{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T10:15:11Z","timestamp":1786356911529,"version":"3.56.0"},"reference-count":140,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T00:00:00Z","timestamp":1728950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T00:00:00Z","timestamp":1728950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S024093\/1"],"award-info":[{"award-number":["EP\/S024093\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-024-00699-0","type":"journal-article","created":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T10:02:28Z","timestamp":1728986548000},"page":"735-743","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["The future of machine learning for small-molecule drug discovery will be driven by data"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3249-3793","authenticated-orcid":false,"given":"Guy","family":"Durant","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fergus","family":"Boyles","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristian","family":"Birchall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1388-2252","authenticated-orcid":false,"given":"Charlotte M.","family":"Deane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,15]]},"reference":[{"key":"699_CR1","doi-asserted-by":"publisher","first-page":"100075","DOI":"10.1016\/j.medidd.2020.100075","volume":"9","author":"FD Makurvet","year":"2021","unstructured":"Makurvet, F. D. Biologics vs. small molecules: drug costs and patient access. Med. Drug Discov. 9, 100075 (2021).","journal-title":"Med. Drug Discov."},{"key":"699_CR2","doi-asserted-by":"crossref","unstructured":"Midlam, C. Status of Biologic Drugs in Modern Therapeutics-Targeted Therapies vs. Small Molecule Drugs 31\u201346 (Wiley, 2020).","DOI":"10.1002\/9781119564690.ch3"},{"key":"699_CR3","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s43556-022-00112-0","volume":"3","author":"Z Liu","year":"2022","unstructured":"Liu, Z. et al. An overview of PROTACs: a promising drug discovery paradigm. Mol. Biomed. 3, 46 (2022).","journal-title":"Mol. Biomed."},{"key":"699_CR4","doi-asserted-by":"publisher","first-page":"10606","DOI":"10.1021\/acs.jmedchem.1c00895","volume":"64","author":"G Dong","year":"2021","unstructured":"Dong, G., Ding, Y., He, S. & Sheng, C. Molecular glues for targeted protein degradation: from serendipity to rational discovery. J. Med. Chem. 64, 10606\u201310620 (2021).","journal-title":"J. Med. Chem."},{"key":"699_CR5","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1038\/nrd3681","volume":"11","author":"JW Scannell","year":"2012","unstructured":"Scannell, J. W., Blanckley, A., Boldon, H. & Warrington, B. Diagnosing the decline in pharmaceutical R&D efficiency. Nat. Rev. Drug Discov. 11, 191\u2013200 (2012).","journal-title":"Nat. Rev. Drug Discov."},{"key":"699_CR6","doi-asserted-by":"publisher","DOI":"10.1039\/9781782622345-00001","author":"D Taylor","year":"2015","unstructured":"Taylor, D. The pharmaceutical industry and the future of drug development. Pharm. Environ. https:\/\/doi.org\/10.1039\/9781782622345-00001 (2015).","journal-title":"Pharm. Environ."},{"key":"699_CR7","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1001\/jama.2020.1166","volume":"323","author":"OJ Wouters","year":"2020","unstructured":"Wouters, O. J., McKee, M. & Luyten, J. Estimated research and development investment needed to bring a new medicine to market, 2009\u20132018. JAMA 323, 844\u2013853 (2020).","journal-title":"JAMA"},{"key":"699_CR8","doi-asserted-by":"publisher","first-page":"891","DOI":"10.3390\/ph16060891","volume":"16","author":"A Blanco-Gonzalez","year":"2023","unstructured":"Blanco-Gonzalez, A. et al. The role of AI in drug discovery: challenges, opportunities, and strategies. Pharmaceuticals 16, 891 (2023).","journal-title":"Pharmaceuticals"},{"key":"699_CR9","unstructured":"Ramesh, A. et al. Zero-shot text-to-image generation. In International Conference on Machine Learning 8821\u20138831 (PMLR, 2021)."},{"key":"699_CR10","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"F-A Croitoru","year":"2023","unstructured":"Croitoru, F.-A., Hondru, V., Ionescu, R. T. & Shah, M. Diffusion models in vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45, 10850\u201310869 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"699_CR11","unstructured":"Bubeck, S. et al. Sparks of artificial general intelligence: early experiments with GPT4. Preprint at https:\/\/arxiv.org\/abs\/2303.12712 (2023)."},{"key":"699_CR12","first-page":"1","volume":"1","author":"R Gozalo-Brizuela","year":"2023","unstructured":"Gozalo-Brizuela, R. & Garrido-Merch\u00e1n, E. C. ChatGPT is not all you need. A State of the Art Review of large generative AI models. GRACE 1, 1 (2023).","journal-title":"GRACE"},{"key":"699_CR13","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583\u2013589 (2021).","journal-title":"Nature"},{"key":"699_CR14","doi-asserted-by":"publisher","first-page":"1120370","DOI":"10.3389\/fbinf.2023.1120370","volume":"3","author":"LM Bertoline","year":"2023","unstructured":"Bertoline, L. M., Lima, A. N., Krieger, J. E. & Teixeira, S. K. Before and after AlphaFold2: an overview of protein structure prediction. Front. Bioinform. 3, 1120370 (2023).","journal-title":"Front. Bioinform."},{"key":"699_CR15","doi-asserted-by":"publisher","first-page":"108","DOI":"10.3389\/frobt.2019.00108","volume":"6","author":"CF Lipinski","year":"2019","unstructured":"Lipinski, C. F., Maltarollo, V. G., Oliveira, P. R., Da Silva, A. B. & Honorio, K. M. Advances and perspectives in applying deep learning for drug design and discovery. Front. Robot. AI 6, 108 (2019).","journal-title":"Front. Robot. AI"},{"key":"699_CR16","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1021\/ar500432k","volume":"48","author":"J-L Reymond","year":"2015","unstructured":"Reymond, J.-L. The chemical space project. Acc. Chem. Res. 48, 722\u2013730 (2015).","journal-title":"Acc. Chem. Res."},{"key":"699_CR17","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1016\/j.drudis.2021.05.019","volume":"26","author":"J Meyers","year":"2021","unstructured":"Meyers, J., Fabian, B. & Brown, N. De novo molecular design and generative models. Drug Discov. Today 26, 2707\u20132715 (2021).","journal-title":"Drug Discov. Today"},{"key":"699_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.04.021","author":"Y Jiang","year":"2022","unstructured":"Jiang, Y. et al. Artificial intelligence for retrosynthesis prediction. Engineering https:\/\/doi.org\/10.1016\/j.eng.2022.04.021 (2022).","journal-title":"Engineering"},{"key":"699_CR19","first-page":"100062","volume":"3","author":"N S\u00e1nchez-Cruz","year":"2023","unstructured":"S\u00e1nchez-Cruz, N. Deep graph learning in molecular docking: advances and opportunities. Artif. Intell. Life Sci. 3, 100062 (2023).","journal-title":"Artif. Intell. Life Sci."},{"key":"699_CR20","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1002\/wcms.1183","volume":"4","author":"JohnBO Mitchell","year":"2014","unstructured":"Mitchell, JohnB. O. Machine learning methods in chemoinformatics. Wiley Interdiscip. Rev. Comput. Mol. Sci. 4, 468\u2013481 (2014).","journal-title":"Wiley Interdiscip. Rev. Comput. Mol. Sci."},{"key":"699_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13321-021-00522-2","volume":"13","author":"AT McNutt","year":"2021","unstructured":"McNutt, A. T. et al. GNINA 1.0: molecular docking with deep learning. J. Cheminform. 13, 43 (2021).","journal-title":"J. Cheminform."},{"key":"699_CR22","doi-asserted-by":"publisher","first-page":"5485","DOI":"10.1021\/acs.jcim.2c01149","volume":"62","author":"H Zhu","year":"2022","unstructured":"Zhu, H., Yang, J. & Huang, N. Assessment of the generalization abilities of machine-learning scoring functions for structure-based virtual screening. J. Chem. Inf. Model. 62, 5485\u20135502 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR23","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1021\/acs.jcim.7b00403","volume":"58","author":"I Wallach","year":"2018","unstructured":"Wallach, I. & Heifets, A. Most ligand-based classification benchmarks reward memorization rather than generalization. J. Chem. Inf. Model. 58, 916\u2013932 (2018).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR24","doi-asserted-by":"publisher","first-page":"3130","DOI":"10.1039\/D3SC04185A","volume":"15","author":"M Buttenschoen","year":"2024","unstructured":"Buttenschoen, M., Morris, G. M. & Deane, C. M. PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences. Chem. Sci. 15, 3130\u20133139 (2024).","journal-title":"Chem. Sci."},{"key":"699_CR25","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1038\/s42256-023-00636-2","volume":"5","author":"M Mokaya","year":"2023","unstructured":"Mokaya, M. et al. Testing the limits of SMILES-based de novo molecular generation with curriculum and deep reinforcement learning. Nat. Mach. Intell. 5, 386\u2013394 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"699_CR26","doi-asserted-by":"publisher","first-page":"4263","DOI":"10.1021\/acs.jcim.0c00155","volume":"60","author":"V-K Tran-Nguyen","year":"2020","unstructured":"Tran-Nguyen, V.-K., Jacquemard, C. & Rognan, D. LIT-PCBA: an unbiased data set for machine learning and virtual screening. J. Chem. Inf. Model. 60, 4263\u20134273 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR27","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1039\/D3DD00252G","volume":"3","author":"P Torren-Peraire","year":"2024","unstructured":"Torren-Peraire, P. et al. Models matter: the impact of single-step retrosynthesis on synthesis planning. Digit. Discov. 3, 558\u2013572 (2024).","journal-title":"Digit. Discov."},{"key":"699_CR28","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1021\/acsmedchemlett.3c00041","volume":"14","author":"Y Ivanenkov","year":"2023","unstructured":"Ivanenkov, Y. et al. The hitchhiker\u2019s guide to deep learning driven generative chemistry. ACS Med. Chem. Lett. 14, 901\u2013915 (2023).","journal-title":"ACS Med. Chem. Lett."},{"key":"699_CR29","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1186\/s13321-023-00781-1","volume":"15","author":"K Handa","year":"2023","unstructured":"Handa, K., Thomas, M. C., Kageyama, M., Iijima, T. & Bender, A. On the difficulty of validating molecular generative models realistically: a case study on public and proprietary data. J. Cheminform. 15, 112 (2023).","journal-title":"J. Cheminform."},{"key":"699_CR30","unstructured":"Harris, C. et al. PoseCheck: generative models for 3D structure-based drug design produce unrealistic poses. In NeurIPS 2023 Generative AI and Biology (GenBio) Workshop (2023)."},{"key":"699_CR31","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.3389\/fphar.2018.01275","volume":"9","author":"BJ Neves","year":"2018","unstructured":"Neves, B. J. et al. QSAR-based virtual screening: advances and applications in drug discovery. Front. Pharmacol. 9, 1275 (2018).","journal-title":"Front. Pharmacol."},{"key":"699_CR32","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.2174\/1389450116666151102095555","volume":"17","author":"X Yan","year":"2016","unstructured":"Yan, X. et al. Chemical structure similarity search for ligand-based virtual screening: methods and computational resources. Curr. Drug Targets 17, 1580\u20131585 (2016).","journal-title":"Curr. Drug Targets"},{"key":"699_CR33","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","volume":"630","author":"J Abramson","year":"2024","unstructured":"Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493\u2013500 (2024).","journal-title":"Nature"},{"key":"699_CR34","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1002\/prot.26171","volume":"89","author":"J Pereira","year":"2021","unstructured":"Pereira, J. et al. High-accuracy protein structure prediction in CASP14. Proteins 89, 1687\u20131699 (2021).","journal-title":"Proteins"},{"key":"699_CR35","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1021\/acs.jcim.8b00545","volume":"59","author":"M Su","year":"2019","unstructured":"Su, M. et al. Comparative assessment of scoring functions: the CASF-2016 update. J. Chem. Inf. Model. 59, 895\u2013913 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR36","unstructured":"Lowe, D. M. Extraction of Chemical Structures and Reactions from the Literature. PhD thesis, Univ. Cambridge (2012)."},{"key":"699_CR37","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2018","unstructured":"Wu, Z. et al. MoleculeNet: a benchmark for molecular machine learning. Chem. Sci. 9, 513\u2013530 (2018).","journal-title":"Chem. Sci."},{"key":"699_CR38","doi-asserted-by":"publisher","first-page":"6582","DOI":"10.1021\/jm300687e","volume":"55","author":"MM Mysinger","year":"2012","unstructured":"Mysinger, M. M., Carchia, M., Irwin, J. J. & Shoichet, B. K. Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking. J. Med. Chem. 55, 6582\u20136594 (2012).","journal-title":"J. Med. Chem."},{"key":"699_CR39","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1021\/acs.jcim.0c00411","volume":"60","author":"PG Francoeur","year":"2020","unstructured":"Francoeur, P. G. et al. Three-dimensional convolutional neural networks and a crossdocked data set for structure-based drug design. J. Chem. Inf. Model. 60, 4200\u20134215 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR40","unstructured":"Vaswani, A. et al. Attention is all you need. In Proc. 31st International Conference on Neural Information Processing Systems 6000\u20136010 (ACM, 2017)."},{"key":"699_CR41","unstructured":"Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. International Conference of Learning Representations (ICLR) (2017)."},{"key":"699_CR42","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41586-023-06735-9","volume":"624","author":"A Merchant","year":"2023","unstructured":"Merchant, A. et al. Scaling deep learning for materials discovery. Nature 624, 80\u201385 (2023).","journal-title":"Nature"},{"key":"699_CR43","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","volume":"180","author":"JM Stokes","year":"2020","unstructured":"Stokes, J. M. et al. A deep learning approach to antibiotic discovery. Cell 180, 688\u2013702.e13 (2020).","journal-title":"Cell"},{"key":"699_CR44","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1038\/s41586-023-06887-8","volume":"626","author":"F Wong","year":"2023","unstructured":"Wong, F. et al. Discovery of a structural class of antibiotics with explainable deep learning. Nature 626, 177\u2013185 (2023).","journal-title":"Nature"},{"key":"699_CR45","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13321-020-00479-8","volume":"13","author":"D Jiang","year":"2021","unstructured":"Jiang, D. et al. Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. J. Cheminform. 13, 12 (2021).","journal-title":"J. Cheminform."},{"key":"699_CR46","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1021\/acs.jcim.9b00587","volume":"60","author":"V Korolev","year":"2020","unstructured":"Korolev, V., Mitrofanov, A., Korotcov, A. & Tkachenko, V. Graph convolutional neural networks as \u2018general-purpose\u2019 property predictors: the universality and limits of applicability. J. Chem. Inf. Model. 60, 22\u201328 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR47","unstructured":"Geiger, M. & Smidt, T. e3nn: Euclidean neural networks. Preprint at https:\/\/arxiv.org\/abs\/2207.09453 (2022)."},{"key":"699_CR48","first-page":"9323","volume":"139","author":"VG Satorras","year":"2021","unstructured":"Satorras, V. G., Hoogeboom, E. & Welling, M. E(n) equivariant graph neural networks. PLMR 139, 9323\u20139332 (2021).","journal-title":"PLMR"},{"key":"699_CR49","doi-asserted-by":"publisher","first-page":"2960","DOI":"10.1021\/acs.jcim.3c00322","volume":"63","author":"J Scantlebury","year":"2023","unstructured":"Scantlebury, J. et al. A small step toward generalizability: training a machine learning scoring function for structure-based virtual screening. J. Chem. Inf. Model. 63, 2960\u20132974 (2023).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR50","unstructured":"Corso, G. et al. DiffDock: diffusion steps, twists, and turns for molecular docking. In International Conference on Learning Representations (2023)."},{"key":"699_CR51","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1038\/s42256-024-00815-9","volume":"6","author":"I Igashov","year":"2024","unstructured":"Igashov, I. et al. Equivariant 3D-conditional diffusion model for molecular linker design. Nat. Mach. Intell. 6, 417\u2013427 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"699_CR52","unstructured":"Jing, B., Corso, G., Chang, J., Barzilay, R. & Jaakkola, T. Torsional diffusion for molecular conformer generation. In Proc. 36th International Conference on Neural Information Processing Systems article no. 1760, 24240\u201324253 (ACM, 2022)."},{"key":"699_CR53","unstructured":"Schneuing, A. et al. Structure-based drug design with equivariant diffusion models. Preprint at https:\/\/arxiv.org\/abs\/2210.13695v2 (2022)."},{"key":"699_CR54","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A. & Abbeel, P. Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"699_CR55","first-page":"369","volume":"34","author":"J Reed","year":"2023","unstructured":"Reed, J., Alterio, B., Coblenz, H., O\u2019Lear, T. & Metz, T. AI image-generation as a teaching strategy in nursing education. J. Interact. Learn. Res. 34, 369\u2013399 (2023).","journal-title":"J. Interact. Learn. Res."},{"key":"699_CR56","unstructured":"Yildirim, E. In Art and Architecture: Theory, Practice and Experience 97 (2022)."},{"key":"699_CR57","doi-asserted-by":"publisher","first-page":"220238","DOI":"10.1098\/rsos.220238","volume":"10","author":"G Azuaje","year":"2023","unstructured":"Azuaje, G. et al. Exploring the use of AI text-to-image generation to downregulate negative emotions in an expressive writing application. R. Soc. Open Sci. 10, 220238 (2023).","journal-title":"R. Soc. Open Sci."},{"key":"699_CR58","unstructured":"Fishman, N., Klarner, L., Mathieu, E., Hutchinson, M. & De Bortoli, V. Metropolis sampling for constrained diffusion models. In Proc. 37th International Conference on Neural Information Processing Systems article no. 2721, 62296\u20136233 (ACM, 2024)."},{"key":"699_CR59","unstructured":"Song, Y., Dhariwal, P., Chen, M. & Sutskever, I. Consistency models. In International Conference on Machine Learning 32211\u201332252 (PMLR, 2023)."},{"key":"699_CR60","unstructured":"Lipman, Y., Chen, R. T., Ben-Hamu, H., Nickel, M. & Le, M. Flow matching for generative modeling. In The Eleventh International Conference on Learning Representations (2022)."},{"key":"699_CR61","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S. & Gupta, A. Revisiting unreasonable effectiveness of data in deep learning era. In Proc. IEEE International Conference on Computer Vision 843\u2013852 (IEEE, 2017).","DOI":"10.1109\/ICCV.2017.97"},{"key":"699_CR62","unstructured":"Betker, J. et al. Improving image generation with better captions. Open AI https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf (2023)."},{"key":"699_CR63","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1093\/bioinformatics\/btu626","volume":"31","author":"Z Liu","year":"2014","unstructured":"Liu, Z. et al. PDB-wide collection of binding data: current status of the PDBbind database. Bioinformatics 31, 405\u2013412 (2014).","journal-title":"Bioinformatics"},{"key":"699_CR64","first-page":"D271","volume":"45","author":"PW Rose","year":"2016","unstructured":"Rose, P. W. et al. The RCSB protein data bank: integrative view of protein, gene and 3D structural information. Nucleic Acids Res. 45, D271\u2013D281 (2016).","journal-title":"Nucleic Acids Res."},{"key":"699_CR65","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","volume":"52","author":"B Zdrazil","year":"2024","unstructured":"Zdrazil, B. et al. The ChEMBL database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids Res 52, D1180\u2013D1192 (2024).","journal-title":"Nucleic Acids Res"},{"key":"699_CR66","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C. & Chen, M. Hierarchical text-conditional image generation with clip latents. Preprint at https:\/\/arxiv.org\/abs\/2204.06125 (2022)."},{"key":"699_CR67","unstructured":"Touvron, H. et al. Llama 2: open foundation and fine-tuned chat models. Preprint at https:\/\/arxiv.org\/abs\/2307.09288 (2023)."},{"key":"699_CR68","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1126\/science.abj8754","volume":"373","author":"M Baek","year":"2021","unstructured":"Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871\u2013876 (2021).","journal-title":"Science"},{"key":"699_CR69","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123\u20131130 (2023).","journal-title":"Science"},{"key":"699_CR70","first-page":"D570","volume":"48","author":"AL Mitchell","year":"2019","unstructured":"Mitchell, A. L. et al. MGnify: the microbiome analysis resource in 2020. Nucleic Acids Res 48, D570\u2013D578 (2019).","journal-title":"Nucleic Acids Res"},{"key":"699_CR71","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1093\/bioinformatics\/btm098","volume":"23","author":"BE Suzek","year":"2007","unstructured":"Suzek, B. E., Huang, H., McGarvey, P., Mazumder, R. & Wu, C. H. UniRef: comprehensive and non-redundant UniProt reference clusters. Bioinformatics 23, 1282\u20131288 (2007).","journal-title":"Bioinformatics"},{"key":"699_CR72","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1021\/ci400709d","volume":"54","author":"J Tang","year":"2014","unstructured":"Tang, J. et al. Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis. J. Chem. Inf. Model. 54, 735\u2013743 (2014).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR73","doi-asserted-by":"publisher","first-page":"85","DOI":"10.3389\/fenvs.2015.00085","volume":"3","author":"R Huang","year":"2016","unstructured":"Huang, R. et al. Tox21challenge to build predictive models of nuclear receptor and stress response pathways as mediated by exposure to environmental chemicals and drugs. Front. Environ. Sci. 3, 85 (2016).","journal-title":"Front. Environ. Sci."},{"key":"699_CR74","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1039\/D3RA08147H","volume":"14","author":"T Voitsitskyi","year":"2024","unstructured":"Voitsitskyi, T. et al. Augmenting a training dataset of the generative diffusion model for molecular docking with artificial binding pockets. RSC Adv. 14, 1341\u20131353 (2024).","journal-title":"RSC Adv."},{"key":"699_CR75","doi-asserted-by":"publisher","first-page":"7946","DOI":"10.1021\/acs.jmedchem.2c00487","volume":"65","author":"M Volkov","year":"2022","unstructured":"Volkov, M. et al. On the frustration to predict binding affinities from protein\u2013ligand structures with deep neural networks. J. Med. Chem. 65, 7946\u20137958 (2022).","journal-title":"J. Med. Chem."},{"key":"699_CR76","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1016\/j.coph.2004.04.007","volume":"4","author":"TL Blundell","year":"2004","unstructured":"Blundell, T. L. & Patel, S. High-throughput X-ray crystallography for drug discovery. Curr. Opin. Pharmacol. 4, 490\u2013496 (2004).","journal-title":"Curr. Opin. Pharmacol."},{"key":"699_CR77","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1126\/science.abb8330","volume":"369","author":"NF Polizzi","year":"2020","unstructured":"Polizzi, N. F. & DeGrado, W. F. A defined structural unit enables de novo design of small-molecule-binding proteins. Science 369, 1227\u20131233 (2020).","journal-title":"Science"},{"key":"699_CR78","unstructured":"Stark, H., Jing, B., Barzilay, R. & Jaakkola, T. Harmonic prior self-conditioned flow matching for multi-ligand docking and binding site design. In NeurIPS 2023 AI for Science Workshop (2023)."},{"key":"699_CR79","unstructured":"Corso, G., Deng, A., Polizzi, N., Barzilay, R. & Jaakkola, T. The discovery of binding modes requires rethinking docking generalization. In NeurIPS 2023 Generative AI and Biology (GenBio) Workshop (2023)."},{"key":"699_CR80","unstructured":"Liu, L. et al. Pre-training on large-scale generated docking conformations with helixdock to unlock the potential of protein\u2013ligand structure prediction models. Preprint at https:\/\/arxiv.org\/abs\/2310.13913 (2023)."},{"key":"699_CR81","doi-asserted-by":"publisher","DOI":"10.1093\/bioadv\/vbad072","volume":"3","author":"M McFee","year":"2023","unstructured":"McFee, M. & Kim, P. M. GDockScore: a graph-based protein\u2013protein docking scoring function. Bioinform. Adv. 3, vbad072 (2023).","journal-title":"Bioinform. Adv."},{"key":"699_CR82","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3389\/fphar.2018.00011","volume":"9","author":"M R\u00e9au","year":"2018","unstructured":"R\u00e9au, M., Langenfeld, F., Zagury, J.-F., Lagarde, N. & Montes, M. Decoys selection in benchmarking datasets: overview and perspectives. Front. Pharmacol. 9, 11 (2018).","journal-title":"Front. Pharmacol."},{"key":"699_CR83","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1002\/anie.202204647","volume":"61","author":"F Strieth-Kalthoff","year":"2022","unstructured":"Strieth-Kalthoff, F. et al. Machine learning for chemical reactivity: the importance of failed experiments. Angew. Chem. Int. Ed. 61, 29 (2022).","journal-title":"Angew. Chem. Int. Ed."},{"key":"699_CR84","doi-asserted-by":"publisher","first-page":"447","DOI":"10.11613\/BM.2017.030201","volume":"27","author":"A Mlinari\u0107","year":"2017","unstructured":"Mlinari\u0107, A., Horvat, M. & \u0160upak Smol\u010di\u0107, V. Dealing with the positive publication bias: why you should really publish your negative results. Biochem. Med. 27, 447\u2013452 (2017).","journal-title":"Biochem. Med."},{"key":"699_CR85","doi-asserted-by":"publisher","first-page":"8857","DOI":"10.1021\/acs.jmedchem.0c00452","volume":"63","author":"K McCloskey","year":"2020","unstructured":"McCloskey, K. et al. Machine learning on DNA-encoded libraries: a new paradigm for hit finding. J. Med. Chem. 63, 8857\u20138866 (2020).","journal-title":"J. Med. Chem."},{"key":"699_CR86","doi-asserted-by":"publisher","first-page":"2945","DOI":"10.1021\/acs.orglett.3c01282","volume":"25","author":"MP Maloney","year":"2023","unstructured":"Maloney, M. P. et al. Negative data in data sets for machine learning training. Org. Lett. 25, 2945\u20132947 (2023).","journal-title":"Org. Lett."},{"key":"699_CR87","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1515\/ci-2023-0104","volume":"45","author":"L McEwen","year":"2023","unstructured":"McEwen, L. & Mustafa, F. Worldfair chemistry: making IUPAC assets fair. Chem. Int. 45, 14\u201317 (2023).","journal-title":"Chem. Int."},{"key":"699_CR88","doi-asserted-by":"publisher","first-page":"e55852","DOI":"10.3897\/rio.6.e55852","volume":"6","author":"C Steinbeck","year":"2020","unstructured":"Steinbeck, C. et al. NFDI4chem\u2014towards a national research data infrastructure for chemistry in Germany. Res. Ideas Outcomes 6, e55852 (2020).","journal-title":"Res. Ideas Outcomes"},{"key":"699_CR89","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/nature25978","volume":"555","author":"MH Segler","year":"2018","unstructured":"Segler, M. H., Preuss, M. & Waller, M. P. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555, 604\u2013610 (2018).","journal-title":"Nature"},{"key":"699_CR90","doi-asserted-by":"publisher","DOI":"10.1038\/nature.2016.19866","author":"P Ball","year":"2016","unstructured":"Ball, P. Computer gleans chemical insight from lab notebook failures. Nature https:\/\/doi.org\/10.1038\/nature.2016.19866 (2016).","journal-title":"Nature"},{"key":"699_CR91","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1021\/acs.jcim.6b00207","volume":"56","author":"MC Swain","year":"2016","unstructured":"Swain, M. C. & Cole, J. M. ChemDataExtractor: a toolkit for automated extraction of chemical information from the scientific literature. J. Chem. Inf. Model. 56, 1894\u20131904 (2016).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR92","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40782-0","volume":"14","author":"K Rajan","year":"2023","unstructured":"Rajan, K., Brinkhaus, H. O., Agea, M. I., Zielesny, A. & Steinbeck, C. DECIMER.ai: an open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications. Nat. Commun. 14, 5045 (2023).","journal-title":"Nat. Commun."},{"key":"699_CR93","unstructured":"Blecher, L., Cucurull, G., Scialom, T. & Stojnic, R. Nougat: neural optical understanding for academic documents. Preprint at https:\/\/arxiv.org\/abs\/2308.13418 (2023)."},{"key":"699_CR94","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1038\/s41557-020-0496-2","volume":"12","author":"J Chodera","year":"2020","unstructured":"Chodera, J., Lee, A. A., London, N. & von Delft, F. Crowdsourcing drug discovery for pandemics. Nat. Chem. 12, 581 (2020).","journal-title":"Nat. Chem."},{"key":"699_CR95","doi-asserted-by":"publisher","unstructured":"The COVID Moonshot Consortium. COVID Moonshot: open science discovery of SARS-CoV-2 main protease inhibitors by combining crowdsourcing, high-throughput experiments, computational simulations, and machine learning. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2020.10.29.339317 (2020).","DOI":"10.1101\/2020.10.29.339317"},{"key":"699_CR96","unstructured":"Boby, M. L. et al. Open science discovery of potent noncovalent SARS-CoV-2 main protease inhibitors. Science 382, eabo7201 (2023)."},{"key":"699_CR97","doi-asserted-by":"publisher","first-page":"102545","DOI":"10.1016\/j.sbi.2023.102545","volume":"79","author":"T Hanser","year":"2023","unstructured":"Hanser, T. Federated learning for molecular discovery. Curr. Opin. Struct. Biol. 79, 102545 (2023).","journal-title":"Curr. Opin. Struct. Biol."},{"key":"699_CR98","unstructured":"Hanser, T. et al. Using privacy-preserving federated learning to enable pre-competitive cross-industry knowledge sharing and improve QSAR models. In Society of Toxicology (SOT) Annual Meeting (2022)."},{"key":"699_CR99","doi-asserted-by":"publisher","first-page":"e2211613120","DOI":"10.1073\/pnas.2211613120","volume":"120","author":"R Wang","year":"2023","unstructured":"Wang, R., Chaudhari, P. & Davatzikos, C. Bias in machine learning models can be significantly mitigated by careful training: evidence from neuroimaging studies. Proc. Natl Acad. Sci. USA 120, e2211613120 (2023).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"699_CR100","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.jbusres.2022.01.076","volume":"144","author":"B Van Giffen","year":"2022","unstructured":"Van Giffen, B., Herhausen, D. & Fahse, T. Overcoming the pitfalls and perils of algorithms: a classification of machine learning biases and mitigation methods. J. Bus. Res. 144, 93\u2013106 (2022).","journal-title":"J. Bus. Res."},{"key":"699_CR101","doi-asserted-by":"crossref","unstructured":"Leavy, S. Gender bias in artificial intelligence: the need for diversity and gender theory in machine learning. In Proc. 1st International Workshop on Gender Equality in Software Engineering 14\u201316 (2018).","DOI":"10.1145\/3195570.3195580"},{"key":"699_CR102","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1108\/JICES-06-2018-0056","volume":"16","author":"NT Lee","year":"2018","unstructured":"Lee, N. T. Detecting racial bias in algorithms and machine learning. J. Inf. Commun. Ethics Soc. 16, 252\u2013260 (2018).","journal-title":"J. Inf. Commun. Ethics Soc."},{"key":"699_CR103","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1021\/acs.jcim.6b00290","volume":"56","author":"G Subramanian","year":"2016","unstructured":"Subramanian, G., Ramsundar, B., Pande, V. & Denny, R. A. Computational modeling of \u03b2-secretase 1 (BACE-1) inhibitors using ligand based approaches. J. Chem. Inf. Model. 56, 1936\u20131949 (2016).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR104","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1021\/ci300124c","volume":"52","author":"IF Martins","year":"2012","unstructured":"Martins, I. F., Teixeira, A. L., Pinheiro, L. & Falcao, A. O. A Bayesian approach to in silico blood\u2013brain barrier penetration modeling. J. Chem. Inf. Model. 52, 1686\u20131697 (2012).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR105","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1021\/ci034243x","volume":"44","author":"JS Delaney","year":"2004","unstructured":"Delaney, J. S. ESOL: estimating aqueous solubility directly from molecular structure. J. Chem. Inf. Comput. Sci. 44, 1000\u20131005 (2004).","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"699_CR106","unstructured":"Xie, Y., Xu, Z., Ma, J. & Mei, Q. How much space has been explored? Measuring the chemical space covered by databases and machine-generated molecules. In The Eleventh International Conference on Learning Representations (2022)."},{"key":"699_CR107","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1021\/acscentsci.3c00372","volume":"9","author":"A Thakkar","year":"2023","unstructured":"Thakkar, A. et al. Unbiasing retrosynthesis language models with disconnection prompts. ACS Cent. Sci. 9, 1488\u20131498 (2023).","journal-title":"ACS Cent. Sci."},{"key":"699_CR108","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s10822-007-9150-y","volume":"22","author":"AE Cleves","year":"2008","unstructured":"Cleves, A. E. & Jain, A. N. Effects of inductive bias on computational evaluations of ligand-based modeling and on drug discovery. J. Comput. Aided Mol. Des. 22, 147\u2013159 (2008).","journal-title":"J. Comput. Aided Mol. Des."},{"key":"699_CR109","doi-asserted-by":"publisher","first-page":"e0220113","DOI":"10.1371\/journal.pone.0220113","volume":"14","author":"L Chen","year":"2019","unstructured":"Chen, L. et al. Hidden bias in the DUD-E dataset leads to misleading performance of deep learning in structure-based virtual screening. PLoS ONE 14, e0220113 (2019).","journal-title":"PLoS ONE"},{"key":"699_CR110","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1021\/acs.jcim.8b00712","volume":"59","author":"J Sieg","year":"2019","unstructured":"Sieg, J., Flachsenberg, F. & Rarey, M. In need of bias control: evaluating chemical data for machine learning in structure-based virtual screening. J. Chem. Inf. Model. 59, 947\u2013961 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR111","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1021\/ci050407t","volume":"46","author":"M Jacobsson","year":"2006","unstructured":"Jacobsson, M. & Karl\u00e9n, A. Ligand bias of scoring functions in structure-based virtual screening. J. Chem. Inf. Model. 46, 1334\u20131343 (2006).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR112","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s13321-016-0167-x","volume":"8","author":"L Chaput","year":"2016","unstructured":"Chaput, L., Martinez-Sanz, J., Saettel, N. & Mouawad, L. Benchmark of four popular virtual screening programs: construction of the active\/decoy dataset remains a major determinant of measured performance. J. Cheminform. 8, 56 (2016).","journal-title":"J. Cheminform."},{"key":"699_CR113","doi-asserted-by":"publisher","first-page":"18209","DOI":"10.1021\/acs.jmedchem.1c01830","volume":"64","author":"D Jiang","year":"2021","unstructured":"Jiang, D. et al. Interactiongraphnet: a novel and efficient deep graph representation learning framework for accurate protein\u2013ligand interaction predictions. J. Med. Chem. 64, 18209\u201318232 (2021).","journal-title":"J. Med. Chem."},{"key":"699_CR114","doi-asserted-by":"publisher","first-page":"8129","DOI":"10.1039\/D3SC02044D","volume":"14","author":"C Shen","year":"2023","unstructured":"Shen, C. et al. A generalized protein\u2013ligand scoring framework with balanced scoring, docking, ranking and screening powers. Chem. Sci. 14, 8129\u20138146 (2023).","journal-title":"Chem. Sci."},{"key":"699_CR115","doi-asserted-by":"crossref","unstructured":"Farahani, A., Voghoei, S., Rasheed, K. & Arabnia, H. R. A brief review of domain adaptation. Advances in Data Science and Information Engineering: Proc. ICDATA 2020 and IKE 2020 877\u2013894 (2021).","DOI":"10.1007\/978-3-030-71704-9_65"},{"key":"699_CR116","unstructured":"Han, X., Baldwin, T. & Cohn, T. Towards equal opportunity fairness through adversarial learning. Preprint at https:\/\/arxiv.org\/abs\/2203.06317 (2022)."},{"key":"699_CR117","doi-asserted-by":"crossref","unstructured":"Shao, S., Ziser, Y. & Cohen, S. B. Gold doesn\u2019t always glitter: spectral removal of linear and nonlinear guarded attribute information. In The 17th Conference of the European Chapter of the Association for Computational Linguistics 1611\u20131622 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.eacl-main.118"},{"key":"699_CR118","unstructured":"Klarner, L. et al. Drug discovery under covariate shift with domain-informed prior distributions over functions. In Proc. 40th International Conference on Machine Learning article no. 706, 17176\u201317197 (ACM, 2023)."},{"key":"699_CR119","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1002\/cmdc.200700221","volume":"3","author":"C Kramer","year":"2008","unstructured":"Kramer, C., Beck, B., Kriegl, J. M. & Clark, T. A composite model for hERG blockade. ChemMedChem 3, 254\u2013265 (2008).","journal-title":"ChemMedChem"},{"key":"699_CR120","doi-asserted-by":"crossref","unstructured":"Kausar, S. & Falcao, A. O. An automated framework for QSAR model building. J. Cheminform. https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-017-0256-5 (2018).","DOI":"10.1186\/s13321-017-0256-5"},{"key":"699_CR121","doi-asserted-by":"publisher","first-page":"4393","DOI":"10.3390\/molecules24234393","volume":"24","author":"S Simeon","year":"2019","unstructured":"Simeon, S. & Jongkon, N. Construction of quantitative structure activity relationship (QSAR) models to predict potency of structurally diversed Janus kinase 2 inhibitors. Molecules 24, 4393 (2019).","journal-title":"Molecules"},{"key":"699_CR122","doi-asserted-by":"publisher","first-page":"e61007","DOI":"10.1371\/journal.pone.0061007","volume":"8","author":"T Kalliokoski","year":"2013","unstructured":"Kalliokoski, T., Kramer, C., Vulpetti, A. & Gedeck, P. Comparability of mixed IC50 data\u2014a statistical analysis. PLoS ONE 8, e61007 (2013).","journal-title":"PLoS ONE"},{"key":"699_CR123","doi-asserted-by":"publisher","first-page":"5165","DOI":"10.1021\/jm300131x","volume":"55","author":"C Kramer","year":"2012","unstructured":"Kramer, C., Kalliokoski, T., Gedeck, P. & Vulpetti, A. The experimental uncertainty of heterogeneous public Ki data. J. Med. Chem. 55, 5165\u20135173 (2012).","journal-title":"J. Med. Chem."},{"key":"699_CR124","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1021\/acs.jcim.4c00049","volume":"64","author":"GA Landrum","year":"2024","unstructured":"Landrum, G. A. & Riniker, S. Combining IC50 or Ki values from different sources is a source of significant noise. J. Chem. Inf. Model. 64, 1560\u20131567 (2024).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR125","first-page":"100087","volume":"4","author":"CA Hern\u00e1ndez-Garrido","year":"2023","unstructured":"Hern\u00e1ndez-Garrido, C. A. & S\u00e1nchez-Cruz, N. Experimental uncertainty in training data for protein\u2013ligand binding affinity prediction models. Artif. Intell. Life Sci. 4, 100087 (2023).","journal-title":"Artif. Intell. Life Sci."},{"key":"699_CR126","doi-asserted-by":"publisher","first-page":"32119","DOI":"10.1021\/acsomega.2c03363","volume":"7","author":"A Speck-Planche","year":"2022","unstructured":"Speck-Planche, A. & Kleandrova, V. V. Multi-condition QSAR model for the virtual design of chemicals with dual pan-antiviral and anti-cytokine storm profiles. ACS Omega 7, 32119\u201332130 (2022).","journal-title":"ACS Omega"},{"key":"699_CR127","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1021\/acschembio.7b00903","volume":"13","author":"JB Baell","year":"2018","unstructured":"Baell, J. B. & Nissink, J. W. M. Seven year itch: pan-assay interference compounds (PAINs) in 2017 utility and limitations. ACS Chem. Biol. 13, 36\u201344 (2018).","journal-title":"ACS Chem. Biol."},{"key":"699_CR128","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1002\/cmdc.200700139","volume":"3","author":"R Brenk","year":"2008","unstructured":"Brenk, R. et al. Lessons learnt from assembling screening libraries for drug discovery for neglected diseases. ChemMedChem 3, 435\u2013444 (2008).","journal-title":"ChemMedChem"},{"key":"699_CR129","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1021\/jm901070c","volume":"53","author":"A Jadhav","year":"2010","unstructured":"Jadhav, A. et al. Quantitative analyses of aggregation, autofluorescence, and reactivity artifacts in a screen for inhibitors of a thiol protease. J. Med. Chem. 53, 37\u201351 (2010).","journal-title":"J. Med. Chem."},{"key":"699_CR130","unstructured":"Walters, P. We need better benchmarks for machine learning in drug discovery. Practical Cheminformatics Blog https:\/\/practicalcheminformatics.blogspot.com\/2023\/08\/we-need-better-benchmarks-for-machine.html (2023)."},{"key":"699_CR131","unstructured":"Klarner, L., Reutlinger, M., Schindler, T., Deane, C. & Morris, G. Bias in the benchmark: systematic experimental errors in bioactivity databases confound multi-task and meta-learning algorithms. In ICML 2022 2nd AI for Science Workshop (2022)."},{"key":"699_CR132","doi-asserted-by":"publisher","first-page":"3790","DOI":"10.1021\/acs.jcim.4c00292","volume":"64","author":"DS Wigh","year":"2024","unstructured":"Wigh, D. S., Arrowsmith, J., Pomberger, A., Felton, K. C. & Lapkin, A. A. Orderly: data sets and benchmarks for chemical reaction data. J. Chem. Inf. Model. 64, 3790\u20133798 (2024).","journal-title":"J. Chem. Inf. Model."},{"key":"699_CR133","doi-asserted-by":"publisher","unstructured":"Durant, G., Boyles, F., Birchall, K., Marsden, B. & Deane, C. Robustly interrogating machine learning based scoring functions: what are they learning? Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.10.30.564251 (2023).","DOI":"10.1101\/2023.10.30.564251"},{"key":"699_CR134","doi-asserted-by":"publisher","unstructured":"Li, S. et al. Structure-aware interactive graph neural networks for the prediction of protein\u2013ligand binding affinity. In KDD21: Proc. 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining https:\/\/doi.org\/10.1145\/3447548.3467311 (ACM, 2021).","DOI":"10.1145\/3447548.3467311"},{"key":"699_CR135","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1093\/bioinformatics\/bty757","volume":"35","author":"M W\u00f3jcikowski","year":"2019","unstructured":"W\u00f3jcikowski, M., Kukie\u0142ka, M., Stepniewska-Dziubinska, M. M. & Siedlecki, P. Development of a protein\u2013ligand extended connectivity (PLEC) fingerprint and its application for binding affinity predictions. Bioinformatics 35, 1334\u20131341 (2019).","journal-title":"Bioinformatics"},{"key":"699_CR136","first-page":"913","volume":"9","author":"Z Wang","year":"2021","unstructured":"Wang, Z. et al. OnionNet-2: a convolutional neural network model for predicting protein\u2013ligand binding affinity based on residue-atom contacting shells. Front. Chem. 9, 913 (2021).","journal-title":"Front. Chem."},{"key":"699_CR137","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C. B. et al. A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4, 1\u201343 (2012).","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"699_CR138","unstructured":"Huang, K. et al. Therapeutics data commons: machine learning datasets and tasks for drug discovery and development. Preprint at https:\/\/arxiv.org\/abs\/2102.09548v2 (2021)."},{"key":"699_CR139","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s10822-021-00433-2","volume":"36","author":"JL Gan","year":"2022","unstructured":"Gan, J. L. et al. Benchmarking ensemble docking methods in D3R Grand Challenge 4. J. Comput. Aided Mol. Des. 36, 87\u201399 (2022).","journal-title":"J. Comput. Aided Mol. Des."},{"key":"699_CR140","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41570-022-00363-z","volume":"6","author":"S Ackloo","year":"2022","unstructured":"Ackloo, S. et al. CACHE (critical assessment of computational hit-finding experiments): a public\u2013private partnership benchmarking initiative to enable the development of computational methods for hit-finding. Nat. Rev. Chem. 6, 287\u2013295 (2022).","journal-title":"Nat. Rev. Chem."}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00699-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00699-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00699-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:06:31Z","timestamp":1729706791000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00699-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,15]]},"references-count":140,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["699"],"URL":"https:\/\/doi.org\/10.1038\/s43588-024-00699-0","relation":{},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,15]]},"assertion":[{"value":"1 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}