{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:49:21Z","timestamp":1768031361479,"version":"3.49.0"},"reference-count":51,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T00:00:00Z","timestamp":1620000000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006227","name":"Lawrence Livermore National Laboratory","doi-asserted-by":"publisher","award":["ASC"],"award-info":[{"award-number":["ASC"]}],"id":[{"id":"10.13039\/100006227","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of High Performance Computing Applications"],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:p> We improved the quality and reduced the time to produce machine learned models for use in small molecule antiviral design. Our globally asynchronous multi-level parallel training approach strong scales to all of Sierra with up to 97.7% efficiency. We trained a novel, character-based Wasserstein autoencoder that produces a higher quality model trained on 1.613 billion compounds in 23 minutes while the previous state of the art takes a day on 1 million compounds. Reducing training time from a day to minutes shifts the model creation bottleneck from computer job turnaround time to human innovation time. Our implementation achieves 318 PFLOPs for 17.1% of half-precision peak. We will incorporate this model into our molecular design loop enabling the generation of more diverse compounds; searching for novel, candidate antiviral drugs improves and reduces the time to synthesize compounds to be tested in the lab. <\/jats:p>","DOI":"10.1177\/10943420211010930","type":"journal-article","created":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T09:41:27Z","timestamp":1620034887000},"page":"469-482","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":28,"title":["Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models"],"prefix":"10.1177","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3425-5602","authenticated-orcid":false,"given":"Sam Ade","family":"Jacobs","sequence":"first","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Tim","family":"Moon","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Kevin","family":"McLoughlin","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Derek","family":"Jones","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"David","family":"Hysom","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Dong H","family":"Ahn","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"John","family":"Gyllenhaal","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Pythagoras","family":"Watson","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Felice C","family":"Lightstone","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Jonathan E","family":"Allen","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Ian","family":"Karlin","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]},{"given":"Brian","family":"Van Essen","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}]}],"member":"179","published-online":{"date-parts":[[2021,5,3]]},"reference":[{"key":"bibr1-10943420211010930","unstructured":"Akiba T, Suzuki S, Fukuda K (2017) Extremely large minibatch SGD: training ResNet-50 on ImageNet in 15 minutes. arXiv preprint arXiv:1711.04325."},{"key":"bibr2-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201700123"},{"key":"bibr3-10943420211010930","first-page":"773","volume-title":"PMLR","volume":"97","author":"Brookes D","year":"2019"},{"key":"bibr4-10943420211010930","unstructured":"Centers for Disease Control and Prevention (2020) 1918 pandemic (H1N1 virus). Available at: https:\/\/www.cdc.gov\/flu\/pandemic-resources\/1918-pandemic-h1n1.html (accessed 21 April 2021)."},{"key":"bibr5-10943420211010930","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, et al. (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"key":"bibr6-10943420211010930","volume-title":"International conference on machine learning (ICML)","author":"Coates A","year":"2013"},{"key":"bibr7-10943420211010930","volume-title":"Advances in Neural Information Processing Systems","author":"Dean J","year":"2012"},{"key":"bibr8-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2018.8638639"},{"key":"bibr9-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1039\/C9ME00039A"},{"key":"bibr10-10943420211010930","unstructured":"Enamine (2020) Real compounds: new chemical space for discovery. Available at: https:\/\/enamine.net\/library-synthesis\/real-compounds (accessed 21 April 2021)."},{"key":"bibr11-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00572"},{"key":"bibr12-10943420211010930","unstructured":"Goyal P, Doll\u00e1r P, Girshick R, et al. (2017) Accurate, large minibatch SGD: training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677."},{"key":"bibr13-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201700111"},{"key":"bibr14-10943420211010930","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.00770"},{"key":"bibr15-10943420211010930","doi-asserted-by":"crossref","unstructured":"Iandola FN, Ashraf K, Moskewicz MW, et al. (2015) FireCaffe: near-linear acceleration of deep neural network training on compute clusters. arXiv preprint arXiv:1511.00175.","DOI":"10.1109\/CVPR.2016.284"},{"key":"bibr16-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146353"},{"key":"bibr17-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891012"},{"key":"bibr18-10943420211010930","unstructured":"Jaderberg M, Dalibard V, Osindero S, et al. (2017) Population based training of neural networks. arXiv preprint arXiv:1711.09846."},{"key":"bibr19-10943420211010930","first-page":"2323","volume-title":"PMLR","volume":"80","author":"Jin W","year":"2018"},{"key":"bibr20-10943420211010930","volume-title":"Proceedings of the fifth international conference on learning representations","author":"Keskar NS","year":"2017"},{"key":"bibr21-10943420211010930","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114."},{"key":"bibr22-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00054"},{"key":"bibr23-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/3281464.3281468"},{"key":"bibr24-10943420211010930","volume-title":"Dihydrogen","author":"Maruyama N","year":"2020"},{"key":"bibr25-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00068"},{"key":"bibr26-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-019-0404-1"},{"key":"bibr27-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b01053"},{"key":"bibr28-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01264"},{"key":"bibr29-10943420211010930","unstructured":"Peterson JL, Anirudh R, Athey K, et al. (2019) Merlin: enabling machine learning-ready HPC ensembles. arXiv preprint arXiv:1912.02892."},{"key":"bibr30-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050204"},{"key":"bibr31-10943420211010930","unstructured":"Polykovskiy D, Zhebrak A, Sanchez-Lengeling B, et al. (2018) Molecular sets (MOSES): a benchmarking platform for molecular generation models. arXiv preprint arXiv:1811.12823."},{"key":"bibr32-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/2427023.2427030"},{"key":"bibr33-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1042\/EBC20170029"},{"key":"bibr34-10943420211010930","unstructured":"RDKit (2020) RDKit: open-source cheminformatics software. Available at: https:\/\/www.rdkit.org (accessed 21 April 2021)."},{"key":"bibr35-10943420211010930","first-page":"693","volume-title":"Advances in Neural Information Processing Systems","author":"Recht B","year":"2011"},{"key":"bibr36-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1021\/ar500432k"},{"key":"bibr37-10943420211010930","unstructured":"Rezende DJ, Mohamed S, Wierstra D (2014) Stochastic backpropagation and approximate inference in deep generative models. arXiv preprint arXiv:1401.4082."},{"key":"bibr38-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat2663"},{"key":"bibr39-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.8b00706"},{"key":"bibr40-10943420211010930","first-page":"347","volume":"27","author":"Tabe TB","year":"1995","journal-title":"Computing Science and Statistics"},{"key":"bibr41-10943420211010930","unstructured":"Tolstikhin I, Bousquet O, Gelly S, et al. (2017) Wasserstein auto-encoders. arXiv preprint arXiv:1711.01558."},{"key":"bibr42-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/2834892.2834897"},{"key":"bibr43-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00055"},{"key":"bibr44-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC04175J"},{"key":"bibr45-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1039\/C9SC01928F"},{"key":"bibr46-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356137"},{"key":"bibr47-10943420211010930","unstructured":"You Y, Li J, Reddi S, et al. (2020) Large batch optimization for deep learning: training BERT in 76 minutes. In: Proceeding International Conference on Learning Representations, online. Available at: https:\/\/openreview.net\/forum?id=Syx4wnEtvH"},{"key":"bibr48-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"bibr49-10943420211010930","unstructured":"Zeldovich L (2020) How America brought the 1957 influenza pandemic to a halt. JSTOR Available at: https:\/\/daily.jstor.org\/how-america-brought-the-1957-influenza-pandemic-to-a-halt\/ (accessed 22 April 2021)."},{"key":"bibr50-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00026"},{"key":"bibr51-10943420211010930","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356166"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10943420211010930","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/10943420211010930","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10943420211010930","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10943420211010930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T05:35:28Z","timestamp":1740980128000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/10943420211010930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,3]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["10.1177\/10943420211010930"],"URL":"https:\/\/doi.org\/10.1177\/10943420211010930","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"value":"1094-3420","type":"print"},{"value":"1741-2846","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,3]]}}}