{"id":"https://openalex.org/W7202043373","doi":"https://doi.org/10.64898/2026.08.06.743405","title":"Scalable Extraction of Information on Protein-Protein Interactions using Topological Data Analysis","display_name":"Scalable Extraction of Information on Protein-Protein Interactions using Topological Data Analysis","publication_year":2026,"publication_date":"2026-08-09","ids":{"openalex":"https://openalex.org/W7202043373","doi":"https://doi.org/10.64898/2026.08.06.743405"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.06.743405","doi":"https://doi.org/10.64898/2026.08.06.743405","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.06.743405","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.08.06.743405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008105361","display_name":"Angan Mukherjee","orcid":"https://orcid.org/0000-0002-5580-153X","observed_orcids":["https://orcid.org/0000-0002-5580-153X"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angan Mukherjee","raw_affiliation_strings":["Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA"],"raw_orcid":"https://orcid.org/0000-0002-5580-153X","affiliations":[{"raw_affiliation_string":"Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038579702","display_name":"ByungUk Park","orcid":"https://orcid.org/0000-0001-7539-4743","observed_orcids":["https://orcid.org/0000-0001-7539-4743"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ByungUk Park","raw_affiliation_strings":["Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA"],"raw_orcid":"https://orcid.org/0000-0001-7539-4743","affiliations":[{"raw_affiliation_string":"Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146226817","display_name":"Adam Malmstrom","orcid":null,"observed_orcids":[]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Malmstrom","raw_affiliation_strings":["Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053204880","display_name":"Jessi Cisewski-Kehe","orcid":"https://orcid.org/0000-0002-9656-2272","observed_orcids":["https://orcid.org/0000-0002-9656-2272"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessi Cisewski-Kehe","raw_affiliation_strings":["Department of Statistics, University of Wisconsin-Madison, Madison, WI 53706, USA"],"raw_orcid":"https://orcid.org/0000-0002-9656-2272","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Wisconsin-Madison, Madison, WI 53706, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026973748","display_name":"Reid C. Van Lehn","orcid":"https://orcid.org/0000-0003-4885-6599","observed_orcids":["https://orcid.org/0000-0003-4885-6599"]},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reid C. Van Lehn","raw_affiliation_strings":["Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA"],"raw_orcid":"https://orcid.org/0000-0003-4885-6599","affiliations":[{"raw_affiliation_string":"Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083590669","display_name":"V\u00ed\u00adctor M. Zavala","orcid":"https://orcid.org/0000-0002-5744-7378","observed_orcids":["https://orcid.org/0000-0002-5744-7378"]},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Victor M. Zavala","raw_affiliation_strings":["Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA"],"raw_orcid":"https://orcid.org/0000-0002-5744-7378","affiliations":[{"raw_affiliation_string":"Department of Chemical & Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083590669"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.6074000000953674,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.6074000000953674,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.2542000114917755,"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":0.08250000327825546,"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/protein-protein-interaction","display_name":"protein-protein interaction","score":0.9879999756813049},{"id":"https://openalex.org/keywords/topological-data-analysis","display_name":"topological data analysis","score":0.9520000219345093},{"id":"https://openalex.org/keywords/point-cloud-representation","display_name":"point cloud representation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.6320000290870667},{"id":"https://openalex.org/keywords/molecular-surface","display_name":"molecular surface","score":0.32199999690055847},{"id":"https://openalex.org/keywords/geometric-deep-learning","display_name":"geometric deep learning","score":0.5389999747276306}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7713000178337097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6722000241279602},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6438000202178955},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C2776477805","wikidata":"https://www.wikidata.org/wiki/Q4460773","display_name":"Topological data analysis","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.41339999437332153},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38510000705718994},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.37880000472068787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C29123130","wikidata":"https://www.wikidata.org/wiki/Q874709","display_name":"Computational geometry","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C181576044","wikidata":"https://www.wikidata.org/wiki/Q4129926","display_name":"Computational topology","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.06.743405","doi":"https://doi.org/10.64898/2026.08.06.743405","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.06.743405","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.06.743405","doi":"https://doi.org/10.64898/2026.08.06.743405","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.06.743405","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W28435248","https://openalex.org/W124643305","https://openalex.org/W1957046493","https://openalex.org/W2006782375","https://openalex.org/W2114998314","https://openalex.org/W2116159413","https://openalex.org/W2124511088","https://openalex.org/W2128728535","https://openalex.org/W2130479394","https://openalex.org/W2138312771","https://openalex.org/W2418697643","https://openalex.org/W2733638363","https://openalex.org/W2896791121","https://openalex.org/W2992752586","https://openalex.org/W3001282080","https://openalex.org/W3004917954","https://openalex.org/W3033354424","https://openalex.org/W3080498684","https://openalex.org/W3084798277","https://openalex.org/W3134327232","https://openalex.org/W3165474212","https://openalex.org/W3171236517","https://openalex.org/W3185671814","https://openalex.org/W3213364424","https://openalex.org/W4220824576","https://openalex.org/W4223481922","https://openalex.org/W4229031603","https://openalex.org/W4255383393","https://openalex.org/W4293003482","https://openalex.org/W4300926135","https://openalex.org/W4312075150","https://openalex.org/W4316669456","https://openalex.org/W4317802023","https://openalex.org/W4318484896","https://openalex.org/W4321503062","https://openalex.org/W4321851522","https://openalex.org/W4366279959","https://openalex.org/W4383216409","https://openalex.org/W4385373960","https://openalex.org/W4385575189","https://openalex.org/W4396721167","https://openalex.org/W4399893452","https://openalex.org/W4405035146","https://openalex.org/W4406385470","https://openalex.org/W4411463597","https://openalex.org/W4411983851","https://openalex.org/W4412708324","https://openalex.org/W4413117324","https://openalex.org/W4414313157","https://openalex.org/W4416774217","https://openalex.org/W7125900310","https://openalex.org/W7127037633","https://openalex.org/W7127958222"],"related_works":["https://openalex.org/W4412813858","https://openalex.org/W4416251878","https://openalex.org/W7151311814","https://openalex.org/W7214728597","https://openalex.org/W2940821463","https://openalex.org/W7118569412","https://openalex.org/W3182984727","https://openalex.org/W4226343290","https://openalex.org/W4401284289","https://openalex.org/W7130604916"],"abstract_inverted_index":{"Abstract":[0],"Protein-protein":[1],"interactions":[2],"(PPIs)":[3],"govern":[4],"a":[5,70,88,129,219],"wide":[6],"range":[7],"of":[8,115,132,191,198,211,228],"cellular":[9],"functions.":[10],"The":[11],"ability":[12],"to":[13,143,158,169],"predict":[14],"PPI":[15],"interfaces":[16],"from":[17,80,98,110,154,165,230],"protein":[18,25,46,100,116],"molecular":[19],"surfaces":[20,47],"is":[21,176],"important":[22],"for":[23,74,92,125,195,225],"understanding":[24],"function":[26],"and":[27,51,60,161,193,201,221],"enabling":[28],"therapeutic":[29],"discovery.":[30],"While":[31],"recent":[32],"advances":[33],"in":[34],"structure-based":[35],"learning,":[36],"particularly":[37],"molecular-surface":[38],"geometric":[39,50,146],"deep":[40,147],"learning":[41,123,148],"frameworks,":[42],"have":[43],"demonstrated":[44],"that":[45,216],"encode":[48],"rich":[49],"physicochemical":[52],"information,":[53],"such":[54],"approaches":[55],"often":[56],"remain":[57],"computationally":[58,222],"intensive":[59],"data-hungry.":[61],"Alternatively,":[62],"topological":[63,107],"data":[64],"analysis":[65],"(TDA)":[66],"has":[67],"emerged":[68],"as":[69],"mathematically":[71],"rigorous":[72],"framework":[73,91],"extracting":[75,93],"robust,":[76],"multiscale":[77,106],"shape":[78],"information":[79,94,229],"complex":[81,231],"data.":[82],"In":[83],"this":[84,173],"work,":[85],"we":[86],"introduce":[87],"scalable":[89,220],"TDA":[90],"on":[95],"PPIs":[96],"directly":[97],"localized":[99],"surface":[101],"patches.":[102],"Our":[103,213],"approach":[104,137,224],"leverages":[105],"descriptors,":[108],"evaluated":[109],"patch-wise":[111],"point":[112],"cloud":[113],"representations":[114],"mesh":[117],"surfaces,":[118],"combined":[119],"with":[120],"supervised":[121],"machine":[122],"models":[124],"interface":[126],"prediction.":[127],"On":[128],"full":[130],"dataset":[131],"3,362":[133],"proteins,":[134],"the":[135,184,207],"proposed":[136],"substantially":[138],"reduced":[139],"computational":[140,174],"cost":[141],"relative":[142],"an":[144],"established":[145],"method,":[149],"MaSIF-site,":[150],"decreasing":[151],"preprocessing":[152],"time":[153,164],"approximately":[155,166],"27":[156],"s/protein":[157,160],"5-8":[159],"total":[162],"training":[163],"6":[167],"h":[168],"1-1.3":[170],"h.":[171],"Importantly,":[172],"reduction":[175],"achieved":[177],"while":[178],"maintaining":[179],"mean":[180],"test":[181,209],"area":[182],"under":[183],"receiver":[185],"operating":[186],"characteristic":[187],"curve":[188],"(AUC)":[189],"values":[190],"0.76":[192],"0.77":[194],"patch":[196],"radii":[197],"9":[199],"\u00c5":[200],"12":[202],"\u00c5,":[203],"respectively,":[204],"thus":[205],"approaching":[206],"MaSIF-site":[208],"AUC":[210],"0.84.":[212],"results":[214],"suggest":[215],"topology":[217],"offers":[218],"efficient":[223],"high-throughput":[226],"extraction":[227],"biomolecular":[232],"interfaces.":[233]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-10T00:00:00"}