Sfcnn: a novel scoring function based on 3D convolutional neural network for accurate and stable protein-ligand affinity prediction.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Computer-aided drug design provides an effective method of identifying lead compounds. However, success rates are significantly bottlenecked by the lack of accurate and reliable scoring functions needed to evaluate binding affinities of protein-ligand complexes. Therefore, many scoring functions based on machine learning or deep learning have been developed to improve prediction accuracies in recent years. In this work, we proposed a novel featurization method, generating a new scoring function model based on 3D convolutional neural network.

Authors

  • Yu Wang
    Clinical and Technical Support, Philips Healthcare, Shanghai, China.
  • Zhengxiao Wei
    Department of Clinical Laboratory, Public Health Clinical Center of Chengdu, Chengdu, 610095, China.
  • Lei Xi
    Ministry-of-Education Key Laboratory of Laboratory Medical Diagnostics, College of Laboratory Medicine, Chongqing Medical University, Chongqing 400016, China.