Abstract
Synthetic lethality (SL) is a promising concept for novel discovery of anti-cancer drug targets. However, wet-lab experiments for detecting SLs are faced with various challenges, such as high cost, low consistency across platforms, or cell lines. Therefore, computational predictionmethods are needed to address these issues. This paper proposes a novel SL predictionmethod, named (SLMF)-M-2, which employs logisticmatrix factorization to learn latent representations of genes fromthe observed SL data. The probability that two genes are likely to form SL ismodeled by the linear combination of gene latent vectors. As known SL pairs aremore trustworthy than unknown pairs, we design importance weighting schemes to assign higher importance weights for known SL pairs and lower importance weights for unknown pairs in (SLMF)-M-2. Moreover, we also incorporate biological knowledge about genes fromprotein-protein interaction (PPI) data and Gene Ontology (GO). In particular, we calculate the similarity between genes based on theirGOannotations and topological properties in the PPI network. Extensive experiments on the SL interaction data fromSynLethDB database have been conducted to demonstrate the effectiveness of (SLMF)-M-2.