annotate PhageDPO.xml @ 28:2a17d4833692 draft

Uploaded
author jose_duarte
date Sun, 12 Dec 2021 10:50:13 +0000
parents
children 269e43aa8721
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
28
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
1 <tool id="PhageDPO" name="PhageDPO" version="0.1.0" python_template_version="3.5">
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
2 <description>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
3 Phage Depolymerase Finder
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
4 </description>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
5 <requirements>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
6 <requirement type="package" version="1.78">biopython</requirement>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
7 <requirement type="package" version="0.24.1">scikit-learn</requirement>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
8 <requirement type="package" version="1.19.2">numpy</requirement>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
9 <requirement type="package" version="1.2.3">pandas</requirement>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
10 </requirements>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
11 <command detect_errors="exit_code"><![CDATA[
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
12 python '$__tool_directory__/DPOGALAXY.py' '$adv.model' '${input1}'
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
13 ]]></command>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
14 <inputs>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
15 <param type="data" name="input1" format="fasta" label="Fasta file"/>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
16 <section name = 'adv' title= 'Advanced Options' expanded = 'False'>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
17 <param type = "select" name="model" label="Model">
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
18 <option value="SVM4311" selected="yes">SVM4311</option>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
19 <option value="ANN7185">ANN7185</option>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
20 </param>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
21 </section>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
22
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
23 </inputs>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
24 <outputs>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
25 <data name="output1" format="html" from_work_dir="output.html"
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
26 label="DPO Prediction"/>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
27 </outputs>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
28 <tests>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
29 <test>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
30 <param name="model" value="SVM4311"/>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
31 <param name="input1" value="fasta_file.fasta"/>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
32 <output name="output1" file="output.html"/>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
33 </test>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
34 </tests>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
35 <help><![CDATA[
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
36
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
37 ========
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
38 PhageDPO
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
39 ========
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
40
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
41 Predicts the existance of Phage Polysaccharide Depolymerase.
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
42
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
43 PhageDPO is a python script that predicts the existance of depolymerases (DPOs) using supervised machine learning models.
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
44 Two different datasets were used to develop two models: The SVM model was built using a dataset with 45 features and 4311 examples (1437 positives and 2874 negatives) and the ANN model was created using a dataset with 166 features and 7185 examples (1437 positives and 5748 negatives).
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
45
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
46 **Inputs:**
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
47
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
48 * fasta file: fasta file format contain the nucleotide sequences.
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
49
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
50 **Advanced options:**
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
51
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
52 * Model: selection of the model to run: the SVM model (default) or the ANN model. The SVM model focus on true positive detection while avoiding false positives. On the other hand, the ANN model uses more negative data ensuring that all DPOs are identified.
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
53
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
54 **Outputs:**
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
55
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
56 The tool outputs an html file containing the name of the sequence and the percentage of positive prediction for DPO.
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
57
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
58 **Requirements:**
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
59
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
60 * Biopython
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
61 * Sklearn
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
62 * Numpy
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
63 * Pandas
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
64
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
65 ]]></help>
2a17d4833692 Uploaded
jose_duarte
parents:
diff changeset
66 </tool>