# Validating the Validation: Reanalyzing a large-scale comparison of Deep Learning and Machine Learning models for bioactivity prediction

## TL;DR

This paper reanalyzes a large-scale comparison of machine learning models for bioactivity prediction, questioning previous conclusions and emphasizing the importance of proper validation metrics and uncertainty estimation.

## Contribution

It provides a critical reexamination of model benchmarking in bioactivity prediction, highlighting the competitiveness of SVMs and advocating for better validation practices.

## Key findings

- Support vector machines are competitive with deep learning models.
- Area under the precision-recall curve is more relevant than ROC AUC in virtual screening.
- Estimating uncertainty in model performance remains challenging.

## Abstract

Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion. We show that the performance of support vector machines is competitive with that of deep learning methods. Additionally, using a series of numerical experiments, we question the relevance of area under the receiver operating characteristic curve as a metric in virtual screening, and instead suggest that area under the precision-recall curve should be used in conjunction with the receiver operating characteristic. Our numerical experiments also highlight challenges in estimating the uncertainty in model performance via scaffold-split nested cross validation.