MIND lab – Laboratory of Computational multi-OmIcs of Neurological Disorders

The MIND Lab, joint research platform between Politecnico di Milano and Fondazione IRCCS Istituto Neurologico “Carlo Besta”, offers a crucial collaborative synergy combining data science and artificial intelligence with clinical expertise for supporting precision medicine, improving personalized diagnoses and therapeutic strategies, and achieving innovative results in neurological research.

Activities focus on the integration of multi-omics, microscopy and clinical data, and their comprehensive analysis to improve our understanding of neurological disorders. Using advanced artificial intelligence and data science techniques, the lab team provides innovative solutions to stratify patients and identify diagnostic and predictive biomarkers for biological response predictions.

Team Leaders

Marco Masseroli

Associate Professor

Department of Electronics, Information and Bioengineering
Politecnico di Milano;
MIND Lab, Joint Research Platform between Politecnico di Milano
and Fondazione IRCCS Istituto Neurologico “Carlo Besta”;
Fondazione IRCCS Istituto Neurologico “Carlo Besta”

Erika Salvi

Associate Professor

Data Science Center
Fondazione IRCCS Istituto Neurologico “Carlo Besta”;
MIND Lab, Joint Research Platform between Politecnico di Milano
and Fondazione IRCCS Istituto Neurologico “Carlo Besta”;
Department of Electronics, Information and Bioengineering
Politecnico di Milano

Researchers

Linda Maldera

@Istituto Neurologico Carlo Besta

PhD Candidate – XL cycle
Information Technology,
Politecnico di Milano

Simone Tomè

@Istituto Neurologico Carlo Besta

PhD Candidate – XXXIX cycle
Information Technology,
Politecnico di Milano

Silvia Cascianelli

@Istituto Neurologico Carlo Besta

Postdoctoral researcher
PhD in Information Technology,
Politecnico di Milano

Research Activities

MIND lab's activities involve the use of multiple computational methodologies, including: 

• Data science and bioinformatics analytical techniques for the management of complex, heterogeneous, and multimodal data to extract biologically and clinically useful insights through artificial intelligence algorithms and predictive models. 

• Data modeling and feature engineering to build robust models that represent biological processes and to identify the most relevant variables from omics, imaging and clinical data. 

• Integration of data from diverse sources (genomics, transcriptomics, epigenomics, proteomics, imaging, clinical) into a unified framework for achieving a comprehensive view of biological systems and an interdisciplinary understanding of neurological disorders. 

• Statistical learning methods and integrative multimodal analysis to combine different types of data (e.g., omics, imaging, clinical) for a deeper and more accurate interpretation of case studies. 

• Complex network analysis to study interactions within biological systems, such as gene regulatory networks or protein interactions, and identify key elements and biomarkers that play a critical role in pathological processes.

Publications

Maldera L, Masseroli M, Cascianelli S. Novel nested conformal prediction analysis to unravel complexity in patient subtyping. Frontiers in Artificial Intelligence, 2026. (in press).

Sarro L, Valenza M, Mongelli A, Passoni A, Castaldo A, Favagrossa M, Pasetto L, Bonetto V, Bagnati R, Grisoli M, Nigri A, Birolini G, Zerbini E, Tomè S, Masseroli M, Salvi E, Colombo L, Salmona M, Cattaneo E, Mariotti C. Longitudinal and combined assessment of 24(S)-Hydroxycholesterol and Neurofilament light chain to monitor early stages of Huntington disease. Neurobiology of Disease, 2026.

Tomè S, Cascianelli S, Salvi E, Masseroli M. Benchmark study on supervised Relevance-Redundancy assessment for feature selection in genomic data. In: Cerulo L, Napolitano F, Bardozzo F, Cheng L, Occhipinti A, Pagnotta SM, editors. Springer LNBI (Lecture Notes in Bioinformatics) – Computational Intelligence Methods for Bioinformatics and Biostatistics, 2025.

Tomè S, Cascianelli S, Salvi E, Masseroli M. Supervised Relevance-Redundancy assessment for feature selection in high-dimensional genotype data. In: Napolitano F, Cerulo M, editors. Proceedings of the 19th International Conference on Computational Intelligence Methods for Bioinformatics and Biostatistics, CIBB2024, September 4-6, 2024; University of Sannio, Benevento, IT.