Mercurial > repos > jay > pdaug_word_vector_descriptor
view PDAUG_Word_Vector_Descriptor/PDAUG_Word_Vector_Descriptor.xml @ 7:9749ee65cf47 draft
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 32b9c48c81639a81be24bb3e2f48dc0a81c0deca"
author | jay |
---|---|
date | Sun, 09 Jan 2022 04:53:41 +0000 |
parents | a3a1d9bea1ad |
children |
line wrap: on
line source
<tool id="pdaug_word_vector_descriptor" name="PDAUG Word Vector Descriptor" version="0.1.0" python_template_version="3.7"> <description>Calculates word vector descriptor</description> <requirements> <requirement type="package" version="3.5">nltk</requirement> <requirement type="package" version="1.0.3">pandas</requirement> <requirement type="package" version="1.76">biopython</requirement> <requirement type="package" version="3.8.0">gensim</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ python '$__tool_directory__/PDAUG_Word_Vector_Descriptor.py' -I '$Input' -M '$ModelInput' -R '$row' -P '$positive' -N '$negative' -O '$output' ]]></command> <inputs> <param name="ModelInput" type="data" label="Input model file" value="model.txt" format="txt" argument= "--ModelInput" help="Input word Vector model file"/> <param name="Input" type="data" label="Training data" format="fasta" argument= "--InputFasta" help="Input tabular data file "/> <param name="row" type="integer" label="Number of traning samples" value="200" argument= "--row" help="Number of positive and negative samples"/> <param name="positive" type="integer" label="Positives samples" value="100" argument= "--positive" help="Number of positive samples"/> <param name="negative" type="integer" label="Negative samples" value="100" argument= "--negative" help="Number of ngative samples"/> </inputs> <outputs> <data name='output' format='tabular' label="${tool.name} on $on_string - (tabular)" /> </outputs> <tests> <test> <param name="Input" value="test.fasta" /> <param name="ModelInput" value="model.txt" /> <param name="row" value="276" /> <param name="positive" value="138" /> <param name="negative" value="138" /> <output name="output" value="Out.tsv" /> </test> </tests> <help><![CDATA[ .. class:: infomark **What it does** Calculates word vector based descriptors derived from the Skip-gram model. ----- **Inputs** * **--InputFasta** A fasta file with negative and positive samples. * **--ModelInput** Skip-gram model as ".txt" file generated from "Word_Vector_Model". * **--row** Number of training samples. * **--positive** Positive samples. * **--negative** Negative samples. ----- **Outputs** * **--OutFile** Tabular file with descriptor data.]]></help> <citations> <citation type="bibtex"> @misc{PDAUGGITHUB, author = {Joshi, Jayadev and Blankenberg, Daniel}, year = {2020}, title ={PDAUG - a Galaxy based toolset for peptide library analysis, visualization, and machine learning modeling}, publisher = {GitHub}, journal = {GitHub repository}, url = {https://github.com/jaidevjoshi83/pdaug.git}, } </citation> <citation type="bibtex"> @inproceedings{rehurek_lrec, title = {{Software Framework for Topic Modelling with Large Corpora}}, author = {Radim {\v R}eh{\r u}{\v r}ek and Petr Sojka}, booktitle = {{Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks}}, pages = {45--50}, year = 2010, month = May, day = 22, publisher = {ELRA}, address = {Valletta, Malta}, url={http://is.muni.cz/publication/884893/en}, language={English} } </citation> <citation type="bibtex"> @article{Md_Nafiz, title= {Identifying antimicrobial peptides using word embedding with deep recurrent neural networks}, volume={35}, DOI={https://doi.org/10.1093/bioinformatics/bty937}, issue={12}, year={2018}, pages={2009-2016}, journal={Europe PMC}, author={Hamid, Md-Nafiz and Friedberg, Iddo} } </citation> </citations> </tool>