Neural networks prediction of the protein-ligand binding affinity with circular fingerprints.

Journal: Technology and health care : official journal of the European Society for Engineering and Medicine
Published Date:

Abstract

BACKGROUND: Protein-ligand binding affinity is of significant importance in structure-based drug design. Recently, the development of machine learning techniques has provided an efficient and accurate way to predict binding affinity. However, the prediction performance largely depends on how molecules are represented.

Authors

  • Zuode Yin
    Institute of Bioinformatics and Medical Engineering, Jiangsu University of Technology, Changzhou, Jiangsu, China.
  • Wei Song
    School of Pharmaceutical Science, Jiangnan University, Wuxi, 214122, Jiangsu, China.
  • Baiyi Li
    Institute of Bioinformatics and Medical Engineering, Jiangsu University of Technology, Changzhou, Jiangsu, China.
  • Fengfei Wang
    School of Mathematics and Physics, Jiangsu University of Technology, Changzhou, Jiangsu, China.
  • Liangxu Xie
    Institute of Bioinformatics and Medical Engineering, Jiangsu University of Technology, Changzhou, 213001, China. Electronic address: xieliangxu@jsut.edu.cn.
  • Xiaojun Xu
    Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China; Joint Laboratory of Clinical Radiology, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.