{"id":"https://openalex.org/W4388581069","doi":"https://doi.org/10.1145/3624062.3624081","title":"Scalable Lead Prediction with Transformers using HPC resources","display_name":"Scalable Lead Prediction with Transformers using HPC resources","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581069","doi":"https://doi.org/10.1145/3624062.3624081"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624081","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624081","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":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624081","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036460202","display_name":"Archit Vasan","orcid":"https://orcid.org/0000-0002-8299-1033"},"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":"Archit Vasan","raw_affiliation_strings":["Argonne National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8299-1033","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States of America","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046675967","display_name":"Thomas Brettin","orcid":"https://orcid.org/0000-0001-9301-9760"},"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":"Thomas Brettin","raw_affiliation_strings":["Argonne National Lab, USA"],"raw_orcid":"https://orcid.org/0000-0001-9301-9760","affiliations":[{"raw_affiliation_string":"Argonne National Lab, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053682943","display_name":"Rick Stevens","orcid":"https://orcid.org/0000-0002-4268-4020"},"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":"Rick Stevens","raw_affiliation_strings":["Argonne National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4268-4020","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States of America","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","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, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-1622-5488","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States of America","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","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, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7248-6116","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States of America","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9815000295639038,"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/supercomputer","display_name":"Supercomputer","score":0.7853459119796753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7372788190841675},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6517826318740845},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.5873702168464661},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5105801224708557},{"id":"https://openalex.org/keywords/docking","display_name":"Docking (animal)","score":0.4538291096687317},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.4243048429489136},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4209517240524292},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4046177268028259},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3942973017692566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34985828399658203},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3211817741394043},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.25713083148002625},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2164289951324463},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1544114649295807},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11314144730567932}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7853459119796753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372788190841675},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6517826318740845},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.5873702168464661},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5105801224708557},{"id":"https://openalex.org/C41685203","wikidata":"https://www.wikidata.org/wiki/Q1974042","display_name":"Docking (animal)","level":2,"score":0.4538291096687317},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.4243048429489136},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4209517240524292},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4046177268028259},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3942973017692566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34985828399658203},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3211817741394043},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.25713083148002625},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2164289951324463},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1544114649295807},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11314144730567932},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C159110408","wikidata":"https://www.wikidata.org/wiki/Q121176","display_name":"Nursing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624081","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624081","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":{"id":"doi:10.1145/3624062.3624081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624081","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624081","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581069.pdf","grobid_xml":"https://content.openalex.org/works/W4388581069.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2059230675","https://openalex.org/W2376003823","https://openalex.org/W2773493604","https://openalex.org/W2269591907","https://openalex.org/W2027065525","https://openalex.org/W2057846043","https://openalex.org/W2093426296","https://openalex.org/W2336040088","https://openalex.org/W4402273478","https://openalex.org/W2594726310"],"abstract_inverted_index":{"A":[0],"promising":[1],"direction":[2,279],"in":[3,245],"cancer":[4],"drug":[5,286],"discovery":[6],"is":[7,86,212],"high-throughput":[8],"screening":[9,233],"of":[10,77,157,186,194,208,234,241,298],"extensive":[11,259],"compound":[12,260],"datasets":[13],"to":[14,21,101,123,141,196,219,257,290,294],"identify":[15],"advantageous":[16],"properties,":[17],"including":[18],"their":[19,81],"ability":[20],"interact":[22],"with":[23,51,174],"relevant":[24],"biomolecules":[25],"such":[26,37,52],"as":[27,38,269],"proteins.":[28],"However,":[29],"traditional":[30],"structural":[31],"approaches":[32],"for":[33,105,262,280],"assessing":[34],"binding":[35,82,126,166],"affinity,":[36],"free":[39],"energy":[40],"methods":[41],"or":[42],"molecular":[43,71,164,198,226,264],"docking,":[44],"pose":[45],"significant":[46,206],"computational":[47],"bottlenecks":[48],"when":[49],"dealing":[50],"vast":[53],"datasets.":[54],"To":[55,151],"address":[56],"this,":[57],"we":[58,137,160],"have":[59],"developed":[60],"a":[61,90,97,120,139],"docking":[62,165,177],"surrogate":[63],"called":[64],"the":[65,74,110,125,129,153,192,209,220,242,296],"SMILES":[66,75,84],"transformer":[67],"(ST),":[68],"which":[69,223],"learns":[70],"features":[72,199],"from":[73,201],"representation":[76],"compounds":[78,237,271,300],"and":[79,94,145,155,189],"approximates":[80],"affinity.":[83,127],"data":[85,168],"first":[87],"tokenized":[88],"using":[89,163,228],"well-established":[91],"SMILES-pair":[92],"tokenizer":[93],"fed":[95,118],"into":[96,119],"BERT-like":[98],"Transformer":[99],"model":[100,122,143],"generate":[102],"vector":[103],"embeddings":[104,115],"each":[106],"molecule,":[107],"effectively":[108],"capturing":[109],"essential":[111],"information.":[112],"These":[113],"extracted":[114],"are":[116],"then":[117],"regression":[121],"predict":[124],"Leveraging":[128],"high-performance":[130],"computing":[131],"resources":[132],"at":[133],"Argonne":[134],"National":[135],"Lab,":[136],"devised":[138],"workflow":[140,231,282],"scale":[142,291],"training":[144],"inference":[146],"across":[147],"multiple":[148,170],"supercomputing":[149],"nodes.":[150],"evaluate":[152],"performance":[154],"accuracy":[156],"our":[158,251,281,292],"workflow,":[159],"conducted":[161],"experiments":[162],"affinity":[167],"on":[169,238],"receptors,":[171],"comparing":[172],"ST":[173,195,210],"another":[175],"state-of-the-art":[176],"surrogate.":[178],"Impressively,":[179],"both":[180],"surrogates":[181],"yielded":[182],"comparable":[183],"val-r2":[184],"measurements":[185],"between":[187],"70":[188],"90%,":[190],"affirming":[191],"capability":[193],"learn":[197],"directly":[200],"language-based":[202],"data.":[203],"Furthermore,":[204],"one":[205],"advantage":[207],"approach":[211,252],"its":[213],"notably":[214],"faster":[215],"tokenization":[216],"preprocessing":[217],"compared":[218],"alternative":[221],"method,":[222],"requires":[224],"generating":[225],"descriptors":[227],"Mordred.":[229],"Our":[230],"facilitated":[232],"\u223c3":[235],"billion":[236],"48":[239],"nodes":[240],"Polaris":[243],"supercomputer":[244],"approximately":[246],"an":[247,254,276],"hour.":[248],"In":[249],"summary,":[250],"presents":[253],"efficient":[255],"means":[256],"screen":[258],"databases":[261],"potential":[263],"properties":[265],"that":[266],"could":[267],"serve":[268],"lead":[270],"targeting":[272],"cancer.":[273],"Looking":[274],"ahead,":[275],"important":[277],"future":[278],"involves":[283],"integrating":[284],"de-novo":[285],"design,":[287],"enabling":[288],"us":[289],"efforts":[293],"explore":[295],"limits":[297],"synthesizable":[299],"within":[301],"chemical":[302],"space.":[303]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}