{"type":"ScholarlyArticle","title":"GLPocket: A Multi-Scale Representation Learning Approach for Protein Binding Site Prediction","authors":[{"name":"Peiying Li","slug":"peiying-li","given":"Peiying","family":"Li","affiliation":"Department of Computer Science and Engineering , Shanghai Jiao Tong University , Shanghai , China"},{"name":"Yongchang Liu","slug":"yongchang-liu","given":"Yongchang","family":"Liu","affiliation":"Department of Computer Science and Engineering , Shanghai Jiao Tong University , Shanghai , China"},{"name":"Shikui Tu","slug":"shikui-tu","given":"Shikui","family":"Tu","affiliation":"Department of Computer Science and Engineering , Shanghai Jiao Tong University , Shanghai , China"},{"name":"Lei Xu","slug":"lei-xu","given":"Lei","family":"Xu","affiliation":"Department of Computer Science and Engineering , Shanghai Jiao Tong University , Shanghai , China; Guangdong Institute of Intelligence Science and Technology , Zhuhai , Guangdong , China"}],"abstract":"Protein binding site prediction is an important prerequisite for the discovery of new drugs. Usually, natural 3D U-Net is adopted as the standard site prediction framework to do per-voxel binary mask classification. However, this scheme only performs feature extraction for single-scale samples, which may bring the loss of global or local information, resulting in incomplete, artifacted or even missed predictions. To tackle this issue, we propose a network called GLPocket, which is based on the Lmser (Least mean square error reconstruction) network and utilizes multi-scale representation to predict binding sites. Firstly, GLPocket uses Target Cropping Block (TCB) for targeted prediction. TCB selects the local interested feature from the global representations to perform concentrated prediction, and reduces the volume of feature maps to be calculated by 82% without adding additional parameters. It integrates global distribution information into local regions, making prediction more concentrated on decoding stage. Secondly, GLPocket establishes long-range relationship of patches within the local region with Transformer Block (TB), to enrich local context semantic information. Experiments show that GLPocket improves by 0.5%-4% on DCA Top-n prediction compared with previous state-of-the-art methods on four datasets. Our code has been released in https://github.com/CMACH508/GLPocket.","doi":"10.24963/ijcai.2023/536","url":"https://ijcai.org/proceedings/2023/536","pdf":"https://ijcai.org/proceedings/2023/0536.pdf","markdown":"https://ijcai.org/proceedings/2023/536.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/536","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":536,"pages":{"first":4821,"last":4828},"keywords":["Multidisciplinary Topics and Applications: MDA: Bioinformatics","Computer Vision: CV: Biomedical image analysis"],"videos":[],"references":[{"position":1,"raw":"[Aggarwal et al., 2021] Rishal Aggarwal, Akash Gupta, Vi- neeth Chelur, CV Jawahar, and U Deva Priyakumar. Deep- pocket: ligand binding site detection and segmentation us- ing 3d convolutional neural networks. Journal of Chemical Information and Modeling, 62(21):5069-5079, 2021.","title":"Deeppocket: ligand binding site detection and segmentation using 3d convolutional neural networks","authors":"Aggarwal","year":"2021","venue":"Journal of Chemical Information and Modeling","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Anderson, 2003] Amy C Anderson. The process of structure-based drug design. Chemistry & biology, 10(9):787-797, 2003.","title":"The process of structure-based drug design","authors":"Amy C Anderson","year":"2003","venue":"Chemistry & biology","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Brylinski and Skolnick, 2008] Michal Brylinski and Jef- frey Skolnick. A threading-based method (findsite) for ligand-binding site prediction and functional annota- tion. Proceedings of the National Academy of sciences, 105(1):129-134, 2008.","title":"Michal Brylinski and Jeffrey Skolnick. A threading-based method (findsite) for ligand-binding site prediction and functional annotation","authors":"Skolnick Brylinski","year":"2008","venue":"Proceedings of the National Academy of sciences","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2011] Ke Chen, Marcin J Mizianty, Jianzhao Gao, and Lukasz Kurgan. A critical comparative assess- ment of predictions of protein-binding sites for biologi- cally relevant organic compounds. Structure, 19(5):613- 621, 2011.","title":"A critical comparative assessment of predictions of protein-binding sites for biologically relevant organic compounds","authors":"Ke Chen, J Marcin, Jianzhao Mizianty, Lukasz Gao, Kurgan","year":"2011","venue":"Structure","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Desaphy et al., 2015] Jérémy Desaphy, Guillaume Bret, Di- dier Rognan, and Esther Kellenberger. sc-pdb: a 3d- database of ligandable binding sites-10 years on. Nucleic acids research, 43(D1):D399-D404, 2015.","title":"sc-pdb: a 3ddatabase of ligandable binding sites-10 years on","authors":"Jérémy Desaphy, Guillaume Bret, Didier Rognan, Esther Kellenberger","year":"2015","venue":"Nucleic acids research","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hendlich et al., 1997] Manfred Hendlich, Friedrich Ripp- mann, and Gerhard Barnickel. Ligsite: automatic and effi- cient detection of potential small molecule-binding sites in proteins. Journal of Molecular Graphics and Modelling, 15(6):359-363, 1997.","title":"Ligsite: automatic and efficient detection of potential small molecule-binding sites in proteins","authors":"Hendlich","year":"1997","venue":"Journal of Molecular Graphics and Modelling","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hernandez et al., 2009] Marylens Hernandez, Dario Ghersi, and Roberto Sanchez. Sitehound-web: a server for ligand binding site identification in protein structures. Nucleic acids research, 37(suppl 2):W413-W416, 2009.","title":"Sitehound-web: a server for ligand binding site identification in protein structures","authors":"Hernandez","year":"2009","venue":"Nucleic acids research","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Huang and Schroeder, 2006] Bingding Huang and Michael Schroeder. Ligsite csc: predicting ligand binding sites us- ing the connolly surface and degree of conservation. BMC structural biology, 6(1):1-11, 2006.","title":"Ligsite csc: predicting ligand binding sites using the connolly surface and degree of conservation","authors":"Schroeder ; Huang, Bingding Huang, Michael Schroeder","year":"2006","venue":"BMC structural biology","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jiménez et al., 2017] José Jiménez, Stefan Doerr, Gerard Martínez-Rosell, Alexander S Rose, and Gianni De Fab- ritiis. Deepsite: protein-binding site predictor us- ing 3d-convolutional neural networks. Bioinformatics, 33(19):3036-3042, 2017.","title":"Deepsite: protein-binding site predictor using 3d-convolutional neural networks","authors":"José Jiménez, Stefan Doerr, Gerard Martínez-Rosell, Alexander S Rose, Gianni De, Fabritiis","year":"2017","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Krivák and Hoksza, 2015] Radoslav Krivák and David Hoksza. Improving protein-ligand binding site prediction accuracy by classification of inner pocket points using local features. Journal of cheminformatics, 7(1):1-13, 2015.","title":"Improving protein-ligand binding site prediction accuracy by classification of inner pocket points using local features","authors":"Hoksza Krivák, Radoslav Krivák, David Hoksza","year":"2015","venue":"Journal of cheminformatics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Le Guilloux et al., 2009] Vincent Le Guilloux, Peter Schmidtke, and Pierre Tuffery. Fpocket: an open source platform for ligand pocket detection. BMC bioinformatics, 10(1):1-11, 2009.","title":"Fpocket: an open source platform for ligand pocket detection","authors":"Le Guilloux","year":"2009","venue":"BMC bioinformatics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2019] Peiying Li, Shikui Tu, and Lei Xu. Gan flex- ible lmser for super-resolution. In Proceedings of the 27th ACM International Conference on Multimedia, pages 756- 764, 2019.","title":"Gan flexible lmser for super-resolution","authors":"Peiying Li, Shikui Tu, Lei Xu","year":"2019","venue":"Proceedings of the 27th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2022] Peiying Li, Boheng Cao, Shikui Tu, and Lei Xu. Recurpocket: Recurrent lmser network with gating mechanism for protein binding site detection. In 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 334-339. IEEE, 2022.","title":"Recurpocket: Recurrent lmser network with gating mechanism for protein binding site detection","authors":"Peiying Li, Boheng Cao, Shikui Tu, Lei Xu","year":"2022","venue":"IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2023] Yongchang Liu, Peiying Li, Shikui Tu, and Lei Xu. Refinepocket: An attention-enhanced and mask- guided deep learning approach for protein binding site pre- diction. IEEE/ACM Transactions on Computational Biol- ogy and Bioinformatics, 2023.","title":"Refinepocket: An attention-enhanced and maskguided deep learning approach for protein binding site prediction","authors":"Yongchang Liu, Peiying Li, Shikui Tu, Lei Xu","year":"2023","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mylonas et al., 2021] Stelios K Mylonas, Apostolos Axenopoulos, and Petros Daras. Deepsurf: a surface- based deep learning approach for the prediction of ligand binding sites on proteins. Bioinformatics, 37(12):1681- 1690, 2021.","title":"Deepsurf: a surfacebased deep learning approach for the prediction of ligand binding sites on proteins","authors":"Apostolos Stelios K Mylonas, Petros Axenopoulos, Daras","year":"2021","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ngan et al., 2012] Chi-Ho Ngan, David R Hall, Brandon Zerbe, Laurie E Grove, Dima Kozakov, and Sandor Va- jda. Ftsite: high accuracy detection of ligand binding sites on unbound protein structures. Bioinformatics, 28(2):286- 287, 2012.","title":"Ftsite: high accuracy detection of ligand binding sites on unbound protein structures","authors":"Ngan","year":"2012","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nguyen et al., 2017] Nguyen, T. Quoc, Gomes, J. P. Abel, Dias, E. D. Sergio, Jorge, and A. Joaquim. Multi-gpu- based detection of protein cavities using critical points. Future generations computer systems: FGCS, 2017.","title":"Multi-gpubased detection of protein cavities using critical points","authors":"T Nguyen, Quoc, J P Gomes, Abel, E D Dias, Sergio, A Jorge, Joaquim","year":"2017","venue":"Future generations computer systems: FGCS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Patani and LaVoie, 1996] George A Patani and Edmond J LaVoie. Bioisosterism: a rational approach in drug design. Chemical reviews, 96(8):3147-3176, 1996.","title":"Bioisosterism: a rational approach in drug design","authors":"A George, Edmond J Patani, Lavoie","year":"1996","venue":"Chemical reviews","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Radoslav and David, 2018] Krivák Radoslav and Hoksza David. P2rank: machine learning based tool for rapid and accurate prediction of ligand binding sites from protein structure. Journal of Cheminformatics, 10(1):39-, 2018.","title":"P2rank: machine learning based tool for rapid and accurate prediction of ligand binding sites from protein structure","authors":"David ; Radoslav, Krivák Radoslav, Hoksza David","year":"2018","venue":"Journal of Cheminformatics","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ravindranath and Sanner, 2016] Pradeep Anand Ravin- dranath and Michel F Sanner. Autosite: an automated approach for pseudo-ligands prediction-from ligand- binding sites identification to predicting key ligand atoms. Bioinformatics, 32(20):3142-3149, 2016.","title":"Autosite: an automated approach for pseudo-ligands prediction-from ligandbinding sites identification to predicting key ligand atoms","authors":"Anand Pradeep, Michel F Ravindranath, Sanner","year":"2016","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ronneberger et al., 2015] Olaf Ronneberger, Philipp Fis- cher, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer- assisted intervention, pages 234-241. Springer, 2015.","title":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation","authors":"Ronneberger","year":"2015","venue":"International Conference on Medical image computing and computerassisted intervention","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Stepniewska-Dziubinska et al., 2020] Marta M Stepniewska-Dziubinska, Piotr Zielenkiewicz, and Pawel Siedlecki. Improving detection of protein-ligand binding sites with 3d segmentation. Scientific reports, 10(1):1-9, 2020.","title":"Improving detection of protein-ligand binding sites with 3d segmentation","authors":"Marta M Stepniewska-Dziubinska, Piotr Zielenkiewicz, Pawel Siedlecki","year":"2020","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2005] Renxiao Wang, Xueliang Fang, Yipin Lu, Chao-Yie Yang, and Shaomeng Wang. The pdbbind database: methodologies and updates. Journal of medici- nal chemistry, 48(12):4111-4119, 2005.","title":"The pdbbind database: methodologies and updates","authors":"Wang","year":"2005","venue":"Journal of medicinal chemistry","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xu, 1993] Lei Xu. Least mean square error reconstruction principle for self-organizing neural-nets. Neural networks, 6(5):627-648, 1993.","title":"Least mean square error reconstruction principle for self-organizing neural-nets","authors":"Lei Xu","year":"1993","venue":"Neural networks","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xu, 2019] Lei Xu. An overview and perspectives on bidi- rectional intelligence: Lmser duality, double ia harmony, and causal computation. IEEE/CAA Journal of Automatica Sinica, 6(4):865-893, 2019.","title":"An overview and perspectives on bidirectional intelligence: Lmser duality, double ia harmony, and causal computation","authors":"Lei Xu","year":"2019","venue":"IEEE/CAA Journal of Automatica Sinica","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}