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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recent advances in machine learning and their applications have lead to thedevelopment of diverse structure-property relationship models for crucialchemical properties, and the solvation free energy is one of them. Here, weintroduce a novel ML-based solvation model, which calculates the solvationenergy from pairwise atomistic interactions. The novelty of the proposed modelconsists of a simple architecture: two encoding functions extract atomicfeature vectors from the given chemical structure, while the inner productbetween two atomistic features calculates their interactions. The results on6,493 experimental measurements achieve outstanding performance andtransferability for enlarging training data due to its solvent-non-specificnature. Analysis of the interaction map shows there is a great potential thatour model reproduces group contributions on the solvation energy, which makesus believe that the model not only provides the predicted target property butalso gives us more detailed physicochemical insights.

MLSolv-A: A Novel Machine Learning-Based Prediction of Solvation Free Energies from Pairwise Atomistic Interactions