A small-scale data driven and graph neural network based toxicity prediction method of compounds.

Journal: Computational biology and chemistry
PMID:

Abstract

Toxicity prediction is crucial in drug discovery, helping identify safe compounds and reduce development risks. However, the lack of known toxicity data for most compounds is a major challenge. Recently, data-driven models have gained attention as a more efficient alternative to traditional in vivo and in vitro experiments. In this paper, we propose a small-scale, data-driven toxicity prediction method based on Graph Neural Network (GNN). We introduce a joint learning strategy for multiple toxicity types and construct a graph-based model, JLGCN-MTT, to improve prediction accuracy. In addition, we integrate a transfer learning strategy that leverages data from multiple toxicity types, allowing the model to make reliable predictions even when data for a specific toxicity type is limited. We conducted experiments using data from 3566 compounds in the Tox21 dataset, which contains 12 types of toxicity-related bioactivity data. The experimental results show that JLGCN-MTT outperforms traditional machine learning methods and single-task GNN in all 12 toxicity prediction tasks, with AUC improving by over 10% in 11 tasks. For small-scale data with 50, 100, and 300 training samples, the AUC improved in all cases, with the highest improvement of 11% observed when the sample size was 50. These results demonstrate that the small-scale, data-driven toxicity prediction method we propose can achieve high prediction accuracy.

Authors

  • Xin Zhao
    Florida International University.
  • Shuyi Zhang
    Department of Intensive Care Medicine, Renji Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Tao Zhang
    Department of Traumatology, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, 40044, People's Republic of China.
  • Yahui Cao
    School of Electronic and Information Engineering, Tianjin University, 92 Weijin Road, Tianjin, 300072, Tianjin, China.
  • Jingjing Liu
    School of Electro-Mechanical Engineering, Xidian University, Xi'an 710071, China.