Rustam Zhumagambetov

Elizaveta Vinogradova, Abay Artykbayev, Alisher Amanatay et al.

While generative models have recently become ubiquitous in many scientific areas, less attention has been paid to their evaluation. For molecular generative models, the state-of-the-art examines their output in isolation or in relation to its input. However, their biological and functional properties, such as ligand-target interaction is not being addressed. In this study, a novel biologically-inspired benchmark for the evaluation of molecular generative models is proposed. Specifically, three diverse reference datasets are designed and a set of metrics are introduced which are directly relevant to the drug discovery process. In particular we propose a recreation metric, apply drug-target affinity prediction and molecular docking as complementary techniques for the evaluation of generative outputs. While all three metrics show consistent results across the tested generative models, a more detailed comparison of drug-target affinity binding and molecular docking scores revealed that unimodal predictiors can lead to erroneous conclusions about target binding on a molecular level and a multi-modal approach is thus preferrable. The key advantage of this framework is that it incorporates prior physico-chemical domain knowledge into the benchmarking process by focusing explicitly on ligand-target interactions and thus creating a highly efficient tool not only for evaluating molecular generative outputs in particular, but also for enriching the drug discovery process in general.

Stefan Haufe, Rick Wilming, Benedict Clark et al.

The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its current state, XAI itself needs scrutiny. Popular methods cannot reliably answer relevant questions about ML models, their training data, or test inputs, because they systematically attribute importance to input features that are independent of the prediction target. This limits the utility of XAI for diagnosing and correcting data and models, for scientific discovery, and for identifying intervention targets. The fundamental reason for this is that current XAI methods do not address well-defined problems and are not evaluated against targeted criteria of explanation correctness. Researchers should formally define the problems they intend to solve and design methods accordingly. This will lead to diverse use-case-dependent notions of explanation correctness and objective metrics of explanation performance that can be used to validate XAI algorithms.

Antonio Cerone, Markus Roggenbach, James Davenport et al.

This white paper argues that formal methods need to be better rooted in higher education curricula for computer science and software engineering programmes of study. To this end, it advocates (i) improved teaching of formal methods; (ii) systematic highlighting of formal methods within existing, `classical' computer science courses; and (iii) the inclusion of a compulsory formal methods course in computer science and software engineering curricula. These recommendations are based on the observations that (a) formal methods are an essential and cost-effective means to increase software quality; however (b) computer science and software engineering programmes typically fail to provide adequate training in formal methods; and thus (c) there is a lack of computer science graduates who are qualified to apply formal methods in industry. This white paper is the result of a collective effort by authors and participants of the 1st International Workshop on "Formal Methods, Fun for Everybody" which was held in Bergen, Norway, 2-3 December 2019. As such, it represents insights based on learning and teaching computer science and software engineering (with or without formal methods) at various universities across Europe.