Multimodal Representation Learning via Graph Isomorphism Network for Toxicity Multitask Learning

被引:4
作者
Wang, Guishen [1 ]
Feng, Hui [1 ]
Du, Mengyan [1 ]
Feng, Yuncong [1 ]
Cao, Chen [2 ]
机构
[1] Changchun Univ Technol, Sch Comp Sci & Engn, Changchun 130012, Jilin, Peoples R China
[2] Nanjing Med Univ, Sch Biomed Engn & Informat, Key Lab Bioelectromagnet Environm & Adv Med Theran, Nanjing 211166, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
PREDICTION;
D O I
10.1021/acs.jcim.4c01061
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
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.
引用
收藏
页码:8322 / 8338
页数:17
相关论文
共 50 条
[41]   Protein Complexes Detection Based on Global Network Representation Learning [J].
Xu, Bo ;
Li, Kun ;
Liu, Xiaoxia ;
Liu, Delong ;
Zhang, Yijia ;
Lin, Hongfei ;
Yang, Zhihao ;
Wang, Jian ;
Xia, Feng .
PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2018, :210-213
[42]   iGRLCDA: identifying circRNA-disease association based on graph representation learning [J].
Zhang, Han-Yuan ;
Wang, Lei ;
You, Zhu-Hong ;
Hu, Lun ;
Zhao, Bo-Wei ;
Li, Zheng-Wei ;
Li, Yang-Ming .
BRIEFINGS IN BIOINFORMATICS, 2022, 23 (03)
[43]   ReLMole: Molecular Representation Learning Based on Two-Level Graph Similarities [J].
Ji, Zewei ;
Shi, Runhan ;
Lu, Jiarui ;
Li, Fang ;
Yang, Yang .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2022, 62 (22) :5361-5372
[44]   Detecting operons in bacterial genomes via visual representation learning [J].
Assaf, Rida ;
Xia, Fangfang ;
Stevens, Rick .
SCIENTIFIC REPORTS, 2021, 11 (01)
[45]   Preterm infant general movements assessment via representation learning [J].
Gong, Xiaohui ;
Li, Xiao ;
Ma, Li ;
Tong, Weilin ;
Shi, Fangyu ;
Hu, Menghan ;
Zhang, Xiao-Ping ;
Yu, Guangjun ;
Yang, Cheng .
DISPLAYS, 2022, 75
[46]   Improving Commute Experience for Private Car Users via Blockchain-Enabled Multitask Learning [J].
Yang, Jiali ;
Yang, Kehua ;
Xiao, Zhu ;
Jiang, Hongbo ;
Xu, Shenyuan ;
Dustdar, Schahram .
IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (24) :21656-21669
[47]   Regulation-aware graph learning for drug repositioning over network [J].
Zhao, Bo-Wei ;
Su, Xiao-Rui ;
Yang, Yue ;
Li, Dong-Xu ;
Li, Guo-Dong ;
Hu, Peng-Wei ;
You, Zhu-Hong ;
Luo, Xin ;
Hu, Lun .
INFORMATION SCIENCES, 2025, 686
[48]   Self-Supervised Contrastive Molecular Representation Learning with a Chemical Synthesis Knowledge Graph [J].
Xie, Jiancong ;
Wang, Yi ;
Rao, Jiahua ;
Zheng, Shuangjia ;
Yang, Yuedong .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2024, 64 (06) :1945-1954
[49]   Machine-guided representation for accurate graph-based molecular machine learning [J].
Na, Gyoung S. ;
Chang, Hyunju ;
Kim, Hyun Woo .
PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2020, 22 (33) :18526-18535
[50]   A Graph-Representation-Learning Framework for Supporting Android Malware Identification and Polymorphic Evolution [J].
Cuzzocrea, Alfredo ;
Quebrado, Miguel ;
Hafsaoui, Abderraouf ;
Serra, Edoardo .
2023 10TH IEEE SWISS CONFERENCE ON DATA SCIENCE, SDS, 2023, :34-41