Victor Batista
John Gamble Kirkwood Professor of ChemistryCards
About
Research
Publications
2025
Distal Mutations Rewire Allosteric Networks to Control Substrate Specificity in PTP1B
Wang X, Anderson R, Liu J, Batista V, Loria J. Distal Mutations Rewire Allosteric Networks to Control Substrate Specificity in PTP1B. Biochemistry 2025, 64: 4661-4674. PMID: 41292192, DOI: 10.1021/acs.biochem.5c00539.Peer-Reviewed Original ResearchConceptsSubstrate specificityAcidic loopControl substrate specificityRegulation of cellular signaling pathwaysDistal allosteric siteWild-type enzymeCatalytic mechanismAllosteric siteProtein tyrosine phosphataseActive-site dynamicsCellular signaling pathwaysCommunity network analysisAllosteric mutantsProtein tyrosine phosphatase 1BMicrosecond molecular dynamics simulationsSubstrate preferencePhosphotyrosine peptidesAllosteric regulationAllosteric communicationDistal mutationsTyrosine phosphatase 1BTyrosine phosphataseEnzymatic dynamicsSignaling pathwayCatalytic centerAtomistic modulation of MIF‐2 structure, catalysis, and biological signaling via cysteine residues and a small molecule, Ebselen
Widjaja V, D'Orazio S, Das P, Rajendran D, Takada X, Shi Y, Varghese I, Lam Y, DaSilva N, Wang J, Batista V, Bhandari V, Lisi G. Atomistic modulation of MIF‐2 structure, catalysis, and biological signaling via cysteine residues and a small molecule, Ebselen. Protein Science 2025, 34: e70344. PMID: 41099614, PMCID: PMC12529878, DOI: 10.1002/pro.70344.Peer-Reviewed Original ResearchConceptsMIF-2Small moleculesBiological functionsMolecular dynamics simulationsMIF trimerMacrophage migration inhibitory factorNuclear magnetic resonanceRegulation of macrophage migration inhibitory factorD-dopachrome tautomeraseSelenylsulfide bondAllosteric crosstalkAllosteric switchDynamics simulationsAllosteric pathwaysBiochemical functionsConformational transitionCysteine residuesProximal cysteineStructural biologyBiological signalsQuaternary structureAllosteric mechanismSignaling activityCatalysisD-dopachromeDynamic and structural insights into allosteric regulation on MKP5 a dual-specificity phosphatase
Skeens E, Maschietto F, Manjula R, Shillingford S, Murphy J, Lolis E, Batista V, Bennett A, Lisi G. Dynamic and structural insights into allosteric regulation on MKP5 a dual-specificity phosphatase. Nature Communications 2025, 16: 7011. PMID: 40745179, PMCID: PMC12313947, DOI: 10.1038/s41467-025-62150-w.Peer-Reviewed Original ResearchMeSH KeywordsAllosteric RegulationAllosteric SiteCatalytic DomainCrystallography, X-RayDual-Specificity PhosphatasesHumansMagnetic Resonance SpectroscopyMitogen-Activated Protein Kinase PhosphatasesMolecular Dynamics Simulationp38 Mitogen-Activated Protein KinasesPhosphorylationProtein BindingProtein ConformationConceptsMitogen-activated protein kinaseMAPK bindingMolecular mechanismsCatalytic mechanismDual-specificity phosphataseMechanism of dephosphorylationAllosteric siteMolecular dynamics simulationsNMR spectroscopy approachesP38 mitogen-activated protein kinaseCatalytic domainAllosteric regulationRegulatory interplayProtein kinaseCrucial residuesConformational flexibilityDynamics simulationsActive siteStructural insightsMolecular pictureAllosteric pocketDephosphorylationY435MKP5Spectroscopy approachCorrection to “A Hybrid Transformer Architecture with a Quantized Self-Attention Mechanism Applied to Molecular Generation”
Smaldone A, Shee Y, Kyro G, Farag M, Chandani Z, Kyoseva E, Batista V. Correction to “A Hybrid Transformer Architecture with a Quantized Self-Attention Mechanism Applied to Molecular Generation”. Journal Of Chemical Theory And Computation 2025, 21: 7726-7726. PMID: 40744647, DOI: 10.1021/acs.jctc.5c01204.Peer-Reviewed Original ResearchQuantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
Smaldone A, Shee Y, Kyro G, Xu C, Vu N, Dutta R, Farag M, Galda A, Kumar S, Kyoseva E, Batista V. Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries. Chemical Reviews 2025, 125: 5436-5460. PMID: 40479601, DOI: 10.1021/acs.chemrev.4c00678.Peer-Reviewed Original ResearchConceptsQuantum machine learningQuantum computationGate-based quantum computersQuantum-classical approachVariational quantum circuitsQuantum neural networkDrug discoveryQuantum circuitsMachine learningContext of drug discoveryMolecular property predictionQuantumMolecular generationProperty predictionNeural networkLearningA Triple-Action Inhibitory Mechanism of Allosteric TYK2-Specific Inhibitors
Wang J, Lomakin I, Batista V, Bunick C. A Triple-Action Inhibitory Mechanism of Allosteric TYK2-Specific Inhibitors. Journal Of Investigative Dermatology 2025, 145: 3158-3173. PMID: 40378946, DOI: 10.1016/j.jid.2025.04.025.Peer-Reviewed Original ResearchJak-signal transducer and activatorAutoinhibited statePseudokinase domainIFN-induced gene expressionAtomic resolution structuresPhosphorylation of downstream proteinsAdenosine triphosphate bindingTyk2 kinaseTriphosphate bindingKinase domainActive stateResolution structureKinase activityTYK2Gene expressionStructural basisDownstream proteinsAllosteric drugsSteric clashesAllosteric inhibitorsInhibition mechanismMechanistic hypothesesKinaseBindingProteinA Hybrid Transformer Architecture with a Quantized Self-Attention Mechanism Applied to Molecular Generation
Smaldone A, Shee Y, Kyro G, Farag M, Chandani Z, Kyoseva E, Batista V. A Hybrid Transformer Architecture with a Quantized Self-Attention Mechanism Applied to Molecular Generation. Journal Of Chemical Theory And Computation 2025, 21: 5143-5154. PMID: 40333363, DOI: 10.1021/acs.jctc.5c00331.Peer-Reviewed Original ResearchNatural language processingSelf-attentionHybrid transformer architectureSelf-attention matrixSelf-attention mechanismPairs of tokensMachine learning modelsTransformer decoderTransformer architectureComputational overheadLanguage modelCondition generatorSMILES stringsTime complexityLanguage processingQM9 datasetLearning modelsDot productInput sequenceMolecular generationAttention scoresArchitectureTheoretical analysisSequence lengthNVIDIADirectMultiStep: Direct Route Generation for Multistep Retrosynthesis
Shee Y, Morgunov A, Li H, Batista V. DirectMultiStep: Direct Route Generation for Multistep Retrosynthesis. Journal Of Chemical Information And Modeling 2025, 65: 3903-3914. PMID: 40197023, DOI: 10.1021/acs.jcim.4c01982.Peer-Reviewed Original ResearchMeSH KeywordsChemistry Techniques, SyntheticConceptsComputer-aided synthesis planningTop-1State-of-the-art methodsTop-1 accuracyState-of-the-artTransformer-based modelsGeneralization capabilityTraining dataModel sizeTraining setPrediction processRoute generationSynthetic routeTarget compoundsRetrosynthetic planningSynthesis planningReaction typesAccuracyFDA-approved drugsSpace growthScalabilityTrainingDatasetRetrosynthesisRouteCardioGenAI: a machine learning-based framework for re-engineering drugs for reduced hERG liability
Kyro G, Martin M, Watt E, Batista V. CardioGenAI: a machine learning-based framework for re-engineering drugs for reduced hERG liability. Journal Of Cheminformatics 2025, 17: 30. PMID: 40045386, PMCID: PMC11881490, DOI: 10.1186/s13321-025-00976-8.Peer-Reviewed Original ResearchMachine learning-based frameworkLearning-based frameworkState-of-the-artVirtual screening pipelineDiscriminant modelChannel activitySoftware open sourceCav1.2 channel activityQT interval prolongationTorsades de pointesHERG liabilityHERG channel activityPharmacological activitiesOpen-sourceFramework's abilityAntipsychotic agentsCav1.2 channelsInterval prolongationChannel blockadeHERG activityIon channel inhibitionFDA-approved compoundsHERG channel blockadeDevelopmental compoundsDrug discovery workflowT‑ALPHA: A Hierarchical Transformer-Based Deep Neural Network for Protein–Ligand Binding Affinity Prediction with Uncertainty-Aware Self-Learning for Protein-Specific Alignment
Kyro G, Smaldone A, Shee Y, Xu C, Batista V. T‑ALPHA: A Hierarchical Transformer-Based Deep Neural Network for Protein–Ligand Binding Affinity Prediction with Uncertainty-Aware Self-Learning for Protein-Specific Alignment. Journal Of Chemical Information And Modeling 2025, 65: 2395-2415. PMID: 39965912, DOI: 10.1021/acs.jcim.4c02332.Peer-Reviewed Original ResearchConceptsProtein-Ligand Binding Affinity PredictionBinding affinity predictionState-of-the-art performanceTransformer-based deep neural networksMultimodal feature representationAffinity predictionBinding affinity of small moleculesState-of-the-artDeep neural networksDeep learning modelsAffinity of small moleculesSelf-learning methodSARS-CoV-2 main proteasePredicted binding affinitiesFeature representationBinding affinityOn-target potencyNeural networkDrug discovery applicationsTransformation frameworkLearning modelsScoring functionCrystal structureSelf-learningMain protease