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

In order to design a more potent and effective chemical entity, it isessential to identify molecular structures with the desired chemicalproperties. Recent advances in generative models using neural networks andmachine learning are being widely used by many emerging startups andresearchers in this domain to design virtual libraries of drug-like compounds.Although these models can help a scientist to produce novel molecularstructures rapidly, the challenge still exists in the intelligent explorationof the latent spaces of generative models, thereby reducing the randomness inthe generative procedure. In this work we present a manifold traversal withheuristic search to explore the latent chemical space. Different heuristics andscores such as the Tanimoto coefficient, synthetic accessibility, bindingactivity, and QED drug-likeness can be incorporated to increase the validityand proximity for desired molecular properties of the generated molecules. Forevaluating the manifold traversal exploration, we produce the latent chemicalspace using various generative models such as grammar variational autoencoders(with and without attention) as they deal with the randomized generation andvalidity of compounds. With this novel traversal method, we are able to findmore unseen compounds and more specific regions to mine in the latent space.Finally, these components are brought together in a simple platform allowingusers to perform search, visualization and selection of novel generatedcompounds.

ChemoVerse: Manifold traversal of latent spaces for novel molecule discovery