Giovanni Birolo

Codon usage bias is a central record of mutation, selection, drift, and translational constraints, but it is usually treated separately from generalized Chargaff symmetry, the tendency for words and their reverse complements to occur at similar frequencies in long DNA sequences. Here we ask whether codon usage contains a measurable reverse-complement component, and whether departures from that component can be quantified. We first avoided imposing reverse-complement symmetry. Instead, we exhaustively evaluated all nontrivial factorized codon involutions . Across taxa, the reverse-complement transformation was the optimum , giving the highest median correlation between codon frequencies and transformed codon frequencies. Random and amino-acid-preserving reference models showed that the signal is not a generic property of codon profiles and is only partly explained by protein composition. Additional controls preserving amino-acid composition and matching GC3 in expectation showed that the observed reverse-complement correlation remains higher than expected from these constraints alone, and genus-level aggregation confirmed that the optimum is not driven by overrepresented genera. The symmetry breaks in a biologically ordered manner: the third, most degenerate codon position remains closest to the reverse-complement baseline, whereas the first departs most strongly and the second is intermediate and lineage dependent. Taxonomic comparisons reveal broad and fine-scale heterogeneity in codon-level symmetry preservation. Together, these results show that codon usage combines reverse-complement preservation with position-, lineage-, and function-dependent departures from the GCT-associated compositional baseline.

We introduce DeepFHT, a survival-analysis framework that couples deep neural networks with first hitting time (FHT) distributions from stochastic process theory. Time to event is represented as the first passage of a latent diffusion process to an absorbing boundary. A neural network maps input variables to physically meaningful parameters including initial condition, drift, and diffusion, within a chosen FHT process such as Brownian motion, both with drift and driftless. This yields closed-form survival and hazard functions and captures time-varying risk without assuming proportional hazards. We compare DeepFHT with Cox regression and DeepHit using synthetic and real-world datasets. The method achieves predictive accuracy on par with state-of-the-art approaches, while maintaining a physics-based interpretable parametrization that elucidates the relation between input features and risk. This combination of stochastic process theory and deep learning provides a principled avenue for modeling survival phenomena in complex systems.

Background: High sodium intake is associated with arterial hypertension and cardiovascular disease, through mechanisms that go beyond hemodynamic changes, including endothelial dysfunction, oxidative stress, and induction of a proinflammatory milieu. The aim of this study was to assess the role of dietary sodium modulation on renal pathophysiology through evaluation of small RNA cargos on urinary extracellular vesicles. Methods: Fourteen high‐risk normotensive subjects with normal kidney function were prospectively enrolled to undergo a low‐sodium diet followed by a high‐sodium diet (HSD). The urinary extracellular vesicles were isolated from a 24‐hour urine collection at the end of each diet phase and profiled by small RNA sequencing. Selected differentially expressed miRNAs were validated in human proximal tubular cell line (human kidney 2 cells) to assess miRNA‐mRNA target interactions. Results: We identified 111 small RNA species, of which 30 were significantly different between the low‐sodium diet and HSD. Bioinformatic network analysis showed that pathways related to the innate and adaptive immune system, interleukin and interferon signaling were enriched in the HSD, whereas pathways related to PPARα (peroxisome proliferator‐activated receptor α) regulation were enriched in the low‐sodium diet. In human kidney 2 cells, the inhibition of miR‐320b, downregulated in the HSD, increased ICAM‐1 (intercellular adhesion molecule 1), with renal proinflammatory effects. The inhibition of miR‐10b‐5p, downregulated in the low‐sodium diet, increased PPARα, which has an antifibrotic and anti‐inflammatory role in the kidney. Conclusions: Small RNA characterization from extracellular vesicles revealed that an HSD is associated with proinflammatory changes, potentially contributing to sodium‐induced low‐grade renal inflammation.

Amyotrophic lateral sclerosis (ALS) and multiple sclerosis (MS) are debilitating diseases with unpredictable progression. Artificial Intelligence-based tools for modelling disease progression could significantly improve the quality of life for patients and caregivers while supporting clinicians in delivering more personalized and timely care. However, the limited availability of data hinders the development, testing, and reproducibility of such predictive tools. To address this challenge, we curated, in the context of the H2020 BRAINTEASER project, four datasets containing clinical data from a total of 2,290 ALS patients and 723 MS patients. These datasets also include environmental data and information collected through wearable devices. Unlike most existing resources, the BRAINTEASER datasets are gathered from clinical practice, offering a more accurate representation of the data that an AI progression prediction tool would encounter in real-world scenarios. In addition to manual and automated data quality checks, the research community has validated the datasets through three editions of the intelligent Disease Progression Prediction challenges held within the Conference and Labs of the Evaluation Forum (CLEF).

The integration of deep learning (DL) with multi-omics data has significantly advanced our understanding of biological systems, particularly in cancer research. DL enables the analysis of high-dimensional datasets and the discovery of novel disease mechanisms and biomarkers, contributing to improved patient treatment and management. This review provides a detailed overview of recent developments in deep learning models applied to genomics data, with a focus on cancer type classification, driver gene identification, survival analysis, and drug response prediction. We introduce the foundational concepts of machine and deep learning and explain the characteristics of multi-omics data, addressing a broad and interdisciplinary audience. Methods published since 2020 are systematically reviewed, including their model architectures, datasets, and key innovations.

Survival analysis, a foundational tool for modeling time-to-event data, has seen growing integration with machine learning (ML) approaches to handle the complexities of censored data and time-varying risks. Despite these advances, leveraging state-of-the-art survival models remains a challenge due to the fragmented nature of existing implementations, which lack standardized interfaces and require extensive preprocessing. We introduce SurvHive, a Python-based framework designed to unify survival analysis methods within a coherent and extensible interface modeled on scikit-learn. SurvHive integrates classical statistical models with cutting-edge deep learning approaches, including transformer-based architectures and parametric survival models. Using a consistent API, SurvHive simplifies model training, evaluation, and optimization, significantly reducing the barrier to entry for ML practitioners exploring survival analysis. The package includes enhanced support for hyper-parameter tuning, time-dependent risk evaluation metrics, and cross-validation strategies tailored to censored data. With its extensibility and focus on usability, SurvHive provides a bridge between survival analysis and the broader ML community, facilitating advancements in time-to-event modeling across domains. The SurvHive code and documentation are available freely at https://github.com/compbiomed-unito/survhive.