Paper Publications
Current position: Home > Scientific Research > Paper Publications
理工科高水平行业特色大学创新创业教育政策、模式与实践研究——以中国矿业大学为例
- Release time:2024-07-20
- Hits:
Impact Factor:
9.5Journal:
Briefings in BioinformaticsKey Words:
essential gene prediction; large language model; graph neural network; adversarial training; biological interpretationAbstract:
Theidentificationandcharacterizationofessentialgenesarecentraltoourunderstandingofthecorebiologicalfunctionsineukaryoticorganisms,andhasimportantimplicationsforthetreatmentofdiseasescausedby,forexample,cancersandpathogens.Giventhemajorconstraintsintestingthefunctionsofgenesofmanyorganismsinthelaboratory,duetotheabsenceofinvitroculturesand/orgeneperturbationassaysformostmetazoanspecies,therehasbeenaneedtodevelopinsilicotoolsfortheaccuratepredictionorinferenceofessentialgenestounderpinsystemsbiologicalinvestigations.Majoradvancesinmachinelearningapproachesprovideunprecedentedopportunitiestoovercometheselimitationsandacceleratethediscoveryofessentialgenesonagenome-widescale.Here,wedevelopedandevaluatedalargelanguagemodel-andgraphneuralnetwork(LLM–GNN)-basedapproach,called‘Bingo’,topredictessentialprotein-codinggenesinthemetazoanmodelorganismsCaenorhabditiselegansandDrosophilamelanogasteraswellasinMusmusculusandHomosapiens(aHepG2cellline)byintegratingLLMandGNNswithadversarialtraining.Bingopredictsessentialgenesundertwo‘zero-shot’scenarioswithtransferlearning,showingpromisetocompensateforalackofhigh-qualitygenomicandproteomicdatafornon-modelorganisms.Inaddition,theattentionmechanismsandGNNExplainerwereemployedtomanifestthefunctionalsitesandstructuraldomainwithmostcontributiontoessentiality.Inconclusion,Bingoprovidestheprospectofbeingabletoaccuratelyinfertheessentialgenesoflittle-orunder-studiedorganismsofinterest,andprovidesabiologicalexplanationforgeneessentiality.Indexed by:
Journal paperDocument Type:
JTranslation or Not:
noDate of Publication:
2024-01-12Included Journals:
SCI