2024
CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation
Liu C, Amodio M, Shen L, Gao F, Avesta A, Aneja S, Wang J, Del Priore L, Krishnaswamy S. CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation. Lecture Notes In Computer Science 2024, 15008: 155-165. DOI: 10.1007/978-3-031-72111-3_15.Peer-Reviewed Original ResearchMedical image segmentationImage segmentationLack of labeled dataUnsupervised deep learning frameworkSegmenting medical imagesDeep learning frameworkBrain MRI imagesRetinal fundus imagesContrastive learningLearning frameworkUnsupervised methodDeep learningExpert annotationsData topologyMedical imagesGranularity levelsEmbedding mapHausdorff distanceFundus imagesDice coefficientImage dataEmbeddingAnnotationLearningMRI imagesSingle-cell analysis reveals transcriptional dynamics in healthy primary parathyroid tissue.
Venkat A, Carlino M, Lawton B, Prasad M, Amodio M, Gibson C, Zeiss C, Youlten S, Krishnaswamy S, Krause D. Single-cell analysis reveals transcriptional dynamics in healthy primary parathyroid tissue. Genome Research 2024, 34: 837-850. PMID: 38977309, PMCID: PMC11293540, DOI: 10.1101/gr.278215.123.Peer-Reviewed Original ResearchCell statesMitochondrial transcript abundanceParathyroid glandsHuman parathyroidCell-cell communication analysisRNA expression analysisSingle-cell analysisTranscriptional dynamicsTranscript abundanceExpression dynamicsRNA transcriptomeEpithelial cell statesCell abundanceExpression analysisPseudotime analysisStrokeClassifier: ischemic stroke etiology classification by ensemble consensus modeling using electronic health records
Lee H, Schwamm L, Sansing L, Kamel H, de Havenon A, Turner A, Sheth K, Krishnaswamy S, Brandt C, Zhao H, Krumholz H, Sharma R. StrokeClassifier: ischemic stroke etiology classification by ensemble consensus modeling using electronic health records. Npj Digital Medicine 2024, 7: 130. PMID: 38760474, PMCID: PMC11101464, DOI: 10.1038/s41746-024-01120-w.Peer-Reviewed Original ResearchElectronic health recordsWeighted F1MIMIC-IIIClinical decision support systemsMulti-class classificationNatural language processingMIMIC-III datasetHealth recordsMachine learning classifiersDecision support systemArtificial intelligence toolsVascular neurologistsLearning classifiersBinary classificationCross-validation accuracyLanguage processingMeta-modelIntelligence toolsStroke prevention effortsAcute ischemic strokeStroke etiologySupport systemStroke etiology classificationClassification toolClassifierInferring Metabolic States from Single Cell Transcriptomic Data via Geometric Deep Learning
Steach H, Viswanath S, He Y, Zhang X, Ivanova N, Hirn M, Perlmutter M, Krishnaswamy S. Inferring Metabolic States from Single Cell Transcriptomic Data via Geometric Deep Learning. Lecture Notes In Computer Science 2024, 14758: 235-252. DOI: 10.1007/978-1-0716-3989-4_15.Peer-Reviewed Original ResearchSingle-cell resolutionMetabolic networksStructure of metabolic networksBiological processesGlobal metabolic networkMetabolic stateMeasure gene expressionGenomic informationTranscriptomic dataTranscriptome dataPost-translationallyEpigenetic modificationsMultimodal regulationGene expressionSingle-cellTissue scaleBiological featuresCellsTranscriptomeMetabolomicsTranscriptionFlux ratesMultiomicsScRNAseqBiologySupervised latent factor modeling isolates cell-type-specific transcriptomic modules that underlie Alzheimer’s disease progression
Hodgson L, Li Y, Iturria-Medina Y, Stratton J, Wolf G, Krishnaswamy S, Bennett D, Bzdok D. Supervised latent factor modeling isolates cell-type-specific transcriptomic modules that underlie Alzheimer’s disease progression. Communications Biology 2024, 7: 591. PMID: 38760483, PMCID: PMC11101463, DOI: 10.1038/s42003-024-06273-8.Peer-Reviewed Original ResearchConceptsGene programAlzheimer's diseaseLate-onset Alzheimer's diseaseAD risk lociCell type-specificSingle-nucleus RNA sequencingRisk lociAD brainAlzheimer's disease progressionSnRNA-seqRNA sequencingAD pathophysiologySignaling cascadesTranscriptome modulationProgressive neurodegenerative diseaseCell-typeGWASNeurodegenerative diseasesNeuronal lossGlial cellsTranscriptomeLociGenesPseudo-trajectoriesDisease progressionGeometric scattering on measure spaces
Chew J, Hirn M, Krishnaswamy S, Needell D, Perlmutter M, Steach H, Viswanath S, Wu H. Geometric scattering on measure spaces. Applied And Computational Harmonic Analysis 2024, 70: 101635. DOI: 10.1016/j.acha.2024.101635.Peer-Reviewed Original ResearchConvolutional neural networkGeometric deep learningDeep learningNeural networkSuccess of convolutional neural networksModel of convolutional neural networkMeasure spaceScattering transformData-driven graphsInvariance propertiesRiemannian manifoldsNon-Euclidean structureUndirected graphWavelet-based transformCompact Riemannian manifoldsData structuresRate of convergenceSpherical imagesNetwork stabilityHigh-dimensional single-cell dataData setsDirected graphDiffusion-mapsSigned graphGraphDirected Scattering for Knowledge Graph-Based Cellular Signaling Analysis
Venkat A, Chew J, Rodriguez F, Tape C, Perlmutter M, Krishnaswamy S. Directed Scattering for Knowledge Graph-Based Cellular Signaling Analysis. 2024, 00: 9761-9765. DOI: 10.1109/icassp48485.2024.10446530.Peer-Reviewed Original ResearchParasympathetic neurons derived from human pluripotent stem cells model human diseases and development
Wu H, Saito-Diaz K, Huang C, McAlpine J, Seo D, Magruder D, Ishan M, Bergeron H, Delaney W, Santori F, Krishnaswamy S, Hart G, Chen Y, Hogan R, Liu H, Ivanova N, Zeltner N. Parasympathetic neurons derived from human pluripotent stem cells model human diseases and development. Cell Stem Cell 2024, 31: 734-753.e8. PMID: 38608707, PMCID: PMC11069445, DOI: 10.1016/j.stem.2024.03.011.Peer-Reviewed Original ResearchConceptsAutonomic nervous systemSjogren's syndromeParasympathetic neuronsFamilial dysautonomiaWhite adipocytesAutoimmune disease Sjogren's syndromeHuman pluripotent stem cellsHuman pluripotent stem cell (hPSC)-derived neuronsHuman developmental studiesPluripotent stem cellsSARS-CoV-2 infectionSchwann cell progenitorsAutonomic neuropathyCell progenitorsStem cellsModel systemNervous systemSARS-CoV-2Human diseasesDysfunctionNeuronsDifferentiation paradigmOrgan developmentNeuropathyDrug discovery studiesLearnable Filters for Geometric Scattering Modules
Tong A, Wenkel F, Bhaskar D, Macdonald K, Grady J, Perlmutter M, Krishnaswamy S, Wolf G. Learnable Filters for Geometric Scattering Modules. IEEE Transactions On Signal Processing 2024, 72: 2939-2952. DOI: 10.1109/tsp.2024.3378001.Peer-Reviewed Original ResearchGraph neural networksGraph classification benchmarksEncode graph structureData exploration tasksGeometric scattering transformGraph wavelet filtersClassification benchmarksLearned representationsLearnable filtersLearning parametersGraph structureNeural networkExploration tasksWavelet filtersBand-pass featureBiochemical domainNetworkAdaptive tuningWaveletGraphPredictive performanceScattering modulationScattering transformMathematical propertiesFilterAssessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy
Liao D, Liu C, Christensen B, Tong A, Huguet G, Wolf G, Nickel M, Adelstein I, Krishnaswamy S. Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy. 2024, 00: 1-6. DOI: 10.1109/ciss59072.2024.10480166.Peer-Reviewed Original ResearchMutual information neural estimatorMutual informationHigh-dimensional simulation dataHigh-dimensional dataNeural network representationSpectral entropyCIFAR-10Information-theoretic measuresClass labelsSTL-10Classification networkNeural representationSelf-supervisionSupervised learningIntrinsic dimensionalityClassification accuracyNeural networkAmbient dimensionNoise-resilientNeural estimatorNetwork initializationData geometryNetwork representationOverfittingNetworkBayesian Spectral Graph Denoising with Smoothness Prior
Leone S, Sun X, Perlmutter M, Krishnaswamy S. Bayesian Spectral Graph Denoising with Smoothness Prior. 2024, 00: 1-6. DOI: 10.1109/ciss59072.2024.10480177.Peer-Reviewed Original ResearchPresence of noisy dataGraph signal processingMaximum A PosterioriAffinity graphDenoised featuresGaussian noiseNoisy dataHigh-dimensionalComplex dataAlgorithm's abilityA-posterioriModel of noise generationSmoothness priorsRestored signalDistributed noiseSignal processingAlgorithmImage dataGraphFrequency domainNoiseNoise generationDenoisingWhite noiseSmoothingCorrection: Cell cycle controls long-range calcium signaling in the regenerating epidermis
Moore J, Bhaskar D, Gao F, Matte-Martone C, Du S, Lathrop E, Ganesan S, Shao L, Norris R, Sanz N, Annusver K, Kasper M, Cox A, Hendry C, Rieck B, Krishnaswamy S, Greco V. Correction: Cell cycle controls long-range calcium signaling in the regenerating epidermis. Journal Of Cell Biology 2024, 223: e20230209503052024c. PMID: 38477880, PMCID: PMC10938063, DOI: 10.1083/jcb.20230209503052024c.Peer-Reviewed Original ResearchStem cell migration drives lung repair in living mice
Chioccioli M, Liu S, Magruder S, Tata A, Borriello L, McDonough J, Konkimalla A, Kim S, Nouws J, Gonzalez D, Traub B, Ye X, Yang T, Entenberg D, Krishnaswamy S, Hendry C, Kaminski N, Tata P, Sauler M. Stem cell migration drives lung repair in living mice. Developmental Cell 2024, 59: 830-840.e4. PMID: 38377991, PMCID: PMC11003834, DOI: 10.1016/j.devcel.2024.02.003.Peer-Reviewed Original ResearchStem cell migrationCell migrationAlveolar type 2 cellsAlveolar unitsStem cell motilityAlveolar type 1 cellsStem cell activityCellular response to injuryResponse to injuryType 2 cellsMotile phenotypeType 1 cellsCell motilityLung repairImpaired regenerationGenetic depletionCell activationAT2Stem cellsTissue repairAT1Longitudinal imagingInjuryMotilityCellular resolution
2023
Trellis tree-based analysis reveals stromal regulation of patient-derived organoid drug responses
Ramos Zapatero M, Tong A, Opzoomer J, O'Sullivan R, Cardoso Rodriguez F, Sufi J, Vlckova P, Nattress C, Qin X, Claus J, Hochhauser D, Krishnaswamy S, Tape C. Trellis tree-based analysis reveals stromal regulation of patient-derived organoid drug responses. Cell 2023, 186: 5606-5619.e24. PMID: 38065081, DOI: 10.1016/j.cell.2023.11.005.Peer-Reviewed Original ResearchWire Before You Walk
Asmara T, Bhaskar D, Adelstein I, Krishnaswamy S, Perlmutter M. Wire Before You Walk. 2023, 00: 714-716. DOI: 10.1109/ieeeconf59524.2023.10477089.Peer-Reviewed Original ResearchGraph Fourier MMD for Signals on Graphs
Leone S, Venkat A, Huguet G, Tong A, Wolf G, Krishnaswamy S. Graph Fourier MMD for Signals on Graphs. 2023, 00: 1-6. DOI: 10.1109/sampta59647.2023.10301384.Peer-Reviewed Original ResearchState-space characterizationEmbedding of distributionsRNA-sequencing data analysisSingle-cell RNA-sequencing data analysisMeaningful gene clustersPairs of distributionsOptimization problemProbability distributionGene clusterEuclidean spaceSpace characterizationAnalytical solutionSuch graphsGene embeddingsDisconnected graphsScale invarianceGene selectionGraphSuch distancesEmbeddingGenesNovel typeDistributionNumerous methodsBenchmark datasetsPD-1 maintains CD8 T cell tolerance towards cutaneous neoantigens
Damo M, Hornick N, Venkat A, William I, Clulo K, Venkatesan S, He J, Fagerberg E, Loza J, Kwok D, Tal A, Buck J, Cui C, Singh J, Damsky W, Leventhal J, Krishnaswamy S, Joshi N. PD-1 maintains CD8 T cell tolerance towards cutaneous neoantigens. Nature 2023, 619: 151-159. PMID: 37344588, PMCID: PMC10989189, DOI: 10.1038/s41586-023-06217-y.Peer-Reviewed Original ResearchConceptsEffector CD8 T cellsCD8 T cellsAntigen-specific effector CD8 T cellsAntigen-specific CD8 T cellsAntigen-expressing cellsT cell tolerancePD-1T cellsAdverse eventsCell toleranceCD8 T cell toleranceImmune-related adverse eventsPeripheral T cell repertoirePeripheral T cell toleranceNon-lesional skinT cell repertoireT-cell antigensPeripheral toleranceCheckpoint receptorsSkin biopsiesLocal infiltrationLocal pathologyCell repertoireMouse modelSkin toleranceMultiscale geometric and topological analyses for characterizing and predicting immune responses from single cell data
Venkat A, Bhaskar D, Krishnaswamy S. Multiscale geometric and topological analyses for characterizing and predicting immune responses from single cell data. Trends In Immunology 2023, 44: 551-563. PMID: 37301677, DOI: 10.1016/j.it.2023.05.003.Peer-Reviewed Original ResearchHSV-2 triggers upregulation of MALAT1 in CD4+ T cells and promotes HIV latency reversal
Pierce C, Loh L, Steach H, Cheshenko N, Preston-Hurlburt P, Zhang F, Stransky S, Kravets L, Sidoli S, Philbrick W, Nassar M, Krishnaswamy S, Herold K, Herold B. HSV-2 triggers upregulation of MALAT1 in CD4+ T cells and promotes HIV latency reversal. Journal Of Clinical Investigation 2023, 133: e164317. PMID: 37079384, PMCID: PMC10232005, DOI: 10.1172/jci164317.Peer-Reviewed Original ResearchConceptsHIV-1 reactivationHIV latency reversalT cellsLatency reversalHuman CD4HIV-1 viral loadHIV-1 restriction factorsHSV-2 recurrencesHSV-2 infectionHIV-1 latencyUpregulation of MALAT1Primary human CD4HSV-2 proteinsViral loadHIV replicationPeripheral bloodMALAT1 expressionHSV-2Tissue reservoirsCD4Viral replicationExpression of transcriptsBystander cellsRestriction factorsMALAT1Time-Inhomogeneous Diffusion Geometry and Topology
Huguet G, Tong A, Rieck B, Huang J, Kuchroo M, Hirn M, Wolf G, Krishnaswamy S. Time-Inhomogeneous Diffusion Geometry and Topology. SIAM Journal On Mathematics Of Data Science 2023, 5: 346-372. DOI: 10.1137/21m1462945.Peer-Reviewed Original Research