MPFit

This is the landing page of the release of source code and supplementary files for the research article "Genome-scale prediction of moonlighting proteins using diverse protein association information" by Ishita K Khan & Daisuke Kihara, Bioinformatics, 32: 2281-2288 (2016)

Source code is available in .tar.gz format. A ReadMe file is provided with necessary information to run the codes.
MPFit Source Code

Uniprot Accessions of Moonlighting Proteins
Contains Uniprot accession numbers of moonlighting proteins taken from the MOONPROT database in Nov, 2014.
Uniprot Accessions of non-Moonlighting Proteins
Contains Uniprot accession numbers of non-moonlighting proteins selected from Uniprot database version Nov, 2014
MPFit-Predicted Moonlighting Proteins in Yeast
Contains two columns: the first column specifies the Uniprot accession numbers of predicted moonlighting proteins in the yeast genome by MPFit model, and second column specifies the gene ontology (GO) annotations in Uniprot of the protein in the previous column.
MPFit-Predicted Moonlighting Proteins in Celegans
Contains two columns: the first column specifies the Uniprot accession numbers of predicted moonlighting proteins in the C. elegans genome by MPFit model, and second column specifies the gene ontology (GO) annotations in Uniprot of the protein in the previous column.
MPFit-Predicted Moonlighting Proteins in Human
Contains two columns: the first column specifies the Uniprot accession numbers of predicted moonlighting proteins in the human genome by MPFit model, and second column specifies the gene ontology (GO) annotations in Uniprot of the protein in the previous column.

If you have any questions or suggestions, please feel free to contact us ([email protected]).

Moonlighting protein Prediction with Missing Feature Imputation