2025
Network-based modeling of emotional expressions for multiple cancers via a linguistic analysis of an online health community
Fan X, Liu M, Ma S. Network-based modeling of emotional expressions for multiple cancers via a linguistic analysis of an online health community. The Annals Of Applied Statistics 2025, 19: 2218-2236. DOI: 10.1214/25-aoas2047.Peer-Reviewed Original ResearchOnline health communitiesNetwork-based modelModel of emotional expressionsLow-rank matrixAmerican Cancer Society Cancer Survivors NetworkHealth communityFear of judgmentSemantic networkNetwork analysis techniquesComputational propertiesSurvivors NetworkSimulation resultsNetworkAdverse emotionsLinguistic analysisCluster structureSingle diseaseCancer patientsPenalization approachCancer typesEmotional expressionCancerAnalysis techniquesComputerData analysisGE-IA-NAM: gene–environment interaction analysis via imaging-assisted neural additive model
Li J, Xu Y, Ma S, Fang K. GE-IA-NAM: gene–environment interaction analysis via imaging-assisted neural additive model. Bioinformatics 2025, 41: btaf481. PMID: 40880282, PMCID: PMC12452269, DOI: 10.1093/bioinformatics/btaf481.Peer-Reviewed Original ResearchConceptsGene-environmentNeural additive modelsGene-environment modelGene-environment analysisGene-environment interaction analysisEnvironmental factorsCancer Genome AtlasPathological imagesSkin cancer datasetGenome AtlasCancer datasetsNetwork architectureCompetitive performanceGenetic factorsPython codeCancer outcomesInteraction analysisData patternsCancer researchAdditive modelInteraction methodEnvironmental dataJoint analysisCancer modelsRegression-basedSubgroup Testing in the Change‐Plane Cox Model
Zhang X, Ren P, Shi X, Ma S, Liu X. Subgroup Testing in the Change‐Plane Cox Model. Statistics In Medicine 2025, 44: e70179. PMID: 40662752, DOI: 10.1002/sim.70179.Peer-Reviewed Original ResearchConceptsFinite sample performanceAnalysis of survival dataLikelihood ratio testAsymptotic distributionSample performanceLung cancer dataScore testSimulation studyRatio testSurvival dataCancer dataCox modelImmune checkpoint blockade therapyCheckpoint blockade therapySolid tumor patientsTumor mutational burdenSubgroup testsTreatment effectsCovariatesBlockade therapyMutational burdenSubgroupsRobust Transfer Learning for High‐Dimensional GLM Using γ$$ \gamma $$‐Divergence With Applications to Cancer Genomics
Xu F, Ma S, Zhang Q, Xu Y. Robust Transfer Learning for High‐Dimensional GLM Using γ$$ \gamma $$‐Divergence With Applications to Cancer Genomics. Statistics In Medicine 2025, 44: e70170. PMID: 40662636, PMCID: PMC12313224, DOI: 10.1002/sim.70170.Peer-Reviewed Original ResearchConceptsTransfer learningReal world biomedical dataRisk of negative transferProximal gradient descentTransfer learning methodTransfer learning approachHigh-dimensional dataHigh-dimensional settingsGradient descentCompetitive performanceLearning methodsEstimation error boundsBiomedical dataEfficient algorithmLearning approachDetection schemeNegative transferAnalysis of complex diseasesDebiasing stepMethod's effectivenessCancer genomic dataData contaminationError boundsHigh-dimensional profiling dataOutliersJoint modeling of mixed outcomes using a rank-based sparse neural network
Xue J, Xu Y, Li J, Ma S, Fang K. Joint modeling of mixed outcomes using a rank-based sparse neural network. Journal Of Biomedical Informatics 2025, 169: 104870. PMID: 40623577, PMCID: PMC12306493, DOI: 10.1016/j.jbi.2025.104870.Peer-Reviewed Original ResearchSparse neural networksNeural networkCompetitive performanceImbalance issueLoss functionSparse layerLeverage informationPrediction accuracyTraditional methodsNetworkParametric frameworkPenalization methodFaces challengesJoint modelPrediction modelInformationSkin cutaneous melanomaHigh-throughput profilingHigh-dimensional covariatesDimensionalityGenomic researchFeaturesMethodSimulation studyBiomedical studiesSubgroup Analysis of Differential Networks with Latent Variables
Li L, Ma S, Zhang Q. Subgroup Analysis of Differential Networks with Latent Variables. Statistics And Computing 2025, 35: 140. DOI: 10.1007/s11222-025-10681-z.Peer-Reviewed Original ResearchLow-rank structureSubgroup networksBaseline networkCompetitive performanceDifferential networksReal-world observational dataLatent variablesEfficient computational algorithmNetworkSparsityHeterogeneity analysis methodComputational algorithmInfluence of latent variablesDense networkSubgroup structureStatistical propertiesAlgorithmNetwork analysisSimulation studyMethodAnalysis methodDifferential network analysisRobust sparse Bayesian regression for longitudinal gene–environment interactions
Fan K, Jiang Y, Ma S, Wang W, Wu C. Robust sparse Bayesian regression for longitudinal gene–environment interactions. Journal Of The Royal Statistical Society Series C (Applied Statistics) 2025, qlaf027. DOI: 10.1093/jrsssc/qlaf027.Peer-Reviewed Original ResearchCancer Prevention StudyGene-environment interactionsVariable selectionSpike-and-slab priorsGene-environmentIntra-cluster correlationBayesian variable selectionPrevention StudyMeasured body weightMeasures analysisLongitudinal studyPosterior inferenceGibbs samplerMCMC algorithmInteraction effectsStructured sparsityMixed modelsGenetic factorsExtensive simulationsFast computationPhenotypic measurementsInter-relatednessLongitudinal observationsANOVAInteraction problemsHeterogeneous network analysis of disease clinical treatment measures via mining electronic medical record data
Wang J, Li R, Chang W, Hsiao K, Shia B, Ma S. Heterogeneous network analysis of disease clinical treatment measures via mining electronic medical record data. The Annals Of Applied Statistics 2025, 19 DOI: 10.1214/24-aoas1976.Peer-Reviewed Original ResearchLocal Clustering for Functional Data
Chen Y, Zhang Q, Ma S. Local Clustering for Functional Data. Journal Of Computational And Graphical Statistics 2025, 34: 1075-1090. DOI: 10.1080/10618600.2024.2431057.Peer-Reviewed Original ResearchA Selective Review of Network Analysis Methods for Gene Expression Data
Li R, Yi H, Ma S. A Selective Review of Network Analysis Methods for Gene Expression Data. Methods In Molecular Biology 2025, 2880: 293-307. PMID: 39900765, DOI: 10.1007/978-1-0716-4276-4_14.Peer-Reviewed Original ResearchConceptsGene expression dataGene expression networksExpression dataDownstream analysisExpression networksGene expressionBiological processesGenesMolecular mechanismsBiological implicationsHigh-throughput profiling techniquesBiological findingsGlobal viewComplex interactionsProfiling techniquesRegulationHierarchical Multi‐Label Classification With Gene‐Environment Interactions in Disease Modeling
Li J, Zhang Q, Ma S, Fang K, Xu Y. Hierarchical Multi‐Label Classification With Gene‐Environment Interactions in Disease Modeling. Statistics In Medicine 2025, 44: e10330. PMID: 39865593, PMCID: PMC12201914, DOI: 10.1002/sim.10330.Peer-Reviewed Original ResearchConceptsHierarchical multi-label classificationMulti-label classificationGene-environment interaction analysisGene-environmentEfficient expectation-maximizationGene-environment interactionsSemi-supervised scenariosCancer Genome AtlasUnlabeled dataInteraction analysisExpectation-maximizationGenome AtlasSuperior performanceHierarchical responseDisease outcomeClassificationPenalized estimatorsPractice settingsDisease modelsBiomedical studiesAnalysis literatureE effectsBayesian Modeling of Cancer Outcomes Using Genetic Variables Assisted by Pathological Imaging Data
Im Y, Li R, Ma S. Bayesian Modeling of Cancer Outcomes Using Genetic Variables Assisted by Pathological Imaging Data. Statistics In Medicine 2025, 44: e10350. PMID: 39840672, PMCID: PMC11774474, DOI: 10.1002/sim.10350.Peer-Reviewed Original ResearchIntegrative rank-based regression for multi-source high-dimensional data with multi-type responses
Xu F, Ma S, Zhang Q. Integrative rank-based regression for multi-source high-dimensional data with multi-type responses. Journal Of Applied Statistics 2025, 52: 2011-2030. PMID: 40904949, PMCID: PMC12404076, DOI: 10.1080/02664763.2025.2452964.Peer-Reviewed Original Research
2024
Statistical Methods for Accommodating Immortal Time: A Selective Review and Comparison
Wang J, Peduzzi P, Wininger M, Ma S. Statistical Methods for Accommodating Immortal Time: A Selective Review and Comparison. 2024, 53-92. DOI: 10.1007/978-3-031-65937-9_3.Peer-Reviewed Original ResearchIntegrative factor-adjusted sparse generalized linear models
Xu F, Ma S, Zhang Q. Integrative factor-adjusted sparse generalized linear models. Journal Of Statistical Computation And Simulation 2024, 95: 764-780. DOI: 10.1080/00949655.2024.2439450.Peer-Reviewed Original ResearchVariable selection consistencyHigh-dimensional dataIncreased accessibility of dataSelection consistencyConsistency propertiesCorrelated covariatesGeneralized linear modelVariable selectionAnalysis of genetic dataAccessibility of dataIdiosyncratic componentsCompetitive performanceCovariatesGenetic dataLinear modelSample sizeImprove model performanceEstimationIntegrated analysisModel estimatesLatent factorsModel performancePractical useConsistencyThe spike‐and‐slab quantile LASSO for robust variable selection in cancer genomics studies
Liu Y, Ren J, Ma S, Wu C. The spike‐and‐slab quantile LASSO for robust variable selection in cancer genomics studies. Statistics In Medicine 2024, 43: 4928-4983. PMID: 39260448, PMCID: PMC11585335, DOI: 10.1002/sim.10196.Peer-Reviewed Original ResearchAsymmetric Laplace distributionSpike-and-slab LASSORobust variable selection methodHeavy-tailed errorsRobust variable selectionHeavy-tailed distributionsAnalysis of high-dimensional genomic dataHigh-dimensional genomic dataExpectation-maximizationComprehensive simulation studyVariable selection methodsLaplace distributionCoordinate descent frameworkPosterior modeCancer genomics studiesRobust likelihoodVariable selectionSparsity patternSimulation studyComputational advantagesQuantile regressionNonrobust oneSelf-adaptationLoss functionGenomic studiesHigh-Dimensional Gene–Environment Interaction Analysis
Wu M, Li Y, Ma S. High-Dimensional Gene–Environment Interaction Analysis. Annual Review Of Statistics And Its Application 2024, 12: 361-383. PMID: 40881670, PMCID: PMC12383825, DOI: 10.1146/annurev-statistics-112723-034315.Peer-Reviewed Original ResearchFixed- and random-effects analysisG-E interaction analysisG-E interactionsVariable selectionFrequentist analysisGene-environmentRandom effects analysisGeneral frameworkStatistical propertiesProgression of complex diseasesDimension reductionHypothesis testingG-EComplex diseasesGenetic factorsInteraction analysisNonlinear effect analysisStatistical perspectiveDisease outcomeEnvironmental factorsPrediction-basedEstimation-basedIncorporating prior information in gene expression network-based cancer heterogeneity analysis
Li R, Xu S, Li Y, Tang Z, Feng D, Cai J, Ma S. Incorporating prior information in gene expression network-based cancer heterogeneity analysis. Biostatistics 2024, 26: kxae028. PMID: 39074174, DOI: 10.1093/biostatistics/kxae028.Peer-Reviewed Original ResearchCTHRC1+ fibroblasts and SPP1+ macrophages synergistically contribute to pro-tumorigenic tumor microenvironment in pancreatic ductal adenocarcinoma
Li E, Cheung H, Ma S. CTHRC1+ fibroblasts and SPP1+ macrophages synergistically contribute to pro-tumorigenic tumor microenvironment in pancreatic ductal adenocarcinoma. Scientific Reports 2024, 14: 17412. PMID: 39075108, PMCID: PMC11286765, DOI: 10.1038/s41598-024-68109-z.Peer-Reviewed Original ResearchConceptsPancreatic ductal adenocarcinomaTumor-associated macrophagesTumor microenvironmentEpithelial mesenchymal transitionDuctal adenocarcinomaImmune-suppressive tumor microenvironmentPro-tumorigenic tumor microenvironmentPancreatic cancer casesHeterogeneous tumor microenvironmentCombination of single-cellCancer-associated myofibroblastsSurgical resectionMyeloid cellsCurrent therapiesCancer casesLethal cancersSurvival rateExtracellular matrixTreat cancerMesenchymal transitionTherapeutic targetAdenocarcinomaCellular populationsCancerIntercellular interactionsEditorial
Ma S. Editorial. Briefings In Bioinformatics 2024, 25: bbae453. PMID: 39288229, PMCID: PMC11407437, DOI: 10.1093/bib/bbae453.Peer-Reviewed Original Research
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply