Zhangsheng Yu
Professor Adjunct of BiostatisticsCards
About
Research
Publications
2024
Mediation analysis in longitudinal study with high-dimensional methylation mediators
Cui Y, Lin Q, Yuan X, Jiang F, Ma S, Yu Z. Mediation analysis in longitudinal study with high-dimensional methylation mediators. Briefings In Bioinformatics 2024, 25: bbae496. PMID: 39406521, PMCID: PMC11479716, DOI: 10.1093/bib/bbae496.Peer-Reviewed Original ResearchConceptsBody mass indexMediation analysisPaternal body mass indexGeneralized estimating equationsLinear mixed-effects modelsCohort dataMass indexMixed-effects modelsDNA methylation sitesHigh-dimensional mediation analysisLongitudinal studyBonferroni correctionAccurate parameter estimatesSobel testVariable selectionLongitudinal dataSimulation studyIndependence screeningMethylation sitesCpG sitesIndirect effectsParameter estimationLinearization methodHypothesis testingCT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy
Xia Y, Zhou J, Xun X, Zhang J, Wei T, Gao R, Reddy B, Liu C, Kim G, Yu Z. CT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy. Insights Into Imaging 2024, 15: 214. PMID: 39186192, PMCID: PMC11347550, DOI: 10.1186/s13244-024-01784-8.Peer-Reviewed Original ResearchConvolutional-recurrent neural networkAdvanced hepatocellular carcinomaSpatial-temporal informationHepatocellular carcinomaCT scanOverall survival predictionRECIST criteriaClinical variablesPatients treated with immunotherapyExtract spatial-temporal informationFollow-up CT imagesPrognostic modelAdvanced HCC patientsRisk group stratificationDeep learning-based modelTest setDisease statusMethodsThis retrospective studyLog-rank testMultimodal deep learningMulti-modal inputsSurvival predictionDeep learning modelsAnalysis of CT scansPatient's disease statusHEARTSVG: a fast and accurate method for identifying spatially variable genes in large-scale spatial transcriptomics
Yuan X, Ma Y, Gao R, Cui S, Wang Y, Fa B, Ma S, Wei T, Ma S, Yu Z. HEARTSVG: a fast and accurate method for identifying spatially variable genes in large-scale spatial transcriptomics. Nature Communications 2024, 15: 5700. PMID: 38972896, PMCID: PMC11228050, DOI: 10.1038/s41467-024-49846-1.Peer-Reviewed Original ResearchConceptsSpatially variable genesVariable genesSpatial expression patternsSpatial transcriptomics technologiesSpatial transcriptomics researchTranscriptome researchTranscriptomic technologiesBiological functionsExpression patternsSpatial transcriptomicsGenesState-of-the-art methodsColorectal cancer dataIssues and Solutions in Psychiatric Clinical Trial with Case Studies
Chen X, Chen J, Zhao X, Mu R, Tan H, Yu Z. Issues and Solutions in Psychiatric Clinical Trial with Case Studies. Neuropsychiatric Disease And Treatment 2024, 20: 1191-1200. PMID: 38855383, PMCID: PMC11162181, DOI: 10.2147/ndt.s454813.Peer-Reviewed Original ResearchMental disordersFeatures of mental disordersPsychiatric clinical trialsTreat mental disordersMental health servicesAnxiety disordersSymptom presentationLongitudinal designRating ScaleDiverse sampleDisorder progressionResearch criteriaMental diseasesClinical interventionsDependability of findingsHistory gatheringDisordersClinical researchHealth servicesPsychotherapyDiagnosing mental diseaseSample representativePsychiatricAnxietyPsychiatristsDeep Learning-Based Detect-Then-Track Pipeline for Treatment Outcome Assessments in Immunotherapy-Treated Liver Cancer
Zhou J, Xia Y, Xun X, Yu Z. Deep Learning-Based Detect-Then-Track Pipeline for Treatment Outcome Assessments in Immunotherapy-Treated Liver Cancer. Journal Of Digital Imaging 2024, 1-14. PMID: 38740661, DOI: 10.1007/s10278-024-01132-8.Peer-Reviewed Original ResearchHarnessing TME depicted by histological images to improve cancer prognosis through a deep learning system
Gao R, Yuan X, Ma Y, Wei T, Johnston L, Shao Y, Lv W, Zhu T, Zhang Y, Zheng J, Chen G, Sun J, Wang Y, Yu Z. Harnessing TME depicted by histological images to improve cancer prognosis through a deep learning system. Cell Reports Medicine 2024, 5: 101536. PMID: 38697103, PMCID: PMC11149411, DOI: 10.1016/j.xcrm.2024.101536.Peer-Reviewed Original ResearchColorectal cancer cohortTumor microenvironmentCancer prognosisCancer cohortCancer Genome Atlas-Breast CancerAssociated with cancer prognosisImprove cancer prognosisPrognosis prediction modelBreast cancerConcordance indexClinical availabilitySurvival modelsSpatial transcriptomicsST expressionCancer typesPrognosisCancerSurvivalHistological imagesSingle-cell biclustering for cell-specific transcriptomic perturbation detection in AD progression
Gong Y, Xu J, Wu M, Gao R, Sun J, Yu Z, Zhang Y. Single-cell biclustering for cell-specific transcriptomic perturbation detection in AD progression. Cell Reports Methods 2024, 4: 100742. PMID: 38554701, PMCID: PMC11045878, DOI: 10.1016/j.crmeth.2024.100742.Peer-Reviewed Original ResearchConceptsSnRNA-seq dataGene modulesAD progressionPathogenesis of Alzheimer's diseaseBiologically interpretable resultsSingle-cell data analysisGene regulatory changesFunctional gene modulesGene coexpression patternsAlzheimer's diseaseSingle-cell levelSnRNA-seqBiclustering methodsPolygenic diseaseBatch effectsDropout eventsCoexpression patternsNetwork biomarkersCell typesBiclusteringCellsGenesScRNABiologyComparative analysisPredicting long-term progression of Alzheimer’s disease using a multimodal deep learning model incorporating interaction effects
Wang Y, Gao R, Wei T, Johnston L, Yuan X, Zhang Y, Yu Z. Predicting long-term progression of Alzheimer’s disease using a multimodal deep learning model incorporating interaction effects. Journal Of Translational Medicine 2024, 22: 265. PMID: 38468358, PMCID: PMC10926590, DOI: 10.1186/s12967-024-05025-w.Peer-Reviewed Original ResearchConceptsAlzheimer's diseaseGenetic polymorphism dataProgression of Alzheimer's diseaseMild cognitive impairmentPolymorphism dataAlzheimer's Disease Neuroimaging InitiativeAD progressionArea under the receiver operating characteristic curvePrediction of AD progressionDeep learning modelsADNI-1AlzheimerPatient careLearning modelsMCI to ADInteraction effectsADNI-3Increase prediction accuracyMild cognitive impairment to ADEarly interventionCognitive impairmentClinical assessmentBayesian network-based Mendelian randomization for variant prioritization and phenotypic causal inference
Sun J, Zhou J, Gong Y, Pang C, Ma Y, Zhao J, Yu Z, Zhang Y. Bayesian network-based Mendelian randomization for variant prioritization and phenotypic causal inference. Human Genetics 2024, 1-14. PMID: 38381161, DOI: 10.1007/s00439-024-02640-x.Peer-Reviewed Original ResearchMendelian randomizationGenetic instrumental variablesGenomic dataIndividual-level dataInstrumental variablesUK BiobankFalse-positive discoveriesGenetic structureVariant prioritizationEffect estimatesMR methodsGene interactionsGenetic variantsCausal inferencePsychiatric disordersStatistical powerBlood pressureBayesian frameworkInference frameworkInferenceBiobankEstimationCausal relationshipsPleiotropyGenesA generalized calibrated Bayesian hierarchical modeling approach to basket trials with multiple endpoints
Chi X, Yuan Y, Yu Z, Lin R. A generalized calibrated Bayesian hierarchical modeling approach to basket trials with multiple endpoints. Biometrical Journal 2024, 66: e2300122. PMID: 38368277, PMCID: PMC11323483, DOI: 10.1002/bimj.202300122.Peer-Reviewed Original ResearchConceptsBayesian hierarchical modeling approachShrinkage parameterTheoretical propertiesPhase II basket trialBasket trialsSimulation studyHierarchical modelHierarchical modeling approachFunctional formGeneral hierarchical modelEfficacy endpointLatent variable approachApproach yieldsRisk-benefit profileVariable approachImmunotherapy agentsTumor responseGeneralizationTargeted therapyCancer subtypesMultiple cancer subtypesTreatment effectsMonitoring procedures