{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T07:44:37Z","timestamp":1772264677711,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-025-01004-5","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T15:21:38Z","timestamp":1747927298000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking molecular conformer augmentation with context-enriched training: graph-based transformer versus GNN models"],"prefix":"10.1186","volume":"17","author":[{"given":"Cecile","family":"Valsecchi","sequence":"first","affiliation":[]},{"given":"Jose A.","family":"Arjona-Medina","sequence":"additional","affiliation":[]},{"given":"Natalia","family":"Dyubankova","sequence":"additional","affiliation":[]},{"given":"Ramil","family":"Nugmanov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"issue":"16","key":"1004_CR1","doi-asserted-by":"publisher","first-page":"8705","DOI":"10.1021\/acs.jmedchem.0c00385","volume":"63","author":"KV Chuang","year":"2020","unstructured":"Chuang KV, Gunsalus LM, Keiser MJ (2020) Learning molecular representations for medicinal chemistry: miniperspective. J Med Chem 63(16):8705\u20138722","journal-title":"J Med Chem"},{"issue":"2","key":"1004_CR2","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1039\/D2SC05089G","volume":"14","author":"Z Tu","year":"2023","unstructured":"Tu Z, Stuyver T, Coley CW (2023) Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery. Chem Sci 14(2):226\u2013244","journal-title":"Chem Sci"},{"issue":"12","key":"1004_CR3","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1038\/s42256-021-00418-8","volume":"3","author":"K Atz","year":"2021","unstructured":"Atz K, Grisoni F, Schneider G (2021) Geometric deep learning on molecular representations. Nature Machine Intell 3(12):1023\u20131032","journal-title":"Nature Machine Intell"},{"key":"1004_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2023.102527","volume":"79","author":"F Grisoni","year":"2023","unstructured":"Grisoni F (2023) Chemical language models for de novo drug design: challenges and opportunities. Current Opinion Struct Biol 79:102527","journal-title":"Current Opinion Struct Biol"},{"key":"1004_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2024.102818","volume":"86","author":"D van Tilborg","year":"2024","unstructured":"van Tilborg D, Brinkmann H, Criscuolo E, Rossen L, \u00f6z\u00e7elik R, Grisoni F, (2024) Deep learning for low-data drug discovery: hurdles and opportunities. Current Opinion Struct Biol 86:102818. https:\/\/doi.org\/10.1016\/j.sbi.2024.102818","journal-title":"Current Opinion Struct Biol"},{"issue":"4","key":"1004_CR6","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3390\/biom8040131","volume":"8","author":"EJ Bjerrum","year":"2018","unstructured":"Bjerrum EJ, Sattarov B (2018) Improving chemical autoencoder latent space and molecular de novo generation diversity with heteroencoders. Biomolecules 8(4):131","journal-title":"Biomolecules"},{"issue":"5","key":"1004_CR7","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"D Rogers","year":"2010","unstructured":"Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inform Model 50(5):742\u2013754. https:\/\/doi.org\/10.1021\/ci100050t. (PMID: 20426451)","journal-title":"J Chem Inform Model"},{"issue":"3","key":"1004_CR8","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1039\/D2DD00129B","volume":"2","author":"H Kneiding","year":"2023","unstructured":"Kneiding H, Lukin R, Lang L, Reine S, Pedersen TB, De Bin R et al (2023) Deep learning metal complex properties with natural quantum graphs. Digital Disc 2(3):618\u2013633","journal-title":"Digital Disc"},{"key":"1004_CR9","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2024-m5bpn","author":"B Haas","year":"2024","unstructured":"Haas B, Hardy M, SV SS, Adams K, Coley C, Paton R, et al (2024) Rapid Prediction of Conformationally-Dependent DFT-Level Descriptors using Graph Neural Networks for Carboxylic Acids and Alkyl Amines. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2024-m5bpn","journal-title":"ChemRxiv"},{"key":"1004_CR10","unstructured":"Zhu Y, Hwang J, Adams K, Liu Z, Nan B, Stenfors B, et\u00a0al (2023) Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks. In: The Twelfth International Conference on Learning Representations"},{"issue":"1","key":"1004_CR11","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1698","volume":"14","author":"D Zankov","year":"2024","unstructured":"Zankov D, Madzhidov T, Varnek A, Polishchuk P (2024) Chemical complexity challenge: Is multi-instance machine learning a solution? Wiley interdisciplinary reviews. Computat Mol Sci 14(1):e1698","journal-title":"Computat Mol Sci"},{"issue":"3","key":"1004_CR12","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","volume":"4","author":"Y Wang","year":"2022","unstructured":"Wang Y, Wang J, Cao Z, Barati Farimani A (2022) Molecular contrastive learning of representations via graph neural networks. Nature Machine Intell 4(3):279\u2013287","journal-title":"Nature Machine Intell"},{"key":"1004_CR13","unstructured":"Adams K, Pattanaik L, Coley CW (2021) Learning 3d representations of molecular chirality with invariance to bond rotations. arXiv preprint arXiv:2110.04383"},{"key":"1004_CR14","doi-asserted-by":"crossref","unstructured":"Gai\u0144ski P, Koziarski M, Tabor J, \u015amieja M (2023) ChiENN: Embracing Molecular Chirality with Graph Neural Networks. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer; p. 36\u201352","DOI":"10.1007\/978-3-031-43418-1_3"},{"key":"1004_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2023.102548","volume":"79","author":"C Isert","year":"2023","unstructured":"Isert C, Atz K, Schneider G (2023) Structure-based drug design with geometric deep learning. Current Opin Struct Biol 79:102548","journal-title":"Current Opin Struct Biol"},{"issue":"10","key":"1004_CR16","doi-asserted-by":"publisher","first-page":"4913","DOI":"10.1021\/acs.jcim.1c00692","volume":"61","author":"DV Zankov","year":"2021","unstructured":"Zankov DV, Matveieva M, Nikonenko AV, Nugmanov RI, Baskin II, Varnek A et al (2021) QSAR modeling based on conformation ensembles using a multi-instance learning approach. J Chem Inform Model 61(10):4913\u20134923","journal-title":"J Chem Inform Model"},{"issue":"7","key":"1004_CR17","doi-asserted-by":"publisher","first-page":"3342","DOI":"10.1021\/acs.jcim.0c00200","volume":"60","author":"PP Kyaw Zin","year":"2020","unstructured":"Kyaw Zin PP, Borrel A, Fourches D (2020) Benchmarking 2D\/3D\/MD-QSAR models for Imatinib derivatives: how far can we predict? J Chem Inform Model 60(7):3342\u20133360","journal-title":"J Chem Inform Model"},{"key":"1004_CR18","unstructured":"Liu L, He D, Ye X, Zhang S, Zhang X, Zhou J, et\u00a0al (2023) Pre-Training on Large-Scale Generated Docking Conformations with HelixDock to Unlock the Potential of Protein-ligand Structure Prediction Models. arXiv preprint arXiv:2310.13913"},{"key":"1004_CR19","first-page":"28877","volume":"34","author":"C Ying","year":"2021","unstructured":"Ying C, Cai T, Luo S, Zheng S, Ke G, He D et al (2021) Do transformers really perform badly for graph representation? Adv Neural Inform Process Syst 34:28877\u201328888","journal-title":"Adv Neural Inform Process Syst"},{"key":"1004_CR20","unstructured":"Luo S, Chen T, Xu Y, Zheng S, Liu TY, Wang L, et\u00a0al (2022) One transformer can understand both 2d & 3d molecular data. In: The Eleventh International Conference on Learning Representations"},{"key":"1004_CR21","unstructured":"Hussain MS, Zaki MJ, Subramanian D (2024) Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers. arXiv preprint arXiv:2402.04538"},{"key":"1004_CR22","unstructured":"Lu S, Gao Z, He D, Zhang L, Ke G (2023) Highly accurate quantum chemical property prediction with uni-mol+. arXiv preprint arXiv:2303.16982"},{"key":"1004_CR23","unstructured":"Masters D, Dean J, Klaser K, Li Z, Maddrell-Mander S, Sanders A, et\u00a0al (2022) Gps++: An optimised hybrid mpnn\/transformer for molecular property prediction. arXiv preprint arXiv:2212.02229"},{"key":"1004_CR24","unstructured":"Liao YL, Smidt T (2022) Equiformer: Equivariant graph attention transformer for 3d atomistic graphs. arXiv preprint arXiv:2206.11990"},{"key":"1004_CR25","unstructured":"Arjona-Medina J, Nugmanov R. Analysis of Atom-level pretraining with Quantum Mechanics (QM) data for Graph Neural Networks Molecular property models. https:\/\/arxiv.org\/abs\/2405.14837"},{"key":"1004_CR26","first-page":"10","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN et al (2017) Attention is all you need. Adv Neural Inform Process Syst 30:10","journal-title":"Adv Neural Inform Process Syst"},{"key":"1004_CR27","unstructured":"Mitchell TM (1980) The Need for Biases in Learning Generalizations. Laboratory for Computer Science Research, Rutgers University, Department of Computer Science"},{"key":"1004_CR28","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); p. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"1004_CR29","first-page":"12","volume":"10","author":"KD Luong","year":"2024","unstructured":"Luong KD, Singh A (2024) Application of transformers in cheminformatics. J Chem Inform Model 10:12","journal-title":"J Chem Inform Model"},{"key":"1004_CR30","unstructured":"M\u00fcller L, Galkin M, Morris C, Ramp\u00e1\u0161ek L. Attending to Graph Transformers. https:\/\/arxiv.org\/abs\/2302.04181"},{"issue":"1","key":"1004_CR31","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","volume":"64","author":"E Heid","year":"2023","unstructured":"Heid E, Greenman KP, Chung Y, Li SC, Graff DE, Vermeire FH et al (2023) Chemprop: A machine learning package for chemical property prediction. J Chem Inform Model 64(1):9\u201317","journal-title":"J Chem Inform Model"},{"key":"1004_CR32","first-page":"22118","volume":"33","author":"W Hu","year":"2020","unstructured":"Hu W, Fey M, Zitnik M, Dong Y, Ren H, Liu B et al (2020) Open graph benchmark: datasets for machine learning on graphs. Adv Neural Inform Process Syst 33:22118\u201322133","journal-title":"Adv Neural Inform Process Syst"},{"key":"1004_CR33","unstructured":"Sch\u00fctt K, Unke O, Gastegger M (2021) Equivariant message passing for the prediction of tensorial properties and molecular spectra. In: International Conference on Machine Learning. PMLR; p. 9377\u20139388"},{"key":"1004_CR34","first-page":"12","volume":"30","author":"K Sch\u00fctt","year":"2017","unstructured":"Sch\u00fctt K, Kindermans PJ, Sauceda Felix HE, Chmiela S, Tkatchenko A, M\u00fcller KR (2017) Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. Adv Neural Inform Process Syst 30:12","journal-title":"Adv Neural Inform Process Syst"},{"issue":"14","key":"1004_CR35","doi-asserted-by":"publisher","first-page":"3307","DOI":"10.1021\/acs.jcim.2c00344","volume":"62","author":"R Nugmanov","year":"2022","unstructured":"Nugmanov R, Dyubankova N, Gedich A, Wegner JK (2022) Bidirectional graphormer for reactivity understanding: neural network trained to reaction atom-to-atom mapping task. J Chem Inform Model 62(14):3307\u20133315","journal-title":"J Chem Inform Model"},{"issue":"35","key":"1004_CR36","doi-asserted-by":"publisher","first-page":"7069","DOI":"10.1039\/C8SC01949E","volume":"9","author":"B Meyer","year":"2018","unstructured":"Meyer B, Sawatlon B, Heinen S, Von Lilienfeld OA, Corminboeuf C (2018) Machine learning meets volcano plots: computational discovery of cross-coupling catalysts. Chem Sci 9(35):7069\u20137077","journal-title":"Chem Sci"},{"issue":"3","key":"1004_CR37","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1021\/jacs.1c09718","volume":"144","author":"T Gensch","year":"2022","unstructured":"Gensch T, dos Passos Gomes G, Friederich P, Peters E, Gaudin T, Pollice R et al (2022) A comprehensive discovery platform for organophosphorus ligands for catalysis. J Am Chem Soc 144(3):1205\u20131217","journal-title":"J Am Chem Soc"},{"issue":"1","key":"1004_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/wcms.51","volume":"2","author":"ED Glendening","year":"2012","unstructured":"Glendening ED, Landis CR, Weinhold F (2012) Natural bond orbital methods. Wiley Interdiscipl Rev Computat Mol Sci 2(1):1\u201342","journal-title":"Wiley Interdiscipl Rev Computat Mol Sci"},{"key":"1004_CR39","unstructured":"Landrum G. RDKit: Open-source cheminformatics. http:\/\/www.rdkit.org\/"},{"issue":"6","key":"1004_CR40","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.1039\/D0SC04823B","volume":"12","author":"Y Guan","year":"2021","unstructured":"Guan Y, Coley CW, Wu H, Ranasinghe D, Heid E, Struble TJ et al (2021) Regio-selectivity prediction with a machine-learned reaction representation and on-the-fly quantum mechanical descriptors. Chem Sci 12(6):2198\u20132208","journal-title":"Chem Sci"},{"key":"1004_CR41","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana R (1997) Multitask learning. Machine Learn 28:41\u201375","journal-title":"Machine Learn"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01004-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-01004-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01004-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T15:21:50Z","timestamp":1747927310000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-01004-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1004"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-01004-5","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,22]]},"assertion":[{"value":"28 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"80"}}