{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T04:08:37Z","timestamp":1772770117673,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3626087","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"95-101","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Protein Generation via Genome-scale Language Models with Bio-physical Scoring"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1472-1947","authenticated-orcid":false,"given":"Gautham","family":"Dharuman","sequence":"first","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1323-5939","authenticated-orcid":false,"given":"Logan","family":"Ward","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7667-922X","authenticated-orcid":false,"given":"Heng","family":"Ma","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3373-5981","authenticated-orcid":false,"given":"Priyanka V.","family":"Setty","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5299-1983","authenticated-orcid":false,"given":"Ozan","family":"Gokdemir","sequence":"additional","affiliation":[{"name":"University of Chicago, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9981-0876","authenticated-orcid":false,"given":"Sam","family":"Foreman","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6279-0007","authenticated-orcid":false,"given":"Murali","family":"Emani","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9470-572X","authenticated-orcid":false,"given":"Kyle","family":"Hippe","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9873-9177","authenticated-orcid":false,"given":"Alexander","family":"Brace","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-8582","authenticated-orcid":false,"given":"Kristopher","family":"Keipert","sequence":"additional","affiliation":[{"name":"Nvidia Inc."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9196-5830","authenticated-orcid":false,"given":"Thomas","family":"Gibbs","sequence":"additional","affiliation":[{"name":"Nvidia Inc."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2129-5269","authenticated-orcid":false,"given":"Ian","family":"Foster","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-6797","authenticated-orcid":false,"given":"Anima","family":"Anandkumar","sequence":"additional","affiliation":[{"name":"California Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7248-6116","authenticated-orcid":false,"given":"Venkatram","family":"Vishwanath","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1622-5488","authenticated-orcid":false,"given":"Arvind","family":"Ramanathan","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2021. ProxyStore. https:\/\/github.com\/proxystore\/proxystore."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3325400"},{"key":"e_1_3_2_2_3_1","volume-title":"Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 6557","author":"Baek Minkyung","year":"2021","unstructured":"Minkyung Baek, Frank DiMaio, Ivan Anishchenko, Justas Dauparas, Sergey Ovchinnikov, Gyu\u00a0Rie Lee, Jue Wang, Qian Cong, Lisa\u00a0N Kinch, R\u00a0Dustin Schaeffer, 2021. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 6557 (2021), 871\u2013876."},{"key":"e_1_3_2_2_4_1","volume-title":"An exciting but challenging road ahead for computational enzyme design. Protein science: a publication of the Protein Society 19, 10","author":"Baker David","year":"2010","unstructured":"David Baker. 2010. An exciting but challenging road ahead for computational enzyme design. Protein science: a publication of the Protein Society 19, 10 (2010), 1817."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/hipc.2018.00014"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2017.12.001"},{"key":"e_1_3_2_2_7_1","unstructured":"D.A. Case H.M. Aktulga K. Belfon I.Y. Ben-Shalom J.T. Berryman S.R. Brozell D.S. Cerutti T.E. Cheatham III G.A. Cisneros V.W.D. Cruzeiro T.A. Darden R.E. Duke G. Giambasu M.K. Gilson H. Gohlke A.W. Goetz R. Harris S. Izadi S.A. Izmailov K. Kasavajhala M.C. Kaymak E. King A. Kovalenko T. Kurtzman T.S. Lee S. LeGrand P. Li C. Lin J. Liu T. Luchko R. Luo M. Machado V. Man M. Manathunga K.M. Merz Y. Miao O. Mikhailovskii G. Monard H. Nguyen K.A. O\u2019Hearn A. Onufriev F. Pan S. Pantano R. Qi A. Rahnamoun D.R. Roe A. Roitberg C. Sagui S. Schott-Verdugo A. Shajan J. Shen C.L. Simmerling N.R. Skrynnikov J. Smith J. Swails R.C. Walker J. Wang J. Wang H. Wei R.M. Wolf X. Wu Y. Xiong Y. Xue D.M. York S. Zhao and P.A. Kollman. 2022. Amber 2022. University of California San Francisco."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392683"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1021\/bi962734n"},{"key":"e_1_3_2_2_10_1","volume-title":"De novo protein design: fully automated sequence selection. Science 278, 5335","author":"Dahiyat I","year":"1997","unstructured":"Bassil\u00a0I Dahiyat and Stephen\u00a0L Mayo. 1997. De novo protein design: fully automated sequence selection. Science 278, 5335 (1997), 82\u201387."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005659"},{"key":"e_1_3_2_2_12_1","volume-title":"Experimental design and analysis of antibody microarrays: applying methods from cDNA arrays. Cancer research 65, 8","author":"Eckel-Passow E","year":"2005","unstructured":"Jeanette\u00a0E Eckel-Passow, Antje Hoering, Terry\u00a0M Therneau, and Irene Ghobrial. 2005. Experimental design and analysis of antibody microarrays: applying methods from cDNA arrays. Cancer research 65, 8 (2005), 2985\u20132989."},{"key":"e_1_3_2_2_13_1","volume-title":"Prottrans: Toward understanding the language of life through self-supervised learning","author":"Elnaggar Ahmed","year":"2021","unstructured":"Ahmed Elnaggar, Michael Heinzinger, Christian Dallago, Ghalia Rehawi, Yu Wang, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Martin Steinegger, 2021. Prottrans: Toward understanding the language of life through self-supervised learning. IEEE transactions on pattern analysis and machine intelligence 44, 10 (2021), 7112\u20137127."},{"key":"e_1_3_2_2_14_1","volume-title":"ProtGPT2 is a deep unsupervised language model for protein design. Nature communications 13, 1","author":"Ferruz Noelia","year":"2022","unstructured":"Noelia Ferruz, Steffen Schmidt, and Birte H\u00f6cker. 2022. ProtGPT2 is a deep unsupervised language model for protein design. Nature communications 13, 1 (2022), 1\u201310."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_2_16_1","unstructured":"Alan Grossfield. [n. d.]. WHAM: The weighted histogram analysis method version 2.0.11. http:\/\/membrane.urmc.rochester.edu\/wordpress\/?page_id=126"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2021.3082815"},{"key":"e_1_3_2_2_18_1","volume-title":"Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. https:\/\/github.com\/huggingface\/transformers","year":"2022","unstructured":"huggingface. 2022. Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. https:\/\/github.com\/huggingface\/transformers"},{"key":"e_1_3_2_2_19_1","unstructured":"Shantenu Jha Vincent\u00a0R. Pascuzzi and Matteo Turilli. 2022. AI-coupled HPC Workflows. https:\/\/arxiv.org\/abs\/2208.11745"},{"key":"e_1_3_2_2_20_1","volume-title":"Highly accurate protein structure prediction with AlphaFold. Nature 596, 7873","author":"Jumper John","year":"2021","unstructured":"John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin \u017d\u00eddek, Anna Potapenko, 2021. Highly accurate protein structure prediction with AlphaFold. Nature 596, 7873 (2021), 583\u2013589."},{"key":"e_1_3_2_2_21_1","volume-title":"Principles for designing ideal protein structures. Nature 491, 7423","author":"Koga Nobuyasu","year":"2012","unstructured":"Nobuyasu Koga, Rie Tatsumi-Koga, Gaohua Liu, Rong Xiao, Thomas\u00a0B Acton, Gaetano\u00a0T Montelione, and David Baker. 2012. Principles for designing ideal protein structures. Nature 491, 7423 (2012), 222\u2013227."},{"key":"e_1_3_2_2_22_1","volume-title":"Design of a novel globular protein fold with atomic-level accuracy. science 302, 5649","author":"Kuhlman Brian","year":"2003","unstructured":"Brian Kuhlman, Gautam Dantas, Gregory\u00a0C Ireton, Gabriele Varani, Barry\u00a0L Stoddard, and David Baker. 2003. Design of a novel globular protein fold with atomic-level accuracy. science 302, 5649 (2003), 1364\u20131368."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.540130812"},{"key":"e_1_3_2_2_24_1","volume-title":"Maryam Fazel-Zarandi, Tom Sercu, Salvatore Candido, and Alexander Rives.","author":"Lin Zeming","year":"2023","unstructured":"Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, Robert Verkuil, Ori Kabeli, Yaniv Shmueli, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Salvatore Candido, and Alexander Rives. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 6637 (2023), 1123\u20131130."},{"key":"e_1_3_2_2_25_1","volume-title":"Deep neural language modeling enables functional protein generation across families. bioRxiv","author":"Madani Ali","year":"2021","unstructured":"Ali Madani, Ben Krause, Eric\u00a0R Greene, Subu Subramanian, Benjamin\u00a0P Mohr, James\u00a0M Holton, Jose\u00a0Luis Olmos\u00a0Jr, Caiming Xiong, Zachary\u00a0Z Sun, Richard Socher, 2021. Deep neural language modeling enables functional protein generation across families. bioRxiv (2021), 2021\u201307."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.5b00255"},{"key":"e_1_3_2_2_27_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730\u201327744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_28_1","unstructured":"Rafael Rafailov Archit Sharma Eric Mitchell Stefano Ermon Christopher\u00a0D. Manning and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. arxiv:2305.18290\u00a0[cs.LG]"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_2_31_1","volume-title":"The calculation of the potential of mean force using computer simulations. Computer physics communications 91, 1-3","author":"Roux Beno\u00eet","year":"1995","unstructured":"Beno\u00eet Roux. 1995. The calculation of the potential of mean force using computer simulations. Computer physics communications 91, 1-3 (1995), 275\u2013282."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(77)90121-8"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW59300.2023.00018"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC54614.2021.00007"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1021\/ja00540a008"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2508-4"},{"key":"e_1_3_2_2_37_1","volume-title":"Rational design of envelope identifies broadly neutralizing human monoclonal antibodies to HIV-1. Science 329, 5993","author":"Wu Xueling","year":"2010","unstructured":"Xueling Wu, Zhi-Yong Yang, Yuxing Li, Carl-Magnus Hogerkorp, William\u00a0R Schief, Michael\u00a0S Seaman, Tongqing Zhou, Stephen\u00a0D Schmidt, Lan Wu, Ling Xu, 2010. Rational design of envelope identifies broadly neutralizing human monoclonal antibodies to HIV-1. Science 329, 5993 (2010), 856\u2013861."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1908723117"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.10.10.511571"},{"key":"e_1_3_2_2_40_1","volume-title":"Bharat Kale","author":"Zvyagin T","year":"2022","unstructured":"Max\u00a0T Zvyagin, Alexander Brace, Kyle Hippe, Yuntian Deng, Bin Zhang, Cindy\u00a0Orozco Bohorquez, Austin Clyde, Bharat Kale, Danilo Perez-Rivera, Heng Ma, 2022. GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics.bioRxiv (2022)."}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","location":"Denver CO USA","acronym":"SC-W 2023"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3626087","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3626087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:02:16Z","timestamp":1755745336000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3626087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":40,"alternative-id":["10.1145\/3624062.3626087","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3626087","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}