Imputation of sensory properties using deep learning.
J Comput Aided Mol Des
; 35(11): 1125-1140, 2021 11.
Article
de En
| MEDLINE
| ID: mdl-34716833
ABSTRACT
Predicting the sensory properties of compounds is challenging due to the subjective nature of the experimental measurements. This testing relies on a panel of human participants and is therefore also expensive and time-consuming. We describe the application of a state-of-the-art deep learning method, Alchemite™, to the imputation of sparse physicochemical and sensory data and compare the results with conventional quantitative structure-activity relationship methods and a multi-target graph convolutional neural network. The imputation model achieved a substantially higher accuracy of prediction, with improvements in R2 between 0.26 and 0.45 over the next best method for each sensory property. We also demonstrate that robust uncertainty estimates generated by the imputation model enable the most accurate predictions to be identified and that imputation also more accurately predicts activity cliffs, where small changes in compound structure result in large changes in sensory properties. In combination, these results demonstrate that the use of imputation, based on data from less expensive, early experiments, enables better selection of compounds for more costly studies, saving experimental time and resources.
Mots clés
Texte intégral:
1
Collection:
01-internacional
Base de données:
MEDLINE
Sujet principal:
Cellules réceptrices sensorielles
/
Apprentissage profond
Type d'étude:
Prognostic_studies
Limites:
Humans
Langue:
En
Journal:
J Comput Aided Mol Des
Sujet du journal:
BIOLOGIA MOLECULAR
/
ENGENHARIA BIOMEDICA
Année:
2021
Type de document:
Article
Pays d'affiliation:
Royaume-Uni