This article is part of the supplement: Proceedings of the 5th International Conference of the Brazilian Association for Bioinformatics and Computational Biology (X-meeting 2009)

Open Access Proceedings

A machine learning approach for genome-wide prediction of morbid and druggable human genes based on systems-level data

Pedro R Costa, Marcio L Acencio* and Ney Lemke

Departamento de Física e Biofísica, Instituto de Biociências de Botucatu, UNESP - Univ Estadual Paulista, Distrito de Rubião Jr. s/n, Botucatu, São Paulo, 18618-970, Brazil

For all author emails, please log on.

BMC Genomics 2010, 11(Suppl 5):S9 doi:10.1186/1471-2164-11-S5-S9

Published: 22 December 2010

Additional files

Additional file 1:

Network topological features Description: This file includes a table showing the functions and descriptions of the 12 network topological features used as learning attributes for training the classifier algorithm

Format: PDF Size: 45KB Download file

This file can be viewed with: Adobe Acrobat Reader

Open Data

Additional file 2:

Morbidity and druggability scores of genes in INHGI Description: Tab-limited text file containing all genes (Entrez GeneIDs) in the INHGI with their morbidity and druggability scores.

Format: TXT Size: 1.1MB Download file

Open Data

Additional file 3:

Parameters used to train the meta-classifier and J48 Description: File containing all parameters values used to train the meta-classifier for prediction of morbid and druggable genes and all parameters values used to train the J48 algorithm to generate decision trees for discovery of cellular rules for morbidity and druggability.

Format: PDF Size: 53KB Download file

This file can be viewed with: Adobe Acrobat Reader

Open Data