Cluster validity indices (CVIs) are used to detect a reliable number of clusters. We revised and evaluated 68 validity indices for crisp clustering by comparison on 21 real and simulated datasets. Have a look to the paper: https://doi.org/10.1016/j.chemolab.2024.105117
Molecular fingerprints for exploring the chemical space of natural products
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
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
QSAR for REACH
Milano Chemometrics has been involved in several projects related to the use of QSAR for the REACH registration of chemicals. If you are interested in collaboration on these topics, read here. |
Molecular Descriptors Data Base
The MOLE db – Molecular Descriptors Data Base is a free on-line database constituted of 1124 molecular descriptors calculated on 234773 molecules, released by Milano Chemometrics and QSAR Research Group: explore the MOLE db data base here! |
Download software and data
Visit the download page, where you can find softwares, MATLAB toolboxes and datasets you can freely download: N3-BNN toolbox, PCA toolbox, Kohonen and CPANN toolbox, Classification toolbox, Applicability Domain toolbox, RSR toolbox for variable selection. |