Machine Learning 101: How to optimise hyperparameters
What are parameters in machine learning models? The regular (non-hyper) parameters of an ML model are the numbers that it…
Abstract
We introduce a new method for rapid computation of 3D molecular similarity that combines electrostatic field comparison with comparison of molecular surface-shape and directional hydrogen-bonding preferences (called “eSim”). Rather than employing heuristic “colors” or user-defined molecular feature types to represent conformation-dependent molecular electrostatics, eSim calculates the similarity of the electrostatic fields of two molecules (in addition to shape and hydrogen-bonding). We present detailed virtual screening performance data on the standard 102 target DUD-E set. In its moderately fast screening mode, eSim running on a single computing core is capable of processing over 60 molecules per second.
The eSim approach enables both large-scale screening and rational design of ligands and is rooted in physically meaningful, non-heuristic, molecular comparisons.
Citation details
A.E. Cleves, et al. (2019) J Comput. Aided Mol. Des. 33, pp. 865–886
DOI: 10.1002/cbdv.200900148
More publications to browse
How does StarDrop compare to LiveDesign?
No glove fits every hand perfectly—and it’s the same with software tools. There’s no one-size-fits-all solution when it comes to…
How much does 3D molecular modelling software cost?
Introduction 3D molecular modelling plays a vital role in modern drug discovery, offering powerful applications to streamline research, reduce costs,…
