{"id":"https://openalex.org/W4406682439","doi":"https://doi.org/10.3389/fdata.2024.1466391","title":"A scalable tool for analyzing genomic variants of humans using knowledge graphs and graph machine learning","display_name":"A scalable tool for analyzing genomic variants of humans using knowledge graphs and graph machine learning","publication_year":2025,"publication_date":"2025-01-21","ids":{"openalex":"https://openalex.org/W4406682439","doi":"https://doi.org/10.3389/fdata.2024.1466391","pmid":"https://pubmed.ncbi.nlm.nih.gov/39906190"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2024.1466391","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1466391","pdf_url":null,"source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"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 Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3389/fdata.2024.1466391","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046514599","display_name":"Shivika Prasanna","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivika Prasanna","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065206515","display_name":"Ajay Kumar","orcid":"https://orcid.org/0000-0003-3654-5566"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Kumar","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108727338","display_name":"Deepthi Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepthi Rao","raw_affiliation_strings":["Department of Pathology and Anatomical Sciences, University of Missouri, Columbia, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology and Anatomical Sciences, University of Missouri, Columbia, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082710912","display_name":"Eduardo J. Sim\u00f5es","orcid":"https://orcid.org/0000-0003-4371-4305"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduardo J. Simoes","raw_affiliation_strings":["Department of Biomedical Informatics, Biostatistics and Medical Epidemiology, University of Missouri, Columbia, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Biostatistics and Medical Epidemiology, University of Missouri, Columbia, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087950601","display_name":"Praveen Rao","orcid":"https://orcid.org/0000-0002-1859-0438"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Praveen Rao","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":{"value":1285,"currency":"USD","value_usd":1285},"apc_paid":{"value":1285,"currency":"USD","value_usd":1285},"fwci":1.2652,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76015249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"1466391","last_page":"1466391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9932000041007996,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9932000041007996,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.7226640582084656},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6929863691329956},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5686160326004028},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.5246900916099548},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5185049772262573},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5083627104759216},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.4485812485218048},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3493397831916809},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3447585701942444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2841339111328125},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25753253698349},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19000980257987976},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.16685643792152405},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1494421362876892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226640582084656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6929863691329956},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5686160326004028},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.5246900916099548},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5185049772262573},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5083627104759216},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.4485812485218048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3493397831916809},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3447585701942444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2841339111328125},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25753253698349},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19000980257987976},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.16685643792152405},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1494421362876892}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2024.1466391","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1466391","pdf_url":null,"source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"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 Big Data","raw_type":"journal-article"},{"id":"pmid:39906190","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39906190","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 big data","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11790625","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11790625","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11790625/pdf/fdata-07-1466391.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:36a188f6b8ed452e8fe24a724da359ea","is_oa":true,"landing_page_url":"https://doaj.org/article/36a188f6b8ed452e8fe24a724da359ea","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 Big Data, Vol 7 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2024.1466391","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1466391","pdf_url":null,"source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"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 Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5501047039","display_name":"RAPID: Democratizing Genome Sequence Analysis for COVID-19 Using CloudLab","funder_award_id":"2034247","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W592349567","https://openalex.org/W1552847225","https://openalex.org/W2013532104","https://openalex.org/W2080133951","https://openalex.org/W2103441770","https://openalex.org/W2104846587","https://openalex.org/W2106578986","https://openalex.org/W2112113834","https://openalex.org/W2119180969","https://openalex.org/W2149992227","https://openalex.org/W2196674927","https://openalex.org/W2520381032","https://openalex.org/W2596218679","https://openalex.org/W2883780523","https://openalex.org/W2892518423","https://openalex.org/W2905452503","https://openalex.org/W2913319647","https://openalex.org/W2948715311","https://openalex.org/W2950982802","https://openalex.org/W2951333474","https://openalex.org/W2964121744","https://openalex.org/W2970119293","https://openalex.org/W2972317931","https://openalex.org/W2985331920","https://openalex.org/W2988287745","https://openalex.org/W3022290554","https://openalex.org/W3080555959","https://openalex.org/W3088646411","https://openalex.org/W3102245839","https://openalex.org/W3116278528","https://openalex.org/W3128128460","https://openalex.org/W3129351841","https://openalex.org/W3202281227","https://openalex.org/W3208182228","https://openalex.org/W4282012582","https://openalex.org/W4294558607","https://openalex.org/W4305082132","https://openalex.org/W4307838179","https://openalex.org/W4322719852","https://openalex.org/W4384408101","https://openalex.org/W4390722969","https://openalex.org/W4399688294","https://openalex.org/W6622957738","https://openalex.org/W6738964360","https://openalex.org/W6745782156","https://openalex.org/W6944905653"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W1548523074"],"abstract_inverted_index":{"Advances":[0],"in":[1,10,139],"high-throughput":[2],"genome":[3,8,87,203],"sequencing":[4,9,88],"have":[5],"enabled":[6],"large-scale":[7],"clinical":[11],"practice":[12],"and":[13,37,41,50,80,112,137,149,176,188,191,227,242,250,263],"research":[14],"studies.":[15],"By":[16],"analyzing":[17,72],"genomic":[18,45,73,267],"variants":[19,74,268],"of":[20,27,31,75,173,221,269],"humans,":[21],"scientists":[22],"can":[23,55,169,184],"gain":[24],"better":[25],"understanding":[26],"the":[28,43,106,114,123,154,174,186,225],"risk":[29],"factors":[30],"complex":[32],"diseases":[33],"such":[34,163,235],"as":[35,58,164,236],"cancer":[36],"COVID-19.":[38,93],"To":[39],"model":[40,261,264],"analyze":[42],"rich":[44],"data,":[46],"knowledge":[47],"graphs":[48],"(KGs)":[49],"graph":[51,142],"machine":[52],"learning":[53],"(GML)":[54],"be":[56],"regarded":[57],"enabling":[59,252],"technologies.":[60],"In":[61],"this":[62],"article,":[63],"we":[64,83],"present":[65],"a":[66,101,119,140,171,219,253],"scalable":[67,141],"tool":[68],"called":[69],"VariantKG":[70,94,152,196,216,245],"for":[71,197,258],"humans":[76],"modeled":[77],"using":[78,122,180,201,215,231],"KGs":[79],"GML.":[81],"Specifically,":[82],"used":[84],"publicly":[85],"available":[86],"data":[89,108],"from":[90,224],"patients":[91],"with":[92,109,134],"extracts":[95],"variant-level":[96],"genetic":[97],"information":[98,117],"output":[99],"by":[100,200,217],"variant":[102,107,116],"calling":[103],"pipeline,":[104],"annotates":[105],"additional":[110],"metadata,":[111],"converts":[113],"annotated":[115],"into":[118],"KG":[120,130,175,198,226,259],"represented":[121],"Resource":[124],"Description":[125],"Framework":[126],"(RDF).":[127],"The":[128,182],"resulting":[129],"is":[131],"further":[132],"enhanced":[133],"patient":[135],"metadata":[136],"stored":[138],"database":[143],"that":[144],"enables":[145],"efficient":[146],"RDF":[147,209],"indexing":[148],"query":[150],"processing.":[151],"employs":[153],"Deep":[155],"Graph":[156,238,243],"Library":[157],"(DGL)":[158],"to":[159,206,256],"perform":[160,177],"GML":[161,213,233],"tasks":[162,179,214],"node":[165,229],"classification.":[166],"A":[167],"user":[168,183,248],"extract":[170],"subset":[172,220],"inference":[178],"DGL.":[181],"monitor":[185],"training":[187],"testing":[189],"performance":[190],"hardware":[192],"utilization.":[193],"We":[194,211],"tested":[195],"construction":[199],"1,508":[202],"sequences,":[204],"leading":[205],"4":[207],"billion":[208],"statements.":[210],"evaluated":[212],"selecting":[218],"500":[222],"sequences":[223],"performing":[228],"classification":[230],"well-known":[232],"techniques":[234],"GraphSAGE,":[237],"Convolutional":[239],"Network":[240],"(GCN)":[241],"Transformer.":[244],"has":[246],"intuitive":[247],"interfaces":[249],"features":[251],"low":[254],"barrier":[255],"entry":[257],"construction,":[260],"inference,":[262],"interpretation":[265],"on":[266],"humans.":[270]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}