{"id":"https://openalex.org/W4416004470","doi":"https://doi.org/10.1145/3731599.3767345","title":"Compute4Biology: Taking Stock of High Performance Computing Needs for Foundation Models in Biological Sciences","display_name":"Compute4Biology: Taking Stock of High Performance Computing Needs for Foundation Models in Biological Sciences","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004470","doi":"https://doi.org/10.1145/3731599.3767345"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767345","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767345","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 '25 Workshops of the International Conference for High Performance Computing, Networking, 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/A5007048284","display_name":"Pratik Dutta","orcid":"https://orcid.org/0000-0002-1579-8946"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pratik Dutta","raw_affiliation_strings":["Stony Brook University, Stony Brook, USA"],"raw_orcid":"https://orcid.org/0000-0002-1579-8946","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081072666","display_name":"Tirthankar Ghosal","orcid":"https://orcid.org/0000-0002-2358-522X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tirthankar Ghosal","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-2358-522X","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007048284"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.31347176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.31949999928474426,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.31949999928474426,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.27090001106262207,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.07270000129938126,"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":0.6439999938011169},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46389999985694885},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.42289999127388},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.42250001430511475},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.40630000829696655},{"id":"https://openalex.org/keywords/computational-genomics","display_name":"Computational genomics","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467000246047974},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5827999711036682},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C39238701","wikidata":"https://www.wikidata.org/wiki/Q2091816","display_name":"Computational genomics","level":5,"score":0.38670000433921814},{"id":"https://openalex.org/C2992077199","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biological sciences","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3492000102996826},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C28225019","wikidata":"https://www.wikidata.org/wiki/Q4915005","display_name":"Biological network","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C137866125","wikidata":"https://www.wikidata.org/wiki/Q4299308","display_name":"Modelling biological systems","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767345","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767345","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 '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2911489562","https://openalex.org/W3127238141","https://openalex.org/W3146944767","https://openalex.org/W3177500196","https://openalex.org/W3179485843","https://openalex.org/W4205773061","https://openalex.org/W4214868967","https://openalex.org/W4290546063","https://openalex.org/W4291302261","https://openalex.org/W4297243391","https://openalex.org/W4297253404","https://openalex.org/W4319065545","https://openalex.org/W4327550249","https://openalex.org/W4382239609","https://openalex.org/W4384133826","https://openalex.org/W4392168151","https://openalex.org/W4404349982","https://openalex.org/W4404821554","https://openalex.org/W4406817136"],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1,69],"are":[2,45],"driving":[3],"a":[4,76,141,171,184],"paradigm":[5],"shift":[6],"across":[7,162],"the":[8,19,58,84,92,100,109,152,163,178],"life":[9],"sciences,":[10],"yet":[11],"their":[12],"transformative":[13],"potential":[14],"is":[15,170],"fundamentally":[16],"coupled":[17],"to":[18,39,80,89],"capabilities":[20],"of":[21,63,96,144,155,159,166,174],"high-performance":[22],"computing":[23],"(HPC).":[24],"The":[25],"computational":[26,86],"workloads":[27],"presented":[28],"by":[29,139],"different":[30],"biology":[31],"and":[32,37,42,48,82,108,126,133,147],"allied":[33],"domains,":[34],"from":[35,104],"genomics":[36],"transcriptomics":[38],"proteomics,":[40],"chemistry,":[41],"biomedical":[43],"literature,":[44],"remarkably":[46],"diverse":[47,120],"create":[49],"distinct":[50],"challenges":[51],"for":[52,66,114,150],"HPC":[53,64,156,175],"infrastructure.":[54],"This":[55,169],"paper":[56],"presents":[57],"first":[59],"systematic,":[60],"cross-domain":[61],"analysis":[62],"needs":[65,176],"state-of-the-art":[67],"foundation":[68],"in":[70,128,177],"biological":[71,179],"sciences.":[72],"We":[73,137],"move":[74],"beyond":[75],"simple":[77],"cost":[78],"summary":[79],"characterize":[81],"compare":[83],"specific":[85],"bottlenecks":[87],"inherent":[88],"each":[90],"domain:":[91],"massive":[93],"I/O":[94],"demands":[95],"genomic":[97],"sequence":[98],"data,":[99],"intense":[101],"memory":[102],"pressure":[103],"protein":[105],"structure":[106],"prediction,":[107],"unique":[110],"compute":[111],"kernels":[112],"required":[113],"molecular":[115],"modeling.":[116],"By":[117],"analyzing":[118],"these":[119],"workloads,":[121],"we":[122,181],"identify":[123],"common":[124],"patterns":[125],"trade-offs":[127],"hardware":[129],"utilization,":[130],"data":[131],"management,":[132],"software":[134],"stack":[135],"design.":[136],"conclude":[138],"outlining":[140],"unified":[142],"set":[143],"best":[145],"practices":[146],"co-design":[148],"principles":[149],"building":[151],"next":[153],"generation":[154],"systems":[157],"capable":[158],"accelerating":[160],"discovery":[161],"full":[164],"spectrum":[165],"AI-driven":[167],"science.":[168],"running":[172],"survey":[173],"domain;":[180],"would":[182],"maintain":[183],"project":[185],"page":[186],"at":[187],"www.abc.xxx":[188]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-07T00:00:00"}
