{"id":"https://openalex.org/W7224816787","doi":"https://doi.org/10.64898/2026.10.25.761509","title":"Negative sampling shapes benchmark discrimination and experimental retrieval in synthetic-lethality prediction","display_name":"Negative sampling shapes benchmark discrimination and experimental retrieval in synthetic-lethality prediction","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224816787","doi":"https://doi.org/10.64898/2026.10.25.761509"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.25.761509","doi":"https://doi.org/10.64898/2026.10.25.761509","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.25.761509","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.25.761509.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.25.761509.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068182723","display_name":"Zhongwei Huang","orcid":"https://orcid.org/0000-0002-4061-9321","observed_orcids":["https://orcid.org/0000-0002-4061-9321","https://orcid.org/0009-0003-4163-2020"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhongwei Huang","raw_affiliation_strings":["University of Washington;"],"raw_orcid":"https://orcid.org/0009-0003-4163-2020","affiliations":[{"raw_affiliation_string":"University of Washington;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111086046","display_name":"Ruohan Huang","orcid":"https://orcid.org/0009-0007-8244-739X","observed_orcids":["https://orcid.org/0009-0007-8244-739X"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruohan Huang","raw_affiliation_strings":["Yale University"],"raw_orcid":"https://orcid.org/0009-0007-8244-739X","affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068182723"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9146000146865845,"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":0.9146000146865845,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.030700000002980232,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.007400000002235174,"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/benchmark-evaluation","display_name":"benchmark evaluation","score":0.38600000739097595},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"sampling bias","score":0.6890000104904175},{"id":"https://openalex.org/keywords/drug-screening","display_name":"drug screening","score":0.3199999928474426},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.5239999890327454},{"id":"https://openalex.org/keywords/circuit-diagrams","display_name":"circuit diagrams","score":0.6370000243186951}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8248000144958496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5702999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113000273704529},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4120999872684479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027000069618225},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.37779998779296875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3628999888896942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.3183000087738037},{"id":"https://openalex.org/C154020017","wikidata":"https://www.wikidata.org/wiki/Q520171","display_name":"Repeatability","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C3019714060","wikidata":"https://www.wikidata.org/wiki/Q322514","display_name":"Validation test","level":4,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.25.761509","doi":"https://doi.org/10.64898/2026.10.25.761509","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.25.761509","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.25.761509.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.25.761509","doi":"https://doi.org/10.64898/2026.10.25.761509","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.25.761509","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.25.761509.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.4043000042438507,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224816787.pdf","grobid_xml":"https://content.openalex.org/works/W7224816787.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2597062310","https://openalex.org/W2963277165","https://openalex.org/W2995178483","https://openalex.org/W3131175301","https://openalex.org/W3161372396","https://openalex.org/W4225820450","https://openalex.org/W4287446891","https://openalex.org/W4392470326","https://openalex.org/W4392500220","https://openalex.org/W4403572618","https://openalex.org/W4404460807","https://openalex.org/W4409283703","https://openalex.org/W4411178498","https://openalex.org/W4414333341","https://openalex.org/W7155922522","https://openalex.org/W7203832691","https://openalex.org/W7223448391"],"related_works":["https://openalex.org/W2887476663","https://openalex.org/W7204247377","https://openalex.org/W7214484919","https://openalex.org/W7202081072","https://openalex.org/W2947432339","https://openalex.org/W7216073035","https://openalex.org/W7214779028","https://openalex.org/W7208781546","https://openalex.org/W7213951216","https://openalex.org/W7072847203"],"abstract_inverted_index":{"Benchmarks":[0],"for":[1,100,124,173],"synthetic-lethality":[2],"prediction":[3],"compare":[4],"known":[5],"interactions":[6],"with":[7,161],"sampled":[8],"negatives.":[9,63],"Does":[10],"performance":[11],"under":[12,53],"degree":[13,31],"matching":[14,27],"predict":[15],"which":[16],"gene":[17,133],"pairs":[18,114],"a":[19,50],"model":[20],"can":[21],"prioritize?":[22],"Across":[23],"five":[24],"gene-disjoint":[25],"folds,":[26],"test":[28,47],"negatives":[29,91,120],"by":[30,45,78],"in":[32,85],"the":[33,54,117,152,170,190],"full":[34],"labelled":[35],"graph":[36,178],"brought":[37],"four":[38,157],"methods":[39],"near":[40],"chance.":[41,79],"SLMGAE":[42],"states":[43,66],"selected":[44],"benchmark":[46],"F1":[48],"had":[49],"mean":[51],"area":[52],"receiver":[55],"operating":[56],"characteristic":[57],"curve":[58],"of":[59,109,151,175],"0.501":[60],"on":[61],"matched":[62,119],"The":[64],"same":[65],"retrieved":[67],"21":[68],"experimental":[69,183],"hits":[70,99],"among":[71],"198":[72],"SPIDR":[73],"selections,":[74],"versus":[75],"8.00":[76],"expected":[77],"Comparable":[80],"enrichment":[81],"was":[82],"not":[83],"established":[84],"three":[86],"other":[87],"screens.":[88],"Changing":[89],"training":[90],"increased":[92],"HAP1":[93,122],"retrieval":[94,123,184],"from":[95],"3.6":[96],"to":[97,143,164],"15.8":[98],"logistic":[101,125],"regression;":[102],"swapping":[103],"28":[104],"endpoint":[105],"coefficients":[106],"transferred":[107],"most":[108],"this":[110],"difference.":[111],"Rewiring":[112],"positive":[113],"while":[115],"keeping":[116],"original":[118],"reduced":[121],"regression":[126],"and":[127,182],"gradient":[128],"boosting.":[129],"This":[130],"preserved":[131],"individual":[132],"degrees":[134],"but":[135],"also":[136],"changed":[137],"their":[138],"joint":[139],"distribution,":[140],"limiting":[141],"attribution":[142],"partner":[144],"identity.":[145],"A":[146],"density-ratio":[147],"estimate":[148],"closed":[149],"55-65%":[150],"logistic-regression":[153],"shortlist":[154,171],"gap":[155],"across":[156],"previously":[158],"evaluated":[159],"pools,":[160],"limited":[162],"transfer":[163],"nonlinear":[165],"models.":[166],"Frozen":[167],"predictions":[168],"met":[169],"criterion":[172],"one":[174],"two":[176],"new":[177],"relations.":[179],"Benchmark":[180],"discrimination":[181],"therefore":[185],"warrant":[186],"separate":[187],"evaluation":[188],"at":[189],"intended":[191],"screening":[192],"budget.":[193]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-31T00:00:00"}