Computational Biomedicine Group
Featured articles
ArticleOpen access
Sparsity is all you need: rethinking biologically informed neural networks
Biologically informed neural networks are increasingly adopted in bioinformatics under the premise that embedding biological knowledge into model architectures yields more accurate and interpretable predictions. This…
ArticleOpen access
JanusDDG: a physics-informed neural network for sequence-based protein stability via two-fronts attention
Predicting how residue variations affect protein stability is crucial for rational protein design and for assessing the impact of disease-related mutations. Recent advances in protein language models have revolutionized…
ArticleOpen access
Beyond Cox models: Assessing the performance of machine-learning methods in non-proportional hazards and non-linear survival analysis
Survival analysis often relies on Cox models, assuming both linearity and proportional hazards (PH). This study evaluates machine and deep learning methods that relax these constraints, comparing their performance with…
ArticleOpen access
Quantum enhanced stratification of breast cancer: exploring quantum expressivity for real omics data
Quantum machine learning (QML) is considered one of the most promising applications of quantum computing in the noisy intermediate-scale quantum (NISQ) era for the impact it is thought to have in the near future…
ArticleOpen access
The specification game: rethinking the evaluation of drug response prediction for precision oncology
Precision oncology plays a pivotal role in contemporary healthcare, aiming to optimize treatments for each patient based on their unique characteristics. This objective has spurred the emergence of various cancer cell…
About the group
The Computational Biomedicine Group is a dedicated research team focused on advancing the field of biomedicine through the application of Artificial Intelligence (AI) and computational techniques. The group's primary aims revolve around harnessing the power of AI in various aspects of biology and medicine, contributing to scientific knowledge, and facilitating biomedical research and application.
Research areas
All publications →Protein Stability and Variant Effect Prediction
Methods that predict protein properties from sequence and structure, above all how amino acid variants change protein stability and function.
Go to publications →Clinical Prediction and Survival Analysis
Machine learning and statistical models that predict clinical outcomes and survival from patient data, including federated learning across hospitals.
Go to publications →Multi-omics and Interpretable Deep Learning
Deep learning on genomic, transcriptomic and other omics data, with a focus on how reliable and interpretable the models are, especially in cancer research.
Go to publications →Genome Sequence Statistics and Evolution
Statistical and physical models of DNA sequences: strand symmetries, codon usage and mutation patterns across genomes.
Go to publications →Quantum Machine Learning
Quantum kernels and quantum machine learning methods, their expressivity and their application to biomedical data.
Go to publications →Bioinformatics Software
Papers that present open-source software, databases and web tools for bioinformatics.
Go to publications →Biomedical Collaborations
Data analysis carried out with clinical and laboratory partners, from biomarker discovery to clinical cohort studies.
Go to publications →
News
All news →ProbJanusDDG presented at BBCC2026
Our PhD student Guido Barducci presented ProbJanusDDG at BBCC2026, the 21st Bioinformatics and Computational Biology Conference, held in Naples from 21 to 23 October 2026. The title of the presentation was ProbJanusDDG…
Sparsity is all you need: out in Briefings in Bioinformatics
Our paper "Sparsity is all you need: rethinking biologically informed neural networks" is now out in Briefings in Bioinformatics. The code is available on GitHub.
JanusDDG published in Communications Biology
Our paper "JanusDDG: a physics-informed neural network for sequence-based protein stability via two-fronts attention" is now published in Communications Biology. The code is available on GitHub.
Web predictors
All tools & software →- PIVKA-HCC (opens in a new tab)
Predict Hepatocellular Carcinoma risk using the PIVKA-II biomarker.
- InterTAKO (opens in a new tab)
Predict in-hospital death for patients with Takotsubo syndrome.
- Canine DLBCL (opens in a new tab)
Predict survival for canine diffuse large B-cell lymphoma.
These predictors are research tools. They are not intended for diagnosis, prognosis or treatment decisions for individual patients, and their results must not replace clinical judgment.
People
Faculty & Staff
Piero Fariselli
Full Professor, Department of Medical Sciences
Tiziana Sanavia
Research Associate, Department of Medical Sciences
Giovanni Birolo
Staff Scientist
Members
Francesco Codicé
Postdoctoral Fellow · PhD in Complex Systems
Flavio Sartori
PhD Student
Isabella Caranzano
PhD Student
Valeria Repetto
PhD Student
Guido Barducci
PhD Student
Virginia Iannibelli
PhD Student
Collaborators
Ivan Rossi
PhD, Fellow at the University of Turin
Past members
Silvia Benevenuta
Corrado Pancotti
Cesare Rollo