Predicting gene functions from text using a cross-species approach.
We propose a cross-species approach for assigning Gene Ontology terms to LocusLink genes based on evidence extracted from biomedical journal articles. We make use of information from orthologous genes to derive and merge two sets of GO codes for a given target gene. For the first set, we restrict GO code assignments to be selected from only those codes which have already been assigned to the target gene's ortholog. Since this approach results in high precision but low recall, for the second set, we allow any GO code to be a candidate, but then eliminate those codes which are illogical to pair with a GO code that is known to be associated with the orthologous gene. Experimental results on three datasets show that the F-measure obtained with this algorithm is consistently higher than the F-measure of other current solutions.