datduong / NLPMethods2CompareGOterms

Natural language processing methods to compare 2 Gene Ontology terms
5 stars 2 forks source link

Full paper.

Please cite from BioRxiv https://www.biorxiv.org/content/early/2018/05/14/103648.

This code introduces a word and a sentence embedding method to compare 2 Gene Ontology terms.

Go to DataSource folder to download all the needed files (more instruction inside).

Go to Code folder to download all the source code (more instruction inside).

ROCplots contains plots for the Receiver Operating Characteristic curve in the classification of human protein-protein network, and human/mouse/fly orthologs.

TrainingInferSent shows you how to train the InferSent model.

getAncestors shows you how to get the ancestors of a GO term.

In this project, along with the main result, we also created Gene names to vectors.