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

Aqueous solubility is a valuable yet challenging property to predict.Computing solubility using first-principles methods requires accounting for thecompeting effects of entropy and enthalpy, resulting in long computations forrelatively poor accuracy. Data-driven approaches, such as deep learning, offerimproved accuracy and computational efficiency but typically lack uncertaintyquantification. Additionally, ease of use remains a concern for anycomputational technique, resulting in the sustained popularity of group-basedcontribution methods. In this work, we addressed these problems with a deeplearning model with predictive uncertainty that runs on a static website(without a server). This approach moves computing needs onto the websitevisitor without requiring installation, removing the need to pay for andmaintain servers. Our model achieves satisfactory results in solubilityprediction. Furthermore, we demonstrate how to create molecular propertyprediction models that balance uncertainty and ease of use. The code isavailable at \url{https://github.com/ur-whitelab/mol.dev}, and the model isusable at \url{https://mol.dev}.

Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks