Projects

This project aims to develop new bioinformatics tools based on Machine Learning methods (supervised and unsupervised), heuristic search methods, and high-performance computing to explore high-dimensional data in problems of scientific and economic interest in the area of human and animal health. We will develop: (i) algorithms based on adaptive and multiobjective metaheuristics; (ii) multimodal metaheuristics; (iii) time series-based metaheuristics; (iv) combinatorial optimization; (v) interpretable machine learning methods; (vi) algorithms for feature extraction and selection; and (vii) combination of interpretability methods aiming at building general-purpose strategies that contribute to the analysis of large data with complex structure...

In this project, we are working on developing new approaches that allow the extraction of implicit and hidden knowledge in the huge mass of existing data in different application domains. The domains studied cover, but are not limited to, problems in Bioinformatics, allowing us to understand better the functional and structural aspects of how genes and proteins and their relationships with pathological phenotypes. Machine learning techniques can efficiently deal with non-linear and noisy environments and adequately handle missing data. However, machine learning models cannot always be easily interpreted. Interpretable machine learning is the collection of algorithms and techniques that allow humans to...

The current scenario is characterized by a technical capacity to produce large-scale data that goes beyond our analytical capacity for interpretation. The comprehensive characterization of genomic, epigenomic, transcriptomic and proteomic alterations in pathological states, especially when correlated with clinical characteristics, has a great potential to improve the diagnosis and prognosis of diseases, and especially, to enable the practice of personalized medicine in the reality of care activities. This project comprises four big areas: Computational Sciences, Molecular Biology, Bioinformatics and Health Sciences. The aim of this project is to contribute to the personalized medicine...

There is a wide range of unanswered scientific questions which cannot be answered neither by experiments nor by classical modeling and simulation approaches. One question is how to consider microscopic and macroscopic effects in one model. On the one hand, available microscopic approaches (Molecular Dynamics (MD) type) are precise but computational too complex for large or multi-scale problems. On the other hand, several macroscopic methods (Computational Fluid Dynamics (CFD) type) cannot show crucial microscopic effects. Therefore, a mesoscopic scale model is required that closes this gap. For such a Mesoscopic Molecular Dynamics (MMD) model, we propose to take advantage of...

Structural bioinformatics deals with problems where the rules that govern the biochemical processes and relations are partially known which makes hard to design efficient computational strategies for these problems. There is a wide range of unanswered questions, which cannot be answered neither by experiments nor by classical modeling and simulation approaches. Specifically, there are several problems that still do not have a computational method that can guarantee a minimum quality of solution. The general goal of this project is to develop metaheuristics models based on robust and scalable parallel and distributed computing for structural bioinformatic problems. International Project...

In Structural Bioinformatics, several problems do not present a computational method that can guarantee the minimum quality of their solutions. Structural bioinformatics deals with problems where the rules governing biochemical processes and their relationships are partially known, making it challenging to develop efficient computational strategies. Among these problems, two are the most challenging: predicting the three-dimensional structure of macromolecules and the molecular docking problem. Predicting the structure of a polypeptide/protein just from its linear sequence of amino acid residues represents a challenging problem in the field of mathematical optimization, being classified...