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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Accelerating the discovery of novel and more effective therapeutics is animportant pharmaceutical problem in which deep learning is playing anincreasingly significant role. However, real-world drug discovery tasks areoften characterized by a scarcity of labeled data and significant covariateshift$\unicode{x2013}\unicode{x2013}$a setting that poses a challenge tostandard deep learning methods. In this paper, we present Q-SAVI, aprobabilistic model able to address these challenges by encoding explicit priorknowledge of the data-generating process into a prior distribution overfunctions, presenting researchers with a transparent and probabilisticallyprincipled way to encode data-driven modeling preferences. Building on a novel,gold-standard bioactivity dataset that facilitates a meaningful comparison ofmodels in an extrapolative regime, we explore different approaches to inducedata shift and construct a challenging evaluation setup. We then demonstratethat using Q-SAVI to integrate contextualized prior knowledge of drug-likechemical space into the modeling process affords substantial gains inpredictive accuracy and calibration, outperforming a broad range ofstate-of-the-art self-supervised pre-training and domain adaptation techniques.

Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions