Physics background, biomedical mission.
I'm a PhD researcher at the University of Bologna, where I develop computational methods to predict antimicrobial resistance, discover patient phenotypes, and make sense of high-dimensional omics data. My work spans MALDI-TOF mass spectrometry, multi-omics integration, and metagenomics, always with a focus on interpretability and clinical impact. Part of the Physics4MedicineLab group and the Multi-Omics and Health-Care Data Analytics Unit at Sant'Orsola Hospital.
MaldiSuite - a Python ecosystem for MALDI-TOF spectral processing and analysis in antimicrobial resistance research. Visit the MaldiSuite website.
Three sklearn-compatible packages that chain into an end-to-end clinical AMR pipeline: preprocess with MaldiAMRKit, harmonise across batches/sites with MaldiBatchKit, classify with MaldiDeepKit.
| Research focus | Description |
|---|---|
|
Antimicrobial resistance prediction MALDI-TOF mass spectrometry · supervised learning · deep neural networks |
Machine learning on mass spectra and clinical data to anticipate resistance phenotypes prior to culture-based diagnostics. → MaldiSuite, ResPredAI |
|
Multi-centre data harmonisation Batch-effect correction · ComBat · batch-mixing diagnostics |
Batch-effect correction methods for machine learning models on high-throughput data across instruments and clinical sites. → MaldiBatchKit, combatlearn |
|
Computational patient phenotyping unsupervised clustering · survival analysis · multi-state modelling |
Discovery of clinically meaningful subgroups from heterogeneous patient cohorts, with prognostic and trajectory modelling. → phenocluster |
|
Genomics and metagenomics analyses microbial community networks · pathogen detection · structural and somatic variants · mutational signatures · CRISPR-Cas9 editing |
Network-based modelling of microbial communities for pathogen detection, characterisation of structural and somatic variants and of mutational signatures, with broader interests in computational tools for CRISPR-Cas9 genome editing. → CATS, APOBECSeeker, CAMISIM-BrokenStick |
| Project | Description |
|---|---|
| combatlearn | Scikit-learn compatible ComBat batch-effect correction |
| ResPredAI | AI model to predict resistances in Gram-negative bloodstream infections |
| phenocluster | Unsupervised clinical phenotype discovery with survival and multistate modeling |
| CATS | Automated Cas9 nuclease comparison with ClinVar integration |
| CAMISIM-BrokenStick | Broken stick model extension for metagenomic simulation |
| APOBECSeeker | APOBEC-style mutation identification from multiple sequence alignment |
| nestkit | Nested cross-validation with calibration, threshold optimization, and statistical tests |
For a complete list, see my Google Scholar profile.
-
Rocchi, E. et al. Combining mass spectrometry and machine learning models for predicting Klebsiella pneumoniae antimicrobial resistance: a multicenter experience from clinical isolates in Italy. BMC Microbiology (2026).
-
Bonazzetti, C., Rocchi, E. et al. Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections. npj Digital Medicine 8, 319 (2025).
-
Rocchi, E. et al. CATS: a bioinformatic tool for automated Cas9 nucleases activity comparison in clinically relevant contexts. Frontiers in Genome Editing 7, 1571023 (2025).