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

Machine learning methods may have the potential to significantly acceleratedrug discovery. However, the increasing rate of new methodological approachesbeing published in the literature raises the fundamental question of how modelsshould be benchmarked and validated. We reanalyze the data generated by arecently published large-scale comparison of machine learning models forbioactivity prediction and arrive at a somewhat different conclusion. We showthat the performance of support vector machines is competitive with that ofdeep learning methods. Additionally, using a series of numerical experiments,we question the relevance of area under the receiver operating characteristiccurve as a metric in virtual screening, and instead suggest that area under theprecision-recall curve should be used in conjunction with the receiveroperating characteristic. Our numerical experiments also highlight challengesin estimating the uncertainty in model performance via scaffold-split nestedcross validation.

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