2021
PaccMannRL: De novo generation of hit-like anticancer molecules from transcriptomic data via reinforcement learning
Born J, Manica M, Oskooei A, Cadow J, Markert G, Martínez M. PaccMannRL: De novo generation of hit-like anticancer molecules from transcriptomic data via reinforcement learning. IScience 2021, 24: 102269. PMID: 33851095, PMCID: PMC8022157, DOI: 10.1016/j.isci.2021.102269.Peer-Reviewed Original ResearchDrug designSimilarity to compoundsReinforcement learning methodDeep generative modelsDeep learning approachMolecular designStructurally similar to compoundsDrug-likenessComputational chemistryBridging systems biologyMolecule generationReinforcement learningReward functionLearning methodsGenerative modelLearning approachCompoundsAnticancer moleculesChemical propertiesMoleculesIncorporating informationCandidate drugsSynthesizabilityAnticancer drugsPrediction model
2020
PaccMann: a web service for interpretable anticancer compound sensitivity prediction
Cadow J, Born J, Manica M, Oskooei A, Martínez M. PaccMann: a web service for interpretable anticancer compound sensitivity prediction. Nucleic Acids Research 2020, 48: w502-w508. PMID: 32402082, PMCID: PMC7319576, DOI: 10.1093/nar/gkaa327.Peer-Reviewed Original ResearchConceptsWeb servicesAttention-based neural networkState-of-the-art methodsState-of-the-artOutputs confidence scoresCompound structure informationInteractive editorModel decision makingChemical sub-structuresAttention heatmapsNeural networkWeb-based platformModel interpretationEfficient validationConfidence scoresDrug repositioningCompound structureDrug compoundsWebSource of informationStructural informationCompoundsBiomolecular samplesDecision makingPotential compounds
2015
Elucidating Compound Mechanism of Action by Network Perturbation Analysis
Woo J, Shimoni Y, Yang W, Subramaniam P, Iyer A, Nicoletti P, Martínez M, López G, Mattioli M, Realubit R, Karan C, Stockwell B, Bansal M, Califano A. Elucidating Compound Mechanism of Action by Network Perturbation Analysis. Cell 2015, 162: 441-451. PMID: 26186195, PMCID: PMC4506491, DOI: 10.1016/j.cell.2015.05.056.Peer-Reviewed Original ResearchConceptsGenome-wide identificationRegulatory network analysisBind target proteinsCompound's mechanism of actionNovel proteinsTarget proteinsCompound perturbationGlobal dysregulationSmall molecule compoundsCompound similarityProteinNetwork-based approachRepair activityMolecular interactionsTested compoundsCompoundsMechanism of actionNetwork analysisCompound analysisActivity modulationAnticancer drugsCompound efficacyPerturbation profilesSimilarityEffector