I would like to work on a project that involves the prediction of protein-ligand binding kinetics. What might be the feature that is relevant for the prediction?
This is a comment to redirect to other answers, but go too long.
Docking is the in silico prediction of where a ligand binds in a protein.
There are several Q&As about docking here that are relevant, so please check out:
- machine learning, docking and the factors that affect it: Generate ligands candidates based on protein shape —also worth a read the "learning from the ligand" paper paper, which discusses why some ligand only parameters tell a lot about binding.
- correlation between docking scores and enzyme kinetics: Purpose of correlating docking score with catalytic efficiency(Kcat/km) —discusses a paper https://www.nature.com/articles/ncomms12965 wherein a linear regression is done between docking scores and kcat/KM