Pharmacophore features for machine learning in pharmaceutical virtual screening.

Journal: Molecular diversity
Published Date:

Abstract

Methods of three-dimensional molecular alignment generally treat all pharmacophore features equally when superimposing. However, some pharmacophore features can be more important in a specific system. In this work, we derived the overlap volume of pharmacophore features from a molecular alignment approach as new features of molecules to build machine learning models. Features can be assigned weights to indicate their importance. With validation on DUD-E collection, models based on pharmacophore features represented by the overlap volume yielded significant performances with median AUC of approximately 0.98 and recall rate of almost 0.8.

Authors

  • Xiaojing Wang
    Anhui Province Key Laboratory of Respiratory Tumor and Infectious Disease, First Affiliated Hospital of Bengbu Medical University, Bengbu, China.
  • Wenxiu Han
    Jining First People's Hospital, Jining Medical University, Jining, China.
  • Xin Yan
    Department of Microbiology, College of Life Sciences, Key Laboratory for Microbiological Engineering of Agricultural Environment of the Ministry of Agriculture, Nanjing Agricultural University, 6 Tongwei Road, Nanjing, Jiangsu 210095, China.
  • Jun Zhang
    First School of Clinical Medicine, Shandong University of Traditional Chinese Medicine, Jinan, China.
  • Mengqi Yang
    Jining First People's Hospital, Jining Medical University, Jining, China.
  • Pei Jiang
    College of Mechanical Engineering, Chongqing University, Chongqing 400030, People's Republic of China.