DNA methylation is a key epigenetic modification with diagnostic and prognostic relevance across a wide range of diseases, particularly cancer. Modern array-based technologies enable high-throughput quantification of methylation states at hundreds of thousands of CpG sites, yielding high-dimensional datasets that pose significant challenges for exploratory analysis and feature prioritization. Existing visualization tools often lack interactivity, integration with machine learning methods, or flexible mechanisms for dynamic dimensionality reduction and biological interpretation. This work presents an interactive analytical framework that extends the Self-Organizing Map approach for epigenomic data exploration. Our method introduces metasites-representative prototypes of CpG site clusters-enabling interpretable, real-time visualization and machine learning over reduced feature spaces. Through conditional sample projections (e.g., via PCA, t-SNE, or UMAP), user-driven region selection, and the integration of sparsity-controlled logistic regression, we generate metasite relevance maps that reveal discriminative epigenetic patterns and guide downstream analysis. The proposed approach supports iterative, visually driven discovery of co-regulated modules and disease-associated methylation signatures, offering a powerful and intuitive interface for multidimensional exploration of complex methylation landscapes. Its utility is demonstrated through the analysis of DNA methylation in pheochromocytomas and paragangliomas, focusing on SDHB mutation status and the role of protocadherine gene clusters.

We propose an adversarial-based data augmentation method to improve the robustness of object detection models, specifically for industrial defect detection.Unlike prior approaches focused on classification or synthetic datasets, our method generates adversarial examples that target both classification and localization outputs.We further introduce controlled white noise to these examples, enhancing robustness against environmental variations.Empirical evaluation on a real-world dataset of defective laser welding images shows that our approach outperforms standard data augmentation and existing adversarial training methods, improving both model accuracy and resilience to diverse perturbations encountered in real-world settings.

Abstract Energy management requires reliable tools to support decisions aimed at optimising consumption. Advances in data-driven models provide techniques like Non-Intrusive Load Monitoring (NILM), which estimates the energy demand of appliances from total consumption. Common single-target NILM approaches perform energy disaggregation by using separate learned models for each device. However, the use of single-target systems in real scenarios is computationally expensive and can obscure the interpretation of the resulting feedback. This study assesses a conditioned deep neural network built upon a Fully Convolutional Denoising AutoEncoder (FCNdAE) as multi-target NILM model. The network performs multiple disaggregations using a conditioning input that allows the specification of the target appliance. Experiments compare this approach with several single-target and multi-target models using public residential data from households and non-residential data from a hospital facility. Results show that the multi-target FCNdAE model enhances the disaggregation accuracy compared to previous models, particularly in non-residential data, and improves computational efficiency by reducing the number of trainable weights below 2 million and inference time below 0.25 s for several sequence lengths. Furthermore, the conditioning input helps the user to interpret the model and gain insight into its internal behaviour when predicting the energy demand of different appliances.

By leveraging the SOM algorithm and the extensive epigenomic data from TCGA, this work aims to suggest a valid approach to explore the relationships between epigenetic alterations and PCPG pathogenesis.Additionally, the methodological approach presented here lays the foundation for a potentially valuable analysis tool that can be applied to other cancer types and epigenetic research.

Epistemic uncertainty arises from input data areas where models lack exposure during training and may result in significant performance degradation in deployment.Echo State Networks are often used as virtual sensors or digital twins processing temporal input data, so their robustness against this degradation is crucial.This paper addresses this challenge by proposing a score comparing the similarity between the dynamic evolution of the reservoir in training and in inference.This research aims to enhance model confidence and adaptability in evolving circumstances.

Efforts to reduce energy consumption in buildings are crucial for climate change concerns.In this sense, energy monitoring increases energy awareness and mitigates energy wastes.This study integrates machine learning models, advanced visualisations, and interactive tools to create an insightful energy monitoring dashboard.Novel contributions include a 2D map of daily energy demand profiles combining spatial encodings based on t-SNE, fluid aggregation, and filter operations via a datacube framework, as well as visual encoding powered by morphing projections.This approach facilitates the decisions of end users regarding the optimisation of energy in residential facilities.

One of the major goals in gene expression data analysis is to explore and discover groups of genes and groups of biological conditions with meaningful relationships. While this problem can be addressed by algorithms, their results require an analysis within context, since they may be affected by many side processes -such as tissue differentiation- that could hinder the target goal. Visual analytics-based methods for exploratory analysis of the gene expression matrix (GEM) are essential in biomedical research since they allow us to frame the analysis within the user's knowledge domain. In this paper, we present a visual analytics approach to discover relevant connections between genes and samples based on linking a reordered GEM heatmap and dual 2D projections of its rows and columns, which can be recomputed conditioned by subsets of genes and/or samples selected by the user during the analysis. We demonstrate the capability of our approach to discover relevant knowledge in three case studies involving two cancer types plus normal tissue from the TCGA database.

Biomedical data recorded as a result of clinical practice are often multi-domain -involving lab measurements, medication, patient attributes, logistic information-, and also highly unstructured, with high rates of missing data and asynchronously sampled measurements.In this scenario, we need tools capable of providing a broad picture prior to more detailed analyses.We present here a visual analytics approach that uses the morphing projections technique to combine the visualization of a t-SNE projection of clinical time series, with views of other clinical or patient's information.The proposed approach is demonstrated on an application case study of COVID-19 clinical information taken during the first wave.

We present an application of interactive dimensionality reduction (DR) for exploratory analysis of gene expression data that produces two lively updated projections, a sample map and a gene map, by rendering intermediate results of a t-SNE.The user can condition the projections "on the fly" by subsets of genes or samples, so updated views reveal coexpression patterns for different cancer types or gene groups.

MOTIVATION: Biomedical research entails analyzing high dimensional records of biomedical features with hundreds or thousands of samples each. This often involves using also complementary clinical metadata, as well as a broad user domain knowledge. Common data analytics software makes use of machine learning algorithms or data visualization tools. However, they are frequently one-way analyses, providing little room for the user to reconfigure the steps in light of the observed results. In other cases, reconfigurations involve large latencies, requiring a retraining of algorithms or a large pipeline of actions. The complex and multiway nature of the problem, nonetheless, suggests that user interaction feedback is a key element to boost the cognitive process of analysis, and must be both broad and fluid. RESULTS: In this article, we present a technique for biomedical data analytics, based on blending meaningful views in an efficient manner, allowing to provide a natural smooth way to transition among different but complementary representations of data and knowledge. Our hypothesis is that the confluence of diverse complementary information from different domains on a highly interactive interface allows the user to discover relevant relationships or generate new hypotheses to be investigated by other means. We illustrate the potential of this approach with three case studies involving gene expression data and clinical metadata, as representative examples of high dimensional, multidomain, biomedical data. AVAILABILITY AND IMPLEMENTATION: Code and demo app to reproduce the results available at https://gitlab.com/idiazblanco/morphing-projections-demo-and-dataset-preparation. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Abstract Visual analytics systems combine machine learning or other analytic techniques with interactive data visualization to promote sensemaking and analytical reasoning. It is through such techniques that people can make sense of large, complex data. While progress has been made, the tactful combination of machine learning and data visualization is still under‐explored. This state‐of‐the‐art report presents a summary of the progress that has been made by highlighting and synthesizing select research advances. Further, it presents opportunities and challenges to enhance the synergy between machine learning and visual analytics for impactful future research directions.

Models are descriptions of real facts that serve us to think and reason. In building models, a compromise always exists between accuracy, that is, how precisely the model describes reality, and simplicity, without which the model would be useless. So, a good model must be simple and intuitive while being accurate enough. In this paper we propose a novel approach based on visual techniques aiming to help the human in fine-tuning fuzzy decision trees to enhance its interpretability and insightfulness with a minimal loss of accuracy. By involving the human in the design process, these techniques allow to include prior knowledge in the selection of membership functions as well as to assess the significance of rules in the model to help in the pruning stage.