Sigma profiles in deep learning: towards a universal molecular descriptor

This work showcases the remarkable ability of sigma profiles to function as molecular descriptors in deep learning. The sigma profiles of 1432 compounds are used to train convolutional neural networks that accurately correlate and predict a wide range of physicochemical properties. The architectures developed are then exploited to include temperature as an additional feature.

Automated summary

This work demonstrates the impressive capability of sigma profiles as molecular descriptors in deep learning. Convolutional neural networks trained on sigma profiles of 1432 compounds successfully correlate and predict a wide range of physicochemical properties, with the inclusion of temperature as an additional feature.