作者: Pietro Pinoli , Davide Chicco , Marco Masseroli
DOI: 10.1109/BIBE.2013.6701702
关键词:
摘要: Genomic annotations with functional controlled terms, such as the Gene Ontology (GO) ones, are paramount in modern biology. Yet, they known to be incomplete, since current biological knowledge is far definitive. In this scenario, computational methods that able support and quicken curation of these can very useful. a previous work, we discussed benefits using Probabilistic Latent Semantic Analysis algorithm order predict novel GO annotations, compared some Singular Value Decomposition (SVD) based approaches. paper, propose further enhancement method, which aims at weighting available associations between genes terms before them input predictive system. The tests performed on human showed efficacy our approach.