view PhageDPO.xml @ 28:2a17d4833692 draft

Uploaded
author jose_duarte
date Sun, 12 Dec 2021 10:50:13 +0000
parents
children 269e43aa8721
line wrap: on
line source

<tool id="PhageDPO" name="PhageDPO" version="0.1.0" python_template_version="3.5">
	<description>
Phage Depolymerase Finder
	</description>
    <requirements>
        <requirement type="package" version="1.78">biopython</requirement>
        <requirement type="package" version="0.24.1">scikit-learn</requirement>
        <requirement type="package" version="1.19.2">numpy</requirement>
        <requirement type="package" version="1.2.3">pandas</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        python '$__tool_directory__/DPOGALAXY.py' '$adv.model' '${input1}'
    ]]></command>
    <inputs>
		<param type="data" name="input1" format="fasta" label="Fasta file"/>
		<section name = 'adv' title= 'Advanced Options' expanded = 'False'>
		<param type = "select" name="model" label="Model">
		   <option value="SVM4311" selected="yes">SVM4311</option>
		   <option value="ANN7185">ANN7185</option>
		</param>
	</section>
		
    </inputs>
    <outputs>
		<data name="output1" format="html" from_work_dir="output.html" 
		label="DPO Prediction"/>
    </outputs>
	<tests>
        <test>
			<param name="model" value="SVM4311"/>
	        <param name="input1" value="fasta_file.fasta"/>
            <output name="output1" file="output.html"/>
        </test>
    </tests>
    <help><![CDATA[
	
========
PhageDPO
========

Predicts the existance of Phage Polysaccharide Depolymerase.

PhageDPO is a python script that predicts the existance of depolymerases (DPOs) using supervised machine learning models. 
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).

**Inputs:**

* fasta file: fasta file format contain the nucleotide sequences.

**Advanced options:**
	
* 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.	
	
**Outputs:**

The tool outputs an html file containing the name of the sequence and the percentage of positive prediction for DPO.	

**Requirements:**
	
* Biopython
* Sklearn 
* Numpy
* Pandas 

    ]]></help>
</tool>