7 <requirement type="package">pandas</requirement>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
8 <requirement type="package">scikit-bio</requirement>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
9 </requirements>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
10 <command detect_errors="exit_code" interpreter="python3"><![CDATA[
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
11 $__tool_directory__/run_galaxy.py
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
12 $input_phage.phage_input_type $input_phage.phages
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
13
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
14 $input_bact.bact_input_type $input_bact.bacts
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
15
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
16 $adv.run_interpro $adv.ml_model
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
17
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
18 ]]></command>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
19 <inputs>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
20 <conditional name="input_phage">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
21 <param type="select" name="phage_input_type" label='Phage input:'>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
22 <option value="ID" selected="true">NCBI IDs (comma separated)</option>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
23 <option value="seq_file" selected="false">Sequence fasta file (only one organism)</option>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
24 </param>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
25 <when value="ID">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
26 <param type="text" name="phages" label='Phage IDs'/>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
27 </when>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
28 <when value="seq_file">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
29 <param type="data" name="phages" label='Phage fasta file' format="fasta"/>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
30 </when>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
31 </conditional>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
32
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
33 <conditional name="input_bact">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
34 <param type="select" name="bact_input_type" label='Bacteria input:'>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
35 <option value="ID" selected="true">NCBI IDs (comma separated)</option>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
36 <option value="seq_file" selected="false">Sequence fasta file (only one organism)</option>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
37 </param>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
38 <when value="ID">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
39 <param type="text" name="bacts" label='Bacteria IDs'/>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
40 </when>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
41 <when value="seq_file">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
42 <param type="data" name="bacts" label='Bacteria fasta file' format="fasta"/>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
43 </when>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
44 </conditional>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
45
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
46 <section name='adv' lable="Advanced options" title='Advanced Options' expanded='false'>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
47 <param type="boolean" name="run_interpro" label='Perform interpro search' checked="false" truevalue="True" falsevalue="False" />
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
48 <param type="select" name="ml_model" label="Machine learning model">
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
49 <option value="RandomForests" selected="yes">Random Forests</option>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
50 <option value="SVM">SVM</option>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
51 </param>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
52 </section>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
53 </inputs>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
54 <outputs>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
55 <data name="output1" format="tabular" from_work_dir="output.tsv" />
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
56 </outputs>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
57 <help>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
58
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
59 PhageHostPrediction
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
60 ===================
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
61
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
62 Predict interactions between phages and bacterial strains.
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
63
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
64 PhageHostPrediction is a python script that predicts phage-host interactions for *E. coli*, *K. pneumoniae* and *A. baumannii* phages, using supervised machine learning models. The models were built from a dataset containing 252 features and 23 987 entries with balanced outputs of 'Yes' and 'No'. The positive cases of interaction predicted are described in the file "NCBI_Phage_Bacteria_Data.csv", contained within this tool, while the negative were randomly assigned by pairing phages with bacteria of different species.
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
65
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
66 The prediction resorts to complete host proteome and to phage tail proteins, that are inferred within the tool. This inference is made with a locally created database of phage protein functions, available in the file "phagesProteins.json". Unknown proteins are predicted against this database. To help with this prediction, the use of InterProScan is made optional.
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
67
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
68 **Inputs:**
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
69
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
70 * phage/bacteria genome format: ID vs fasta;
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
71 * ID: must be a GenBank ID, with the proteome described;
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
72 * fasta file: must contain the whole proteome of the organism;
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
73 * machine learning model: random forests have better predictive power, while SVM can be slightly faster to run;
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
74 * interpro search: should predict tails with higher confidence, but it significantly increases time to run.
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
75
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
76 **Outputs:**
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
77 this tool outputs a tabular file in which phage-host pairs are present in the first column and the prediction result in the second.
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
78
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
79 **Requirements:**
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
80
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
81 * Biopython
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
82 * Scikit-learn
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
83 * Numpy
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
84 * Pandas
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
85 * Scikit-bio
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
86 * BLAST_ - must be installed locally and available globally as an environment variable
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
87 * InterProScan_ (optional) - must be installed locally and available globally as an environment variable
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
88
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
89 .. _BLAST: https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/LATEST/
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
90 .. _InterProScan: http://www.ebi.ac.uk/interpro/download/
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
91
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
92 </help>
e4b3fc88efe0 Uploaded
pedro_araujo
parents:
diff changeset
93 </tool>