{"id":"https://openalex.org/W2888735575","doi":"https://doi.org/10.1109/bigdata.2018.8622637","title":"Large-Scale Validation of Hypothesis Generation Systems via Candidate Ranking","display_name":"Large-Scale Validation of Hypothesis Generation Systems via Candidate Ranking","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2888735575","doi":"https://doi.org/10.1109/bigdata.2018.8622637","mag":"2888735575","pmid":"https://pubmed.ncbi.nlm.nih.gov/35789222","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/9248026"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622637","doi":"https://doi.org/10.1109/bigdata.2018.8622637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622637","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"IEEE International Conference on Big Data (BigData)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9248026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057510939","display_name":"Justin Sybrandt","orcid":"https://orcid.org/0000-0001-5073-0122","observed_orcids":["https://orcid.org/0000-0001-5073-0122"]},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Sybrandt","raw_affiliation_strings":["Clemson University, School of Computing, Clemson, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University, School of Computing, Clemson, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016479290","display_name":"Michael S. Shtutman","orcid":"https://orcid.org/0000-0002-2458-3226","observed_orcids":["https://orcid.org/0000-0002-2458-3226"]},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Micheal Shtutman","raw_affiliation_strings":["University of South Carolina, Drug Discovery and Biomedical Sciences, Columbia, USA","Drug Discovery and Biomedical Sciences, University of South Carolina, Columbia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina, Drug Discovery and Biomedical Sciences, Columbia, USA","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"Drug Discovery and Biomedical Sciences, University of South Carolina, Columbia, USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057164472","display_name":"Ilya Safro","orcid":"https://orcid.org/0000-0001-6284-7408","observed_orcids":["https://orcid.org/0000-0001-6284-7408"]},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilya Safro","raw_affiliation_strings":["Clemson University, School of Computing, Clemson, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University, School of Computing, Clemson, USA","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7675,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88018433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"2018","issue":null,"first_page":"1494","last_page":"1503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.34380000829696655,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.34380000829696655,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.11379999667406082,"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/T10028","display_name":"Topic Modeling","score":0.07100000232458115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automated-hypothesis-generation","display_name":"automated hypothesis generation","score":0.9549999833106995},{"id":"https://openalex.org/keywords/hypothesis-ranking","display_name":"hypothesis ranking","score":0.6890000104904175},{"id":"https://openalex.org/keywords/topic-modeling","display_name":"topic modeling","score":0.7250000238418579},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.6919999718666077},{"id":"https://openalex.org/keywords/moliere","display_name":"Moli\u00e8re","score":0.7570000290870667},{"id":"https://openalex.org/keywords/ddx3x","display_name":"DDX3X","score":0.9100000262260437},{"id":"https://openalex.org/keywords/candidate-gene-identification","display_name":"candidate gene identification","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692916989326477},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7329378724098206},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6080695986747742},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5263166427612305},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5115000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47450965642929077},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46155568957328796},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.430819571018219},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.4180666208267212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3926253914833069},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33784839510917664},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09733447432518005},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/bigdata.2018.8622637","doi":"https://doi.org/10.1109/bigdata.2018.8622637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622637","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"IEEE International Conference on Big Data (BigData)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmid:35789222","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35789222","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,"listed_in":[],"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":"Proceedings : ... IEEE International Conference on Big Data. IEEE International Conference on Big Data","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9248026","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9248026","pdf_url":null,"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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Big Data","raw_type":"Text"},{"id":"pmh:oai:arXiv.org:1802.03793","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.03793","pdf_url":"https://arxiv.org/pdf/1802.03793","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,"listed_in":[],"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":"mag:2950439222","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1802.03793v4","pdf_url":null,"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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1802.03793","doi":"https://doi.org/10.48550/arxiv.1802.03793","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.03793","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:9248026","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9248026","pdf_url":null,"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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Big Data","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8242064578","display_name":"Impact of Dead Box RNA Helicase 3 signaling on HIV-1 Tat- and cocaine-induced neurotoxicity","funder_award_id":"R21DA047936","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"}],"funders":[{"id":"https://openalex.org/F4320337347","display_name":"National Institute on Drug Abuse","ror":"https://ror.org/00fq5cm18"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888735575.pdf","grobid_xml":"https://content.openalex.org/works/W2888735575.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W34512917","https://openalex.org/W41401133","https://openalex.org/W1614298861","https://openalex.org/W1620588405","https://openalex.org/W1667925084","https://openalex.org/W1680392829","https://openalex.org/W1880262756","https://openalex.org/W1960685374","https://openalex.org/W1972694920","https://openalex.org/W1972734935","https://openalex.org/W1976909068","https://openalex.org/W1995297116","https://openalex.org/W2006867784","https://openalex.org/W2011726136","https://openalex.org/W2015954361","https://openalex.org/W2024030746","https://openalex.org/W2038316408","https://openalex.org/W2052681001","https://openalex.org/W2054473834","https://openalex.org/W2067096102","https://openalex.org/W2079639311","https://openalex.org/W2082828007","https://openalex.org/W2083225388","https://openalex.org/W2087937280","https://openalex.org/W2089177530","https://openalex.org/W2098946845","https://openalex.org/W2099668895","https://openalex.org/W2105562985","https://openalex.org/W2115425483","https://openalex.org/W2117446654","https://openalex.org/W2118002992","https://openalex.org/W2119412782","https://openalex.org/W2119646114","https://openalex.org/W2120889539","https://openalex.org/W2126276057","https://openalex.org/W2128290814","https://openalex.org/W2130145803","https://openalex.org/W2130190939","https://openalex.org/W2132099158","https://openalex.org/W2135029798","https://openalex.org/W2140190241","https://openalex.org/W2151373442","https://openalex.org/W2152061559","https://openalex.org/W2152846037","https://openalex.org/W2153727510","https://openalex.org/W2168773024","https://openalex.org/W2172024938","https://openalex.org/W2223881431","https://openalex.org/W2312469344","https://openalex.org/W2411035889","https://openalex.org/W2413102523","https://openalex.org/W2563351168","https://openalex.org/W2572015725","https://openalex.org/W2591456992","https://openalex.org/W2769604672","https://openalex.org/W2796840850","https://openalex.org/W2953294533","https://openalex.org/W3127672696","https://openalex.org/W4238452917","https://openalex.org/W4245322178","https://openalex.org/W4249865584","https://openalex.org/W4285719527","https://openalex.org/W6601739783"],"related_works":["https://openalex.org/W2786665421","https://openalex.org/W3005906795","https://openalex.org/W4399629030","https://openalex.org/W2953294533","https://openalex.org/W2132099158","https://openalex.org/W4416540180","https://openalex.org/W7222804300","https://openalex.org/W2946120927","https://openalex.org/W7213785938","https://openalex.org/W4401754055"],"abstract_inverted_index":{"The":[0],"first":[1],"step":[2],"of":[3,15,23,59,80,117,124,144,172,210],"many":[4,71],"research":[5,190],"projects":[6],"is":[7],"to":[8,28,34,86,136,168,205,214],"define":[9],"and":[10,51,83,104,235,246],"rank":[11,137],"a":[12,47,78,110,130,141,154,208,230],"short":[13],"list":[14],"candidates":[16],"for":[17,114],"study.":[18],"In":[19],"the":[20,57,115,170],"modern":[21],"rapidity":[22],"scientific":[24,49],"progress,":[25],"some":[26,84],"turn":[27],"automated":[29],"hypothesis":[30],"generation":[31],"(HG)":[32],"systems":[33,39,75,120,150],"aid":[35],"this":[36,225],"process.":[37],"These":[38,98],"can":[40,248],"identify":[41],"implicit":[42],"or":[43],"overlooked":[44],"connections":[45],"within":[46,196],"large":[48],"corpus,":[50],"while":[52],"their":[53],"importance":[54],"grows":[55],"alongside":[56],"pace":[58],"science,":[60],"they":[61],"lack":[62],"thorough":[63,89],"validation.":[64],"Without":[65],"any":[66],"standard":[67],"numerical":[68,111],"evaluation":[69,112],"method,":[70],"validate":[72],"general-purpose":[73],"HG":[74,119,131,149,201],"by":[76,133,139,192],"rediscovering":[77],"handful":[79],"historical":[81],"findings,":[82],"wishing":[85],"be":[87,249],"more":[88],"may":[90],"run":[91],"laboratory":[92,221],"experiments":[93,222],"based":[94,223],"on":[95,224],"automatic":[96],"suggestions.":[97],"methods":[99],"are":[100],"expensive,":[101],"time":[102],"consuming,":[103],"cannot":[105],"scale.":[106],"Thus,":[107],"we":[108,163,180,228],"present":[109,165],"framework":[113],"purpose":[116],"validating":[118],"that":[121,159,182],"leverages":[122],"thousands":[123],"validation":[125,185,244],"hypotheses.":[126],"This":[127],"method":[128,186,195],"evaluates":[129],"system":[132,177],"its":[134],"ability":[135],"hypotheses":[138,173],"plausibility;":[140],"process":[142],"reminiscent":[143],"human":[145],"candidate":[146,211,226],"selection.":[147],"Because":[148],"do":[151],"not":[152],"produce":[153,160],"ranking":[155],"criteria,":[156],"specifically":[157],"those":[158],"topic":[161,175],"models,":[162],"additionally":[164],"novel":[166],"metrics":[167],"quantify":[169],"plausibility":[171],"given":[174],"model":[176],"output.":[178],"Finally,":[179],"demonstrate":[181],"our":[183,194,198],"proposed":[184],"aligns":[187],"with":[188],"real-world":[189],"goals":[191],"deploying":[193],"MOLIERE,":[197],"recent":[199],"topic-driven":[200],"system,":[202],"in":[203],"order":[204],"automatically":[206],"generate":[207],"set":[209],"genes":[212],"related":[213],"HIV-associated":[215],"neurodegenerative":[216],"disease":[217],"(HAND).":[218],"By":[219],"performing":[220],"set,":[227],"discover":[229],"new":[231],"connection":[232],"between":[233],"HAND":[234],"Dead":[236],"Box":[237],"RNA":[238],"Helicase":[239],"3":[240],"(DDX3).":[241],"Reproducibility:":[242],"code,":[243],"data,":[245],"results":[247],"found":[250],"at":[251],"sybrandt.com/2018/validation.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-08-31T00:00:00"}