{"type":"ScholarlyArticle","title":"GPMO: Gradient Perturbation-Based Contrastive Learning for Molecule Optimization","authors":[{"name":"Xixi Yang","slug":"xixi-yang","given":"Xixi","family":"Yang","affiliation":"College of Computer Science and Electronic Engineering , Hunan University , Changsha , China"},{"name":"Li Fu","slug":"li-fu","given":"Li","family":"Fu","affiliation":"CarbonSilicon AI Technology Co., Ltd , Hangzhou , Zhejiang , China"},{"name":"Yafeng Deng","slug":"yafeng-deng","given":"Yafeng","family":"Deng","affiliation":"CarbonSilicon AI Technology Co., Ltd , Hangzhou , Zhejiang , China"},{"name":"Yuansheng Liu","slug":"yuansheng-liu","given":"Yuansheng","family":"Liu","affiliation":"College of Computer Science and Electronic Engineering , Hunan University , Changsha , China"},{"name":"Dongsheng Cao","slug":"dongsheng-cao","given":"Dongsheng","family":"Cao","affiliation":"Xiangya School of Pharmaceutical Sciences , Central South University , Changsha , Hunan , China"},{"name":"Xiangxiang Zeng","slug":"xiangxiang-zeng","given":"Xiangxiang","family":"Zeng","affiliation":"College of Computer Science and Electronic Engineering , Hunan University , Changsha , China"}],"abstract":"Optimizing molecules with desired properties is a crucial step in de novo drug design. While translation-based methods have achieved initial success, they continue to face the challenge of the “exposure bias” problem. The challenge of preventing the “exposure bias” problem of molecule\r\noptimization lies in the need for both positive and negative molecules of contrastive learning. That is because generating positive molecules through data augmentation requires domain-specific knowledge, and randomly sampled negative molecules are easily distinguished from the real molecules. Hence, in this work, we propose a molecule optimization method called GPMO, which leverages a gradient perturbation-based contrastive learning method to prevent the “exposure bias” problem in translation-based molecule optimization. With the assistance of positive and negative molecules, GPMO is able to effectively handle both real and artificial molecules. GPMO is a molecule optimization method that is conditioned on matched molecule pairs for drug discovery. Our empirical studies show that GPMO outperforms the state-of-the- art molecule optimization methods. Furthermore,  the negative and positive perturbations improve the robustness of GPMO.","doi":"10.24963/ijcai.2023/549","url":"https://ijcai.org/proceedings/2023/549","pdf":"https://ijcai.org/proceedings/2023/0549.pdf","markdown":"https://ijcai.org/proceedings/2023/549.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/549","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":549,"pages":{"first":4940,"last":4948},"keywords":["Multidisciplinary Topics and Applications: MDA: Bioinformatics"],"videos":[],"references":[{"position":1,"raw":"a) Start molecular X: LogD: 2.7, Solubility: 2.4 Clint: 0.5 (b) End molecular Y: LogD: 3.1, Solubility: 2.7 Clint: 0.5 (c) Round 1: LogD: 3.2, Solubility: 2.5 Clint: 0.5 (d) Round 2: LogD: 3.5, Solubility: 2.4 Clint: 0.6 (e) Round 3: LogD: 3.6, Solubility: 2.4 Clint: 0.4 (f) Round 4: LogD: 3.8, Solubility: 2.1 Clint: 0.4 (g) Round 5: LogD: 3.9, Solubility: 2.3 Clint: 0.3","title":"a) Start molecular X: LogD","authors":null,"year":null,"venue":"a) Start molecular X: LogD","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2021] Ziqi Chen, Martin Renqiang Min, Srini- vasan Parthasarathy, and Xia Ning. A deep generative model for molecule optimization via one fragment mod- ification. Nature Machine Intelligence, 3(12):1040-1049, 2021.","title":"A deep generative model for molecule optimization via one fragment modification","authors":"Ziqi Chen, Martin Renqiang Min, Srinivasan Parthasarathy, Xia Ning","year":"2021","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dalke et al., 2018] Andrew Dalke, Jerome Hert, and Chris- tian Kramer. mmpdb: An open-source matched molecular pair platform for large multiproperty data sets. Journal of Chemical Information and Modeling, 58(5):902-910, 2018.","title":"mmpdb: An open-source matched molecular pair platform for large multiproperty data sets","authors":"Andrew Dalke, Jerome Hert, Christian Kramer","year":"2018","venue":"Journal of Chemical Information and Modeling","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fu et al., 2021] Tianfan Fu, Cao Xiao, Xinhao Li, Lu- cas M Glass, and Jimeng Sun. Mimosa: Multi-constraint molecule sampling for molecule optimization. In Proceed- ings of the AAAI Conference on Artificial Intelligence, vol- ume 35, pages 125-133, 2021.","title":"Mimosa: Multi-constraint molecule sampling for molecule optimization","authors":"Tianfan Fu, Cao Xiao, Xinhao Li, Lucas M Glass, Jimeng Sun","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2021] Wenhao Gao, Rocío Mercado, and Con- nor W Coley. Amortized tree generation for bottom-up synthesis planning and synthesizable molecular design. arXiv preprint arXiv:2110.06389, 2021.","title":"Amortized tree generation for bottom-up synthesis planning and synthesizable molecular design","authors":"Wenhao Gao, Rocío Mercado, Connor W Coley","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gómez-Bombarelli et al., 2018] Rafael Gómez- Bombarelli, Jennifer N Wei, David Duvenaud, José Miguel Hernández-Lobato, Benjamín Sánchez- Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D Hirzel, Ryan P Adams, and Alán Aspuru- Guzik. Automatic chemical design using a data-driven continuous representation of molecules. ACS Central Science, 4(2):268-276, 2018.","title":"Automatic chemical design using a data-driven continuous representation of molecules","authors":"Rafael Gómez-Bombarelli, Jennifer N Wei, David Duvenaud, José Miguel Hernández-Lobato, Benjamín Sánchez-Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D Hirzel, Ryan P Adams, Alán Aspuru-Guzik","year":"2018","venue":"ACS Central Science","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Guimaraes et al., 2017] Gabriel Lima Guimaraes, Ben- jamin Sanchez-Lengeling, Carlos Outeiral, Pedro Luis Cunha Farias, and Alán Aspuru-Guzik. Objective- reinforced generative adversarial networks (organ) for sequence generation models. arXiv preprint arXiv:1705.10843, 2017.","title":"Objectivereinforced generative adversarial networks (organ) for sequence generation models","authors":"Gabriel Lima, Guimaraes, Benjamin Sanchez-Lengeling, Carlos Outeiral, Pedro, Luis Cunha Farias, Alán Aspuru-Guzik","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2021] Jiazhen He, Huifang You, Emil Sandström, Eva Nittinger, Esben Jannik Bjerrum, Christian Tyrchan, Werngard Czechtizky, and Ola Engkvist. Molecular opti- mization by capturing chemist's intuition using deep neu- ral networks. Journal of Cheminformatics, 13(1):1-17, 2021.","title":"Molecular optimization by capturing chemist's intuition using deep neural networks","authors":"He","year":"2021","venue":"Journal of Cheminformatics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jin et al., 2018a] Wengong Jin, Regina Barzilay, and Tommi Jaakkola. Junction tree variational autoencoder for molecular graph generation. In International Conference on Machine Learning, pages 2323-2332. PMLR, 2018.","title":"Junction tree variational autoencoder for molecular graph generation","authors":"Jin","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jin et al., 2018b] Wengong Jin, Kevin Yang, Regina Barzi- lay, and Tommi Jaakkola. Learning multimodal graph-to- graph translation for molecule optimization. In Interna- tional Conference on Learning Representations, 2018.","title":"Learning multimodal graph-to-graph translation for molecule optimization","authors":"Jin","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jin et al., 2020] Wengong Jin, Regina Barzilay, and Tommi Jaakkola. Hierarchical generation of molecular graphs us- ing structural motifs. In International Conference on Ma- chine Learning, pages 4839-4848. PMLR, 2020.","title":"Hierarchical generation of molecular graphs using structural motifs","authors":"Jin","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lee et al., 2020] Seanie Lee, Dong Bok Lee, and Sung Ju Hwang. Contrastive learning with adversarial perturba- tions for conditional text generation. In International Con- ference on Learning Representations, 2020.","title":"Contrastive learning with adversarial perturbations for conditional text generation","authors":"Seanie Lee, Dong Bok Lee, Sung Ju Hwang","year":"2020","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lin et al., 2020] Xuan Lin, Zhe Quan, Zhi-Jie Wang, Tengfei Ma, and Xiangxiang Zeng. KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Predic- tion. In IJCAI, volume 380, pages 2739-2745, 2020.","title":"KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction","authors":"Xuan Lin, Zhe Quan, Zhi-Jie Wang, Tengfei Ma, Xiangxiang Zeng","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/380"},{"position":14,"raw":"[Liu et al., 2020] Xianggen Liu, Qiang Liu, Sen Song, and Jian Peng. A chance-constrained generative framework for sequence optimization. In International Conference on Machine Learning, pages 6271-6281. PMLR, 2020.","title":"A chance-constrained generative framework for sequence optimization","authors":"Xianggen Liu, Qiang Liu, Sen Song, Jian Peng","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ma et al., 2022] Tengfei Ma, Xuan Lin, Bosheng Song, S Yu Philip, and Xiangxiang Zeng. KG-MTL: Knowl- edge Graph Enhanced Multi-Task Learning for Molecular Interaction. IEEE Transactions on Knowledge & Data En- gineering, pages 1-12, 2022.","title":"KG-MTL: Knowledge Graph Enhanced Multi-Task Learning for Molecular Interaction","authors":"Tengfei Ma, Xuan Lin, Bosheng Song, Yu Philip, Xiangxiang Zeng","year":"2022","venue":"IEEE Transactions on Knowledge & Data Engineering","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Moss et al., 2020] Henry Moss, David Leslie, Daniel Beck, Javier Gonzalez, and Paul Rayson. Boss: Bayesian opti- mization over string spaces. Advances in Neural Informa- tion Processing Systems, 33:15476-15486, 2020.","title":"Boss: Bayesian optimization over string spaces","authors":"Henry Moss, David Leslie, Daniel Beck, Javier Gonzalez, Paul Rayson","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nigam et al., 2019] AkshatKumar Nigam, Pascal Friederich, Mario Krenn, and Alán Aspuru-Guzik. Augmenting genetic algorithms with deep neural net- works for exploring the chemical space. arXiv preprint arXiv:1909.11655, 2019.","title":"Augmenting genetic algorithms with deep neural networks for exploring the chemical space","authors":"Nigam","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Polykovskiy et al., 2020] Daniil Polykovskiy, Alexander Zhebrak, Benjamin Sanchez-Lengeling, Sergey Golo- vanov, Oktai Tatanov, Stanislav Belyaev, Rauf Kurbanov, Aleksey Artamonov, Vladimir Aladinskiy, Mark Veselov, et al. Molecular sets (MOSES): a benchmarking platform for molecular generation models. Frontiers in Pharmacol- ogy, 11:565644, 2020.","title":"Molecular sets (MOSES): a benchmarking platform for molecular generation models","authors":"Daniil Polykovskiy, Alexander Zhebrak, Benjamin Sanchez-Lengeling, Sergey Golovanov, Oktai Tatanov, Stanislav Belyaev, Rauf Kurbanov, Aleksey Artamonov, Vladimir Aladinskiy, Mark Veselov","year":"2020","venue":"Frontiers in Pharmacology","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shen et al., 2022] Xinke Shen, Xianggen Liu, Xin Hu, Dan Zhang, and Sen Song. Contrastive learning of subject- invariant EEG representations for cross-subject emotion recognition. IEEE Transactions on Affective Computing, pages 1 -1, 2022.","title":"Contrastive learning of subjectinvariant EEG representations for cross-subject emotion recognition","authors":"Shen","year":"2022","venue":"IEEE Transactions on Affective Computing","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shi et al., 2020] Chence Shi, Minkai Xu, Zhaocheng Zhu, Weinan Zhang, Ming Zhang, and Jian Tang. GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation. In International Conference on Learning Rep- resentations, 2020.","title":"GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation","authors":"Shi","year":"2020","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in Neural Information Processing Sys- tems, 30, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2021] Jike Wang, Chang-Yu Hsieh, Mingyang Wang, Xiaorui Wang, Zhenxing Wu, Dejun Jiang, Ben- ben Liao, Xujun Zhang, Bo Yang, Qiaojun He, et al. Multi-constraint molecular generation based on condi- tional transformer, knowledge distillation and reinforce- ment learning. Nature Machine Intelligence, 3(10):914- 922, 2021.","title":"Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning","authors":"Jike Wang, Chang-Yu Hsieh, Mingyang Wang, Xiaorui Wang, Zhenxing Wu, Dejun Jiang, Benben Liao, Xujun Zhang, Bo Yang, Qiaojun He","year":"2021","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[You et al., 2018] Jiaxuan You, Bowen Liu, Zhitao Ying, Vi- jay Pande, and Jure Leskovec. Graph convolutional pol- icy network for goal-directed molecular graph generation. Advances in Neural Information Processing Systems, 31, 2018.","title":"Graph convolutional policy network for goal-directed molecular graph generation","authors":"Jiaxuan You, Bowen Liu, Zhitao Ying, Vijay Pande, Jure Leskovec","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zang and Wang, 2020] Chengxi Zang and Fei Wang. MoFlow: an invertible flow model for generating molec- ular graphs. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 617-626, 2020.","title":"MoFlow: an invertible flow model for generating molecular graphs","authors":"Wang ; ] Chengxi Zang, Fei Zang, Wang","year":"2020","venue":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zeng et al., 2022] Xiangxiang Zeng, Hongxin Xiang, Lin- hui Yu, Jianmin Wang, Kenli Li, Ruth Nussinov, and Feix- iong Cheng. Accurate prediction of molecular properties and drug targets using a self-supervised image represen- tation learning framework. Nature Machine Intelligence, 4(11):1004-1016, 2022.","title":"Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework","authors":"Xiangxiang Zeng, Hongxin Xiang, Linhui Yu, Jianmin Wang, Kenli Li, Ruth Nussinov, Feixiong Cheng","year":"2022","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhou et al., 2019] Zhenpeng Zhou, Steven Kearnes, Li Li, Richard N Zare, and Patrick Riley. Optimization of molecules via deep reinforcement learning. Scientific Re- ports, 9(1):1-10, 2019.","title":"Optimization of molecules via deep reinforcement learning","authors":"Zhou","year":"2019","venue":"Scientific Reports","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}