Work

Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery

Year: 2018

Type: article

Abstract: The new wave of successful generative models in machine learning has increased the interest in deep learning driven de novo drug design. However, method comparison is difficult because of various flaws of the currently employed evaluation metrics. We propose an evaluation metric for generative models called Fréchet ChemNet distance (FCD). The advantage of the FCD over previous metrics is that it can detect whether generated molecules are diverse and have similar chemical and biological properties as real molecules.

Source: Journal of Chemical Information and Modeling

DOI: 10.1021/acs.jcim.8b00234

Authors: Kristina Preuer, Philipp Renz, Thomas Unterthiner, Sepp Hochreiter, Günter Klambauer

Institution: Johannes Kepler University of Linz

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Drug Discovery

Field: Pharmacology, Toxicology and Pharmaceutics

Domain: Life Sciences

Open Access status: green

Funders: Merck, Merck KGaA

Award: G2346175898