{"id":"https://openalex.org/W4415418922","doi":"https://doi.org/10.3389/fbinf.2025.1651623","title":"Inferred global dense residue transition graphs from primary structure sequences enable protein interaction prediction via directed graph convolutional neural networks","display_name":"Inferred global dense residue transition graphs from primary structure sequences enable protein interaction prediction via directed graph convolutional neural networks","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4415418922","doi":"https://doi.org/10.3389/fbinf.2025.1651623","pmid":"https://pubmed.ncbi.nlm.nih.gov/41199760"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1651623","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1651623","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1651623/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1651623/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002401618","display_name":"Islam Akef Ebeid","orcid":"https://orcid.org/0000-0001-5345-0775"},"institutions":[{"id":"https://openalex.org/I150913223","display_name":"Texas Woman's University","ror":"https://ror.org/04dyzkj40","country_code":"US","type":"education","lineage":["https://openalex.org/I150913223"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Islam Akef Ebeid","raw_affiliation_strings":["The Division of Computer Science, Texas Woman's University, Denton, TX, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Division of Computer Science, Texas Woman's University, Denton, TX, United States","institution_ids":["https://openalex.org/I150913223"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079922796","display_name":"Haoteng Tang","orcid":"https://orcid.org/0000-0003-0323-1755"},"institutions":[{"id":"https://openalex.org/I2802326326","display_name":"The University of Texas Rio Grande Valley","ror":"https://ror.org/02p5xjf12","country_code":"US","type":"education","lineage":["https://openalex.org/I2802326326"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoteng Tang","raw_affiliation_strings":["The Department of Computer Science, The University of Texas Rio Grande Valley, Edinburg, TX, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Computer Science, The University of Texas Rio Grande Valley, Edinburg, TX, United States","institution_ids":["https://openalex.org/I2802326326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102865632","display_name":"Pengfei Gu","orcid":"https://orcid.org/0000-0003-1160-9623"},"institutions":[{"id":"https://openalex.org/I2802326326","display_name":"The University of Texas Rio Grande Valley","ror":"https://ror.org/02p5xjf12","country_code":"US","type":"education","lineage":["https://openalex.org/I2802326326"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengfei Gu","raw_affiliation_strings":["The Department of Computer Science, The University of Texas Rio Grande Valley, Edinburg, TX, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Computer Science, The University of Texas Rio Grande Valley, Edinburg, TX, United States","institution_ids":["https://openalex.org/I2802326326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002401618"],"corresponding_institution_ids":["https://openalex.org/I150913223"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":0.4128,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.636125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"5","issue":null,"first_page":"1651623","last_page":"1651623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9994000196456909,"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":0.9976000189781189,"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/representation","display_name":"Representation (politics)","score":0.527999997138977},{"id":"https://openalex.org/keywords/protein\u2013protein-interaction","display_name":"Protein\u2013protein interaction","score":0.4763000011444092},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46540001034736633},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44359999895095825},{"id":"https://openalex.org/keywords/directed-graph","display_name":"Directed graph","score":0.4352000057697296},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42570000886917114},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4065000116825104},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.35420000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5976999998092651},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.527999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001000165939331},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37380000948905945},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.353300005197525},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2883000075817108},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2780806968","wikidata":"https://www.wikidata.org/wiki/Q6045196","display_name":"Interaction model","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3389/fbinf.2025.1651623","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1651623","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1651623/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41199760","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41199760","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:arXiv.org:2510.14139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.14139","pdf_url":"https://arxiv.org/pdf/2510.14139","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:a30c15df33dc4ac797719bf722af3ed2","is_oa":true,"landing_page_url":"https://doaj.org/article/a30c15df33dc4ac797719bf722af3ed2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11395084","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12585958","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:scholarworks.utrgv.edu:cs_fac-1206","is_oa":true,"landing_page_url":"https://scholarworks.utrgv.edu/cs_fac/207","pdf_url":null,"source":{"id":"https://openalex.org/S4306402611","display_name":"ScholarWorks @ UTRGV (The University of Texas Rio Grande Valley)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802326326","host_organization_name":"The University of Texas Rio Grande Valley","host_organization_lineage":["https://openalex.org/I2802326326"],"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":"Computer Science Faculty Publications and Presentations","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1651623","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1651623","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1651623/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415418922.pdf","grobid_xml":"https://content.openalex.org/works/W4415418922.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1990315216","https://openalex.org/W2009405916","https://openalex.org/W2014050554","https://openalex.org/W2015094506","https://openalex.org/W2022284509","https://openalex.org/W2028279608","https://openalex.org/W2045777307","https://openalex.org/W2064675550","https://openalex.org/W2087612189","https://openalex.org/W2116341502","https://openalex.org/W2117831564","https://openalex.org/W2152705149","https://openalex.org/W2157331557","https://openalex.org/W2329592726","https://openalex.org/W2604272474","https://openalex.org/W2911489562","https://openalex.org/W2962711740","https://openalex.org/W2964015378","https://openalex.org/W3093053585","https://openalex.org/W3099768174","https://openalex.org/W3111174583","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3199468887","https://openalex.org/W4280617006","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4294558607","https://openalex.org/W4296746241","https://openalex.org/W4297733535","https://openalex.org/W4309506674","https://openalex.org/W4377130469","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"Introduction":[0],"Accurate":[1],"prediction":[2,67,188],"of":[3,17,45,65,99,120,124,193,212,259,275,288],"protein-protein":[4],"interactions":[5],"(PPIs)":[6],"is":[7,48,164,208],"crucial":[8],"for":[9,61,186,221,272],"understanding":[10],"cellular":[11],"functions":[12],"and":[13,154,224,265],"advancing":[14],"the":[15,42,62,117,167,187,194,234,273],"development":[16],"drugs.":[18],"While":[19],"existing":[20],"in-silico":[21],"methods":[22,214],"leverage":[23],"direct":[24],"sequence":[25,114,260],"embeddings":[26,185],"from":[27,111],"Protein":[28],"Language":[29],"Models":[30],"(PLMs)":[31],"or":[32],"apply":[33],"Graph":[34],"Neural":[35],"Networks":[36],"(GNNs)":[37],"to":[38,49,166,170,182,210,231,269],"3D":[39],"protein":[40],"structures,":[41],"main":[43],"focus":[44],"this":[46],"study":[47],"investigate":[50],"less":[51],"computationally":[52,266],"intensive":[53],"alternatives.":[54],"This":[55],"work":[56,279],"introduces":[57],"a":[58,74,87,92,97,112,121,130,141,159,253,263,285],"novel":[59,88],"framework":[60,237],"downstream":[63],"task":[64,274],"PPI":[66,232,276],"via":[68,158,178],"link":[69],"prediction.":[70,277],"Methods":[71],"We":[72],"introduce":[73],"two-stage":[75],"graph":[76,123,133,227],"representation":[77,258],"learning":[78],"framework,":[79],"ProtGram-DirectGCN":[80,236,283],".":[81],"First,":[82],"we":[83,128],"developed":[84],"ProtGram":[85,168],",":[86,138],"approach":[89],"that":[90,145,211,252],"models":[91],"protein's":[93],"primary":[94],"structure":[95],"as":[96],"hierarchy":[98],"globally":[100,254],"inferred":[101],"n-gram":[102],"graphs.":[103],"In":[104],"these":[105],"graphs,":[106],"residue":[107],"transition":[108],"probabilities,":[109],"aggregated":[110],"large":[113],"corpus,":[115],"define":[116],"edge":[118],"weights":[119],"directed":[122,132,256],"paired":[125],"residues.":[126],"Second,":[127],"propose":[129],"custom":[131],"convolutional":[134,143],"neural":[135],"network,":[136],"DirectGCN":[137,163,195],"which":[139,174],"features":[140],"unique":[142],"layer":[144],"processes":[146],"information":[147],"through":[148],"separate":[149],"path-specific":[150],"(incoming,":[151],"outgoing,":[152],"undirected)":[153],"shared":[155],"transformations,":[156],"combined":[157],"learnable":[160],"gating":[161],"mechanism.":[162],"applied":[165,230],"graphs":[169],"learn":[171],"residue-level":[172],"embeddings,":[173],"are":[175],"then":[176],"pooled":[177],"an":[179],"attention":[180],"mechanism":[181],"generate":[183],"protein-level":[184],"task.":[189],"Results":[190],"The":[191],"efficacy":[192],"model":[196],"was":[197],"first":[198],"established":[199,213],"on":[200,215,245,284],"standard":[201],"node":[202],"classification":[203],"benchmarks,":[204],"where":[205],"its":[206],"performance":[207],"comparable":[209],"general":[216],"datasets,":[217],"while":[218],"demonstrating":[219],"specialization":[220],"complex,":[222],"directed,":[223],"dense":[225],"heterophilic":[226],"structures.":[228],"When":[229],"prediction,":[233],"full":[235],"achieves":[238],"robust":[239],"predictive":[240],"power":[241],"despite":[242],"being":[243],"trained":[244],"limited":[246],"data.":[247],"Discussion":[248],"Our":[249],"results":[250],"suggest":[251],"inferred,":[255],"graph-based":[257],"transitions":[261],"offers":[262],"potent":[264],"distinct":[267],"alternative":[268],"resource-intensive":[270],"PLMs":[271],"Future":[278],"will":[280],"involve":[281],"testing":[282],"wider":[286],"range":[287],"bioinformatics":[289],"tasks.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-22T00:00:00"}