Dinis has his first group paper published in Chem. Comm.

Dinis Abranches published his first paper in our group in Chemical Communications. The paper shows how sigma profiles can be used as a powerful and general molecular descriptor 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. The work is a joint effort between our group and Prof. Col√≥n’s. Congratulations Dinis!