Benchmarks for interpretation of QSAR models

Interpretation of QSAR models is useful to understand the complex nature of biological or physicochemical processes, guide structural optimization or perform knowledge-based validation of QSAR models. Highly predictive models are usually complex and their interpretation is non-trivial. This is particularly true for modern neural networks. Various approaches to interpretation of these models exist. However, it is difficult to evaluate and compare performance and applicability of these ever-emerging methods. Herein, we developed several benchmark data sets with end-points determined by pre-defined patterns. These data sets are purposed for evaluation of the ability of interpretation approaches to retrieve these patterns. They represent tasks with different complexity levels: from simple atom-based additive properties to pharmacophore hypothesis. We proposed several quantitative metrics of interpretation performance. Applicability of benchmarks and metrics was demonstrated on a set of conventional models and end-to-end graph convolutional neural networks, interpreted by the previously suggested universal ML-agnostic approach for structural interpretation. We anticipate these benchmarks to be useful in evaluation of new interpretation approaches and investigation of decision making of complex black box models.

Automated summary

The interpretation of QSAR models is crucial for understanding complex processes and guiding model validation. This study develops benchmark datasets for evaluating interpretation methods of different complexity levels, proposing quantitative metrics for performance assessment. These benchmarks are applied to various models and neural networks, aiding in the evaluation and investigation of decision-making in complex black box models.