{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T21:49:49Z","timestamp":1774993789386,"version":"3.50.1"},"reference-count":40,"publisher":"American Chemical Society (ACS)","issue":"20","license":[{"start":{"date-parts":[[2022,10,4]],"date-time":"2022-10-04T00:00:00Z","timestamp":1664841600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R513052\/1"],"award-info":[{"award-number":["EP\/R513052\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2022,10,24]]},"DOI":"10.1021\/acs.jcim.2c00715","type":"journal-article","created":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T02:32:46Z","timestamp":1664937166000},"page":"4852-4862","source":"Crossref","is-referenced-by-count":30,"title":["Large-Scale Distributed Training of Transformers for Chemical Fingerprinting"],"prefix":"10.1021","volume":"62","author":[{"given":"Hisham","family":"Abdel-Aty","sequence":"first","affiliation":[{"name":"Department of Chemistry and Institute of Chemical Biology, Imperial College London, Molecular Sciences Research Hub, Shepherd\u2019s Bush, LondonW12 0BZ, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3559-0234","authenticated-orcid":true,"given":"Ian R.","family":"Gould","sequence":"additional","affiliation":[{"name":"Department of Chemistry and Institute of Chemical Biology, Imperial College London, Molecular Sciences Research Hub, Shepherd\u2019s Bush, LondonW12 0BZ, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"316","published-online":{"date-parts":[[2022,10,4]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC04175J"},{"key":"ref2\/cit2","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00601"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.9b00576"},{"key":"ref5\/cit5","volume":"30","author":"Jin W.","year":"2017","journal-title":"Adv. Neur. Inf. Proc. Sys."},{"key":"ref6\/cit6","doi-asserted-by":"publisher","DOI":"10.1021\/ci300415d"},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-019-0341-z"},{"key":"ref8\/cit8","doi-asserted-by":"publisher","DOI":"10.1021\/ja902302h"},{"key":"ref9\/cit9","unstructured":"Lowe, D. Chemical Reactions from US Patents (1976-Sep2016), 2017."},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.1039\/C9SC04944D"},{"key":"ref11\/cit11","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref12\/cit12","unstructured":"Chithrananda, S.; Grand, G.; Ramsundar, B.ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction. arXiv:2010.09885 [physics, q-bio] 2020."},{"key":"ref13\/cit13","unstructured":"Fabian, B.; Edlich, T.; Gaspar, H.; Segler, M.; Meyers, J.; Fiscato, M.; Ahmed, M.Molecular Representation Learning with Language Models and Domain-Relevant Auxiliary Tasks. arXiv:2011.13230 [cs] 2020."},{"key":"ref14\/cit14","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpclett.1c03058"},{"key":"ref15\/cit15","volume":"28","author":"Duvenaud D. K.","year":"2015","journal-title":"Adv. Neur. Inf. Proc. Sys."},{"key":"ref16\/cit16","first-page":"1263","volume-title":"International Conference on Machine Learning","author":"Gilmer J.","year":"2017"},{"key":"ref17\/cit17","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"ref18\/cit18","unstructured":"Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, \u0141.; Polosukhin, I. Attention Is All You Need. In Proceedings of the 31st International Conference on Neural Information Processing Systems; NIPS\u201917; Curran Associates Inc.: Red Hook, NY, USA, 2017; pp. 6000\u20136010."},{"key":"ref19\/cit19","unstructured":"Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers); Association for Computational Linguistics: Minneapolis, Minnesota, 2019; pp. 4171\u20134186."},{"key":"ref20\/cit20","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"ref21\/cit21","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC02339E"},{"key":"ref22\/cit22","unstructured":"Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; Levy, O.; Lewis, M.; Zettlemoyer, L.; Stoyanov, V.RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv:1907.11692 [cs] 2019."},{"key":"ref23\/cit23","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-5-26"},{"key":"ref24\/cit24","doi-asserted-by":"publisher","DOI":"10.1021\/ci400466r"},{"key":"ref25\/cit25","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00559"},{"key":"ref26\/cit26","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa971"},{"key":"ref27\/cit27","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr777"},{"key":"ref28\/cit28","unstructured":"Landrum, G.; Tosco, P.; Kelley, B.; sriniker; gedeck; Schneider, N.; Vianello, R.; Ric; Dalke, A.; Cole, B.; Savelyev, A.; Swain, M.; Turk, S.; Dan, N.; Vaucher, A.; Kawashima, E.; W\u00f3jcikowski, M.; Probst, D.; godin, g.; Cosgrove, D.; Pahl, A.; JP; Berenger, F.; strets123; Varjo, J. L.; O\u2019Boyle, N.; Fuller, P.; Jensen, J. H.; Sforna, G.; Gavid, D.  Rdkit\/Rdkit: 2020_03_1 (Q1 2020) Release; Zenodo, 2020."},{"key":"ref29\/cit29","unstructured":"Salle, A. terashuf. 2017. https:\/\/github.com\/alexandres\/terashuf."},{"key":"ref30\/cit30","doi-asserted-by":"crossref","unstructured":"Sennrich, R.; Haddow, B.; Birch, A. Neural Machine Translation of Rare Words with Subword Units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); Association for Computational Linguistics: Berlin, Germany, 2016; pp. 1715\u20131725.","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref31\/cit31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref32\/cit32","volume-title":"Introduction to Information Retrieval","author":"Manning C. D.","year":"2012"},{"key":"ref33\/cit33","first-page":"8024","volume-title":"Adv. Neur. Inf. Proc. Sys. 32","author":"Paszke A.","year":"2019"},{"key":"ref34\/cit34","unstructured":"Distributed Training\nand Fast inter-GPU Communication with NCCL | GTC Silicon Valley2019https:\/\/on-demand-gtc.gputechconf.com\/gtcnew\/sessionview.php?sessionName=s9656-distributed+training+and+fast+inter-gpu+communication+with+nccl (accessed 2021\u201305 -18)."},{"key":"ref35\/cit35","doi-asserted-by":"crossref","first-page":"38","DOI":"10.18653\/v1\/2020.emnlp-demos.6","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Wolf T.","year":"2020"},{"key":"ref36\/cit36","doi-asserted-by":"crossref","unstructured":"Reimers, N.; Gurevych, I.Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks. arXiv:1908.10084 [cs] 2019.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref37\/cit37","doi-asserted-by":"publisher","DOI":"10.1021\/ci300124c"},{"key":"ref38\/cit38","doi-asserted-by":"publisher","DOI":"10.1016\/j.chembiol.2016.07.023"},{"key":"ref39\/cit39","unstructured":"Ramsundar, B; Eastman, P; Feinberg, E; Gomes, J; Leswing, K; Pappu, A; Wu, M; Pande, V. Deepchem: Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology, 2016, https:\/\/github.com\/deepchem\/deepchem"},{"key":"ref40\/cit40","first-page":"2825","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.2c00715","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.2c00715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T18:00:54Z","timestamp":1682445654000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.2c00715"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,4]]},"references-count":40,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2022,10,24]]}},"alternative-id":["10.1021\/acs.jcim.2c00715"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.2c00715","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,4]]}}}