Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints

no code implementations • 10 Mar 2024 • Markus Dablander, Thierry Hanser, Renaud Lambiotte, Garrett M. Morris

Extended-connectivity fingerprints (ECFPs) are a ubiquitous tool in current cheminformatics and molecular machine learning, and one of the most prevalent molecular feature extraction techniques used for chemical prediction.

Molecular Property Prediction Property Prediction

Exploring QSAR Models for Activity-Cliff Prediction

1 code implementation • 31 Jan 2023 • Markus Dablander, Thierry Hanser, Renaud Lambiotte, Garrett M. Morris

Pairs of similar compounds that only differ by a small structural modification but exhibit a large difference in their binding affinity for a given target are known as activity cliffs (ACs).

molecular representation

Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning

1 code implementation • NeurIPS 2020 • Julius Berner, Markus Dablander, Philipp Grohs

We show that a single deep neural network trained on simulated data is capable of learning the solution functions of an entire family of PDEs on a full space-time region.