BLOG
Multi-target Drug Discovery via PTML Modeling: Applications to the Design of Virtual Dual Inhibitors of CDK4 and HER2
Guided by the physicochemical and structural interpretations of the molecular descriptors in the PTML model, we designed six molecules by assembling several fragments with positive contributions. Three of these molecules were predicted as potent dual inhibitors of CDK4 and HER2, while the other three were predicted as inhibitors of at least one of these proteins.
PTML Modeling for Pancreatic Cancer Research: In Silico Design of Simultaneous Multi-Protein and Multi-Cell Inhibitors
We report for the first time two models that combined perturbation theory with machine learning via a multilayer perceptron network (PTML-MLP) to perform the virtual design and prediction of molecules that can simultaneously inhibit multiple PANC cell lines and PANC-related proteins, such as caspase-1, tumor necrosis factor-alpha (TNF-alpha), and the insulin-like growth factor 1 receptor (IGF1R). Both PTML-MLP models exhibited accuracies higher than 78%.
ModesLab
ModesLab Program calculates several families of molecular descriptors, which include (but are not limited to) the atom (vertex)- and bond (edge)-based connectivity indices, classical topological descriptors (e.g., Balaban, Harary, Kier shape indices), as well as physiochemical properties and 3D descriptors. MODESLAB v1.5 is free of charge for academic use.
Multitasking Model for Computer-Aided Design and Virtual Screening of Compounds with High Anti-HIV Activity and Desirable ADMET Properties
The joint use of the fragment contributions and the physicochemical interpretations of the molecular descriptors in the mtk-QSBER model allowed the design of six new molecules, which were predicted as potent and safe anti-HIV agents.
Speeding up Early Drug Discovery in Antiviral Research: A Fragment-Based in Silico Approach for the Design of Virtual Anti-Hepatitis C Leads
These new molecules were predicted to exhibit potent anti-HCV activity and desirable in vitro ADMET properties. In addition, the designed molecules have good druglikeness according to the Lipinski’s rule of five and its variants
Designed Chemicals with Pan-Antiviral and Anti-Cytokine Storm Profiles
We report here the first multicondition model based on quantitative structure–activity relationships and an artificial neural network (mtc-QSAR-ANN) for the virtual design and prediction of molecules with dual pan-antiviral and anti-CS profiles. Our mtc-QSAR-ANN model exhibited an accuracy higher than 80%.
ANTIVIRALS
Virtual design of new molecules with potential pan-antiviral activity.
CANCERS
In Silico generation of multi-protein and/or multi-cell inhibitors against several cancers.
ANTIPARASITICS
Computer-aided discovery of multi-target inhibitors of proteins in diverse parasites.
PESTICIDES
Computational design of virtually potent fungicides and insecticides.
PEPTIDE DISCOVERY
Rational in silico design of bioactive and toxicologically safe peptides.
OTHERS
Use of the methodology named Perturbation Theory & Machine Learning (PTML) for virtual screening.