MOTIVATIONS: Electroencephalography (EEG) is a non-invasive method that records brain electrical activity from scalp electrodes, offering millisecond temporal resolution but limited spatial detail due to sparse sensor layouts. RESULTS: We present DiBiMa-EEGSR, a bidirectional Mamba-2 diffusion framework for spatio-temporal EEG super-resolution that reconstructs high-resolution signals from standard low-density recordings without additional hardware. The method formulates super-resolution as conditional generative inference and integrates a diffusion process with a bidirectional state-space backbone to model long-range temporal dependencies with linear complexity. Conditioning on low-resolution inputs, electrode positions and task labels enables anatomically coherent and context-aware reconstruction. A one-step sampling strategy substantially reduces inference time while preserving fidelity. Across two public benchmarks, the approach improves reconstruction accuracy, spatial coherence and spectral preservation over convolutional, transformer-based and prior diffusion models in both spatial and temporal upsampling tasks, providing a scalable pathway toward high-resolution electrophysiological imaging. AVAILABILITY AND IMPLEMENTATION: Code to reproduce ablation experiments, training and evaluation of the proposed BiMa and DiBiMa EEGSR models are available at https://github.com/UgoLomoio/DiBiMa-EEGSR.git. Model weights are available at https://huggingface.co/Ugo96/DiBiMa-EEGSR while an interactive demo for EEG spatial super-resolution using our models can be found at https://huggingface.co/spaces/Ugo96/DiBiMa-EEGSR-Demo.

Electrocardiogram signals play a pivotal role in cardiovascular diagnostics, providing essential information on electrical hearth activity. However, inherent noise and limited resolution can hinder an accurate interpretation of the recordings. In this paper an advanced Denoising Convolutional Autoencoder designed to process electrocardiogram signals, generating super-resolution reconstructions is proposed; this is followed by in-depth analysis of the enhanced signals. The autoencoder receives a signal window (of 5 s) sampled at 50 Hz (low resolution) as input and reconstructs a denoised super-resolution signal at 500 Hz. The proposed autoencoder is applied to publicly available datasets, demonstrating optimal performance in reconstructing high-resolution signals from very low-resolution inputs sampled at 50 Hz. The results were then compared with current state-of-the-art for electrocardiogram super-resolution, demonstrating the effectiveness of the proposed method. The method achieves a signal-to-noise ratio of 12.20 dB, a mean squared error of 0.0044, and a root mean squared error of 4.86%, which significantly outperforms current state-of-the-art alternatives. This framework can effectively enhance hidden information within signals, aiding in the detection of heart-related diseases. • We defined a novel architecture based on autocencoders which is able to denoise and reconstruct high resolution copies of input low resolution ECG signals. • This unique approach that has not been previously applied to ECG signals. • We also present a deep validation of our approach against traditional and contemporary methods in terms of signal-to-noise ratio, mean squared error, and root mean squared error with those of other widely used ECG signal processing techniques. • The results consistently showed superior performance, further validating the effectiveness of our approach. • Given the increasing reliance on effective and efficient diagnostic techniques in medical practice, especially in cardiology, the findings of our study have significant practical implications.

Recently, the availability of many omics data source has given the rise of modelling biological networks for each individual or patient. Such networks are able to represent individual-specific characteristics, providing insights into the condition of each person. Given a set of networks of individuals, a network representing a particular condition (e.g., an individual with a specific disease) may be seen as an anomaly network. Consequently, the use of Graph Anomaly Detection techniques may support such analysis. Among the others, Generative Adversarial Networks present optimal performances in anomaly detection. This paper presents ADIN (Anomaly Detection in Individual Networks), a framework based on Generative Adversarial Attributed Networks (GAANs) for anomaly detection in convergence/divergence patients attributed networks. Preliminary results on networks generated from computational biology gene expression data demonstrate the effectiveness of our approach in detecting and explaining bladder cancer patients.

There is increasing evidence that many molecular processes exhibit differences with age and sex. Such differences produce also differences in the insurgence and progression of many complex diseases. For instance, demographic data on the insurgence of comorbidities of mellitus diabetes, on the lethality of COVID-19, and on some cancers shows differences between sex and age groups. Therefore, the growing interest in such areas requires the management of related data as well as the development of algorithms and tools for the analysis. The availability of omics data annotated with metadata related to age and sex is mandatory for building the analysis pipeline. The number of databases containing data related to age and sex is henceforth growing. We here show some databases and tools storing such data. Finally, future research directions are highlighted.

MOTIVATION: Studying ageing effects on molecules is an important new topic for life science. To perform such studies, the need for data, models, algorithms, and tools arises to elucidate molecular mechanisms. GTEx (standing for Genotype-Tissue Expression) portal is a web-based data source allowing to retrieve patients' transcriptomics data annotated with tissues, gender, and age information. It represents the more complete data sources for ageing effects studies. Nevertheless, it lacks functionalities to query data at the sex/age level, as well as tools for protein interaction studies, thereby limiting ageing studies. As a result, users need to download query results to proceed to further analysis, such as retrieving the expression of a given gene on different age (or sex) classes in many tissues. RESULTS: We present the GTExVisualizer, a platform to query and analyse GTEx data. This tool contains a web interface able to: (i) graphically represent and study query results; (ii) analyse genes using sex/age expression patterns, also integrated with network-based modules; and (iii) report results as plot-based representation as well as (gene) networks. Finally, it allows the user to obtain basic statistics which evidence differences in gene expression among sex/age groups. CONCLUSION: The GTExVisualizer novelty consists in providing a tool for studying ageing/sex-related effects on molecular processes. AVAILABILITY AND IMPLEMENTATION: GTExVisualizer is available at: http://gtexvisualizer.herokuapp.com. The source code and data are available at: https://github.com/UgoLomoio/gtex_visualizer.

Magnetic Resonance Images (MRI) allow to extract meaningful structural information. Machine learning and neural network based algorithms are used to analyze such images, to extract features and to identify anomalies related to diseases. To perform anomaly detection tasks in MR images of the human brain, we propose the use of the Variational AutoEncoder (VAE) method. A VAE is a deep-learning method able to compress and reconstruct the original image through well-defined functions aiming to extract only significant features that are used to identify abnormal pattern. In this contribution, we present a tool based on VAE method for the identification and annotation of brain lesions in MRI aiming to support physicians in the detection of anomalies. Moreover, a MongoDB database is also used to store the data and manage the annotations.

Recently there is a growing interest for the study of the molecular basis of ageing processes and on the differences among genders. These studies require many data, models and tools for inferring molecular mechanisms. Among the others, the Genotype-Tissue Expression (GTEx) database is one of the prominent resources for the analysis of expression data related to tissues, sex and age. The current version of the database has a lot of querying interfaces that enable many analysis centred on the expression of genes on tissues. Despite this, the database lacks on the analysis at sex/age level, thus the researcher has to download data and then write queries by hand (e.g. for retrieving the expression of a given gene on different age-class in many tissues). It also lacks on the integration with existing protein interaction data. Therefore, the need for the introduction of tools enabling easy access and powerful analysis capabilities (i.e. state of the art network based analysis and integration), arises. We here present NOMA-DB, a framework for ageing studies based on an extension of the GTEx database that enable easy querying at sex/age level, network based analysis. The framework is based on wrapping the GTEx database and on building an application logic level on top of existing data. The current version enables the analysis of genes by tissue, gene and age, thus it may be used in potentially future directions of analysis towards better comprehension of aging/sex-related molecular processes based on the analysis of expression data.