Revealing cytotoxic substructures in molecules using deep learning
| Autor: | Martin Neuenschwander, Talia B. Kimber, Silke Radetzki, Andrea Volkamer, Marc Nazaré, Henry E. Webel |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
Cell Survival In silico Computational biology Deep Taylor Decomposition Toxicology 01 natural sciences Models Biological Article Small Molecule Libraries 03 medical and health sciences Deep Learning Black box Drug Discovery Humans Physical and Theoretical Chemistry 030304 developmental biology Interpretability 0303 health sciences Deep Neural Networks Artificial neural network 010405 organic chemistry business.industry Drug discovery Cytotoxins Deep learning Hep G2 Cells 0104 chemical sciences Computer Science Applications Random forest HEK293 Cells Drug development Cytotoxic substructures Toxicophores Drug Design Computer-Aided Design Artificial intelligence Neural Networks Computer Technology Platforms business Software 600 Technik Medizin angewandte Wissenschaften::610 Medizin und Gesundheit::610 Medizin und Gesundheit |
| Zdroj: | Journal of Computer-Aided Molecular Design |
| DOI: | 10.17169/refubium-36488 |
| Popis: | In drug development, late stage toxicity issues of a compound are the main cause of failure in clinical trials. In silico methods are therefore of high importance to guide the early design process to reduce time, costs and animal testing. Technical advances and the ever growing amount of available toxicity data enabled machine learning, especially neural networks, to impact the field of predictive toxicology. In this study, cytotoxicity prediction, one of the earliest handles in drug discovery, is investigated using a deep learning approach trained on a highly consistent in-house data set of over 34,000 compounds with a share of less than 5% of cytotoxic molecules. The model reached a balanced accuracy of over 70%, similar to previously reported studies using Random Forest. Albeit yielding good results, neural networks are often described as a black box lacking deeper mechanistic understanding of the underlying model. To overcome this absence of interpretability, a Deep Taylor Decomposition method is investigated to identify substructures that may be responsible for the cytotoxic effects, the so-called toxicophores. Furthermore, this study introduces cytotoxicity maps which provide a visual structural interpretation of the relevance of these substructures. Using this approach could be helpful in drug development to predict the potential toxicity of a compound as well as to generate new insights into the toxic mechanism. Moreover, it could also help to de-risk and optimize compounds. Electronic supplementary material The online version of this article (10.1007/s10822-020-00310-4) contains supplementary material, which is available to authorized users. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|