Deep Learning Models for the Estimation of Free Energy of Permeation of Small Molecules across Lipid Membranes

Abstract

Calculating the free energy of drug permeation across membranes carries great importance in pharmaceutical and related applications. Traditional methods, including experiments and molecular simulations, are expensive and time-consuming, and existing statistical methods suffer from low accuracy. In this work, we propose a hybrid approach that combines molecular dynamics simulations and deep learning techniques to predict the free energy of permeation of small drug-like molecules across lipid membranes with high accuracy and at a fraction of the computational cost of advanced sampling methods like umbrella sampling. We have performed several molecular dynamics simulations of molecules in water and lipid bilayers to obtain multidimensional time-series data of features. Deep learning architectures based on Long Short-Term Memory networks, attention mechanisms, and dense layers are built to estimate free energy from the time series data. The prediction errors for the test set and an external validation set are much lower than that of existing data-driven approaches, with R2 of the best model around 0.99 and 0.82 for the two cases. Our approach reduces the time required for free energy calculations by an order of magnitude. This work presents an attractive option for high-throughput virtual screening of molecules based on their membrane permeabilities, demonstrates the applicability of language processing techniques in biochemical problems, and suggests a novel way of integrating physics with statistical learning to great success

Epitope Generation for Peptide-based Cancer Vaccine using Goal-directed Wasserstein Generative Adversarial Network with Gradient Penalty

“…GAN algorithms have been applied to produce novel protein and peptide structures for drug screening and discovery stage 23 . Dutta 24 designed a GAN with a graph convolutional neural network that can predict solubility and toxicity from molecular descriptors to guide the generator network to produce novel small molecules with desired drug properties. Putin 25 proposed a new GAN architecture called "RANC" that combines reinforcement learning to generate more unique and diverse chemical structures with desired chemical features and have similar lengths of the SMILES string in their training data set.…”