Ping An breaks through with AI-driven drug research
This is expected to speed up drug discovery which at present takes up to 15 years.
Ping An Healthcare Technology Research Institute and Tsinghua University has made a breakthrough using deep learning for drug discovery, the Ping An Insurance (Group) Company of China, Ltd. announced.
Drug discovery can take 10 to 15 years from invention to market. But with drug discovery using artificial intelligence it could be accelerated.
“Ping An’s research proposed a novel deep learning framework, named MPG, that learns molecular representations from large volumes of unlabeled molecules, and a powerful GNN, called MolGNet, for modelling molecular graphs,” the company said.
Ping An’s findings were published in the “An effective self-supervised framework for learning expressive molecular global representations to drug discovery” in Briefings in Bioinformatics.
Ping An’s research also proposed a self-supervised pre-training strategy, named Pairwise Half-graph Discrimination.
The research found that after pre-training on 11 million unlabeled molecules, MolGNet can capture meaningful patterns of molecules to produce an interpretable representation.
The findings, Ping An said, is an important first step towards graph-level self-supervised learning on large-scale molecule datasets.
The technology is being used by Ping An Shionogi, a joint venture founded by Ping An and Shionogi & Co., Ltd. a Japanese research-driven pharmaceutical company, for research and development of new drugs and drug repurposing.