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

We propose a new model for making generalizable and diverse retrosyntheticreaction predictions. Given a target compound, the task is to predict thelikely chemical reactants to produce the target. This generative task can beframed as a sequence-to-sequence problem by using the SMILES representations ofthe molecules. Building on top of the popular Transformer architecture, wepropose two novel pre-training methods that construct relevant auxiliary tasks(plausible reactions) for our problem. Furthermore, we incorporate a discretelatent variable model into the architecture to encourage the model to produce adiverse set of alternative predictions. On the 50k subset of reaction examplesfrom the United States patent literature (USPTO-50k) benchmark dataset, ourmodel greatly improves performance over the baseline, while also generatingpredictions that are more diverse.

Learning to Make Generalizable and Diverse Predictions for Retrosynthesis