CIFASIS 20631
CENTRO INTERNACIONAL FRANCO ARGENTINO DE CIENCIAS DE LA INFORMACION Y DE SISTEMAS
Unidad Ejecutora - UE
congresos y reuniones científicas
Título:
Proper integration of feature subsets boosts GO subcellular localization predictions
Autor/es:
J. MURILLO; L. ANGELONE; SPETALE, FLAVIO; F. KRSTICEVIC; BULACIO, PILAR; E. TAPIA; PONCE, SERGIO
Lugar:
Córdoba
Reunión:
Congreso; XXI CONGRESO ARGENTINO DE BIOINGENIERI, X JORNADA DE INGENIERÍA CLÍNICA,A - SABI 2017; 2017
Institución organizadora:
Facultad de Ciencias Exactas, Físicas y Naturales en conjunto con la Facultad de Ciencias Médicas, de la Universidad Nacional de Córdoba
Resumen:
Abstract?Prediction of multiple subcellular localizationsin proteins brings relevant information for biological functiondiscovery. The use of computational methods based onknowledge can be a helpful starting point for guiding thecostly experimental validation. In this work, we present amultilabel classifier framework to perform Gene Ontology -Cellular Component prediction focused on the improvementof two design aspects: i) the protein sequence characterization,regarding biological knowledge with experimental evidence,and ii) the error evaluation by considering a noise modelinherent in real prediction frameworks.Our proposal is validated against sets of well-known proteinsequences of four model organisms D. rerio, A. thaliana, S.cerevisiae and D. melanogaster.
