https://hdl.handle.net/10259/5378 2026-07-26T01:19:24Z 2026-07-26T01:19:24Z Diez Pastor, José Francisco González Moya, Francisco Javier Latorre Carmona, Pedro Pérez-Barbería, Francisco Javier Kuncheva, Ludmila I. . Canepa Oneto, Antonio Jesús Arnaiz González, Álvar García Osorio, César https://hdl.handle.net/10259/11881 2026-06-30T00:05:36Z 2026-02-01T00:00:00Z

Remote sensing colour image semantic segmentation of large herbivorous mammal trails Diez Pastor, José Francisco; González Moya, Francisco Javier; Latorre Carmona, Pedro; Pérez-Barbería, Francisco Javier; Kuncheva, Ludmila I. .; Canepa Oneto, Antonio Jesús; Arnaiz González, Álvar; García Osorio, César Detection of spatial areas where biodiversity is at risk is of paramount importance for the conservation and monitoring of ecosystems. Large terrestrial mammalian herbivores are keystone species as their activity not only has deep effects on soils, plants, and animals but also shapes landscapes, as large herbivores act as allogenic ecosystem engineers. One key landscape feature that indicates intense herbivore activity and potentially impacts biodiversity is the formation of grazing trails. Grazing trails are formed by the continuous trampling activity of large herbivores that can produce complex networks of tracks of bare soil. Here, we evaluated different algorithms based on machine learning techniques to identify grazing trails. Our goal is to automatically detect potential areas with intense herbivory activity, which might be beneficial for conservation and management plans. We have applied five semantic segmentation methods combined with fourteen encoders aimed at mapping grazing trails on aerial images. Our results indicate that in most cases the chosen methodology successfully mapped the trails, although there were a few instances where the actual trail structure was underestimated. The UNet architecture with the MambaOut encoder was the best architecture for mapping trails. The proposed approach could be applied to develop tools for mapping and monitoring temporal changes in these landscape structures to support habitat conservation and land management programmes. This is the first time, to the best of our knowledge, that competitive image segmentation results are obtained for the detection and delineation of trails of large herbivorous mammals.Footnote

2026-02-01T00:00:00Z Rodríguez Iglesias, Daniel Pantoja Pérez, Ana De la Rosa, Ángel Latorre Carmona, Pedro Sala, Nohemi https://hdl.handle.net/10259/11861 2026-06-19T06:08:13Z 2026-02-01T00:00:00Z

Bioengineering approaches to dynamic impact analysis for cranial fracture interpretation in arcaheology Rodríguez Iglesias, Daniel; Pantoja Pérez, Ana; De la Rosa, Ángel; Latorre Carmona, Pedro; Sala, Nohemi Cranial fractures are widely documented in archaeological contexts, yet the application of fracture mechanics to differentiate traumatic events remains limited. This study analyses a dataset of 234 human cadavers subjected to 329 experimentally controlled blunt-impact tests, examining mechanical variables and fracture patterns that could be relevant to archaeological interpretation. The results show substantial methodological variability across the analysed studies. Analysis of these studies indicates that impact energy is the most reliable parameter for assessing fracture severity, suggesting a preliminary fracture threshold of around 2000 N, and that bone thickness is a major determinant of cranial resistance. Clear differences in fracture morphology according to impact surface were also observed: focal surfaces frequently produce depressed and comminuted fractures, whereas broad surfaces predominantly generate linear fractures. These data provide a framework for archaeological analysis: bone thickness, fracture morphology, and the presence and distribution of secondary fractures offer indirect but informative proxies for impact energy and surface characteristics, which could help to distinguish violent from non-violent events. This study emphasizes the need for dynamic fracture-mechanics approaches and targeted experimental work to better characterise archaeological impacts.

2026-02-01T00:00:00Z Olivares Gil, Alicia Barbero Aparicio, José Antonio Rodríguez Diez, Juan José Diez Pastor, José Francisco García Osorio, César Davari, Mehdi D. https://hdl.handle.net/10259/11430 2026-02-26T01:05:59Z 2025-12-01T00:00:00Z

Semi-supervised prediction of protein fitness for data-driven protein engineering Olivares Gil, Alicia; Barbero Aparicio, José Antonio; Rodríguez Diez, Juan José; Diez Pastor, José Francisco; García Osorio, César; Davari, Mehdi D. Protein fitness prediction plays a crucial role in the advancement of protein engineering endeavours. However, the combinatorial complexity of the protein sequence space and the limited availability of assay-labelled data hinder the efficient optimization of protein properties. Data-driven strategies utilizing machine learning methods have emerged as a promising solution, yet their dependence on labelled training datasets poses a significant obstacle. To overcome this challenge, in this work, we explore various ways of introducing the latent information present in evolutionarily related sequences (homologous sequences) into the training process. To do so, we establish several strategies based on semi-supervised learning (unsupervised pre-processing and wrapper methods) and perform a comprehensive comparison using 19 datasets containing protein-fitness pairs. Our findings reveal that using the information present in the homologous sequences can improve the performance of the models, especially when the number of available labelled sequences is considerably low. Specifically, the combination of a sequence encoding method based on Direct Coupling Analysis (DCA), with MERGE (a hybrid regression framework that combines evolutionary information with supervised learning) and an SVM regressor, outperforms other encodings (PAM250, UniRep, eUniRep) and other semi-supervised wrapper methods (Tri-Training Regressor, Co-Training Regressor). In summary, the demonstrated performance gains of this strategy mark a substantial leap towards more robust and reliable predictive models for protein engineering tasks. This advancement holds the potential to streamline the design and optimisation of proteins for diverse applications in biotechnology and therapeutics.

2025-12-01T00:00:00Z Barbero Aparicio, José Antonio Olivares Gil, Alicia Diez Pastor, José Francisco García Osorio, César https://hdl.handle.net/10259/11429 2026-02-26T01:05:47Z 2023-04-01T00:00:00Z

Deep learning and support vector machines for transcription start site identification Barbero Aparicio, José Antonio; Olivares Gil, Alicia; Diez Pastor, José Francisco; García Osorio, César Recognizing transcription start sites is key to gene identification. Several approaches have been employed in related problems such as detecting translation initiation sites or promoters, many of the most recent ones based on machine learning. Deep learning methods have been proven to be exceptionally effective for this task, but their use in transcription start site identification has not yet been explored in depth. Also, the very few existing works do not compare their methods to support vector machines (SVMs), the most established technique in this area of study, nor provide the curated dataset used in the study. The reduced amount of published papers in this specific problem could be explained by this lack of datasets. Given that both support vector machines and deep neural networks have been applied in related problems with remarkable results, we compared their performance in transcription start site predictions, concluding that SVMs are computationally much slower, and deep learning methods, specially long short-term memory neural networks (LSTMs), are best suited to work with sequences than SVMs. For such a purpose, we used the reference human genome GRCh38. Additionally, we studied two different aspects related to data processing: the proper way to generate training examples and the imbalanced nature of the data. Furthermore, the generalization performance of the models studied was also tested using the mouse genome, where the LSTM neural network stood out from the rest of the algorithms. To sum up, this article provides an analysis of the best architecture choices in transcription start site identification, as well as a method to generate transcription start site datasets including negative instances on any species available in Ensembl. We found that deep learning methods are better suited than SVMs to solve this problem, being more efficient and better adapted to long sequences and large amounts of data. We also create a transcription start site (TSS) dataset large enough to be used in deep learning experiments.

2023-04-01T00:00:00Z