Transfer Learning with a Graph Attention Network and Weighted Loss Function for Screening of Persistent, Bioaccumulative, Mobile, and Toxic Chemicals

Haobo Wang; Wenjia Liu; Jingwen Chen; Shengshe Ji

doi:10.1021/acs.est.4c11085

Transfer Learning with a Graph Attention Network and Weighted Loss Function for Screening of Persistent, Bioaccumulative, Mobile, and Toxic Chemicals

Environ Sci Technol. 2024 Dec 16. doi: 10.1021/acs.est.4c11085. Online ahead of print.

Authors

Haobo Wang¹, Wenjia Liu¹, Jingwen Chen¹, Shengshe Ji¹

Affiliation

¹ Key Laboratory of Industrial Ecology and Environmental Engineering (Ministry of Education), Dalian Key Laboratory on Chemicals Risk Control and Pollution Prevention Technology, School of Environmental Science and Technology, Dalian University of Technology, Dalian 116024, China.

PMID: 39680085
DOI: 10.1021/acs.est.4c11085

Abstract

In silico methods for screening hazardous chemicals are necessary for sound management. Persistent, bioaccumulative, mobile, and toxic (PBMT) chemicals persist in the environment and have high mobility in aquatic environments, posing risks to human and ecological health. However, lack of experimental data for the vast number of chemicals hinders identification of PBMT chemicals. Through an extensive search of measured chemical mobility data, as well as persistent, bioaccumulative, and toxic (PBT) chemical inventories, this study constructed comprehensive data sets on PBMT chemicals. To address the limited volume of the PBMT chemical data set, a transfer learning (TL) framework based on graph attention network (GAT) architecture was developed to construct models for screening PBMT chemicals, designating the PBT chemical inventories as source domains and the PBMT chemical data set as target domains. A weighted loss (L_W) function was proposed and proved to mitigate the negative impact of imbalanced data on the model performance. Results indicate the TL-GAT models outperformed GAT models, along with large coverage of applicability domains and interpretability. The constructed models were employed to identify PBMT chemicals from inventories consisting of about 1 × 10⁶ chemicals. The developed TL-GAT framework with the L_W function holds broad applicability across diverse tasks, especially those involving small and imbalanced data sets.

Keywords: applicability domain; bioaccumulative; graph attention network; mobile and toxic chemicals; persistent; transfer learning; weighted loss function.