Milano Chemometrics and QSAR Research Group
Department of Earth and Environmental Sciences – University of Milano-Bicocca
We have developed a new analytical method for the identification of photodegradation products of Escitalopram, details are published here: Termopoli, V., Consonni, V., Ballabio, D., Todeschini, R., Orlandi, M., Gosetti, F. (2022) Identification of photodegradation products of Escitalopram in surface water by HPLC-MS/MS and preliminary characterization of their potential impact on the environment, Separations, 9, 289 [link]
Today Emmanuel Cruz discussed the results after the first year of his PhD project “Geochemical study of sulfide minerals persistence in the sedimentary records” here at Milano Chemometrics and QSAr Research Group. Looking forward to see what’s next!
We were at the XXIX Congresso della Divisione di Chimica Analitica (MIlazzo, 11 – 15 Settembre), where Roberto presented the study “The cluster validity indices: a comprehensive review and multiple comparison by chemometrics methods”, Fabio “Identification of photodegradation products of escitalopram in surface water by HPLC-MS/MS” and Veronica won the best poster award for the category forense e tossicologia “From the streets to the law-enforcement authorities: a rapid and sensitive uhplc-ms/ms method for the determination of 13 illicit substances in drug seizures”.
Here our latest publication: “Multi-task neural networks and molecular fingerprints to enhance compound identification from LC-MS/MS data” Molecules (2022), 27, 5827 [link]. Data to reproduce the results are available at our website: https://michem.unimib.it/download/data/lc-ms-ms-to-fingerprints-dataset/
Today Giacomno Baccolo successfully defended his PhD thesis: “Chemometrics approaches for the automatic analysis of metabolomics GC-MS data”. His thesis deals with the presentation of a new approach called AutoDise to extract meaningful chemical signals from GC-MS data in an automatic way.
If you are interested, the PhD thesis can be downloaded here: https://michem.unimib.it/download/phd-thesis/
ChemTastesDB is a database that includes curated information of 2944 molecular tastants. For each molecule the following information is provided: name, PubChem CID, CAS registry number, canonical SMILES string, class taste. The molecular structure in the HyperChem (.hin) format of each chemical is provided. The database is now available on Zenodo: https://zenodo.org/record/5747393#.Yhnx8ujMKUk
Our paper dealing with the application of multitask neural networks to predict molecular activity on nuclear receptors is now published, have a look here: https://doi.org/10.1002/cem.3325
Today Cecile Valsecchi successfully defended her PhD thesis: “Advancing the prediction of Nuclear Receptor modulators through machine learning methods”. She studied potential interactions between chemicals and nuclear receptors, with the dual purpose of developing in silico tools to search for new modulators and to identify possible endocrine disrupting chemicals.
Congrats! Really a great job!
If you are interested, the PhD thesis can be downloaded here: https://michem.unimib.it/download/phd-thesis/
A new release of the Kohonen and CPANN Toolbox (for Matlab) is now available! The toolbox is a collection of MATLAB modules for calculating Kohonen Maps and Counterpropagation Artificial Neural networs (CPANNs), Supervised Kohonen networks and XY-fused networks. In this new release, it is possible to have calculation on a GPU and RAM usage has been optimised to better deal with big data. The toolbox can be downloaded here.
We compared different appraoches for optimisation of multitask neural network hyperparameters on QSAR data, results were recently published in the following manuscript: Valsecchi, C., Consonni, V., Todeschini, R., Orlandi, M., Gosetti, F., Ballabio, D. (2021) Parsimonious Optimization of Multitask Neural Network Hyperparameters, Molecules, 26, 7254 Have a look here!