Chinese scientists design AI tool to expediate drug discovery

SHANGHAI -- A team of Chinese scientists proposed a new artificial intelligence (AI) tool that may help significantly speed up the process of discovering drugs.

The researchers from the Shanghai Institute of Materia Medica under the Chinese Academy of Sciences, described PBCNet, or pairwise binding comparison network, in a study recently published in the journal Nature Computational Science.

The AI tools have been widely used for hunting chemicals that can potentially be translated into drugs, but their efficiency continues to pose a challenge.

The PBCNet is designed for comparing the relative binding affinity among similar ligands -- molecules or ions that bind to larger molecules, according to the study.

A simulation-based experiment showed that active learning-optimized PBCNet may accelerate structure optimization by 473 percent and save computing resources by an average of 30 percent.

The team also established an open-source web service with an easy-to-operate graphical interface for the convenience of users. The tool can be used at pbcnet.alphama.com.cn.