Keynote speaker

Biomedical robots for the analysis of neurodegenerative and rare diseases

Prof. Juan Luis Fernández Martínez

Prof. Juan Luis Fernández Martínez

Department of Mathematics
University of Oviedo. Spain.
http://matematicas.uniovi.es/
https://www.researchgate.net/profile/Juan_Martinez22
http://matematicas.uniovi.es/investigacion/problemasinversos

Abstract

Cancer genomics is a sub-field of genomics that make use of high throughput technology to discover and characterize genes associated with cancer and other illnesses with genetic background. Particularly the analysis of neurodegenerative and rare diseases is one of the application fields of these techniques and has served to boost the research in these areas, and looking for orphan drugs. Also in the case of rare diseases often have few economic resources are available for research. Therefore it is crucial important having available robust methods to go from the genetic data to the drug/target discovery just in one step. For that purpose, in this paper we define the term biomedical robot as a novel tool for the analysis in genomics studies to improve phenotype prediction, analyzing the mechanisms of action related to any particular illness, and significantly constrain the set of therapeutic targets. The implementation of a biomedical robot in genomic analysis is based in the use of feature selection methods and ensemble learning techniques. Mathematically, a biomedical robot exploits the structure of the uncertainty space of any classification problem conceived as an ill-posed optimization problem, that is, given a classifier several equivalent low scale signatures exist providing similar prediction accuracies. As an example, this methodology was applied to the analysis of two different expression microarrays publically available concerning Inclusion Body Myositis/Polimyositis (IBM-PM) and Amyotrophic Lateral Sclerosis (ALS). In these two examples we show that the final aim of a biomedical robot is to improve knowledge discovery and provide decision systems in order to optimize diagnosis, treatment and prognosis. This is the aim of the FINISTERRAE project that consists in mining all the publically available genetic databases concerning rare and neurodegenerative diseases and constructing a relational database with the results in order to boost their translational research.

Brief biography of the Speaker

Dr. Fernàndez-Martìnez received his Ph.D. in mining engineering from the University of Oviedo (Spain) in 1994, and was previously trained as a petroleum engineer in France (Ècole Nationale du Pètrole et des Moteurs, Paris, 1988) and England (Imperial College, Royal School of Mines, London, 1989). After years of working as a computing software engineer in France, he joined the Mathematics Department of Oviedo University in 1994 and has since held the position as a professor in applied mathematics. During 2008-2010 he was a visiting and research professor at UC Berkeley-Lawrence Berkeley Laboratories and Stanford University. His areas of expertise include inverse problems, uncertainty analysis of very complex systems, feature selection and model reduction techniques, cooperative global optimization methods, with application in oil and gas, biometry, biomedicine and finance.In the area of biomedicine Dr. Fernàndez-Martìnez is interested in designing biomedical robots in translational medicine for the diagnosis, prognosis, and treatment optimization of different illnesses. Dr. Fernández-Martínez is also CEO of Blue Prism Technologies.

Copyright © ICMMI 2017