SPP 2363 - Subproject: Neural fingerprints as structure and activity-sensitive molecular representations

Basic data for this project

Description

The project aim can be summarised as the development of a robust neural network architecture for the training of generic or domain-specific neural fingerprints. These neural fingerprints can be used as structure- and activity-sensitive molecular representations for e.g. virtual screening. In addition, we will integrate Explainable Artificial Intelligence techniques that will provide a better understanding of the training of the molecular representation and that can be used to analyse the important structural features learned by the neural network. This will allow a basic interpretability of the molecular representations created. Furthermore, we will develop different databases for the training of generic and important domain-specific neural fingerprints and develop a uniform benchmark framework for evaluating and comparing neural fingerprints with respect to their functionality in virtual screening approaches.Within the time frame of this project, a general-purpose activity- and structure-sensitive neural fingerprint should thus be available that outperforms standard fingerprints in virtual screening approaches. Explainable artificial intelligence will make it possible to understand the structural features that are important for molecular similarity. In addition, multiple domain-specific neural fingerprints should also be available for specific tasks.