{"id":"https://openalex.org/W4405442842","doi":"https://doi.org/10.1145/3698587.3701371","title":"DeePSP-GIN: identification and classification of phage structural proteins using predicted protein structure, pretrained protein language model, and graph isomorphism network","display_name":"DeePSP-GIN: identification and classification of phage structural proteins using predicted protein structure, pretrained protein language model, and graph isomorphism network","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4405442842","doi":"https://doi.org/10.1145/3698587.3701371"},"language":"en","primary_location":{"id":"doi:10.1145/3698587.3701371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698587.3701371","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 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3698587.3701371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051072835","display_name":"Muhit Islam Emon","orcid":"https://orcid.org/0000-0002-8190-4495"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhit Islam Emon","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084176822","display_name":"Badhan Das","orcid":"https://orcid.org/0000-0002-5327-9952"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Badhan Das","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052168450","display_name":"Ashrith Reddy Thukkaraju","orcid":"https://orcid.org/0000-0002-9977-0050"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashrith Reddy Thukkaraju","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061868278","display_name":"Liqing Zhang","orcid":"https://orcid.org/0000-0003-4660-9199"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liqing Zhang","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051072835"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.6884,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71343269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991000294685364,"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":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.6195629835128784},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5626644492149353},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5078170895576477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053046345710754},{"id":"https://openalex.org/keywords/isomorphism","display_name":"Isomorphism (crystallography)","score":0.4741736650466919},{"id":"https://openalex.org/keywords/graph-isomorphism","display_name":"Graph isomorphism","score":0.4252837598323822},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.42242366075515747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.412983238697052},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36649566888809204},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19977334141731262},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.16115397214889526},{"id":"https://openalex.org/keywords/crystallography","display_name":"Crystallography","score":0.13770121335983276},{"id":"https://openalex.org/keywords/botany","display_name":"Botany","score":0.11612993478775024},{"id":"https://openalex.org/keywords/crystal-structure","display_name":"Crystal structure","score":0.11449509859085083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6195629835128784},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5626644492149353},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5078170895576477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053046345710754},{"id":"https://openalex.org/C203436722","wikidata":"https://www.wikidata.org/wiki/Q902950","display_name":"Isomorphism (crystallography)","level":3,"score":0.4741736650466919},{"id":"https://openalex.org/C61665672","wikidata":"https://www.wikidata.org/wiki/Q303100","display_name":"Graph isomorphism","level":4,"score":0.4252837598323822},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.42242366075515747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.412983238697052},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36649566888809204},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19977334141731262},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.16115397214889526},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.13770121335983276},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.11612993478775024},{"id":"https://openalex.org/C115624301","wikidata":"https://www.wikidata.org/wiki/Q895901","display_name":"Crystal structure","level":2,"score":0.11449509859085083},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3698587.3701371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698587.3701371","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 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/124009","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/124009","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/596d2b48-a55b-4ece-9fcd-86329f5e00f3/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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"}],"best_oa_location":{"id":"doi:10.1145/3698587.3701371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698587.3701371","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 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G3848098116","display_name":null,"funder_award_id":"2004751","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2131871423","https://openalex.org/W2550993779","https://openalex.org/W2791956910","https://openalex.org/W2807988699","https://openalex.org/W2940026215","https://openalex.org/W3003285614","https://openalex.org/W3035978132","https://openalex.org/W3177828909","https://openalex.org/W3195030397","https://openalex.org/W4211003308","https://openalex.org/W4308370073","https://openalex.org/W4327550249","https://openalex.org/W4382631374","https://openalex.org/W4386317415"],"related_works":["https://openalex.org/W1258892498","https://openalex.org/W1522618089","https://openalex.org/W2905073546","https://openalex.org/W3080158623","https://openalex.org/W4360838296","https://openalex.org/W2187958446","https://openalex.org/W1856194915","https://openalex.org/W2389075355","https://openalex.org/W2494517118","https://openalex.org/W2183579781"],"abstract_inverted_index":{"Phages":[0],"are":[1,13,70],"vital":[2],"components":[3],"of":[4,58,80,94,146,167,233,266,273],"the":[5,41,55,78,92,144,151,206,211,221,242,247,256,267,280],"microbial":[6],"ecosystem,":[7],"and":[8,11,32,50,63,104,115,134,141,170,173,191,228],"their":[9,17,33,61],"functions":[10],"roles":[12],"largely":[14],"determined":[15],"by":[16],"structural":[18,23,82,157],"proteins.":[19],"Accurately":[20],"annotating":[21],"phage":[22,30],"proteins":[24],"(PSPs)":[25],"is":[26,150,202,260,275],"essential":[27],"for":[28,43,72,87,112,138,159],"understanding":[29,88],"biology":[31],"interactions":[34],"with":[35],"bacterial":[36,48],"hosts,":[37],"which":[38],"can":[39,100],"pave":[40],"way":[42],"innovative":[44],"strategies":[45],"to":[46,205,209],"combat":[47],"infections":[49],"develop":[51],"phage-based":[52],"therapies.":[53],"However,":[54],"sequence":[56],"diversity":[57],"PSPs":[59,175],"makes":[60],"identification":[62,140,227,249],"annotation":[64],"challenging.":[65],"While":[66],"various":[67],"computational":[68],"methods":[69,223],"available":[71,276],"predicting":[73],"PSPs,":[74],"they":[75],"currently":[76],"lack":[77],"integration":[79],"protein":[81,89,98,107,132,135,156,183,196],"information,":[83],"an":[84],"important":[85],"aspect":[86],"function.":[90],"With":[91],"advent":[93],"deep":[95,127],"learning":[96,128],"models,":[97],"structures":[99,133,184],"be":[101],"predicted":[102,131,155,182],"accurately":[103],"quickly":[105],"from":[106,185,195],"sequences,":[108],"creating":[109],"new":[110],"opportunities":[111],"PSP":[113,139,160,169,226,248,257],"prediction":[114,161],"analysis.":[116],"We":[117],"developed":[118],"DeePSP-GIN,":[119],"a":[120,237],"graph":[121],"isomorphism":[122],"network":[123],"(GIN)":[124],"-":[125],"based":[126],"model":[129,137],"leveraging":[130],"language":[136,197],"classification.":[142],"To":[143],"best":[145],"our":[147],"knowledge,":[148],"DeePSP-GIN":[149,180,219,235,274],"first":[152],"method":[153,245],"utilizing":[154],"information":[158],"tasks.":[162],"It":[163],"offers":[164],"dual":[165],"functionality":[166],"identifying":[168],"non-PSP":[171],"sequences":[172],"classifying":[174],"into":[176,189],"seven":[177],"major":[178],"classes.":[179],"converts":[181],"PDB":[186],"3D":[187],"coordinates":[188],"graphs":[190,208],"extracts":[192],"node":[193],"features":[194],"model-generated":[198],"embeddings.":[199],"The":[200,214,270],"GIN":[201],"then":[203],"applied":[204],"constructed":[207],"learn":[210],"discriminating":[212],"features.":[213],"experimental":[215],"results":[216],"show":[217],"that":[218,265],"outperforms":[220],"state-of-the-art":[222],"in":[224,231,246,255],"both":[225],"classification":[229,258],"tasks":[230],"terms":[232],"F1-score.":[234],"achieves":[236],"1.04%":[238],"higher":[239,263],"F1-score":[240,254],"than":[241,264],"nearest":[243],"competing":[244],"task.":[250],"Additionally,":[251],"its":[252],"overall":[253],"task":[259],"approximately":[261],"34.38%":[262],"second-best":[268],"method.":[269],"source":[271],"code":[272],"at":[277],"https://github.com/muhit-emon/DeePSP-GIN":[278],"under":[279],"MIT":[281],"license.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}