English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The field of machine learning for drug discovery is witnessing an explosionof novel methods. These methods are often benchmarked on simple physicochemicalproperties such as solubility or general druglikeness, which can be readilycomputed. However, these properties are poor representatives of objectivefunctions in drug design, mainly because they do not depend on the candidate'sinteraction with the target. By contrast, molecular docking is a widelysuccessful method in drug discovery to estimate binding affinities. However,docking simulations require a significant amount of domain knowledge to set upcorrectly which hampers adoption. To this end, we present DOCKSTRING, a bundlefor meaningful and robust comparison of ML models consisting of threecomponents: (1) an open-source Python package for straightforward computationof docking scores; (2) an extensive dataset of docking scores and poses of morethan 260K ligands for 58 medically-relevant targets; and (3) a set ofpharmaceutically-relevant benchmark tasks including regression, virtualscreening, and de novo design. The Python package implements a robust ligandand target preparation protocol that allows non-experts to obtain meaningfuldocking scores. Our dataset is the first to include docking poses, as well asthe first of its size that is a full matrix, thus facilitating experiments inmultiobjective optimization and transfer learning. Overall, our resultsindicate that docking scores are a more appropriate evaluation objective thansimple physicochemical properties, yielding more realistic benchmark tasks andmolecular candidates.

DOCKSTRING: easy molecular docking yields better benchmarks for ligand design