Category Archives: Scientific publications

Kernel-based reliability potential to assist QSPR prediction and system transfer of SFC−MS retention time

Posted on

We have recently developed a QSPR framework for the in-silico prediction and system transfer of SFC−MS retention time on the basis of molecular structures. Check the open access publication: Consonni, V., Rojas, C., Guerrero, J., Mendoza, M., Termopoli, V., Ballabio, D. (2025) Kernel-based reliability potential to assist QSPR prediction and system transfer of SFC−MS retention time, Chemometrics and Intelligent Laboratory Systems, 263,105435 [link]

Data to reproduce the models proposed in the manuscript are available in the download section of our website, at this link.

ChemTastesDB: A Curated Database of Molecular Tastants

Posted on

ChemTastesDB is a database that includes curated information of 4075 molecular tastants. ChemTastesDB is distributed to the scientific community to expand the information of molecular tastants, which could assist the analysis of the relationships between molecular structure and taste, as well as in silico (QSAR/QSPR) studies for taste prediction.

The latest version of ChemTastesDB (released in March 2025) is available at the following link: https://zenodo.org/records/15051366

The 4075 molecular tastants are categorized into one of the five basic tastes (sweet, bitter, umami sour and salty), as well as to other classes related to non-basic tastes (tasteless, non-sweet, non-bitter, multitaste and miscellaneous). The molecules are categorized into following ten classes: sweet (1313), bitter (1615), umami (220), sour (49), salty (16), multitaste (179), tasteless (232), non-sweet (304), non-bitter (28), and miscellaneous (119).

Examples of QSPR approaches for the prediction of molecular taste are given in the following publication: Rojas, C., Abril-González, M., Ballabio, D. & García, F. (2025). ChemTastesPredictor: An ensemble of machine learning classifiers to predict the taste of molecular tastants. Chemometrics and Intelligent Laboratory Systems. 261, 105380. https://doi.org/10.1016/j.chemolab.2025.105380.

Cosmic spikes and saturated pixels in hyperspectral Raman spectroscopy

Posted on

ARCHER is a new algorithm for automatic removal of cosmic spikes and saturated pixels in hyperspectral Raman spectroscopy; here the full open access publication: Cruz Muñoz, E., Ballabio, D., Amigo, J,M. (2025) ARCHER. A new algorithm for Automatic Removal of Cosmic Spikes and Saturated Pixels in Hyperspectral Raman spectroscopy, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 336, 126041 [link]

PhD defense by Emmanuel Cruz

Posted on

Emmanuel Cruz brilliantly defended his PhD thesis ‘Geochemical Study of Pyrite Persistence in Sedimentary Records’ at the Università degli Studi di Milano-Bicocca. Emmanuel undertook an impressive interdisciplinary effort, bridging two fields that often speak different scientific “languages.” He facilitated their interaction by developing new analytical methods and applying techniques such as RAMAN imaging, Design of Experiments (DoE), and chemometrics to investigate chemical factors linked to climate change. To top it all off, Emmanuel earned his PhD in Chemical, Geological, and Environmental Sciences with honors! The PhD thesis is available for downlaod here: https://michem.unimib.it/download/phd-thesis/

Molecular fingerprints for exploring the chemical space of natural products

Posted on

We evaluated the effectiveness of multiple types of fingerprints for representing the chemical space of natural substances. The code and data to reproduce the results are also available in the study: Boldini, D., Ballabio, D., Consonni, V., Todeschini, R., Grisoni, F., Sieber, S.A. (2024) Effectiveness of molecular fingerprints for exploring the chemical space of natural products, Journal of Cheminformatics 16, 35 (2024), https://doi.org/10.1186/s13321-024-00830-3

A new metric to assess the degree of accuracy of consensus predictions

Posted on

We proposed a new heuristic metric to assess the degree of accuracy of consensus predictions. It can assist the mapping of reliability in prediction and enhance the delineation of a safe zone, where consensus predictions are expected to have better accuracy. All details are available in the following publication, have a look! We also provide data and code to calculate it, here!

V. Consonni, R. Todeschini, M. Orlandi, D. Ballabio (2024) Kernel-based mapping of reliability in predictions for consensus modelling, Chemometrics and Intelligent Laboratory Systems 246, 105085, https://doi.org/10.1016/j.chemolab.2024.105085

Chemometrics to predict the taste of molecules

Posted on

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]