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

Variational autoencoder (VAE) is a popular method for drug discovery andvarious architectures and pipelines have been proposed to improve itsperformance. However, VAE approaches are known to suffer from poor manifoldrecovery when the data lie on a low-dimensional manifold embedded in a higherdimensional ambient space [Dai and Wipf, 2019]. The consequences of it in drugdiscovery are somewhat under-explored. In this paper, we explore applying amulti-stage VAE approach, that can improve manifold recovery on a syntheticdataset, to the field of drug discovery. We experimentally evaluate ourmulti-stage VAE approach using the ChEMBL dataset and demonstrate its abilityto improve the property statistics of generated molecules substantially frompre-existing methods without incorporating property predictors into thetraining pipeline. We further fine-tune our models on two curated and muchsmaller molecule datasets that target different proteins. Our experiments showan increase in the number of active molecules generated by the multi-stage VAEin comparison to their one-stage equivalent. For each of the two tasks, ourbaselines include methods that use learned property predictors to incorporatetarget metrics directly into the training objective and we discusscomplications that arise with this methodology.

Objective-Agnostic Enhancement of Molecule Properties via Multi-Stage VAE