arXiv subjects

Barbara Di Camillo

Publications and source records attributed to Barbara Di Camillo.

7 recordsLinked to original sources

arXiv2026

muxvizpy: a Python library for the analysis of multilayer biological networks

Biological systems are inherently multilayered: the same entities---genes, cells, or bacterial species---participate simultaneously in qualitatively distinct types of interactions, each carrying complementary information that no single relational view can capture. Analysing such systems with single-layer tools, or by collapsing layers into a monoplex projection, systematically discards inter-layer dependencies and can yield misleading conclusions about centrality, community structure, and robustness. The multilayer network formalism addresses, and \texttt{muxViz} established one of the first comprehensive toolkits for its structural analysis, but its R-only interface and dense data structures limit applicability to large biological networks. We introduce \textit{muxvizpy}, a Python library that reimplements and extends the \texttt{muxViz} analytical catalogue with a sparse linear-algebra stack built on SciPy and PyTorch. Muxvizpy exposes seven categories through a unified, composable API and is numerically validated against \texttt{muxViz} on synthetic Erdős--Rényi and Barabási--Albert multiplex networks while substantially reducing peak memory and wall-clock time at scale. We illustrate its applicability on a virus--human protein-interaction multiplex in which computing some structural analysis was unfeasible. \\[2pt] muxvizpy is freely available under the MIT licence at https://github.com/CoMuNeLab/MuxVizPy. Mathematical definitions of all implemented metrics are provided in the Additional File.

q-bio.QM↗

arXiv2026

Integrating gene regulatory priors into Transformer attention with scTransformer for interpretable scRNA-seq analysis

Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supervised learning on millions of cells. However, most existing approaches treat genes as independent features, and largely ignore prior biological knowledge, which limits interpretability and robustness. In this paper, we explore whether explicitly incorporating gene regulatory information can improve both model performance and biological insight. Results: We present scTransformer, the first Transformer-based approach that builds a priori knowledge of biological mechanisms into the model's attention patterns. By constraining information flow according to known regulatory structures, the model learns representations that are more biologically meaningful. We evaluate scTransformer on a disease-relevant single-nucleus RNA-seq dataset using supervised cell-type classification. Compared to standard Transformers, our approach improves classification accuracy, enhances separation of cell types in embedding space, and produces attention patterns consistent with known regulatory programs. Overall, our results demonstrate that embedding biological structure into Transformer models can enhance interpretability without sacrificing performance, offering a principled step toward biologically grounded foundation models for single-cell omics.

q-bio.GN↗

arXiv2024

Validity of Feature Importance in Low-Performing Machine Learning for Tabular Biomedical Data

In tabular biomedical data analysis, tuning models to high accuracy is considered a prerequisite for discussing feature importance, as medical practitioners expect the validity of feature importance to correlate with performance. In this work, we challenge the prevailing belief, showing that low-performing models may also be used for feature importance. We propose experiments to observe changes in feature rank as performance degrades sequentially. Using three synthetic datasets and six real biomedical datasets, we compare the rank of features from full datasets to those with reduced sample sizes (data cutting) or fewer features (feature cutting). In synthetic datasets, feature cutting does not change feature rank, while data cutting shows higher discrepancies with lower performance. In real datasets, feature cutting shows similar or smaller changes than data cutting, though some datasets exhibit the opposite. When feature interactions are controlled by removing correlations, feature cutting consistently shows better stability. By analyzing the distribution of feature importance values and theoretically examining the probability that the model cannot distinguish feature importance between features, we reveal that models can still distinguish feature importance despite performance degradation through feature cutting, but not through data cutting. We conclude that the validity of feature importance can be maintained even at low performance levels if the data size is adequate, which is a significant factor contributing to suboptimal performance in tabular medical data analysis. This paper demonstrates the potential for utilizing feature importance analysis alongside statistical analysis to compare features relatively, even when classifier performance is not satisfactory.

stat.ML↗

arXiv2024

Effect of Clinical History on Predictive Model Performance for Renal Complications of Diabetes

Diabetes is a chronic disease characterised by a high risk of developing diabetic nephropathy, which, in turn, is the leading cause of end-stage chronic kidney disease. The early identification of individuals at heightened risk of such complications or their exacerbation can be of paramount importance to set a correct course of treatment. In the present work, from the data collected in the DARWIN-Renal (DApagliflozin Real-World evIdeNce-Renal) study, a nationwide multicentre retrospective real-world study, we develop an array of logistic regression models to predict, over different prediction horizons, the crossing of clinically relevant glomerular filtration rate (eGFR) thresholds for patients with diabetes by means of variables associated with demographic, anthropometric, laboratory, pathology, and therapeutic data. In doing so, we investigate the impact of information coming from patient's past visits on the model's predictive performance, coupled with an analysis of feature importance through the Boruta algorithm. Our models yield very good performance (AUROC as high as 0.98). We also show that the introduction of information from patient's past visits leads to improved model performance of up to 4%. The usefulness of past information is further corroborated by a feature importance analysis.

q-bio.QM↗

arXiv2024

Exploring the Impact of Environmental Pollutants on Multiple Sclerosis Progression

Multiple Sclerosis (MS) is a chronic autoimmune and inflammatory neurological disorder characterised by episodes of symptom exacerbation, known as relapses. In this study, we investigate the role of environmental factors in relapse occurrence among MS patients, using data from the H2020 BRAINTEASER project. We employed predictive models, including Random Forest (RF) and Logistic Regression (LR), with varying sets of input features to predict the occurrence of relapses based on clinical and pollutant data collected over a week. The RF yielded the best result, with an AUC-ROC score of 0.713. Environmental variables, such as precipitation, NO2, PM2.5, humidity, and temperature, were found to be relevant to the prediction.

cs.LG↗

arXiv2024

Challenges and opportunities for digital twins in precision medicine: a complex systems perspective

The adoption of digital twins (DTs) in precision medicine is increasingly viable, propelled by extensive data collection and advancements in artificial intelligence (AI), alongside traditional biomedical methodologies. However, the reliance on black-box predictive models, which utilize large datasets, presents limitations that could impede the broader application of DTs in clinical settings. We argue that hypothesis-driven generative models, particularly multiscale modeling, are essential for boosting the clinical accuracy and relevance of DTs, thereby making a significant impact on healthcare innovation. This paper explores the transformative potential of DTs in healthcare, emphasizing their capability to simulate complex, interdependent biological processes across multiple scales. By integrating generative models with extensive datasets, we propose a scenario-based modeling approach that enables the exploration of diverse therapeutic strategies, thus supporting dynamic clinical decision-making. This method not only leverages advancements in data science and big data for improving disease treatment and prevention but also incorporates insights from complex systems and network science, quantitative biology, and digital medicine, promising substantial advancements in patient care.

physics.bio-ph↗

arXiv2010

An Optimized Data Structure for High Throughput 3D Proteomics Data: mzRTree

As an emerging field, MS-based proteomics still requires software tools for efficiently storing and accessing experimental data. In this work, we focus on the management of LC-MS data, which are typically made available in standard XML-based portable formats. The structures that are currently employed to manage these data can be highly inefficient, especially when dealing with high-throughput profile data. LC-MS datasets are usually accessed through 2D range queries. Optimizing this type of operation could dramatically reduce the complexity of data analysis. We propose a novel data structure for LC-MS datasets, called mzRTree, which embodies a scalable index based on the R-tree data structure. mzRTree can be efficiently created from the XML-based data formats and it is suitable for handling very large datasets. We experimentally show that, on all range queries, mzRTree outperforms other known structures used for LC-MS data, even on those queries these structures are optimized for. Besides, mzRTree is also more space efficient. As a result, mzRTree reduces data analysis computational costs for very large profile datasets.

cs.CE↗