Instituto de Ciencia de los Datos e Inteligencia Artificial

Permanent URI for this communityhttps://hdl.handle.net/10171/60356

See

Results

Now showing 1 - 10 of 36
  • Thumbnail Image
    NetActivity enhances transcriptional signals by combining gene expression into robust gene set activity scores through interpretable autoencoders
    (Oxford University Press, 2024) Ruiz, C. (Carlos); Wang, L. (Liewei); Perez-Jurado, L.A. (Luis A.); Ochoa, I. (Idoia); Hernaez, M. (Mikel); Marín-Goñi, I. (Irene)
    Grouping gene expression into gene set activity scores (GSAS) provides better biological insights than studying individual genes. However, existing gene set projection methods cannot return representative, robust, and interpretable GSAS. We developed NetActivity, a machine learning framework that generates GSAS based on a sparsely-connected autoencoder, where each neuron in the inner layer represents a gene set. We proposed a three-tier training that yielded representative, robust, and interpretable GSAS. NetActivity model was trained with 1518 GO biological processes terms and KEGG pathways and all GTEx samples. NetActivity generates GSAS robust to the initialization parameters and representative of the original transcriptome, and assigned higher importance to more biologically relevant genes. Moreover, NetActivity returns GSAS with a more consistent definition and higher interpretability than GSVA and hipathia, state-of-the-art gene set projection methods. Finally, NetActivity enables combining bulk RNA-seq and microarray datasets in a meta-analysis of prostate cancer progression, highlighting gene sets related to cell division, key for disease progression. When applied to metastatic prostate cancer, gene sets associated with cancer progression were also altered due to drug resistance, while a classical enrichment analysis identified gene sets irrelevant to the phenotype. NetActivity is publicly available in Bioconductor and GitHub.
  • Thumbnail Image
    Review and meta-analysis of the genetic Minimal Cut Set approach for gene essentiality prediction in cancer metabolism
    (Oxford University Press, 2024) Valcárcel-García, L.V. (Luis Vitores); Planes-Pedreño, F.J. (Francisco Javier); Barrena, N. (Naroa); Rodríguez, C. (Carlos); Olaverri, D. (Danel)
    Cancer metabolism is a marvellously complex topic, in part, due to the reprogramming of its pathways to self-sustain the malignant phenotype in the disease, to the detriment of its healthy counterpart. Understanding these adjustments can provide novel targeted therapies that could disrupt and impair proliferation of cancerous cells. For this very purpose, genome-scale metabolic models (GEMs) have been developed, with Human1 being the most recent reconstruction of the human metabolism. Based on GEMs, we introduced the genetic Minimal Cut Set (gMCS) approach, an uncontextualized methodology that exploits the concepts of synthetic lethality to predict metabolic vulnerabilities in cancer. gMCSs define a set of genes whose knockout would render the cell unviable by disrupting an essential metabolic task in GEMs, thus, making cellular proliferation impossible. Here, we summarize the gMCS approach and review the current state of the methodology by performing a systematic meta-analysis based on two datasets of gene essentiality in cancer. First, we assess several thresholds and distinct methodologies for discerning highly and lowly expressed genes. Then, we address the premise that gMCSs of distinct length should have the same predictive power. Finally, we question the importance of a gene partaking in multiple gMCSs and analyze the importance of all the essential metabolic tasks defined in Human1. Our meta-analysis resulted in parameter evaluation to increase the predictive power for the gMCS approach, as well as a significant reduction of computation times by only selecting the crucial gMCS lengths, proposing the pertinency of particular parameters for the peak processing of gMCS.
  • Thumbnail Image
    GMCSpy: efficient and accurate computation of genetic minimal cut sets in Python
    (Oxford University Press, 2024) Valcárcel-García, L.V. (Luis Vitores); Ochoa, I. (Idoia); Planes-Pedreño, F.J. (Francisco Javier); Barrena, N. (Naroa); Rodríguez, C. (Carlos); Olaverri, D. (Danel)
    Motivation: The identification of minimal genetic interventions that modulate metabolic processes constitutes one of the most relevant applications of genome-scale metabolic models (GEMs). The concept of Minimal Cut Sets (MCSs) and its extension at the gene level, genetic Minimal Cut Sets (gMCSs), have attracted increasing interest in the field of Systems Biology to address this task. Different computational tools have been developed to calculate MCSs and gMCSs using both commercial and open-source software. Results: Here, we present gMCSpy, an efficient Python package to calculate gMCSs in GEMs using both commercial and non-commercial optimization solvers. We show that gMCSpy substantially overperforms our previous computational tool GMCS, which exclusively relied on commercial software. Moreover, we compared gMCSpy with recently published competing algorithms in the literature, finding significant improvements in both accuracy and computation time. All these advances make gMCSpy an attractive tool for researchers in the field of Systems Biology for different applications in health and biotechnology.
  • Thumbnail Image
    BN-BacArena: Bayesian network extension of BacArena for the dynamic simulation of microbial communities
    (Oxford University Press, 2024) Balzerani, F. (Francesco); Valcárcel-García, L.V. (Luis Vitores); Blasco, T. (Telmo); Larrañaga, P. (Pedro); Rufián-Henares, J.Á. (Ángel José); Francino, M.P. (M. Pilar); Planes-Pedreño, F.J. (Francisco Javier); Bielza, C. (Concha); Pérez-Burillo, S. (Sergio)
    Motivation: Simulating gut microbial dynamics is extremely challenging. Several computational tools, notably the widely used BacArena, enable modeling of dynamic changes in the microbial environment. These methods, however, do not comprehensively account for microbe–microbe stimulant or inhibitory effects or for nutrient–microbe inhibitory effects, typically observed in different compounds present in the daily diet. Results: Here, we present BN-BacArena, an extension of BacArena consisting on the incorporation within the native computational framework of a Bayesian network model that accounts for microbe–microbe and nutrient–microbe interactions. Using in vitro experiments, 16S rRNA gene sequencing data and nutritional composition of 55 foods, the output Bayesian network showed 23 significant nutrient–bacteria interactions, suggesting the importance of compounds such as polyols, ascorbic acid, polyphenols and other phytochemicals, and 40 bacteria–bacteria significant relationships. With test data, BN-BacArena demonstrates a statistically significant improvement over BacArena to predict the time-dependent relative abundance of bacterial species involved in the gut microbiota upon different nutritional interventions. As a result, BN-BacArena opens new avenues for the dynamic modeling and simulation of the human gut microbiota metabolism.
  • Thumbnail Image
    Do climate policy uncertainty and geopolitical risk transmit opportunity or threat to the green market? Evidence from non-linear ARDL
    (Elsevier B.V., 2024) Agbi-Kaiser, H.O. (Henry Ofoe); Asante-Gyamerah, S. (Samuel); Gil-Alana, L.A. (Luis A.)
    This paper examines the asymmetric impacts of climate policy uncertainty (CPU), and geopolitical risk (GPR) on US green bond (GB) returns. By using the non-linear ARDL model and monthly data for GB, CPU and GPR from January 2016 to August 2022, our empirical findings show that in the short run, GB returns are negatively affected by both positive and negative shocks to GPR. In the long term, GB returns are positively impacted by negative shocks in GPR and negatively affected by positive shocks in GPR. CPU on the other hand shows an insignificant symmetric effect. These results have vital implications for policymakers and fund managers. Policymakers should consider implementing policies that reduce uncertainties and ensure stability in the green bond market. For fund managers, there is the need to adopt dynamic approaches to portfolio management, considering the evolving nature of geopolitical risks and their impact on green bond performance.
  • Thumbnail Image
    Exploring indoor thermal comfort and its causes and consequences amid heatwaves in a Southern European city—An unsupervised learning approach
    (Elsevier Ltd., 2024) Arriazu-Ramos, A. (Ainhoa); Monge-Barrio, A. (Aurora); López-Hernández, D. (Dolores); Gamero-Salinas, J. C. (Juan Carlos); González-Martinez, P. (Purificación); Sánchez-Ostiz, A. (Ana)
    This study investigates indoor thermal comfort during heatwaves in dwellings of the Southern European city of Pamplona, Spain. Utilizing K-means and Hierarchical clustering, it explores clustering patterns from occupants’ survey responses (n = 189) to thermal comfort-related questions (i.e. day and night thermal sensation, thermal satisfaction and thermal preference) as well as causal links (i.e. indoor temperatures, building/occupant features) and consequences (i.e. sleep quality, heat-related symptoms) of such clusterings. Both unsupervised learning techniques coherently revealed two groups: the comfortable and uncomfortable clusters. Uncomfortable occupants coherently experience more sensation to heat, greater preference for cooler temperatures, and more thermal dissatisfaction, especially during daytime hours. Dwellings of comfortable occupants experience median indoor temperatures ranging 25.7–26 ◦C; dwellings of uncomfortable occupants 27.4 ◦C, with median temperatures above 28 ◦C during 15:00–23:00 and 23:00–07:00 periods. Discomfort or overheating—coherently expressed by the thermally uncomfortable cluster—is alleviated by multiple factors related to the presence of active cooling technologies in all rooms, and use of passive and low-energy cooling measures (e,g. fans); exacerbated by heatwave conditions. As coherently expressed by the uncomfortable cluster heat worsens the sleep quality of occupants (3 to 6-fold) and increases the likelihood of occupants to experience heat-related symptoms (10–19-fold). This study is particularly important to policymakers, as it sheds light, from dwellers’ first-hand experience in a Southern Europe city, on relevant factors that should be taken in consideration to allow them to cope better with heatwaves without compromising their comfort and health.
  • Thumbnail Image
    Protein biomarkers in lung cancer screening: technical considerations and feasibility assessment
    (Elsevier, 2024) Seijo, L. (Luis); Calle-Arroyo, C. (Carlos) de la; Pineda-Lucena, A. (Antonio); Detterbeck, F. (Frank); Bernasconi-Bisio, F. (Franco); Johansson, M. (Mattias); Montuenga-Badia, L.M. (Luis M.); Orive-Mauleón, D. (Daniel); Hung, J.R. (Rayjean); Valencia, K. (Karmele); Echepare, M. (Mirari); Robbins, H.A. (Hilary); Fernandez-Sanmamed, M. (Miguel)
    Lung cancer remains the leading cause of cancer-related deaths worldwide, mainly due to late diagnosis and the presence of metastases. Several countries around the world have adopted nation-wide LDCT-based lung cancer screening that will benefit patients, shifting the stage at diagnosis to earlier stages with more therapeutic options. Biomarkers can help to optimize the screening process, as well as refine the TNM stratification of lung cancer patients, providing information regarding prognostics and recommending management strategies. Moreover, novel adjuvant strategies will clearly benefit from previous knowledge of the potential aggressiveness and biological traits of a given early-stage surgically resected tumor. This review focuses on proteins as promising biomarkers in the context of lung cancer screening. Despite great efforts, there are still no successful examples of biomarkers in lung cancer that have reached the clinics to be used in early detection and early management. Thus, the field of biomarkers in early lung cancer remains an evident unmet need. A more specific objective of this review is to present an up-to-date technical assessment of the potential use of protein biomarkers in early lung cancer detection and management. We provide an overview regarding the benefits, challenges, pitfalls and constraints in the development process of protein-based biomarkers. Additionally, we examine how a number of emerging protein analytical technologies may contribute to the optimization of novel robust biomarkers for screening and effective management of lung cancer.
  • Thumbnail Image
    Persistence of human capital development in OECD countries over 150 years: evidence from linear and nonlinear fractional integration methods
    (Elsevier, 2024) Hernández-Herrera, M. (María); Gil-Alana, L.A. (Luis A.); Adebola-Solarin, S. (Sakiru)
    The goal of this study is to examine the persistence of human capital development in 21 member countries of the Organization for Economic Cooperation and Development for the period 1870–2019. Gross enrollment rates for secondary and tertiary education are both used as proxies for human capital development. Employing linear and nonlinear fractional integration approaches, our results suggest high degrees of persistence in the series under examination. However, lower orders of integration are observed in the data for tertiary education than for secondary education. Thus, no evidence of reversion to the mean is found in secondary education, and Australia and New Zealand have the highest coefficients for the time trends and the highest dependence. However, mean reversion in tertiary education is found in France, the US, and, in particular, Austria. Finally, evidence of nonlinearity is observed in about eight countries, though without altering the persistence in the series. The implications of the empirical results are also presented.
  • Thumbnail Image
    Aggregation of fuzzy graphs
    (Elsevier, 2024) Bejines-López, C. (Carlos); Ardanza-Trevijano, S. (Sergio); Talavera, F.J. (Francisco Javier); Elorza-Barbajero, J. (Jorge)
    Our study is centered on the aggregation of fuzzy graphs, looking for conditions under which the aggregation process yields another fuzzy graph. We conduct an in-depth analysis of the preservation of several important properties and structures inherent to fuzzy graphs, like paths, cycles, or bridges. In addition we obtain appropriate criteria for when the aggregation of complete fuzzy graphs is again a complete fuzzy graph.
  • Thumbnail Image
    Disentangling anti-tumor response of immunotherapy combinations: a physiologically based framework for V937 oncolytic virus and Pembrolizumab
    (Wiley, 2024) Parra-Guillen, Z.P. (Zinnia Patricia); Troconiz, I.F. (Iñaki F.); Sancho-Araiz, A. (Aymara); Freshwater, T. (Tomoko)
    Immuno-oncology (IO) is a growing strategy in cancer treatment. Oncolytic viruses (OVs) can selectively infect cancer cells and lead to direct and/or immune-dependent tumor lysis. This approach represents an opportunity to potentiate the efficacy of immune checkpoint inhibitors (ICI), such as pembrolizumab. Currently, there is a lack of comprehensive quantitative models for the aforementioned scenarios. In this work, we developed a mechanistic framework describing viral kinetics, viral dynamics, and tumor response after intratumoral (i.t.) or intravenous (i.v.) administration of V937 alone or in combination with pembrolizumab. The model accounts for tumor shrinkage, in both injected and non-injected lesions, induced by: viral-infected tumor cell death and activated CD8 cells. OV-infected tumor cells enhanced the expansion of CD8 cells, whereas pembrolizumab inhibits their exhaustion by competing with PD-L1 in their binding to PD-1. Circulating viral levels and treatment effects on tumor volume were adequately characterized in all the different scenarios. This mechanistic-based model has been developed by combining top-down and bottom-up approaches and provides individual estimates of viral and ICI responses. The robustness of the model is reflected by the description of the tumor size time profiles in a variety of clinical scenarios. Additionally, this platform allows us to investigate not only the contribution of processes related to the viral kinetics and dynamics on tumor response, but also the influence of its interaction with an ICI. Additionally, the model can be used to explore different scenarios aiming to optimize treatment combinations and support clinical development.