Publication Details

Category Text Publication
Reference Category Journals
DOI 10.1093/bioinformatics/btad713
Licence creative commons licence
Title (Primary) deepFPlearn+: enhancing toxicity prediction across the chemical universe using graph neural networks
Author Soulios, K.; Scheibe, P.; Bernt, M. ORCID logo ; Hackermüller, J. ORCID logo ; Schor, J.
Source Titel Bioinformatics
Year 2023
Department BIOINF
Volume 39
Issue 12
Page From btad713
Language englisch
Topic T9 Healthy Planet
Data and Software links https://doi.org/10.5281/zenodo.8146252
Supplements https://oup.silverchair-cdn.com/oup/backfile/Content_public/Journal/bioinformatics/PAP/10.1093_bioinformatics_btad713/1/btad713_supplementary_data.pdf?Expires=1705061536&Signature=0DdwkCdG7GuQoCOaTN49MEA3TgnPM251zLBEj00TkJP61M~h1HEZGsCQy4YukP6D99oU3JZjcCdW2r2TpwvjtstWi3To2urnLCWCVkzHLYPPqqyGmIDpLYYNdDI18AqDGSvrg-8Qj0LSGSysclPasHg4xMkmlV-xwHwj0i8vsvQwL9bV5~dFgv96PFicZVsdbkCU59siUgLsUTXXPvz340dfORGN2wP39XbnyCV77WkNhFzUoyuG6GwZ0k~5DT0fsWpEgJShDc3-SDRgYe7MMege6MKDjFi3xaclYJAegenH8FCW3lE3LpEM-~clVkiWE-TcC8mc8BlU7rYwfCNY0w__&Key-Pair-Id=APKAIE5G5CRDK6RD3PGA
Keywords deep learning; graph neural network; scaffold split; chemical structure; chemical-effect associations
Abstract Sophisticated approaches for the in-silico prediction of toxicity are required to support the risk assessment of chemicals. The number of chemicals on the global chemical market and the speed of chemical innovation stand in massive contrast to the capacity for regularizing chemical use. We recently proved our ready-to-use application deepFPlearn as a suitable approach for this task. Here, we present its extension deepFPlearn+ incorporating i) a graph neural network to feed our AI with a more sophisticated molecular structure representation and ii) alternative train-test splitting strategies that involve scaffold structures and the molecular weights of chemicals. We show that the GNNs outperform the previous model substantially and that our models can generalize on unseen data even with a more robust and challenging test set. Therefore, we highly recommend the application of deepFPlearn+ on the chemical inventory to prioritize chemicals for experimental testing or any chemical subset of interest in monitoring studies.
Persistent UFZ Identifier https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=28352
Soulios, K., Scheibe, P., Bernt, M., Hackermüller, J., Schor, J. (2023):
deepFPlearn+: enhancing toxicity prediction across the chemical universe using graph neural networks
Bioinformatics 39 (12), btad713 10.1093/bioinformatics/btad713