Pasar al contenido principal

NUEVAS TECNOLOGIAS BASADAS EN LA CARACTERIZACION SECUENCIAL PARA LA VINCULACION DE DINAMICAS FISIOLOGICAS A SU FUNCIONALIDAD

PID2021-122347NB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2021
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD AUTONOMA DE MADRID

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

A machine learning approach to identify groups of patients with hematological malignant disorders

  • Rodríguez-Belenguer, Pablo
  • Piñana, José Luis
  • Sánchez Montañés, Manuel
  • Soria Olivas, Emilio
  • Martínez Sober, Marcelino
  • Serrano López, Antonio J.
Background and objective: Vaccination against SARS-CoV-2 in immunocompromised patients with hematologic malignancies (HM) is crucial to reduce the severity of COVID-19. Despite vaccination efforts, over a third of HM patients remain unresponsive, increasing their risk of severe breakthrough infections. This study aims to leverage machine learning's adaptability to COVID-19 dynamics, efficiently selecting patient-specific features to enhance predictions and improve healthcare strategies. Highlighting the complex COVID-hematology connection, the focus is on interpretable machine learning to provide valuable insights to clinicians and biologists. Methods: The study evaluated a dataset with 1166 patients with hematological diseases. The output was the achievement or non-achievement of a serological response after full COVID-19 vaccination. Various machine learning methods were applied, with the best model selected based on metrics such as the Area Under the Curve (AUC), Sensitivity, Specificity, and Matthew Correlation Coefficient (MCC). Individual SHAP values were obtained for the best model, and Principal Component Analysis (PCA) was applied to these values. The patient profiles were then analyzed within identified clusters. Results: Support vector machine (SVM) emerged as the best-performing model. PCA applied to SVM-derived SHAP values resulted in four perfectly separated clusters. These clusters are characterized by the proportion of patients that generate antibodies (PPGA). Cluster 1, with the second-highest PPGA (69.91%), included patients with aggressive diseases and factors contributing to increased immunodeficiency. Cluster 2 had the lowest PPGA (33.3%), but the small sample size limited conclusive findings. Cluster 3, representing the majority of the population, exhibited a high rate of antibody generation (84.39%) and a better prognosis compared to cluster 1. Cluster 4, with a PPGA of 66.33%, included patients with B-cell non-Hodgkin's lymphoma on corticosteroid therapy. Conclusions: The methodology successfully identified four separate patient clusters using Machine Learning and Explainable AI (XAI). We then analyzed each cluster based on the percentage of HM patients who generated antibodies after COVID-19 vaccination. The study suggests the methodology's potential applicability to other diseases, highlighting the importance of interpretable ML in healthcare research and decision-making., We thank the Spanish Hematopoietic Transplant and Cell Therapy group (GETH-TC) for sharing the data. The co-author Manuel Sánchez-Montañés has been supported by grants PID2021-122347NB-I00 and PID2021-127946OB-I00 (funded by MCIN/AEI//10.13039/501100011033 and ERDF “A way of making Europe”), and from project FACINGLCOVID-CM under grant PD2022-004-REACT-EU.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Simulating macroevolutionary trends and open-ended evolution with a novel mechanistic multi-level approach

  • Latorre, Roberto
  • Brun-Usan, Miguel
  • Fernández-Lázaro, Gloria
Microevolution and macroevolution describe evolutionary change at different scales: short-term genetic and phenotypic variation within populations, and long-term patterns of diversification and extinction. Despite their interconnected nature, they have often been studied separately, and the reciprocal causal links between them remain poorly understood due to their operation on different timescales and the complexity of the processes involved, making mechanistic approaches particularly challenging. To bridge this operational gap, we introduce a novel bottom-up, process-based computational framework that integrates genotype-to-phenotype mapping, fitness evaluation under environmental constraints, and biotic interactions shaping ecological niches and adaptive pressures, while incorporating lower-level mechanisms such as mutation, gene flow, and gene-pool expansion through stochastic duplication of genes. Its modular design accommodates diverse microevolutionary mechanisms to study the emergence of large-scale eco-evolutionary patterns from explicit individual-level processes. The framework allows addressing research questions ranging from the formation of spatiotemporal biodiversity patterns to the role of eco-evolutionary feedbacks in macroevolution. It provides an open-ended platform that serves both as a theoretical tool for testing evolutionary hypotheses and as a flexible environment for exploratory simulations. To illustrate its heuristic potential, we present proof-of-concept simulations under biologically plausible conditions that reproduce multiple well-documented macroevolutionary patterns–such as biphasic diversification, saturating and exponential-like biodiversity trends, speciation–extinction correlations, species duration distributions, and niche structuring–as emergent phenomena. Beyond reproducing patterns, the simulations reveal underlying mechanisms, including trial-and-error dynamics in long-term adaptation, high species turnover maintaining biodiversity equilibrium, and self-organized niche occupancy. These findings establish the framework as a versatile tool for investigating the complex interplay of ecological and evolutionary forces shaping biodiversity. By capturing emergent dynamics from mechanistic microevolutionary processes without imposing predefined constraints, the model provides a unique perspective on long-term evolutionary change, contributing to a broader theoretical toolkit for studying macroevolutionary patterns under controlled conditions. Future extensions could assess how variations in environmental dynamics, genomic architecture, or species interactions influence evolutionary trajectories, refining our understanding of biodiversity evolution., This research was supported by grants PID2021-122347NB-I00 and PID2024-155923NB-I00 (MCIN/AEI and ERDF- “A way of making Europe”, Spain)., Peer reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A machine learning approach to identify groups of patients with hematological malignant disorders

  • Rodríguez-Belenguer, Pablo
  • Piñana, José Luis
  • Sánchez Montañés, Manuel
  • Soria Olivas, Emilio
  • Martínez Sober, Marcelino
  • Serrano López, Antonio J.
Background and objective: Vaccination against SARS-CoV-2 in immunocompromised patients with hematologic malignancies (HM) is crucial to reduce the severity of COVID-19. Despite vaccination efforts, over a third of HM patients remain unresponsive, increasing their risk of severe breakthrough infections. This study aims to leverage machine learning's adaptability to COVID-19 dynamics, efficiently selecting patient-specific features to enhance predictions and improve healthcare strategies. Highlighting the complex COVID-hematology connection, the focus is on interpretable machine learning to provide valuable insights to clinicians and biologists. Methods: The study evaluated a dataset with 1166 patients with hematological diseases. The output was the achievement or non-achievement of a serological response after full COVID-19 vaccination. Various machine learning methods were applied, with the best model selected based on metrics such as the Area Under the Curve (AUC), Sensitivity, Specificity, and Matthew Correlation Coefficient (MCC). Individual SHAP values were obtained for the best model, and Principal Component Analysis (PCA) was applied to these values. The patient profiles were then analyzed within identified clusters. Results: Support vector machine (SVM) emerged as the best-performing model. PCA applied to SVM-derived SHAP values resulted in four perfectly separated clusters. These clusters are characterized by the proportion of patients that generate antibodies (PPGA). Cluster 1, with the second-highest PPGA (69.91%), included patients with aggressive diseases and factors contributing to increased immunodeficiency. Cluster 2 had the lowest PPGA (33.3%), but the small sample size limited conclusive findings. Cluster 3, representing the majority of the population, exhibited a high rate of antibody generation (84.39%) and a better prognosis compared to cluster 1. Cluster 4, with a PPGA of 66.33%, included patients with B-cell non-Hodgkin's lymphoma on corticosteroid therapy. Conclusions: The methodology successfully identified four separate patient clusters using Machine Learning and Explainable AI (XAI). We then analyzed each cluster based on the percentage of HM patients who generated antibodies after COVID-19 vaccination. The study suggests the methodology's potential applicability to other diseases, highlighting the importance of interpretable ML in healthcare research and decision-making., We thank the Spanish Hematopoietic Transplant and Cell Therapy group (GETH-TC) for sharing the data. The co-author Manuel Sánchez-Montañés has been supported by grants PID2021-122347NB-I00 and PID2021-127946OB-I00 (funded by MCIN/AEI//10.13039/501100011033 and ERDF “A way of making Europe”), and from project FACINGLCOVID-CM under grant PD2022-004-REACT-EU.