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

Predicting drug properties is key in drug discovery to enable de-risking ofassets before expensive clinical trials, and to find highly active compoundsfaster. Interest from the Machine Learning community has led to the release ofa variety of benchmark datasets and proposed methods. However, it remainsunclear for practitioners which method or approach is most suitable, asdifferent papers benchmark on different datasets and methods, leading tovarying conclusions that are not easily compared. Our large-scale empiricalstudy links together numerous earlier works on different datasets and methods;thus offering a comprehensive overview of the existing property classes,datasets, and their interactions with different methods. We emphasise theimportance of uncertainty quantification and the time and therefore cost ofapplying these methods in the drug development decision-making cycle. Wediscover that the best method depends on the dataset, and that engineeredfeatures with classical ML methods often outperform deep learning.Specifically, QSAR datasets are typically best analysed with classical methodssuch as Gaussian Processes while ADMET datasets are sometimes better describedby Trees or Deep Learning methods such as Graph Neural Networks or languagemodels. Our work highlights that practitioners do not yet have astraightforward, black-box procedure to rely on, and sets the precedent forcreating practitioner-relevant benchmarks. Deep learning approaches must beproven on these benchmarks to become the practical method of choice in drugproperty prediction.

Current Methods for Drug Property Prediction in the Real World