1. Academic Validation
  2. A Novel Scalarized Scaffold Hopping Algorithm with Graph-Based Variational Autoencoder for Discovery of JAK1 Inhibitors

A Novel Scalarized Scaffold Hopping Algorithm with Graph-Based Variational Autoencoder for Discovery of JAK1 Inhibitors

  • ACS Omega. 2021 Aug 24;6(35):22945-22954. doi: 10.1021/acsomega.1c03613.
Yang Yu 1 Tingyang Xu 1 Jiawen Li 2 Yaping Qiu 2 Yu Rong 1 Zhen Gong 2 Xuemin Cheng 2 Liming Dong 2 Wei Liu 1 Jin Li 2 Dengfeng Dou 2 Junzhou Huang 1
Affiliations

Affiliations

  • 1 Tencent AI Lab, Tencent, Shenzhen 518057, P. R. China.
  • 2 HitGen Inc., Tianfu International Bio-Town, Chengdu 610200, Sichuan, P. R. China.
Abstract

We have developed a graph-based Variational Autoencoder with Gaussian Mixture hidden space (GraphGMVAE), a deep learning approach for controllable magnitude of scaffold hopping in generative chemistry. It can effectively and accurately generate molecules from a given reference compound, with excellent scaffold novelty against known molecules in the literature or patents (97.9% are novel scaffolds). Moreover, a pipeline for prioritizing the generated compounds was also proposed to narrow down our validation focus. In this work, GraphGMVAE was validated by rapidly hopping the scaffold from FDA-approved upadacitinib, which is an inhibitor of human Janus kinase 1 (JAK1), to generate more potent molecules with novel chemical scaffolds. Seven compounds were synthesized and tested to be active in biochemical assays. The most potent molecule has 5.0 nM activity against JAK1 kinase, which shows that the GraphGMVAE model can design molecules like how a human expert does but with high efficiency and accuracy.

Figures
Products
  • Cat. No.
    Product Name
    Description
    Target
    Research Area
  • HY-139649
    JAK抑制剂
    JAK