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...

Pathways to a Shiny Future: Building the Foundation for Computational Physical Chemistry and Biophysics in 2050

“…We also should not replace the “knowledge first” concept with the “big amount of data” that AI provides. For instance, while AI algorithms can already streamline the predictions of protein–ligand binding free energies , or free energy of permeation through the membrane, it may struggle with seemingly next-step tasks, such as screening of antimicrobial peptides. Even if we collect all amino-acid sequences known to be effective in a single database and then apply AI to fill in the gaps, the results are far from being guaranteed to be successful.…”