Open Access Highly Accessed Open Badges Software

BioGraph: unsupervised biomedical knowledge discovery via automated hypothesis generation

Anthony ML Liekens1*, Jeroen De Knijf2, Walter Daelemans3, Bart Goethals2, Peter De Rijk1 and Jurgen Del-Favero1

Author Affiliations

1 Applied Molecular Genomics group, VIB Department of Molecular Genetics, Universiteit Antwerpen, Universiteitsplein 1, 2610 Wilrijk, Belgium

2 Advanced Database Research and Modelling group, Department of Mathematics and Computer Science, Universiteit Antwerpen, Groenenborgerlaan 171, 2020 Antwerpen, Belgium

3 Computational Linguistics and Psycholinguistics Research Center, Universiteit Antwerpen, Prinsstraat 13, 2000, Antwerpen, Belgium

For all author emails, please log on.

Genome Biology 2011, 12:R57  doi:10.1186/gb-2011-12-6-r57

Published: 22 June 2011

Additional files

Additional file 1:

Additional materials and methods and Additional Tables. Detailed methods describing technicalities of the database integration and algorithms, with the following sections. Knowledge integration: detecting hub nodes by computing a priori probabilities with random walks; computing a posteriori probabilities and ranking relations; backtracking heuristic for the automated generation of functional hypotheses; additional results. Additional Table 1: top 50 hubs or highest ranking concepts of the computation of the a priori rank score in the integrated network. Additional Table 2: area under the receiver operator characteristic (ROC) curve (AUC) for the prioritization of disease genes in the Endeavour benchmark. Additional Table 3: effect on the Endeavour benchmark after leaving out each separate database from the data integration process.

Format: DOC Size: 270KB Download file

This file can be viewed with: Microsoft Word Viewer

Open Data