Multimodal Representation Learning via Graph Isomorphism Network for Toxicity Multitask Learning

• Published in: Journal of chemical information and modeling 2024-11, Vol.64 (21), p.8322-8338
• Main Authors: Wang, Guishen, Feng, Hui, Du, Mengyan, Feng, Yuncong, Cao, Chen
• Format: Article
• Language: English
• Subjects: Ablation; Artificial neural networks; Bioinformatics; Classification; Datasets; Deep Learning; Drug-Related Side Effects and Adverse Reactions; Effectiveness; Fingerprints; Graph representations; Graphical representations; Graphs; Humans; Isomorphism; Machine Learning; Molecular structure; Neural Networks, Computer; Task complexity; Toxicity; Toxicity testing
• ISSN: 1549-9596; 1549-960X; 1549-960X
• DOI: 10.1021/acs.jcim.4c01061

Toxicity is paramount for comprehending compound properties, particularly in the early stages of drug design. Due to the diversity and complexity of toxic effects, it became a challenge to compute compound toxicity tasks. To address this issue, we propose a multimodal representation learning model, termed multimodal graph isomorphism network (MMGIN), to address this challenge for compound toxicity multitask learning. Based on fingerprints and molecular graphs of compounds, our MMGIN model incorporates a multimodal representation learning model to acquire a comprehensive compound representation. This model adopts a two-channel structure to independently learn fingerprint representation and molecular graph representation. Subsequently, two feedforward neural networks utilize the learned multimodal compound representation to perform multitask learning, encompassing compound toxicity classification and multiple compound category classification simultaneously. To test the effectiveness of our model, we constructed a novel data set, termed the compound toxicity multitask learning (CTMTL) data set, derived from the TOXRIC data set. We compare our MMGIN model with other representative machine learning and deep learning models on the CTMTL and Tox21 data sets. The experimental results demonstrate significant advancements achieved by our MMGIN model. Furthermore, the ablation study underscores the effectiveness of the introduced fingerprints, molecular graphs, the multimodal representation learning model, and the multitask learning model, showcasing the model’s superior predictive capability and robustness.