Skip to content

Slides from ML in Drug Discovery Symposium at the Broad, 16 Nov


PDF Download: Slide deck (56 slides, 2MB)

Abstract

While computational methods have been used in drug discovery since about the 1980s[1], we are currently again witnessing an immense increase in interest in the field. This is partly driven by available large-scale datasets, and partly by novel computational methods; however translation to the clinic is still lacking[2], which is closely linked to the nature of life science data[2,3]. More recently, ‘automating science’ and ‘automating drug discovery’ has been discussed, as well as terminology such as ‘self-driving labs’, an analogy to self-driving cars. This presentation will aim to shed light on the objectives and goals from different areas of science, as well as available data, and requirements for decision making processes that are able to improve not only model metrics, but also process decisions, and thereby project success. We will discover that scientific fields differ greatly in terms of the nature of their goals, available data (with respect to e.g. predictivity, dimensionality etc), and hence feasibility of converting data and technology into better real-world results.

[1]  Bender A, Cortés-Ciriano I. Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 1: Ways to make an impact, and why we are not there yet. Drug Discov. Today (2021) 26, 511-524. doi: https://doi.org/10.1016/j.drudis.2020.12.009
[2] Bender, A. et al. Artificial intelligence in drug discovery — what it is, where we stand and the path forward. Nat. Rev. Drug Discov. (2026). https://doi.org/10.1038/s41573-026-01496-2
[3] Bender A, Cortes-Ciriano I. Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 2: a discussion of chemical and biological data. Drug Discov. Today (2021) 26, 1040-1052. https://doi.org/10.1016/j.drudis.2020.11.037

Leave a Reply

Your email address will not be published. Required fields are marked *