2025
Risks of AI scientists: prioritizing safeguarding over autonomy
Tang X, Jin Q, Zhu K, Yuan T, Zhang Y, Zhou W, Qu M, Zhao Y, Tang J, Zhang Z, Cohan A, Greenbaum D, Lu Z, Gerstein M. Risks of AI scientists: prioritizing safeguarding over autonomy. Nature Communications 2025, 16: 8317. PMID: 40968279, PMCID: PMC12446425, DOI: 10.1038/s41467-025-63913-1.Peer-Reviewed Original ResearchNetwork-based drug repurposing for psychiatric disorders using single-cell genomics
Gupta C, Kalafut N, Clarke D, Choi J, Arachchilage K, Khullar S, Xia Y, Zhou X, Dursun C, Gerstein M, Wang D. Network-based drug repurposing for psychiatric disorders using single-cell genomics. Cell Genomics 2025, 101003. PMID: 40972584, DOI: 10.1016/j.xgen.2025.101003.Peer-Reviewed Original ResearchRisk genesSingle-cell genomic dataGene regulatory networksSingle-cell genomicsCell-type levelQuantitative trait lociCo-regulated modulesNetwork-based drugGenomic dataTrait lociRegulatory networksTranscription factorsNeuropsychiatric disordersTranscriptional phenotypesMolecular mechanismsGenesCell typesTarget expressionBipolar disorderPsychiatric disordersEQTLGenomeDrug target expressionMedicinal resourcesDisordersRegulatory genome annotation
Kumar S, Gerstein M. Regulatory genome annotation. Nature Reviews Genetics 2025, 26: 661-662. PMID: 40957943, DOI: 10.1038/s41576-025-00885-4.Peer-Reviewed Original ResearchAuthor Correction: Complex genetic variation in nearly complete human genomes
Logsdon G, Ebert P, Audano P, Loftus M, Porubsky D, Ebler J, Yilmaz F, Hallast P, Prodanov T, Yoo D, Paisie C, Harvey W, Zhao X, Martino G, Henglin M, Munson K, Rabbani K, Chin C, Gu B, Ashraf H, Scholz S, Austine-Orimoloye O, Balachandran P, Bonder M, Cheng H, Chong Z, Crabtree J, Gerstein M, Guethlein L, Hasenfeld P, Hickey G, Hoekzema K, Hunt S, Jensen M, Jiang Y, Koren S, Kwon Y, Li C, Li H, Li J, Norman P, Oshima K, Paten B, Phillippy A, Pollock N, Rausch T, Rautiainen M, Song Y, Söylev A, Sulovari A, Surapaneni L, Tsapalou V, Zhou W, Zhou Y, Zhu Q, Zody M, Mills R, Devine S, Shi X, Talkowski M, Chaisson M, Dilthey A, Konkel M, Korbel J, Lee C, Beck C, Eichler E, Marschall T. Author Correction: Complex genetic variation in nearly complete human genomes. Nature 2025, 645: e6-e6. PMID: 40858940, PMCID: PMC12443598, DOI: 10.1038/s41586-025-09547-1.Peer-Reviewed Original ResearchThe chronODE framework for modelling multi-omic time series with ordinary differential equations and machine learning
Borsari B, Frank M, Wattenberg E, Xu K, Liu S, Yu X, Gerstein M. The chronODE framework for modelling multi-omic time series with ordinary differential equations and machine learning. Nature Communications 2025, 16: 7021. PMID: 40830112, PMCID: PMC12365117, DOI: 10.1038/s41467-025-61921-9.Peer-Reviewed Original ResearchConceptsGene expressionKinetics of gene regulationCis-regulatory elementsGenome-wide studiesMultiple regulatory elementsBrain-specific functionModel gene expressionEssential genesBiochemical limitationsGroup genesGene regulationRegulatory elementsChromatin changesOrganismal developmentMouse brain developmentGenesChromatinKinetic patternsCell differentiationCell typesBiophysical constraintsBiological systemsExpressionCellsBrain developmentRecent advances and future prospects for blockchain in biomedicine
Ni E, Tang X, Zhou X, Lee D, Elhussein A, Knight E, Gürsoy G, Gerstein M. Recent advances and future prospects for blockchain in biomedicine. Cell Reports Methods 2025, 5: 101114. PMID: 40714006, PMCID: PMC12461581, DOI: 10.1016/j.crmeth.2025.101114.Peer-Reviewed Original ResearchConceptsBlockchain technologyHealthcare data managementHealth data storageData privacyCommunication servicesHealthcare dataData managementData storageData landscapePrivacyOperational efficiencyExponential increaseBlockchainScalabilityImmutabilityTechnologySecurityDataCommunicationObstaclesServicesHealthcareComplex genetic variation in nearly complete human genomes
Logsdon G, Ebert P, Audano P, Loftus M, Porubsky D, Ebler J, Yilmaz F, Hallast P, Prodanov T, Yoo D, Paisie C, Harvey W, Zhao X, Martino G, Henglin M, Munson K, Rabbani K, Chin C, Gu B, Ashraf H, Scholz S, Austine-Orimoloye O, Balachandran P, Bonder M, Cheng H, Chong Z, Crabtree J, Gerstein M, Guethlein L, Hasenfeld P, Hickey G, Hoekzema K, Hunt S, Jensen M, Jiang Y, Koren S, Kwon Y, Li C, Li H, Li J, Norman P, Oshima K, Paten B, Phillippy A, Pollock N, Rausch T, Rautiainen M, Song Y, Söylev A, Sulovari A, Surapaneni L, Tsapalou V, Zhou W, Zhou Y, Zhu Q, Zody M, Mills R, Devine S, Shi X, Talkowski M, Chaisson M, Dilthey A, Konkel M, Korbel J, Lee C, Beck C, Eichler E, Marschall T. Complex genetic variation in nearly complete human genomes. Nature 2025, 644: 430-441. PMID: 40702183, PMCID: PMC12350169, DOI: 10.1038/s41586-025-09140-6.Peer-Reviewed Original ResearchConceptsHuman genomeStructural variantsDiverse human genomesShort-read dataComplex structural variantsMobile element insertionsSequence continuityDisease association studiesComplex structural variationsMajor histocompatibility complexComplex genetic variationPangenome referenceGenotyping accuracyHuman centromeresWhole genomeHypomethylated regionsElement insertionsRepeat arrayKinetochore attachmentComplex locusAssociation studiesGenetic variationEpigenetic analysisGenomeCentromereA map of enhancer regions in primary human neural progenitor cells using capture STARR-seq.
Gaynor-Gillett S, Cheng L, Shi M, Liu J, Wang G, Spector M, Guo Q, Qi L, Flaherty M, Wall M, Hwang A, Gu M, Chen Z, Chen Y, Moran J, Zhang J, Lee D, Gerstein M, Geschwind D, White K. A map of enhancer regions in primary human neural progenitor cells using capture STARR-seq. Genome Research 2025, 35: 1887-1901. PMID: 40645663, PMCID: PMC12315878, DOI: 10.1101/gr.279584.124.Peer-Reviewed Original ResearchConceptsGenome-wide association studiesNoncoding regulatory regionEffects of genetic variationHuman neural progenitor cellsDisease-associated pathwaysNeural progenitor cellsEnhanced activityNervous system developmentSTARR-seqAssociation studiesRegulatory networksRegulatory regionsCRISPR deletionGenetic variationActivity enhancementFunctional characterizationProgenitor cellsEnhancer regionExpression analysisEnhancer deletionTarget genesGene expressionGenesDevelopmental timepointsDeletionCollege Community–Based Physical Activity Support at a Public University During the COVID-19 Pandemic: Retrospective Longitudinal Analysis of Intra- Versus Interpersonal Components for Uptake and Outcome Association
Ash G, Mak S, Haughton A, Augustine M, Bodurtha P, Axtell R, Borsari B, Liu J, Lou S, Xin X, Fucito L, Jeon S, Stults-Kolehmainen M, Gerstein M. College Community–Based Physical Activity Support at a Public University During the COVID-19 Pandemic: Retrospective Longitudinal Analysis of Intra- Versus Interpersonal Components for Uptake and Outcome Association. JMIR MHealth And UHealth 2025, 13: e51707. PMID: 40523272, PMCID: PMC12209730, DOI: 10.2196/51707.Peer-Reviewed Original ResearchConceptsPA promotion programsPhysical activityPromotion programsPhysical activity supportLow physical activityCollege studentsInterpersonal componentsEngagement frequencyRetrospective longitudinal analysisPA interventionsPA outcomesPA supportCOVID-19 pandemicIntervention componentsApp engagementUndergraduate studentsApp useInterpersonal supportAssociated with longer retentionImplementation strategiesStaff membersLong-term trajectoriesOutcome associationsLongitudinal analysisStaffQuantum variational autoencoder utilizing regularized mixed-state latent representations
Wang G, Warrell J, Emani P, Gerstein M. Quantum variational autoencoder utilizing regularized mixed-state latent representations. Physical Review A 2025, 111: 042416. DOI: 10.1103/physreva.111.042416.Peer-Reviewed Original ResearchQuantum modelQuantum dataVariational autoencoderLatent representationQuantum computationNear-term quantum computersQuantum hardware resourcesOptimal latent representationEfficient data compressionLow-dimensional representationQuantum componentsDensity matrixLower-dimensional spaceQuantum frameworkMixed stateFederated LearningRepresentation learningLearned representationsLatent spaceData compressionHardware resourcesMachine learningSynthetic dataData generationAutoencoderScalable and efficient on-chain data management in blockchain for large biomedical data
Ni E, Knight E, Gerstein M. Scalable and efficient on-chain data management in blockchain for large biomedical data. Journal Of Biomedical Informatics 2025, 165: 104818. PMID: 40164439, PMCID: PMC12102614, DOI: 10.1016/j.jbi.2025.104818.Peer-Reviewed Original ResearchConceptsEthereum blockchainOn-chainOn-chain storageEthereum Virtual MachineHealth data managementLow gas costsBiomedical image dataAmount of dataTrustless environmentVirtual machinesBaseline methodsSolidity compilerBiomedical datasetsBlockchain technologyRetrieval speedDatabase sizeStorage usagePoor scalabilityData insertionBlockchainBiomedical dataData managementData typesEthereumPractical case studyA Discard-and-Restart MD algorithm for the sampling of protein intermediate states
Ianeselli A, Howard J, Gerstein M. A Discard-and-Restart MD algorithm for the sampling of protein intermediate states. Biophysical Journal 2025 PMID: 40156184, DOI: 10.1016/j.bpj.2025.03.024.Peer-Reviewed Original ResearchMD simulationsComputational structure-based drug discoveryMolecular dynamicsStructure-based drug discoveryAI-based analysisFolding pathwayIntermediate statePrion protein PrPAlgorithmFlexible fashionConformational landscapeMD algorithmPotential binding pocketDruggable sitesBinding pocketMicrotubule severingDrug discoveryProtein PrPFolding intermediatesPartial unfoldingProtein statesA-tubulinMaxwell-Boltzmann distributionSimulation timeTarget stateIgniting Language Intelligence: The Hitchhiker’s Guide from Chain-of-Thought Reasoning to Language Agents
Zhang Z, Yao Y, Zhang A, Tang X, Ma X, He Z, Wang Y, Gerstein M, Wang R, Liu G, Zhao H. Igniting Language Intelligence: The Hitchhiker’s Guide from Chain-of-Thought Reasoning to Language Agents. ACM Computing Surveys 2025, 57: 1-39. DOI: 10.1145/3719341.Peer-Reviewed Original ResearchLanguage agentsComplex reasoning tasksReasoning capabilitiesReasoning methodologyLanguage modelCOTS techniquesReasoning approachReasoning tasksTheoretical proofLanguage instructionLinguistic contextEmpirical performanceLanguage intelligenceReasoning performanceHitchhiker’s GuideLanguageSurvey articleEnhance interpretationAdvanced cognitive abilitiesCOTSResearch dimensionsExecutive actionProspective research avenuesCognitive abilitiesCOTS approachUncertainty abounds, what now?
Greenbaum D, Gerstein M. Uncertainty abounds, what now? Science 2025, 387: 1261-1261. DOI: 10.1126/science.adv8256.Peer-Reviewed Original ResearchThe human and non-human primate developmental GTEx projects
Bell T, Blanchard T, Hernandez R, Linn R, Taylor D, VonDran M, Ahooyi T, Beitra D, Bernieh A, Delaney M, Faith M, Fattahi E, Footer D, Gilbert M, Guambaña S, Gulino S, Hanson J, Hattrell E, Heinemann C, Kreeb J, Leino D, Mcdevitt L, Palmieri A, Pfeiffer M, Pryhuber G, Rossi C, Rasool I, Roberts R, Salehi A, Savannah E, Stachowicz K, Stokes D, Suplee L, Van Hoose P, Wilkins B, Williams-Taylor S, Zhang S, Ardlie K, Getz G, Lappalainen T, Montgomery S, Aguet F, Anderson L, Bernstein B, Choudhary A, Domenech L, Gaskell E, Johnson M, Liu Q, Marderstein A, Nedzel J, Okonda J, Padhi E, Rosano M, Russell A, Walker B, Sestan N, Gerstein M, Milosavljevic A, Borsari B, Cho H, Clarke D, Deveau A, Galeev T, Gobeske K, Hameed I, Huttner A, Jensen M, Jiang Y, Li J, Liu J, Liu Y, Ma J, Mane S, Meng R, Nadkarni A, Ni P, Park S, Petrosyan V, Pochareddy S, Salamon I, Xia Y, Yates C, Zhang M, Zhao H, Conrad D, Feng G, Brady F, Boucher M, Carbone L, Castro J, del Rosario R, Held M, Hennebold J, Lacey A, Lewis A, Lima A, Mahyari E, Moore S, Okhovat M, Roberts V, de Castro S, Wessel B, Zaniewski H, Zhang Q, Arguello A, Baroch J, Dayal J, Felsenfeld A, Ilekis J, Jose S, Lockhart N, Miller D, Minear M, Parisi M, Price A, Ramos E, Zou S. The human and non-human primate developmental GTEx projects. Nature 2025, 637: 557-564. PMID: 39815096, PMCID: PMC12013525, DOI: 10.1038/s41586-024-08244-9.Peer-Reviewed Original ResearchConceptsChromatin accessibility dataFunctional genomic studiesWhole-genome sequencingEffects of genetic variationSpatial gene expression profilesNon-human primatesGenotype-Tissue ExpressionGene expression profilesGenomic studiesGene regulationGenetic dataGenetic variationGenomic researchDonor diversityCommunity engagementHuman evolutionEarly developmental defectsGene expressionCell statesDevelopmental programmeHuman diseasesExpression profilesAdult tissuesDevelopmental defectsSingle-cellHidden human costs of AI
Greenbaum D, Gerstein M. Hidden human costs of AI. Science 2025, 387: 32-32. DOI: 10.1126/science.adu1541.Peer-Reviewed Original Research
2024
Digital phenotyping from wearables using AI characterizes psychiatric disorders and identifies genetic associations
Liu J, Borsari B, Li Y, Liu S, Gao Y, Xin X, Lou S, Jensen M, Garrido-Martín D, Verplaetse T, Ash G, Zhang J, Girgenti M, Roberts W, Gerstein M. Digital phenotyping from wearables using AI characterizes psychiatric disorders and identifies genetic associations. Cell 2024, 188: 515-529.e15. PMID: 39706190, PMCID: PMC12278733, DOI: 10.1016/j.cell.2024.11.012.Peer-Reviewed Original ResearchGenome-wide association studiesCase-control genome-wide association studyMultivariate genome-wide association studyGenetic lociAssociation studiesGenetic dataGenetic associationPhenotypeGeneticsEnvironmental factorsDetection powerELFN1Adolescent Brain Cognitive DevelopmentLociGenesPsychiatric disordersADORA3Digital phenotypingAn integrative TAD catalog in lymphoblastoid cell lines discloses the functional impact of deletions and insertions in human genomes
Li C, Bonder M, Syed S, Jensen M, Consortium H, Group H, Gerstein M, Zody M, Chaisson M, Talkowski M, Marschall T, Korbel J, Eichler E, Lee C, Shi X. An integrative TAD catalog in lymphoblastoid cell lines discloses the functional impact of deletions and insertions in human genomes. Genome Research 2024, 34: 2304-2318. PMID: 39638559, PMCID: PMC11694747, DOI: 10.1101/gr.279419.124.Peer-Reviewed Original ResearchConceptsTopologically associating domainsTopologically associating domains boundariesImpact of structural variantsLymphoblastoid cell linesStructural variantsHuman genomeGene regulationAdjacent TADsHuman lymphoblastoid cell linesCell linesSub-TADGenomic structureInsulate genesChromatin architectureImpact of deletionChromatin structureGenomeAberrant regulationAnalysis pipelineMammalian speciesGenesCCREsFunctional impactChromatinRegulationDeep learning analysis of fMRI data for predicting Alzheimer’s Disease: A focus on convolutional neural networks and model interpretability
Zhou X, Kedia S, Meng R, Gerstein M. Deep learning analysis of fMRI data for predicting Alzheimer’s Disease: A focus on convolutional neural networks and model interpretability. PLOS ONE 2024, 19: e0312848. PMID: 39630834, PMCID: PMC11616848, DOI: 10.1371/journal.pone.0312848.Peer-Reviewed Original ResearchConceptsConvolutional neural networkNeural networkAlzheimer's diseaseConvolutional neural network modelMultimodal medical datasetsDeep learning methodsPotential of deep learningGenetic risk factorsMedical datasetsAlzheimer's Disease Neuroimaging InitiativeAD predictionDeep learningDeep learning analysisLearning methodsMedical imagesPredicting Alzheimer's diseaseDetection of Alzheimer's diseaseModel interpretationEarly detection of Alzheimer's diseaseAccuracy levelGenetic factorsDatasetEarly detection of ADNetworkDetection of ADImproved Prediction of Ligand–Protein Binding Affinities by Meta-modeling
Lee H, Emani P, Gerstein M. Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling. Journal Of Chemical Information And Modeling 2024, 64: 8684-8704. PMID: 39576762, PMCID: PMC11632770, DOI: 10.1021/acs.jcim.4c01116.Peer-Reviewed Original ResearchBinding affinity predictionAffinity predictionMeta-modelMeta-modeling approachLigand-protein binding affinityState-of-the-art deep learning toolsState-of-the-artBinding affinityDeep learning modelsDeep learning toolsMolecular descriptorsInclusion of featuresVirtual screeningBase modelDatabase scalabilityGeneralization capabilityDiverse modeling approachesTraining databaseApplication benchmarksDrug ligandsLearning modelsLigandPhysicochemical propertiesLearning toolsDevelopment efforts
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply