A compact review of molecular property prediction with graph neural networks. (December 2020)

• Record Type: Journal Article
• Authors: Wieder, Oliver; Kohlbacher, Stefan; Kuenemann, Mélaine; Garon, Arthur; Ducrot, Pierre; Seidel, Thomas; Langer, Thierry
• Is Part Of: Drug discovery today. Volume 37(2020)
• Page Start: 1
• Page End: 12
• Publication Date: 2020-12
• Subjects: AI -- Deep-learning -- Neural-networks -- Graph neural-networks -- Molecular representation -- Molecular property -- Drug discovery -- Computational chemistry; Drug development -- Periodicals; Physiology, Pathological -- Periodicals; Drugs -- Design -- Periodicals; 615.1
• DOI: 10.1016/j.ddtec.2020.11.009
• Languages: English
• ISSNs: 1740-6749

Abstract

Abstract: As graph neural networks are becoming more and more powerful and useful in the field of drug discovery, many pharmaceutical companies are getting interested in utilizing these methods for their own in-house frameworks. This is especially compelling for tasks such as the prediction of molecular properties which is often one of the most crucial tasks in computer-aided drug discovery workflows. The immense hype surrounding these kinds of algorithms has led to the development of many different types of promising architectures and in this review we try to structure this highly dynamic field of AI-research by collecting and classifying 80 GNNs that have been used to predict more than 20 molecular properties using 48 different datasets.