1
|
O’Donovan SD, Cavill R, Wimmenauer F, Lukas A, Stumm T, Smirnov E, Lenz M, Ertaylan G, Jennen DGJ, van Riel NAW, Driessens K, Peeters RLM, de Kok TMCM. Application of transfer learning to predict drug-induced human in vivo gene expression changes using rat in vitro and in vivo data. PLoS One 2023; 18:e0292030. [PMID: 38032940 PMCID: PMC10688741 DOI: 10.1371/journal.pone.0292030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Accepted: 09/11/2023] [Indexed: 12/02/2023] Open
Abstract
The liver is the primary site for the metabolism and detoxification of many compounds, including pharmaceuticals. Consequently, it is also the primary location for many adverse reactions. As the liver is not readily accessible for sampling in humans; rodent or cell line models are often used to evaluate potential toxic effects of a novel compound or candidate drug. However, relating the results of animal and in vitro studies to relevant clinical outcomes for the human in vivo situation still proves challenging. In this study, we incorporate principles of transfer learning within a deep artificial neural network allowing us to leverage the relative abundance of rat in vitro and in vivo exposure data from the Open TG-GATEs data set to train a model to predict the expected pattern of human in vivo gene expression following an exposure given measured human in vitro gene expression. We show that domain adaptation has been successfully achieved, with the rat and human in vitro data no longer being separable in the common latent space generated by the network. The network produces physiologically plausible predictions of human in vivo gene expression pattern following an exposure to a previously unseen compound. Moreover, we show the integration of the human in vitro data in the training of the domain adaptation network significantly improves the temporal accuracy of the predicted rat in vivo gene expression pattern following an exposure to a previously unseen compound. In this way, we demonstrate the improvements in prediction accuracy that can be achieved by combining data from distinct domains.
Collapse
Affiliation(s)
- Shauna D. O’Donovan
- Maastricht Centre for Systems Biology (MaCSBio), Maastricht University, Maastricht, The Netherlands
- Dept. of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
- Eindhoven Artificial Intelligence Systems Institute (EAISI), Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Rachel Cavill
- Dept. of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
| | - Florian Wimmenauer
- Dept. of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
| | - Alexander Lukas
- Dept. of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
| | - Tobias Stumm
- Dept. of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
| | - Evgueni Smirnov
- Dept. of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
| | - Michael Lenz
- Maastricht Centre for Systems Biology (MaCSBio), Maastricht University, Maastricht, The Netherlands
- Institute of Organismic and Molecular Evolution, Johannes Gutenberg University Mainz, Mainz, Germany
- Preventive Cardiology and Preventative Medicine – Center for Cardiology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany
| | - Gokhan Ertaylan
- Maastricht Centre for Systems Biology (MaCSBio), Maastricht University, Maastricht, The Netherlands
- Sustainable Health, Flemish Institute for Technological Research (VITO), Mol, Belgium
| | - Danyel G. J. Jennen
- Dept. of Toxicogenomics, GROW School for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands
| | - Natal A. W. van Riel
- Maastricht Centre for Systems Biology (MaCSBio), Maastricht University, Maastricht, The Netherlands
- Dept. of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
- Eindhoven Artificial Intelligence Systems Institute (EAISI), Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Kurt Driessens
- Dept. of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
| | - Ralf L. M. Peeters
- Maastricht Centre for Systems Biology (MaCSBio), Maastricht University, Maastricht, The Netherlands
- Dept. of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
| | - Theo M. C. M. de Kok
- Maastricht Centre for Systems Biology (MaCSBio), Maastricht University, Maastricht, The Netherlands
- Dept. of Toxicogenomics, GROW School for Oncology and Reproduction, Maastricht University, Maastricht, The Netherlands
| |
Collapse
|
2
|
Abstract
Machine learning and artificial intelligence approaches have revolutionized multiple disciplines, including toxicology. This review summarizes representative recent applications of machine learning and artificial intelligence approaches in different areas of toxicology, including physiologically based pharmacokinetic (PBPK) modeling, quantitative structure-activity relationship modeling for toxicity prediction, adverse outcome pathway analysis, high-throughput screening, toxicogenomics, big data and toxicological databases. By leveraging machine learning and artificial intelligence approaches, now it is possible to develop PBPK models for hundreds of chemicals efficiently, to create in silico models to predict toxicity for a large number of chemicals with similar accuracies compared to in vivo animal experiments, and to analyze a large amount of different types of data (toxicogenomics, high-content image data, etc.) to generate new insights into toxicity mechanisms rapidly, which was impossible by manual approaches in the past. To continue advancing the field of toxicological sciences, several challenges should be considered: (1) not all machine learning models are equally useful for a particular type of toxicology data, and thus it is important to test different methods to determine the optimal approach; (2) current toxicity prediction is mainly on bioactivity classification (yes/no), so additional studies are needed to predict the intensity of effect or dose-response relationship; (3) as more data become available, it is crucial to perform rigorous data quality check and develop infrastructure to store, share, analyze, evaluate, and manage big data; and (4) it is important to convert machine learning models to user-friendly interfaces to facilitate their applications by both computational and bench scientists.
Collapse
Affiliation(s)
- Zhoumeng Lin
- Department of Environmental and Global Health, College of Public Health and Health Professions, University of Florida, Gainesville, FL, 32610, USA.,Center for Environmental and Human Toxicology, University of Florida, FL, 32608, USA
| | - Wei-Chun Chou
- Department of Environmental and Global Health, College of Public Health and Health Professions, University of Florida, Gainesville, FL, 32610, USA.,Center for Environmental and Human Toxicology, University of Florida, FL, 32608, USA
| |
Collapse
|