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

Instant machine learning predictions of molecular properties are desirablefor materials design, but the predictive power of the methodology is mainlytested on well-known benchmark datasets. Here, we investigate the performanceof machine learning with kernel ridge regression (KRR) for the prediction ofmolecular orbital energies on three large datasets: the standard QM9 smallorganic molecules set, amino acid and dipeptide conformers, and organiccrystal-forming molecules extracted from the Cambridge Structural Database. Wefocus on prediction of highest occupied molecular orbital (HOMO) energies,computed at density-functional level of theory. Two different representationsthat encode molecular structure are compared: the Coulomb matrix (CM) and themany-body tensor representation (MBTR). We find that KRR performance dependssignificantly on the chemistry of the underlying dataset and that the MBTR issuperior to the CM, predicting HOMO energies with a mean absolute error as lowas 0.09 eV. To demonstrate the power of our machine learning method, we applyour model to structures of 10k previously unseen molecules. We gain instantenergy predictions that allow us to identify interesting molecules for futureapplications.

Chemical diversity in molecular orbital energy predictions with kernel ridge regression