Link Mining for Kernel-based Compound-Protein Interaction Predictions Using a Chemogenomics Approach
This work addresses a bottleneck in computational drug discovery for researchers by incrementally enhancing prediction accuracy for new compounds.
The study tackled the problem of poor performance in predicting interactions for new compounds in chemogenomics-based virtual screening by improving the pairwise kernel method with link mining, achieving an AUPR of 0.562 compared to 0.425 for the conventional method with minimal increase in computation time.
Virtual screening (VS) is widely used during computational drug discovery to reduce costs. Chemogenomics-based virtual screening (CGBVS) can be used to predict new compound-protein interactions (CPIs) from known CPI network data using several methods, including machine learning and data mining. Although CGBVS facilitates highly efficient and accurate CPI prediction, it has poor performance for prediction of new compounds for which CPIs are unknown. The pairwise kernel method (PKM) is a state-of-the-art CGBVS method and shows high accuracy for prediction of new compounds. In this study, on the basis of link mining, we improved the PKM by combining link indicator kernel (LIK) and chemical similarity and evaluated the accuracy of these methods. The proposed method obtained an average area under the precision-recall curve (AUPR) value of 0.562, which was higher than that achieved by the conventional Gaussian interaction profile (GIP) method (0.425), and the calculation time was only increased by a few percent.