{"type":"ScholarlyArticle","title":"Cross-View Contrastive Fusion for Enhanced Molecular Property Prediction","authors":[{"name":"Yan Zheng","slug":"yan-zheng","given":"Yan","family":"Zheng","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Song Wu","slug":"song-wu","given":"Song","family":"Wu","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China"},{"name":"Junyu Lin","slug":"junyu-lin","given":"Junyu","family":"Lin","affiliation":"Shenzhen Institute for Advanced Study , University of Electronic Science and Technology of China"},{"name":"Yazhou Ren","slug":"yazhou-ren","given":"Yazhou","family":"Ren","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China; Shenzhen Institute for Advanced Study , University of Electronic Science and Technology of China"},{"name":"Jing He","slug":"jing-he","given":"Jing","family":"He","affiliation":"Nuffield Department of Clinical Neurosciences , University of Oxford"},{"name":"Xiaorong Pu","slug":"xiaorong-pu","given":"Xiaorong","family":"Pu","affiliation":"School of Computer Science and Engineering , University of Electronic Science and Technology of China; Shenzhen Institute for Advanced Study , University of Electronic Science and Technology of China"},{"name":"Lifang He","slug":"lifang-he","given":"Lifang","family":"He","affiliation":"Department of Computer Science and Engineering , Lehigh University"}],"abstract":"Machine learning based molecular property prediction has been a hot topic in the field of computer aided drug discovery (CADD). However, current MPP methods face two prominent challenges: 1) single-view MPP methods do not sufficiently exploit the complementary information of molecular data across multiple views, generally producing suboptimal performance, and 2) most existing multi-view MPP methods ignore the disparities in data quality among different views, inadvertently introducing the risk of models being overshadowed by inferior views. To address the above challenges, we introduce a novel cross-view contrastive fusion for enhanced molecular property prediction method (MolFuse). First, we extract intricate molecular semantics and structures from both sequence and graph views to leverage the complementarity of multi-view data. Then, MolFuse employs two distinct graphs, the atomic graph and chemical bond graph, to enhance the representation of the molecular graph, allow us to integrate both the fundamental backbone attributes and the nuanced shape characteristics. Notably, we incorporate a dual learning mechanism to refine the initial feature representations, and global features are obtained by maximizing the coherence among diverse view-specific molecular representations for the downstream task. The overall learning processes are combined into a unified optimization problem for iterative training. Experiments on multiple benchmark datasets demonstrate the superiority of our MolFuse.","doi":"10.24963/ijcai.2024/621","url":"https://ijcai.org/proceedings/2024/621","pdf":"https://ijcai.org/proceedings/2024/0621.pdf","markdown":"https://ijcai.org/proceedings/2024/621.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/621","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":621,"pages":{"first":5617,"last":5625},"keywords":["Machine Learning: ML: Multi-view learning","Multidisciplinary Topics and Applications: MTA: Bioinformatics","Data Mining: DM: Mining graphs"],"videos":[],"references":[{"position":1,"raw":"[Anderson et al., 1987] EricB. Anderson, GD Veith, and D Weininger. Smiles: a line notation and computerized interpreter for chemical structures. Jan 1987.","title":"Smiles: a line notation and computerized interpreter for chemical structures","authors":"Anderson","year":"1987","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bemis and Murcko, 1996] Guy W. Bemis and Mark A. Murcko. The properties of known drugs. 1. molec- ular frameworks. Journal of Medicinal Chemistry, 39(15):2887-2893, Jan 1996.","title":"The properties of known drugs. 1. molecular frameworks","authors":"Guy W Bemis, Mark A Murcko","year":"1996","venue":"Journal of Medicinal Chemistry","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chithrananda et al., 2020] Seyone Chithrananda, Gabriel Grand, and Bharath Ramsundar. Chemberta: large-scale self-supervised pretraining for molecular property predic- tion. arXiv:2010.09885, 2020.","title":"Seyone Chithrananda, Gabriel Grand, and Bharath Ramsundar. Chemberta: large-scale self-supervised pretraining for molecular property prediction","authors":"Chithrananda","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chung et al., 2014] Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. Empirical evalua- tion of gated recurrent neural networks on sequence mod- eling. In NeuralIPS Workshop on Deep Learning, 2014.","title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","authors":"Chung","year":"2014","venue":"NeuralIPS Workshop on Deep Learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fang et al., 2022] Yin Fang, Qiang Zhang, Haihong Yang, Xiang Zhuang, Shumin Deng, Wen Zhang, Ming Qin, Zhuo Chen, Xiaohui Fan, and Huajun Chen. Molecu- lar contrastive learning with chemical element knowledge graph. In AAAI, volume 36, pages 3968-3976, 2022.","title":"Molecular contrastive learning with chemical element knowledge graph","authors":"Yin Fang, Qiang Zhang, Haihong Yang, Xiang Zhuang, Shumin Deng, Wen Zhang, Ming Qin, Zhuo Chen, Xiaohui Fan, Huajun Chen","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2022] Zhihui Guo, Pramod Sharma, Andy Mar- tinez, Liang Du, and Robin Abraham. Multilingual molec- ular representation learning via contrastive pre-training. In ACL, pages 3441-3453, 2022.","title":"Multilingual molecular representation learning via contrastive pre-training","authors":"Zhihui Guo, Pramod Sharma, Andy Martinez, Liang Du, Robin Abraham","year":"2022","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Honda et al., 2019] Shion Honda, Shoi Shi, and Hiroki R Ueda. Smiles transformer: Pre-trained molecular fin- gerprint for low data drug discovery. arXiv:1911.04738, 2019.","title":"Smiles transformer: Pre-trained molecular fingerprint for low data drug discovery","authors":"Honda","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hu et al., 2020] W Hu, B Liu, J Gomes, M Zitnik, P Liang, V Pande, and J Leskovec. Strategies for pre-training graph neural networks. In ICLR, 2020.","title":"Strategies for pre-training graph neural networks","authors":"B Hu, J Liu, M Gomes, P Zitnik, V Liang, Pande, Leskovec","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kearnes et al., 2016] Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, and Patrick Riley. Molecular graph convolutions: Moving beyond fingerprints. Journal of Computer-Aided Molecular Design, page 595-608, Aug 2016.","title":"Molecular graph convolutions: Moving beyond fingerprints","authors":"Steven Kearnes, Kevin Mccloskey, Marc Berndl, Vijay Pande, Patrick Riley","year":"2016","venue":"Journal of Computer-Aided Molecular Design","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2021] Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, and Jian Tang. Pre- training molecular graph representation with 3d geometry. In ICLR, 2021.","title":"Pretraining molecular graph representation with 3d geometry","authors":"Liu","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ma et al., 2022] Runze Ma, Yidan Zhang, Xinye Wang, Zhenyang Yu, and Lei Duan. Morn: Molecular property prediction based on textual-topological-spatial multi-view learning. In CIKM, pages 1461-1470, 2022.","title":"Morn: Molecular property prediction based on textual-topological-spatial multi-view learning","authors":"Ma","year":"2022","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ross et al., 2022] Jerret Ross, Brian Belgodere, Vijil Chen- thamarakshan, Inkit Padhi, Youssef Mroueh, and Payel Das. Large-scale chemical language representations cap- ture molecular structure and properties. Nature Machine Intelligence, 4(12):1256-1264, 2022.","title":"Large-scale chemical language representations capture molecular structure and properties","authors":"Jerret Ross, Brian Belgodere, Inkit Vijil Chenthamarakshan, Youssef Padhi, Payel Mroueh, Das","year":"2022","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Stärk et al., 2022] Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, and Pietro Liò. 3d infomax im- proves gnns for molecular property prediction. In ICML, pages 20479-20502. PMLR, 2022.","title":"3d infomax improves gnns for molecular property prediction","authors":"Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, Pietro Liò","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Tosco et al., 2014] Paolo Tosco, Nikolaus Stiefl, and Gre- gory Landrum. Bringing the mmff force field to the rdkit: implementation and validation. Journal of Cheminformat- ics, Dec 2014.","title":"Bringing the mmff force field to the rdkit: implementation and validation","authors":"Paolo Tosco, Nikolaus Stiefl, Gregory Landrum","year":"2014","venue":"Journal of Cheminformatics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In ICLR, 2018.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Wang et al., 2022] Yuyang Wang, Jianren Wang, Zhonglin Cao, and Amir Barati Farimani. Molecular contrastive learning of representations via graph neural networks. Na- ture Machine Intelligence, 4(3):279-287, 2022.","title":"Molecular contrastive learning of representations via graph neural networks","authors":"Yuyang Wang, Jianren Wang, Zhonglin Cao, Amir Barati, Farimani","year":"2022","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wu et al., 2017] Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S. Pappu, Karl Leswing, and Vijay Pande. Moleculenet: A benchmark for molecular machine learning. Chemical Sci- ence, page 513-530, Oct 2017.","title":"Moleculenet: A benchmark for molecular machine learning","authors":"Wu","year":"2017","venue":"Chemical Science","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Xiong et al., 2020] Zhaoping Xiong, Dingyan Wang, Xi- aohong Liu, Feisheng Zhong, Xiaozhe Wan, Xutong Li, Zhaojun Li, Xiaomin Luo, Kaixian Chen, Hualiang Jiang, and Mingyue Zheng. Pushing the boundaries of molec- ular representation for drug discovery with the graph at- tention mechanism. Journal of Medicinal Chemistry, page 8749-8760, Aug 2020.","title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","authors":"Xiong","year":"2020","venue":"Journal of Medicinal Chemistry","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Xu et al., 2018] Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural net- works? In ICLR, 2018.","title":"How powerful are graph neural networks?","authors":"Xu","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yang et al., 2023] Xixi Yang, Li Fu, Yafeng Deng, Yuan- sheng Liu, Dongsheng Cao, and Xiangxiang Zeng. Gpmo: gradient perturbation-based contrastive learning for molecule optimization. In IJCAI, pages 4940-4948, 2023.","title":"Gpmo: gradient perturbation-based contrastive learning for molecule optimization","authors":"Xixi Yang, Li Fu, Yafeng Deng, Yuansheng Liu, Dongsheng Cao, Xiangxiang Zeng","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/549"},{"position":22,"raw":"[You et al., 2020] Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. Graph contrastive learning with augmentations. NeuralIPS, 33:5812-5823, 2020.","title":"Graph contrastive learning with augmentations","authors":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen","year":"2020","venue":"NeuralIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[You et al., 2021] Yuning You, Tianlong Chen, Yang Shen, and Zhangyang Wang. Graph contrastive learning auto- mated. In ICML, pages 12121-12132. PMLR, 2021.","title":"Graph contrastive learning automated","authors":"You","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhou et al., 2023] Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. Uni-mol: a universal 3d molecular representation learning framework. 2023.","title":"Uni-mol: a universal 3d molecular representation learning framework","authors":"Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, Guolin Ke","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhu et al., 2021] Jinhua Zhu, Yingce Xia, Tao Qin, Wen- gang Zhou, Houqiang Li, and Tie-Yan Liu. Dual-view molecule pre-training. arXiv:2106.10234, 2021.","title":"Dual-view molecule pre-training","authors":"Jinhua Zhu, Yingce Xia, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhu et al., 2022] Yanqiao Zhu, Dingshuo Chen, Yuanqi Du, Yingze Wang, Qiang Liu, and Shu Wu. Featurizations mat- ter: a multiview contrastive learning approach to molecu- lar pretraining. In ICML, 2022.","title":"Featurizations matter: a multiview contrastive learning approach to molecular pretraining","authors":"Yanqiao Zhu, Dingshuo Chen, Yuanqi Du, Yingze Wang, Qiang Liu, Shu Wu","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhuang et al., 2023] Xiang Zhuang, Qiang Zhang, Bin Wu, Keyan Ding, Yin Fang, and Huajun Chen. Graph sampling-based meta-learning for molecular property pre- diction. IJCAI, 2023.","title":"Graph sampling-based meta-learning for molecular property prediction","authors":"Xiang Zhuang, Qiang Zhang, Bin Wu, Keyan Ding, Yin Fang, Huajun Chen","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/526"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}