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/

Zendy Plus

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

Zendy Tools

Zendy Open

The application of deep learning to generative molecule design has shownearly promise for accelerating lead series development. However, questionsremain concerning how factors like training, dataset, and seed bias impact thetechnology's utility to medicine and computational chemists. In this work, weanalyze the impact of seed and training bias on the output of anactivity-conditioned graph-based variational autoencoder (VAE). Leveraging amassive, labeled dataset corresponding to the dopamine D2 receptor, ourgraph-based generative model is shown to excel in producing desired conditionedactivities and favorable unconditioned physical properties in generatedmolecules. We implement an activity swapping method that allows for theactivation, deactivation, or retention of activity of molecular seeds, and weapply independent deep learning classifiers to verify the generative results.Overall, we uncover relationships between noise, molecular seeds, and trainingset selection across a range of latent-space sampling procedures, providingimportant insights for practical AI-driven molecule generation.

Analysis of training and seed bias in small molecules generated with a  conditional graph-based variational autoencoder -- Insights for practical  AI-driven molecule generation