{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:40:50Z","timestamp":1768340450954,"version":"3.49.0"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"Guangdong Science and Technology Programme","award":["2024B0101010003"],"award-info":[{"award-number":["2024B0101010003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:p>In recent years, deep learning techniques have made significant strides in molecular generation for specific targets, driving advancements in drug discovery. However, existing molecular generation methods present significant limitations: those operating at the atomic level often lack synthetic feasibility, drug-likeness, and interpretability, while fragment-based approaches frequently overlook comprehensive factors that influence protein\u2013molecule interactions. To address these challenges, we propose a novel fragment-based molecular generation framework tailored for specific proteins. Our method begins by constructing a protein subpocket and molecular arm concept-based neural network, which systematically integrates interaction force information and geometric complementarity to sample molecular arms for specific protein subpockets. Subsequently, we introduce a diffusion model to generate molecular backbones that connect these arms, ensuring structural integrity and chemical diversity. Our approach improves synthetic feasibility and binding affinity, with a 4% increase in drug-likeness and a 6% improvement in synthetic feasibility. Furthermore, by integrating explicit interaction data through a concept-based model, our framework enhances interpretability, offering valuable insights into the molecular design process.<\/jats:p>","DOI":"10.1145\/3779063","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T14:30:04Z","timestamp":1764685804000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Concept-Driven Deep Learning for Enhanced Protein-Specific Molecular Generation"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4633-7076","authenticated-orcid":false,"given":"Taojie","family":"Kuang","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China and Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9356-2883","authenticated-orcid":false,"given":"Qianli","family":"Ma","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-9877","authenticated-orcid":false,"given":"Athanasios V.","family":"Vasilakos","sequence":"additional","affiliation":[{"name":"University of Agder, Kristiansand, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4976-9366","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3596-2838","authenticated-orcid":false,"given":"Qiang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Kentucky, Lexington, Kentucky, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4104-3790","authenticated-orcid":false,"given":"Zhixiang","family":"Ren","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2022.100794"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2023.102548"},{"key":"e_1_3_1_4_2","first-page":"13912","volume-title":"International Conference on Machine Learning","author":"Liu Meng","year":"2022","unstructured":"Meng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi, and Shuiwang Ji. 2022. Generating 3D molecules for target protein binding. In International Conference on Machine Learning. PMLR, 13912\u201313924."},{"key":"e_1_3_1_5_2","first-page":"17644","volume-title":"International Conference on Machine Learning","author":"Peng Xingang","year":"2022","unstructured":"Xingang Peng, Shitong Luo, Jiaqi Guan, Qi Xie, Jian Peng, and Jianzhu Ma. 2022. Pocket2Mol: Efficient molecular sampling based on 3D protein pockets. In International Conference on Machine Learning. PMLR, 17644\u201317655."},{"issue":"3","key":"e_1_3_1_6_2","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1039\/D4SC05894A","article-title":"DiffBP: Generative diffusion of 3D molecules for target protein binding","volume":"16","author":"Lin Haitao","year":"2025","unstructured":"Haitao Lin, Yufei Huang, Odin Zhang, Siqi Ma, Meng Liu, Xuanjing Li, Lirong Wu, Jishui Wang, Tingjun Hou, and Stan Z. Li. 2025. DiffBP: Generative diffusion of 3D molecules for target protein binding. Chemical Science 16, 3 (2025), 1417\u20131431.","journal-title":"Chemical Science"},{"key":"e_1_3_1_7_2","unstructured":"Jiaqi Guan Wesley Wei Qian Xingang Peng Yufeng Su Jian Peng and Jianzhu Ma .2023. 3D equivariant diffusion for target-aware molecule generation and affinity prediction. arXiv:2303.03543. Retrieved from https:\/\/arxiv.org\/abs\/2303.03543"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-024-00737-x"},{"key":"e_1_3_1_9_2","first-page":"18872","volume-title":"International Conference on Machine Learning","author":"Lee Seul","year":"2023","unstructured":"Seul Lee, Jaehyeong Jo, and Sung Ju Hwang. 2023. Exploring chemical space with score-based out-of-distribution generation. In International Conference on Machine Learning. PMLR, 18872\u201318892."},{"key":"e_1_3_1_10_2","unstructured":"Zijie Geng Shufang Xie Yingce Xia Lijun Wu Tao Qin Jie Wang Yongdong Zhang Feng Wu and Tie-Yan Liu. 2023. De novo molecular generation via connection-aware motif mining. arXiv:2302.01129. Retrieved from https:\/\/arxiv.org\/abs\/2302.01129"},{"key":"e_1_3_1_11_2","unstructured":"Jiaqi Guan Xiangxin Zhou Yuwei Yang Yu Bao Jian Peng Jianzhu Ma Qiang Liu Liang Wang and Quanquan Gu. 2024. DecompDiff: Diffusion models with decomposed priors for structure-based drug design. arXiv:2403.07902. Retrieved from https:\/\/arxiv.org\/abs\/2403.07902"},{"key":"e_1_3_1_12_2","first-page":"1","article-title":"Functional-group-based diffusion for pocket-specific molecule generation and elaboration","volume":"36","author":"Lin Haitao","year":"2024","unstructured":"Haitao Lin, Yufei Huang, Odin Zhang, Yunfan Liu, Lirong Wu, Siyuan Li, Zhiyuan Chen, and Stan Z. Li. 2024. Functional-group-based diffusion for pocket-specific molecule generation and elaboration. In Advances in Neural Information Processing Systems, Vol. 36, 1\u201324.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_13_2","first-page":"28277","volume-title":"International Conference on Machine Learning","author":"Qiang Bo","year":"2023","unstructured":"Bo Qiang, Yuxuan Song, Minkai Xu, Jingjing Gong, Bowen Gao, Hao Zhou, Wei-Ying Ma, and Yanyan Lan. 2023. Coarse-to-fine: A hierarchical diffusion model for molecule generation in 3D. In International Conference on Machine Learning. PMLR, 28277\u201328299."},{"key":"e_1_3_1_14_2","first-page":"7924","article-title":"Hit and lead discovery with explorative RL and fragment-based molecule generation","volume":"34","author":"Yang Soojung","year":"2021","unstructured":"Soojung Yang, Doyeong Hwang, Seul Lee, Seongok Ryu, and Sung Ju Hwang. 2021. Hit and lead discovery with explorative RL and fragment-based molecule generation. In Advances in Neural Information Processing Systems, Vol. 34, 7924\u20137936.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC00163A"},{"key":"e_1_3_1_16_2","unstructured":"Seul Lee Seanie Lee Kenji Kawaguchi and Sung Ju Hwang. 2023. Drug discovery with dynamic goal-aware fragments. arXiv:2310.00841. Retrieved from https:\/\/arxiv.org\/abs\/2310.00841"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv315"},{"key":"e_1_3_1_18_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Luo Youzhi","year":"2022","unstructured":"Youzhi Luo and Shuiwang Ji. 2022. An autoregressive flow model for 3D molecular geometry generation from scratch. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1039\/D3SC02538A"},{"issue":"1","key":"e_1_3_1_20_2","doi-asserted-by":"crossref","first-page":"2688","DOI":"10.1038\/s41467-024-47011-2","article-title":"3D molecular generative framework for interaction-guided drug design","volume":"15","author":"Zhung Wonho","year":"2024","unstructured":"Wonho Zhung, Hyeongwoo Kim, and Woo Youn Kim. 2024. 3D molecular generative framework for interaction-guided drug design. Nature Communications 15, 1 (2024), 2688.","journal-title":"Nature Communications"},{"key":"e_1_3_1_21_2","first-page":"1181","volume-title":"30th ACM International Conference on Information & Knowledge Management","author":"Ma Changsheng","year":"2021","unstructured":"Changsheng Ma and Xiangliang Zhang. 2021. GF-VAE: A flow-based variational autoencoder for molecule generation. In 30th ACM International Conference on Information & Knowledge Management, 1181\u20131190."},{"issue":"5","key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"bbae358","DOI":"10.1093\/bib\/bbae358","article-title":"DiffPROTACs is a deep learning-based generator for proteolysis targeting chimeras","volume":"25","author":"Li Fenglei","year":"2024","unstructured":"Fenglei Li, Qiaoyu Hu, Yongqi Zhou, Hao Yang, and Fang Bai. 2024. DiffPROTACs is a deep learning-based generator for proteolysis targeting chimeras. Briefings in Bioinformatics 25, 5 (2024), bbae358.","journal-title":"Briefings in Bioinformatics"},{"issue":"2","key":"e_1_3_1_23_2","doi-asserted-by":"crossref","first-page":"bbae078","DOI":"10.1093\/bib\/bbae078","article-title":"Diff-AMP: Tailored designed antimicrobial peptide framework with all-in-one generation, identification, prediction and optimization","volume":"25","author":"Wang Rui","year":"2024","unstructured":"Rui Wang, Tao Wang, Linlin Zhuo, Jinhang Wei, Xiangzheng Fu, Quan Zou, and Xiaojun Yao. 2024. Diff-AMP: Tailored designed antimicrobial peptide framework with all-in-one generation, identification, prediction and optimization. Briefings in Bioinformatics 25, 2 (2024), bbae078.","journal-title":"Briefings in Bioinformatics"},{"issue":"3","key":"e_1_3_1_24_2","doi-asserted-by":"crossref","first-page":"bbae174","DOI":"10.1093\/bib\/bbae174","article-title":"Guided diffusion for molecular generation with interaction prompt","volume":"25","author":"Wu Peng","year":"2024","unstructured":"Peng Wu, Huabin Du, Yingchao Yan, Tzong-Yi Lee, Chen Bai, and Song Wu. 2024. Guided diffusion for molecular generation with interaction prompt. Briefings in Bioinformatics 25, 3 (2024), bbae174.","journal-title":"Briefings in Bioinformatics"},{"key":"e_1_3_1_25_2","unstructured":"Yinan Huang Xingang Peng Jianzhu Ma and Muhan Zhang. 2022. 3DLinker: An E(3) equivariant variational autoencoder for molecular linker design. arXiv:2205.07309. Retrieved from https:\/\/arxiv.org\/abs\/2205.07309"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC02436A"},{"key":"e_1_3_1_27_2","first-page":"1","article-title":"Equivariant 3D-conditional diffusion model for molecular linker design","volume":"6","author":"Igashov Ilia","year":"2024","unstructured":"Ilia Igashov, Hannes St\u00e4rk, Cl\u00e9ment Vignac, Arne Schneuing, Victor Garcia Satorras, Pascal Frossard, Max Welling, Michael Bronstein, and Bruno Correia. 2024. Equivariant 3D-conditional diffusion model for molecular linker design. Nature Machine Intelligence 6 (2024), 1\u201311.","journal-title":"Nature Machine Intelligence"},{"key":"e_1_3_1_28_2","unstructured":"Krzysztof Maziarz Henry Jackson-Flux Pashmina Cameron Finton Sirockin Nadine Schneider Nikolaus Stiefl Marwin Segler and Marc Brockschmidt. 2021. Learning to extend molecular scaffolds with structural motifs. arXiv:2103.03864. Retrieved from https:\/\/arxiv.org\/abs\/2103.03864"},{"key":"e_1_3_1_29_2","first-page":"2550","article-title":"Molecule generation by principal subgraph mining and assembling","volume":"35","author":"Kong Xiangzhe","year":"2022","unstructured":"Xiangzhe Kong, Wenbing Huang, Zhixing Tan, and Yang Liu. 2022. Molecule generation by principal subgraph mining and assembling. In Advances in Neural Information Processing Systems, Vol. 35, 2550\u20132563.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_30_2","volume-title":"The 11th International Conference on Learning Representations","author":"Zhang Zaixi","year":"2023","unstructured":"Zaixi Zhang, Yaosen Min, Shuxin Zheng, and Qi Liu. 2023. Molecule generation for target protein binding with structural motifs. In The 11th International Conference on Learning Representations."},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.6b00491"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00411"},{"issue":"10","key":"e_1_3_1_33_2","doi-asserted-by":"crossref","first-page":"1503","DOI":"10.1002\/cmdc.200800178","article-title":"On the art of compiling and using \u2018drug-like\u2019 chemical fragment spaces","volume":"3","author":"Degen J\u00f6rg","year":"2008","unstructured":"J\u00f6rg Degen, Christof Wegscheid-Gerlach, Andrea Zaliani, and Matthias Rarey. 2008. On the art of compiling and using \u2018drug-like\u2019 chemical fragment spaces. ChemMedChem: Chemistry Enabling Drug Discovery 3, 10 (2008), 1503\u20131507.","journal-title":"ChemMedChem: Chemistry Enabling Drug Discovery"},{"issue":"24","key":"e_1_3_1_34_2","doi-asserted-by":"crossref","first-page":"241722","DOI":"10.1063\/1.5019779","article-title":"Schnet\u2014A deep learning architecture for molecules and materials","volume":"148","author":"Sch\u00fctt Kristof T.","year":"2018","unstructured":"Kristof T. Sch\u00fctt, Huziel E. Sauceda, P.-J. Kindermans, Alexandre Tkatchenko, and K.-R. M\u00fcller. 2018. Schnet\u2014A deep learning architecture for molecules and materials. The Journal of Chemical Physics 148, 24 (2018), 241722.","journal-title":"The Journal of Chemical Physics"},{"key":"e_1_3_1_35_2","volume-title":"11th International Conference on Learning Representations","author":"Fan Hehe","year":"2022","unstructured":"Hehe Fan, Zhangyang Wang, Yi Yang, and Mohan Kankanhalli. 2022. Continuous-discrete convolution for geometry-sequence modeling in proteins. In 11th International Conference on Learning Representations."},{"key":"e_1_3_1_36_2","first-page":"6229","article-title":"A 3D generative model for structure-based drug design","volume":"34","author":"Luo Shitong","year":"2021","unstructured":"Shitong Luo, Jiaqi Guan, Jianzhu Ma, and Jian Peng. 2021. A 3D generative model for structure-based drug design. In Advances in Neural Information Processing Systems, Vol. 34, 6229\u20136239.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c00203"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC05976A"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1038\/nchem.1243"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-1-8"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3779063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:54:32Z","timestamp":1768316072000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779063"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2,28]]}},"alternative-id":["10.1145\/3779063"],"URL":"https:\/\/doi.org\/10.1145\/3779063","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]},"assertion":[{"value":"2025-03-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}