{"id":"https://openalex.org/W7170037989","doi":"https://doi.org/10.1145/3785462.3815874","title":"Running AlphaFold3 on Distributed High-Throughput Computing Infrastructure: Scaling Workloads and Enabling Ultra-Large Predictions","display_name":"Running AlphaFold3 on Distributed High-Throughput Computing Infrastructure: Scaling Workloads and Enabling Ultra-Large Predictions","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170037989","doi":"https://doi.org/10.1145/3785462.3815874"},"language":null,"primary_location":{"id":"doi:10.1145/3785462.3815874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815874","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3785462.3815874","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102843009","display_name":"Daniel A. Morales","orcid":"https://orcid.org/0000-0001-7113-3685"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]},{"id":"https://openalex.org/I4210151837","display_name":"High Throughput Biology (United States)","ror":"https://ror.org/05h1bjp83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel A Morales","raw_affiliation_strings":["Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0001-7113-3685","affiliations":[{"raw_affiliation_string":"Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074","https://openalex.org/I4210151837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084719433","display_name":"Brian Lin","orcid":"https://orcid.org/0000-0001-8998-5173"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]},{"id":"https://openalex.org/I4210151837","display_name":"High Throughput Biology (United States)","ror":"https://ror.org/05h1bjp83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Lin","raw_affiliation_strings":["Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0001-8998-5173","affiliations":[{"raw_affiliation_string":"Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074","https://openalex.org/I4210151837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079942660","display_name":"Mats Rynge","orcid":"https://orcid.org/0000-0002-1779-7189"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mats Rynge","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1779-7189","affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024443210","display_name":"Christina Koch","orcid":"https://orcid.org/0000-0001-8600-8158"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]},{"id":"https://openalex.org/I4210151837","display_name":"High Throughput Biology (United States)","ror":"https://ror.org/05h1bjp83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christina L Koch","raw_affiliation_strings":["Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0001-8600-8158","affiliations":[{"raw_affiliation_string":"Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074","https://openalex.org/I4210151837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101621571","display_name":"Brian Bockelman","orcid":"https://orcid.org/0000-0003-2981-3809"},"institutions":[{"id":"https://openalex.org/I29680605","display_name":"Morgridge Institute for Research","ror":"https://ror.org/05cb4rb43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I135310074","https://openalex.org/I29680605"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Bockelman","raw_affiliation_strings":["Morgridge Institute for Research, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0003-2981-3809","affiliations":[{"raw_affiliation_string":"Morgridge Institute for Research, Madison, WI, USA","institution_ids":["https://openalex.org/I29680605"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042010270","display_name":"Miron Livny","orcid":"https://orcid.org/0000-0001-5444-7439"},"institutions":[{"id":"https://openalex.org/I29680605","display_name":"Morgridge Institute for Research","ror":"https://ror.org/05cb4rb43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I135310074","https://openalex.org/I29680605"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miron Livny","raw_affiliation_strings":["Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA and Morgridge Institute for Research, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0000-0001-5444-7439","affiliations":[{"raw_affiliation_string":"Center for High-Throughput Computing, University of Wisconsin-Madison, Madison, WI, USA and Morgridge Institute for Research, Madison, WI, USA","institution_ids":["https://openalex.org/I29680605"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7134000062942505},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5879999995231628},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5152999758720398},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5015000104904175},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4596000015735626},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.43479999899864197},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4277999997138977},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4268999993801117},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4244000017642975},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.413100004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8460999727249146},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7491000294685364},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7134000062942505},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5879999995231628},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4277999997138977},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.25450000166893005},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3785462.3815874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815874","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3785462.3815874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815874","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2124088880","https://openalex.org/W2148317584","https://openalex.org/W2166459269","https://openalex.org/W4281790889","https://openalex.org/W4396721167","https://openalex.org/W4414918113","https://openalex.org/W6907225408","https://openalex.org/W6925878891","https://openalex.org/W6926398869","https://openalex.org/W7140507893"],"related_works":[],"abstract_inverted_index":{"AlphaFold":[0],"3":[1],"(AF3)":[2],"enables":[3],"atomic-resolution":[4],"prediction":[5],"of":[6,65,128],"biomolecular":[7],"complexes,":[8],"driving":[9],"rapidly":[10],"growing":[11],"demand":[12],"across":[13,110],"the":[14,53,71,79],"life":[15],"sciences.":[16],"However,":[17],"its":[18],"\u223c":[19],"750,GB":[20],"reference":[21],"database":[22],"has":[23],"effectively":[24],"confined":[25],"production":[26],"deployments":[27],"to":[28,139],"systems":[29],"with":[30,97],"shared":[31,54],"parallel":[32],"filesystems,":[33],"creating":[34],"a":[35,62,89,103,140,175,190],"major":[36],"barrier":[37],"for":[38,67,73,183,193],"scalability.":[39],"Distributed":[40],"high-throughput":[41],"computing":[42],"(dHTC)":[43],"platforms":[44],"offer":[45],"vast,":[46],"heterogeneous":[47],"compute":[48],"capacity,":[49],"but":[50],"fundamentally":[51],"lack":[52],"data":[55,91,150],"infrastructure":[56],"assumed":[57],"by":[58],"AF3.":[59],"We":[60],"present":[61],"data-aware":[63],"deployment":[64],"AF3":[66],"dHTC,":[68],"implemented":[69],"on":[70,95,198],"Center":[72],"High":[74],"Throughput":[75],"Computing":[76],"(CHTC)":[77],"and":[78,102,152,188],"Open":[80],"Science":[81],"Pool":[82],"(OSPool).":[83],"The":[84],"workflow":[85],"is":[86],"decomposed":[87],"into":[88],"CPU-bound":[90],"pipeline":[92,106],"that":[93,107,131,162],"executes":[94],"nodes":[96],"locally":[98],"staged,":[99],"scheduler-advertised":[100],"databases,":[101],"GPU-bound":[104],"inference":[105,121],"opportunistically":[108],"scales":[109],"distributed":[111,199],"resources.":[112],"Using":[113],"CUDA":[114],"Unified":[115],"Virtual":[116],"Memory":[117],"(UVM),":[118],"we":[119,146,160],"extend":[120],"beyond":[122],"physical":[123],"GPU":[124],"limits,":[125],"enabling":[126],"predictions":[127],"ultra-large":[129],"complexes":[130],"exceed":[132],"device":[133],"vRAM.":[134],"By":[135],"elevating":[136],"dataset":[137],"locality":[138],"schedulable":[141],"resource":[142],"via":[143],"HTCondor":[144],"ClassAds,":[145],"eliminate":[147],"prohibitive":[148],"per-job":[149],"transfers":[151],"enable":[153],"efficient,":[154],"federated":[155],"execution.":[156],"Beyond":[157],"scaling":[158],"throughput,":[159],"demonstrate":[161],"dHTC":[163,173],"can":[164],"support":[165],"previously":[166],"infeasible":[167],"workloads.":[168],"Together,":[169],"these":[170],"results":[171],"establish":[172],"as":[174],"viable\u2014and":[176],"in":[177],"some":[178],"regimes":[179],"superior\u2014":[180],"execution":[181],"model":[182],"data-intensive":[184,196],"structural":[185],"biology":[186],"workflows":[187],"provide":[189],"general":[191],"blueprint":[192],"deploying":[194],"large,":[195],"applications":[197],"cyberinfrastructure.":[200]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-07-23T00:00:00"}