Chemometrics to predict the taste of molecules

We have published a comprehensive review on classification-based chemoemtric approaches to predict taste of molecules, have a look!

Rojas, C., Ballabio, D., Consonni, V., Suárez-Estrella, D., Todeschini, R. (2023) Classification-based machine learning approaches to predict the taste of molecules: a review. Food Research International, 171, 113036 [link]

Kohonen and CPANN toolbox: new release!

A new release of the Kohonen and CPANN toolbox (4.6) is now available. In this release, GPU and CPU calculation has been improved. The Kohonen and CPANN toolbox for MATLAB is a collection of MATLAB modules for training Kohonen Maps (Self Organising Maps, SOMs), Counterpropagation Artificial Neural networs (CPANNs), Supervised Kohonen networks (SKN), XY-fused networks (XY-F). It can be downloaded here:

Characterization of pyrite weathering with Raman hyperspectral imaging and chemometrics

Here our latest poublication, which was the first product of the PhD project of Emmanuel Cruz in collaboration with the Laboratory for Provenance Studies (University of Milano-Bicocca), the Department of Analytical Chemistry (University of the Basque Country) and IKERBASQUE (Basque Society for the Promotion of Science):

Cruz Muñoz, E., Gosetti, F., Ballabio, D., Andò, S., Gómez-Laserna, O., Amigo, J.M., Garzanti, E. (2023) Characterization of pyrite weathering products by Raman hyperspectral imaging and chemometrics techniques. Microchemical Journal, 190, 108655 [link]

Condensed Phase Membrane Introduction Mass Spectrometry (MIMS): a review!

Membrane introduction mass spectrometry (MIMS) is a direct mass spectrometry technique used to monitor online chemical systems or quickly quantify trace levels of different groups of compounds in complex matrices without extensive sample preparation steps and chromatographic separation. Here a recent review:

V. Termopoli, M. Piergiovanni, D. Ballabio, V. Consonni, E. Cruz Muñoz, F. Gosetti (2023) Condensed phase membrane introduction mass spectrometry: a direct alternative to fully exploit the mass spectrometry potential in environmental sample analysis, Separations, 10, 139,

New chapter: tutorial for multitask learning for QSAR

We have published a new chapter, which is a tutorial for training multitask neural networks in the framework of QSAR modelling, have a look here:

Valsecchi, C., Grisoni, F., Consonni, V., Ballabio, D., Todeschini, R. (2023). Multitask Learning for Quantitative Structure–Activity Relationships: A Tutorial. In Machine Learning and Deep Learning in Computational Toxicology. Computational Methods in Engineering & the Sciences. (Hong, H., eds), Springer