{"id":"https://openalex.org/W4388581010","doi":"https://doi.org/10.1145/3624062.3626087","title":"Protein Generation via Genome-scale Language Models with Bio-physical Scoring","display_name":"Protein Generation via Genome-scale Language Models with Bio-physical Scoring","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581010","doi":"https://doi.org/10.1145/3624062.3626087"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3626087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3626087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033128850","display_name":"Gautham Dharuman","orcid":"https://orcid.org/0000-0002-1472-1947"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gautham Dharuman","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-1472-1947","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021403239","display_name":"Logan Ward","orcid":"https://orcid.org/0000-0002-1323-5939"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Logan Ward","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-1323-5939","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710715","display_name":"Heng Ma","orcid":"https://orcid.org/0000-0002-7667-922X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ma","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-7667-922X","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097055016","display_name":"Priyanka V. Setty","orcid":"https://orcid.org/0000-0002-3373-5981"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priyanka V. Setty","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-3373-5981","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015717928","display_name":"Ozan G\u00f6kdemir","orcid":"https://orcid.org/0000-0001-5299-1983"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ozan Gokdemir","raw_affiliation_strings":["University of Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0001-5299-1983","affiliations":[{"raw_affiliation_string":"University of Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028293798","display_name":"Sam Foreman","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Foreman","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-9981-0876","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014448094","display_name":"Murali Emani","orcid":"https://orcid.org/0000-0002-6279-0007"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Emani","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-6279-0007","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077184414","display_name":"Kyle Hippe","orcid":"https://orcid.org/0000-0001-9470-572X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Hippe","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-9470-572X","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059741659","display_name":"Alexander Brace","orcid":"https://orcid.org/0000-0001-9873-9177"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Brace","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-9873-9177","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083201191","display_name":"Kristopher Keipert","orcid":"https://orcid.org/0000-0003-1476-8582"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Kristopher Keipert","raw_affiliation_strings":["Nvidia Inc"],"raw_orcid":"https://orcid.org/0000-0003-1476-8582","affiliations":[{"raw_affiliation_string":"Nvidia Inc","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111407029","display_name":"Thomas Gibbs","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Thomas Gibbs","raw_affiliation_strings":["Nvidia Inc"],"raw_orcid":"https://orcid.org/0000-0002-9196-5830","affiliations":[{"raw_affiliation_string":"Nvidia Inc","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0003-2129-5269","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014498545","display_name":"Anima Anandkumar","orcid":"https://orcid.org/0000-0002-6974-6797"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anima Anandkumar","raw_affiliation_strings":["California Institute of Technology, USA"],"raw_orcid":"https://orcid.org/0000-0002-6974-6797","affiliations":[{"raw_affiliation_string":"California Institute of Technology, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075500139","display_name":"Venkatram Vishwanath","orcid":"https://orcid.org/0000-0001-7248-6116"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatram Vishwanath","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-7248-6116","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028188095","display_name":"Arvind Ramanathan","orcid":"https://orcid.org/0000-0002-1622-5488"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Ramanathan","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-1622-5488","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5033128850"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":0.4498,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67800848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8030762672424316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5698234438896179},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.556671679019928},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5134993195533752},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4940083622932434},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46289199590682983},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4423770010471344},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4373752176761627},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.29733705520629883},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.25120094418525696},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.19685199856758118},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11018401384353638}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8030762672424316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5698234438896179},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.556671679019928},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5134993195533752},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4940083622932434},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46289199590682983},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4423770010471344},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4373752176761627},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29733705520629883},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.25120094418525696},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.19685199856758118},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11018401384353638},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3626087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3626087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1985914867","https://openalex.org/W1993177346","https://openalex.org/W2086786922","https://openalex.org/W2112154906","https://openalex.org/W2135151522","https://openalex.org/W2404280981","https://openalex.org/W2749873612","https://openalex.org/W2906137127","https://openalex.org/W2913525628","https://openalex.org/W2943761765","https://openalex.org/W2949223833","https://openalex.org/W2997244915","https://openalex.org/W3021718926","https://openalex.org/W3081168214","https://openalex.org/W3096831136","https://openalex.org/W3103996135","https://openalex.org/W3104388511","https://openalex.org/W3129831491","https://openalex.org/W3154968648","https://openalex.org/W3164974885","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3203718464","https://openalex.org/W4226278401","https://openalex.org/W4304607335","https://openalex.org/W4385585393"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W4255934811","https://openalex.org/W2465382974","https://openalex.org/W2010229520","https://openalex.org/W2095784700"],"abstract_inverted_index":{"Large":[0],"language":[1,46],"models":[2],"(LLMs)":[3],"trained":[4],"on":[5,130],"vast":[6],"biological":[7,11],"datasets":[8],"can":[9,23],"learn":[10],"motifs":[12],"and":[13,38,53,84,124],"correlations":[14],"across":[15],"the":[16,97,141],"evolutionary":[17],"landscape":[18],"of":[19,31,62,96,113,121,127,133],"natural":[20,110],"proteins.":[21],"LLMs":[22],"then":[24],"be":[25],"used":[26],"for":[27,59,73],"de":[28],"novo":[29],"design":[30,93],"novel":[32,94],"proteins":[33],"with":[34,116,135],"specific":[35],"structures,":[36],"functions,":[37],"physicochemical":[39],"properties.":[40,86],"We":[41,87],"employ":[42],"a":[43,57],"pre-trained":[44],"genome-scale":[45],"model":[47],"that":[48,70,78,102],"uses":[49],"codons":[50],"as":[51],"tokens":[52],"integrate":[54],"it":[55],"into":[56],"workflow":[58,91],"targeted":[60],"generation":[61,119],"sequences.":[63],"Our":[64],"framework":[65],"suggests":[66],"new":[67],"gene":[68],"sequences":[69],"are":[71],"ranked":[72],"downstream":[74],"evaluation":[75],"by":[76],"metrics":[77],"collectively":[79],"capture":[80],"extensive":[81],"sequence-specific,":[82],"biophysical,":[83],"biochemical":[85],"demonstrate":[88],"our":[89],"integrated":[90],"to":[92],"variants":[95],"enzyme,":[98],"malate":[99],"dehydrogenase":[100],"(MDH),":[101],"exhibit":[103],"more":[104],"favorable":[105],"activation":[106],"energies":[107],"than":[108],"their":[109],"counterparts":[111],"(reduction":[112],"4.01":[114],"kJ/mol)":[115],"sustained":[117],"sequence":[118],"rates":[120,126],"\u223c":[122,128],"104/hr":[123],"simulation":[125],"102/hr":[129],"64":[131],"nodes":[132],"Polaris":[134],"about":[136],"99.7":[137],"system":[138],"utilization":[139],"during":[140],"run.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
