{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T03:34:53Z","timestamp":1784172893315,"version":"3.55.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T00:00:00Z","timestamp":1735516800000},"content-version":"vor","delay-in-days":38,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The diffusion generative model has achieved remarkable performance across various research fields. In this study, we propose a transferable graph attention diffusion model, GADIFF, for a molecular conformation generation task. With adopting multiple equivariant networks in the Markov chain, GADIFF adds GIN (Graph Isomorphism Network) to acquire local information of subgraphs with different edge types (atomic bonds, bond angle interactions, torsion angle interactions, long-range interactions) and applies MSA (Multi-head Self-attention) as noise attention mechanism to capture global molecular information, which improves the representative of features. In addition, we utilize MSA to calculate dynamic noise weights to boost molecular conformation noise prediction. Upon the improvements, GADIFF achieves competitive performance compared with recently reported state-of-the-art models in terms of generation diversity(COV-R, COV-P), accuracy (MAT-R, MAT-P), and property prediction for GEOM-QM9 and GEOM-Drugs datasets. In particular, on the GEOM-Drugs dataset, the average COV-R is improved by 3.75% compared with the best baseline model at a threshold (1.25 \u00c5). Furthermore, a transfer model named GADIFF-NCI based on GADIFF is developed to generate conformations for noncovalent interaction (NCI) molecular systems. It takes GADIFF with GEOM-QM9 dataset as a pre-trained model, and incorporates a graph encoder for learning molecular vectors at the NCI molecular level. The resulting NCI molecular conformations are reasonable, as assessed by the evaluation of conformation and property predictions. This suggests that the proposed transferable model may hold noteworthy value for the study of multi-molecular conformations. The code and data of GADIFF is freely downloaded from https:\/\/github.com\/WangDHg\/GADIFF.<\/jats:p>","DOI":"10.1093\/bib\/bbae676","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T01:30:03Z","timestamp":1735608603000},"source":"Crossref","is-referenced-by-count":6,"title":["GADIFF: a transferable graph attention diffusion model for generating molecular conformations"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4912-6355","authenticated-orcid":false,"given":"Donghan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Northeast Normal University , 130117 Changchun ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9778-3290","authenticated-orcid":false,"given":"Xu","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northeast Normal University , 130117 Changchun ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4161-2225","authenticated-orcid":false,"given":"Xueyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northeast Normal University , 130117 Changchun ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3792-2917","authenticated-orcid":false,"given":"LiHong","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Northeast Normal University , 130117 Changchun ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,12,30]]},"reference":[{"key":"2024123101294719600_ref1","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1038\/aps.2012.109","article-title":"Computational drug discovery","volume":"33","author":"Ou-Yang","year":"2012","journal-title":"Acta Pharmacol Sin"},{"key":"2024123101294719600_ref2","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.1021\/acs.jcim.7b00221","article-title":"Conformation generation: the state of the art","volume":"57","author":"Hawkins","year":"2017","journal-title":"J Chem Inf Model"},{"key":"2024123101294719600_ref3","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1038\/s43588-023-00560-w","article-title":"Deep contrastive learning of molecular conformation for efficient property prediction","volume":"3","author":"Park","year":"2023","journal-title":"Nat Comput Sci"},{"key":"2024123101294719600_ref4","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1038\/nchem.2444","article-title":"Molecular docking sites designed for the generation of highly crystalline covalent organic frameworks","volume":"8","author":"Ascherl","year":"2016","journal-title":"Nature Chem"},{"key":"2024123101294719600_ref5","doi-asserted-by":"publisher","first-page":"e1468","DOI":"10.1002\/wcms.1468","article-title":"Next generation 3D pharmacophore modeling","volume":"10","author":"Schaller","year":"2020","journal-title":"Nature Chem"},{"key":"2024123101294719600_ref6","article-title":"Direct molecular conformation generation","author":"Zhu","year":"2022","journal-title":"Transact Mach Learn Res"},{"key":"2024123101294719600_ref7","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1136\/mp.53.1.8","article-title":"X ray crystallography","volume":"53","author":"Smyth","year":"2000","journal-title":"Mol Pathol"},{"key":"2024123101294719600_ref8","doi-asserted-by":"publisher","first-page":"4035","DOI":"10.1021\/acs.jmedchem.5b01684","article-title":"Role of molecular dynamics and related methods in drug discovery","volume":"59","author":"De Vivo","year":"2016","journal-title":"J Med Chem"},{"key":"2024123101294719600_ref9","doi-asserted-by":"publisher","first-page":"20381","DOI":"10.1038\/s41598-019-56773-5","article-title":"Molecular geometry prediction using a deep generative graph neural network","volume":"9","author":"Mansimov","year":"2019","journal-title":"Sci Rep"},{"key":"2024123101294719600_ref10","first-page":"8949","article-title":"A generative model for molecular distance geometry","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Simm","year":"2020"},{"key":"2024123101294719600_ref11","article-title":"Learning neural generative dynamics for molecular conformation generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Xu","year":"2021"},{"key":"2024123101294719600_ref12","first-page":"11537","article-title":"An end-to-end framework for molecular conformation generation via bilevel programming","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Xu","year":"2021"},{"key":"2024123101294719600_ref13","first-page":"9558","article-title":"Learning gradient fields for molecular conformation generation","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Shi","year":"2021"},{"key":"2024123101294719600_ref14","first-page":"13757","article-title":"GeoMol: torsional geometric generation of molecular 3D conformer ensembles","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ganea","year":"2021"},{"key":"2024123101294719600_ref15","first-page":"19784","article-title":"Predicting molecular conformation via dynamic graph score matching","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Luo","year":"2021"},{"key":"2024123101294719600_ref16","article-title":"GEODIFF: a geometric diffusion model for molecular conformation generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Xu","year":"2022"},{"key":"2024123101294719600_ref17","article-title":"Do deep learning methods really perform better in molecular conformation generation?","volume-title":"ICLR 2023-Machine Learning for Drug Discovery workshop","author":"Zhou","year":"2023"},{"key":"2024123101294719600_ref18","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1109\/TAI.2023.3251977","article-title":"Deep learning methods for small molecule drug discovery: a survey","volume":"5","author":"Hu","year":"2024","journal-title":"IEEE Trans Artif Intel"},{"key":"2024123101294719600_ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3554729","article-title":"Diffusion models: a comprehensive survey of methods and applications","volume":"56","author":"Yang","year":"2023","journal-title":"ACM Comput Surv"},{"key":"2024123101294719600_ref20","first-page":"12489","article-title":"Protein design with guided discrete diffusion","volume-title":"Advances in Neural Information Processing Systems (NeurIPS). New Orleans, LA, USA","author":"Gruver","year":"2023"},{"key":"2024123101294719600_ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"2024123101294719600_ref22","doi-asserted-by":"publisher","first-page":"4383","DOI":"10.1021\/jm501853m","article-title":"A survey of the role of noncovalent sulfur interactions in drug design","volume":"58","author":"Beno","year":"2015","journal-title":"J Med Chem"},{"key":"2024123101294719600_ref23","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1021\/ct1002253","article-title":"Comparative study of selected wave function and density functional methods for noncovalent interaction energy calculations using the extended S22 data set","volume":"6","author":"Gr\u00e1fov\u00e1","year":"2010","journal-title":"J Chem Theory Comput"},{"key":"2024123101294719600_ref24","doi-asserted-by":"publisher","first-page":"2427","DOI":"10.1021\/ct2002946","article-title":"S66: a well-balanced database of benchmark interaction energies relevant to biomolecular structures","volume":"7","author":"\u0158ez\u00e1\u010d","year":"2011","journal-title":"J Chem Theory Comput"},{"key":"2024123101294719600_ref25","doi-asserted-by":"publisher","first-page":"4285","DOI":"10.1021\/ct300647k","article-title":"Benchmark calculations of noncovalent interactions of halogenated molecules","volume":"8","author":"\u0158ez\u00e1\u010d","year":"2012","journal-title":"J Chem Theory Comput"},{"key":"2024123101294719600_ref26","doi-asserted-by":"publisher","first-page":"6305","DOI":"10.1021\/acs.jctc.0c00715","article-title":"Non-covalent interactions atlas benchmark data sets 2: hydrogen bonding in an extended chemical space","volume":"16","author":"\u0158ez\u00e1\u010d","year":"2020","journal-title":"J Chem Theory Comput"},{"key":"2024123101294719600_ref27","doi-asserted-by":"publisher","first-page":"2355","DOI":"10.1021\/acs.jctc.9b01265","article-title":"Non-covalent interactions atlas benchmark data sets: hydrogen bonding","volume":"16","author":"\u0158ez\u00e1\u010d","year":"2020","journal-title":"J Chem Theory Comput"},{"key":"2024123101294719600_ref28","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1038\/s41597-022-01288-4","article-title":"GEOM, energy-annotated molecular conformations for property prediction and molecular generation","volume":"9","author":"Axelrod","year":"2022","journal-title":"Sci Data"},{"key":"2024123101294719600_ref29","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1021\/acs.jcim.2c01283","article-title":"TFRegNCI: interpretable noncovalent interaction correction multimodal based on transformer encoder fusion","volume":"63","author":"Wang","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2024123101294719600_ref30","doi-asserted-by":"publisher","first-page":"2562","DOI":"10.1021\/acs.jcim.5b00654","article-title":"Better informed distance geometry: using what we know to improve conformation generation","volume":"55","author":"Riniker","year":"2015","journal-title":"J Chem Inf Model"},{"key":"2024123101294719600_ref31","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1137\/120875909","article-title":"Euclidean distance geometry and applications","volume":"56","author":"Liberti","year":"2014","journal-title":"SIAM Rev"},{"key":"2024123101294719600_ref32","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1107\/S0567739476001873","article-title":"A solution for the best rotation to relate two sets of vectors","volume":"32","author":"Kabsch","year":"1976","journal-title":"Acta Crystallogr Sect A"},{"key":"2024123101294719600_ref33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-3-8","article-title":"Confab - systematic generation of diverse low-energy conformers","volume":"3","author":"O\u2019Boyle","year":"2011","journal-title":"J Chem"},{"key":"2024123101294719600_ref34","doi-asserted-by":"publisher","first-page":"184108","DOI":"10.1063\/5.0006002","article-title":"psi4 1.4: open-source software for high-throughput quantum chemistry","volume":"152","author":"Smith","year":"2020","journal-title":"J Chem Phys"},{"key":"2024123101294719600_ref35","doi-asserted-by":"publisher","first-page":"5090","DOI":"10.1021\/acs.jcim.1c01305","article-title":"DeepNCI: DFT noncovalent interaction correction with transferable multimodal three-dimensional convolutional neural networks","volume":"62","author":"Li","year":"2022","journal-title":"J Chem Inf Model"},{"key":"2024123101294719600_ref36","volume-title":"Gaussian 09, Revision d.01","author":"Frisch","year":"2013"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/1\/bbae676\/61294692\/bbae676.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/1\/bbae676\/61294692\/bbae676.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T01:30:08Z","timestamp":1735608608000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae676\/7934647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,11,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae676","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,11,22]]},"article-number":"bbae676"}}