0000000000699662
AUTHOR
Vicente Cerverón
Learning Improved Feature Rankings through Decremental Input Pruning for Support Vector Based Drug Activity Prediction
The use of certain machine learning and pattern recognition tools for automated pharmacological drug design has been recently introduced. Different families of learning algorithms and Support Vector Machines in particular have been applied to the task of associating observed chemical properties and pharmacological activities to certain kinds of representations of the candidate compounds. The purpose of this work, is to select an appropriate feature ordering from a large set of molecular descriptors usually used in the domain of Drug Activity Characterization. To this end, a new input pruning method is introduced and assessed with respect to commonly used feature ranking algorithms.
Parallel Random Search and Tabu Search for the Minimal Consistent Subset Selection Problem
The Minimal Consistent Subset Selection (MCSS) problem is a discrete optimization problem whose resolution for large scale instances requires a prohibitive processing time. Prior algorithms addressing this problem are presented. Randomization and approximation techniques are suitable to face the problem, then random search and meta-heuristics are proposed and consequently Tabu Search strategies are applied and evaluated. Parallel computing helps to reduce processing time and/or produce better results; different approaches for designing parallel tabu search are analyzed.
Use of parallel computing to improve the accuracy of calculated molecular properties
Calculation of electron correlation energy in molecules is unavoidable in accurate studies of chemical reactivity. However, these calculations involve, a computational effort several, even in the simplest cases, orders of magnitude larger than the computer power nowadays available. In this work the possibility of parallelize the calculations of the electron correlation energy is studied. The formalism chosen is the dressing of matrices in both distributed and shared memory parallel systems MIMD. Algorithms developed on PVM are presented, and the results are evaluated on several platforms. These results show that the parallel techniques are useful in order to decrease very appreciably the ti…
II Congreso de Educación Tecnológica (CEDUTEC
Ponencia titulada ''II Congreso de Educación Tecnológica (CEDUTEC '12). Una experiencia de colaboración Universidad-Secundaria para mejorar y fomentar la formación en tecnología'' a cargo de Enric Torres (Presidente de la APTCV: Asociación del Profesorado de Tecnología de la Comunitat Valenciana) y Vicente Cerverón (Director de la ETSE : Escola Tecnica Superior d'Enginyeria); Producción: Servei de Formació Permanent i Innovació Educativa de la Universitat de València (SFPIE). Centre de Recursos Educatius i Aprenentatge Multimèdia de la UV (CREAM). (www.uv.es/sfpie)(http://cream.uv.es)