2024
Kernel-elastic autoencoder for molecular design
Li H, Shee Y, Allen B, Maschietto F, Morgunov A, Batista V. Kernel-elastic autoencoder for molecular design. PNAS Nexus 2024, 3: pgae168. PMID: 38689710, PMCID: PMC11059255, DOI: 10.1093/pnasnexus/pgae168.Peer-Reviewed Original ResearchMaximum mean discrepancyMean discrepancyTransformer architectureCondition generatorWeighted reconstructionTraining datasetGenerative modelGeneration approachDocking applicationsMolecular designAutoencoderAccurate reconstructionVAESpectrum of applicationsAutoDock VinaEnhanced performanceDesignDatasetArchitectureGeneration performanceBenchmarksApplicationsGlide scoreReconstructionGeneration behavior
2013
CHAPTER 1
Konezny S, Batista V. CHAPTER 1. Energy And Environment Series 2013, 1-36. DOI: 10.1039/9781849735445-00001.Peer-Reviewed Original ResearchMolecular adsorbatesEarth abundant transition metal complexesTransition metal complexesInverse molecular designSolar cellsNew photocatalytic materialsSolar light absorptionMetal complexesRedox propertiesSolar cell componentsChemical fuelsMolecular designPhotocatalytic materialsSolar cell assemblyNanoporous materialsRedox potentialFirst-principles calculationsCharge transportCurrent-voltage characteristicsLight absorptionPrinciples calculationsSemiconductor materialsAdsorbatesFundamental insightsMechanistic characterizationChapter 1
Xiao D, Warnke I, Bedford J, Batista V. Chapter 1. Chemical Modelling 2013, 10: 1-31. DOI: 10.1039/9781849737241-00001.Peer-Reviewed Original ResearchInverse molecular designMolecular designDye-sensitized solar cellsMaterials discoveryMolecular design strategyElectronic structure calculationsNovel nonlinear optical materialNonlinear optical materialsCatalyst designSolar fuelsMolecular systemsStructure calculationsSolar cellsOptical materialsDesign strategyComputational approachPromising approach