Coastal marine ecosystems face mounting pressures from anthropogenic activities and climate change, necessitating advanced monitoring and modeling approaches for effective management. This paper pioneers the development of a Marine Digital Twin Platform aimed at modeling the Mar Menor Coastal Lagoon Ecosystem in the Region of Murcia. The platform leverages Artificial Intelligence to emulate complex hydrological and ecological models, facilitating the simulation of what-if scenarios to predict ecosystem responses to various stressors. We integrate diverse datasets from public sources to construct a comprehensive digital representation of the lagoon’s dynamics. The platform’s modular design enables real-time stakeholder engagement and informed decision-making in marine management. Our work contributes to the ongoing discourse on advancing marine science through innovative digital twin technologies.

The association of a given human phenotype with a genetic variant remains a critical challenge in biomedical research. We present PhenoLinker, a novel graph-based system capable of associating a score to a phenotype-gene relationship by using heterogeneous information networks and a convolutional neural network-based model for graphs, which can provide an explanation for the predictions. Unlike previous approaches, PhenoLinker integrates gene and phenotype attributes, while maintaining explainability through Integrated Gradients. PhenoLinker consistently outperforms existing models in both retrospective and temporal validation tasks. This system can aid in the discovery of new associations and in understanding the consequences of human genetic variation. • PhenoLinker: Advanced Gene-Phenotype Prediction Model: Superior prediction capabilities for gene-phenotype associations • Clear Explanations for Association Predictions: Provides insights into gene-phenotype links • Validated Real-World Impact: Proven reliability in improving genetic diagnoses • Accessible Research Tool: Predictions and visualization openly available, fostering collaboration in gene-phenotype studies

• We propose a new method for embedding dimensions interpretation based on assigning concepts to the individual dimensions that we apply to a variety of LLMs. • Our innovation includes 1) using ontologies within a domain to extract the interpretation concepts, 2) a new metric that allows us to measure the goodness of allocation of the concepts within dimension in terms of interpretability, and 3) a thorough study of statistical distances identifying KL as the best one. • We empirically demonstrate that the quality of interpretability within equally complex LLMs is not neccesarily associated with the language model performance. • We illustrate the feasibility and applicability of our method through experiments with two ontologies, HPO and GO, and four different LLMs. As language models are used in more applications, a key problem has become clear: their numerical embeddings are hard to interpret because it is unclear how each part of the vector relates to real-world meanings in specific fields. The prevailing embedding methods are inadequate in their current state, as they are unable to effectively bridge the gap between mathematical representations and human-understandable knowledge structures. The present study proposes a novel framework that explicitly links ontology classes to specific embedding dimensions through a dual-component architecture combining a text encoder that produces the target embedding dimensions with domain knowledge graphs. The Area Under the Interpretability Curve (AUIC) metric is introduced as a means to systematically evaluate model-alignment with ontological concepts. The analysis reveals that targeted dimensional mapping enables direct interpretation of individual vector components through ontological terms. The practical applications of this framework are illustrated through case studies in biomedical contexts, demonstrating enhanced model transparency without compromising performance. This approach establishes a measurable pathway for reconciling statistical language representations with structured domain knowledge, particularly benefiting fields requiring precise concept alignment like biomedicine. The implementation is publicly available at: https://github.com/Mellandd/DEIBO .

BACKGROUND: Gene set enrichment analysis (detecting phenotypic terms that emerge as significant in a set of genes) plays an important role in bioinformatics focused on diseases of genetic basis. To facilitate phenotype-oriented gene set analysis, we developed PhenoExam, a freely available R package for tool developers and a web interface for users, which performs: (1) phenotype and disease enrichment analysis on a gene set; (2) measures statistically significant phenotype similarities between gene sets and (3) detects significant differential phenotypes or disease terms across different databases. RESULTS: PhenoExam generates sensitive and accurate phenotype enrichment analyses. It is also effective in segregating gene sets or Mendelian diseases with very similar phenotypes. We tested the tool with two similar diseases (Parkinson and dystonia), to show phenotype-level similarities but also potentially interesting differences. Moreover, we used PhenoExam to validate computationally predicted new genes potentially associated with epilepsy. CONCLUSIONS: We developed PhenoExam, a freely available R package and Web application, which performs phenotype enrichment and disease enrichment analysis on gene set G, measures statistically significant phenotype similarities between pairs of gene sets G and G' and detects statistically significant exclusive phenotypes or disease terms, across different databases. We proved with simulations and real cases that it is useful to distinguish between gene sets or diseases with very similar phenotypes. Github R package URL is https://github.com/alexcis95/PhenoExam . Shiny App URL is https://alejandrocisterna.shinyapps.io/phenoexamweb/ .

MOTIVATION: Co-expression networks are a powerful gene expression analysis method to study how genes co-express together in clusters with functional coherence that usually resemble specific cell type behavior for the genes involved. They can be applied to bulk-tissue gene expression profiling and assign function, and usually cell type specificity, to a high percentage of the gene pool used to construct the network. One of the limitations of this method is that each gene is predicted to play a role in a specific set of coherent functions in a single cell type (i.e. at most we get a single for each gene). We present here GMSCA (Gene Multifunctionality Secondary Co-expression Analysis), a software tool that exploits the co-expression paradigm to increase the number of functions and cell types ascribed to a gene in bulk-tissue co-expression networks. RESULTS: We applied GMSCA to 27 co-expression networks derived from bulk-tissue gene expression profiling of a variety of brain tissues. Neurons and glial cells (microglia, astrocytes and oligodendrocytes) were considered the main cell types. Applying this approach, we increase the overall number of predicted triplets by 46.73%. Moreover, GMSCA predicts that the SNCA gene, traditionally associated to work mainly in neurons, also plays a relevant function in oligodendrocytes. AVAILABILITYAND IMPLEMENTATION: The tool is available at GitHub, https://github.com/drlaguna/GMSCA as open-source software. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.