In this article, the team demonstrates the application of Alchemite, a deep learning imputation method which underpins our Cerella technology, to physicochemical and sensory data. They compare the deep learning model with traditional QSAR models, demonstrating significantly improved accuracy using Cerella.

Citation details

S. Mahmoud et al., J. Comput. Aided Mol. Des., 2021, 35(11), pp. 1125-1140
DOI: 10.1007/s10822-021-00424-3

Find out more about deep learning imputation

Find out details on the imputation of sensory properties using deep learning in our webinar with Samar Mahmoud and Tamsin Mansley (Optibrium) and Dmitriy Chekmarev (IFF).

More AI-guided discovery resources