Tobias Harren is a PhD student and research assistant in the research group of Matthias Rarey at the Center of Bioinformatics Hamburg. He graduated with his BSc. in Computing in Science from the Universität Hamburg in 2020 and his MSc. in Bioinformatics in 2022. He furthermore is part of the universities Fast-Track PhD program.
His research interest are broadly in the are of Machine Learning and Artificial Intelligence in Drug Discovery. A particular focus lies on Explainable Artifical Intelligence. Furthermore he has also worked on Generative Models, and currently focuses on Structure-Based Drug Design.
OpenTox Virtual Conference 2023
Explainable Artificial Intelligence for Structure-Activity Relationships in Real-World Drug Design Datasets
Deep Neural Networks have been successfully used for predicting molecular properties and activities. However, due to their complexity, their reasoning is inherently hard to follow, leading to the so-called black-box character. Unfortunately, this can often hinder Drug Development, as it becomes impossible to identify the components of a molecule that have positive contributions to its activity. This problem is addressed by Explainable Artificial Intelligence, which untangles the complicated Machine Learning models and provides clear connections between the input features and outputs. We applied such methods to a lead optimization dataset, with a well-established Structure Activity Relationship and visualized the results in easy-to-understand heatmaps.
We compared some simple baseline methods with novel methods, in particular SHAP-based explanations. Our analysis focused on how well we could reproduce the known Structure-Activity Relationship and how the model quality influence the explanations. We showed that SHAP-based methods are very powerful for explaining model predictions, but a good understanding of the underlying machine learning model and data is required to prevent misunderstandings.
Interpretation of Structure–Activity Relationships in Real-World Drug Design Data Sets Using Explainable Artificial Intelligence
Tobias Harren, Hans Matter, Gerhard Hessler, Matthias Rarey, and Christoph Grebner
Journal of Chemical Information and Modeling 2022 62 (3), 447-462
DOI: 10.1021/acs.jcim.1c01263