Learning-to-rank based compound virtual screening by using pairwise kernel with multiple heterogeneous experimental data
翔吾 鈴木, 雅史 大上, Masahito Ohue, 泰 秋山, Yutaka Akiyama, Yutaka Akiyama · Institutional Repositories DataBase (IRDB) · 2017
The development of a new drug takes over 10 years and costs approximately US$2.6 billion. Virtual compound screening (VS) is part of the effort to reduce the cost. Learning- to-rank is a machine learning technique in information retrieval that was recently introduced to VS. It works well because the application of VS requires the ranking of compounds. Moreover, learning-to-rank can treat multiple heterogeneous experimental data because it is trained using only the order of activity of compounds. In this study, we propose PKRank, a learning-to-rank based VS method that uses a pairwise kernel defined as the product of a compound kernel and a protein kernel. PKRank is a general case of the previous method by Zhang et al. with the advantage of extensibility in terms of kernel selection. In comparisons of predictive accuracy, PKRank yielded a more accurate model than the previous method.