The emergence of drug-resistant strains of Plasmodium falciparum continues to challenge global malaria control efforts, underscoring the urgent need for novel therapeutic strategies. In this study, we present an integrative computational framework that combines ensemble machine learning, molecular docking, and molecular dynamics simulations to predict and characterize the antimalarial activity of compounds from the Malaria Box database. Initially, topographical and quantum mechanical descriptors were used to construct regression models for predicting pEC50 values, but due to the limited predictive performance in the global regression, a classification strategy was adopted, categorizing compounds into “active” and “very active” classes. The best ensemble classifier achieved robust performance (Acc10-fold = 0.738, Accext = 0.675), with good sensitivity and specificity over individual models. Subsequent regression modeling within each class yielded high predictive accuracy, with ensemble models reaching Q210-fold values of 0.810 and 0.793 for the very active and active classes, respectively. To explore potential mechanisms of action, molecular docking was performed against P. falciparum Cytochrome B, revealing strong binding affinities for most compounds, particularly those forming π–π stacking and hydrogen bonds with Glu272. Molecular dynamics simulations over 200 ns confirmed the stability of several ligand–protein complexes, including unexpected behavior from compound M31, which demonstrated stable binding despite poor docking scores, suggesting a possible competitive inhibition mechanism. Binding free energy calculations further validated these findings, highlighting several promising candidates for future experimental evaluation. This integrative approach offers a powerful platform for accelerating antimalarial drug discovery by combining predictive modeling with mechanistic insights.
16 November 2021 in ACI Avances en Ciencias e Ingenierías
Los bifenilos policlorados (PCBs) son contaminantes persistentes que afectan enormemente a los ecosistemas marinos. Utilizando técnicas de aprendizaje de máquina, se construyeron modelos de relación cuantitativa estructura-actividad (RCEA) para predecir el factor de bioconcentración (BCF) de los PCBs. Estos modelos se construyeron a partir de descriptores topográficos 2D y 3D calculados para la estructura molecular optimizada en el nivel de mecánica molecular. Después de analizar sus parámetros estadísticos, se determinó que dos modelos son bastante robustos para la predicción de logBCF. Los modelos seleccionados fueron: M_4_LR construido con dos descriptores moleculares y presenta valores de r2 = 0,9154, Q2LOO = 0,8944, y Q2ext = 0,9119, y M_13 construido con cuatro descriptores moleculares y presenta valores de r2 = 0,9375, Q2LOO = 0,9155, y Q2ext = 0,844. Los dos modelos pasaron la doble fase de validación y cumplieron con los criterios de la prueba de Tropsha. Esto implica que las predicciones para el logBCF fueron bastante precisas tal como se muestra en los resultados del presente estudio.