ClassificaÃÃo de proteÃnas usando mÃquinas de aprendizagem e descoberta de padrÃes / Classification of proteins using machines learning and pattern discovery

AUTOR(ES)

Francisco do Nascimento JÃnior

DATA DE PUBLICAÇÃO

2008

RESUMO

Machines learning have been applied in several different problems in bioinformatics. Similarly, pattern discovery algorithms have also been used to discovery motifs in protein sequences, contributing to define signatures (such as fingerprints) that describes function classes of proteins. For instance, the G-protein coupled receptors (GPCRs) class represents one of the largest protein families in Human Genome. This family is a major target for drug discovery and development, therefore, they are of great interest to the pharmaceutical industry. The technique used in this dissertation combine machine learning, such as SVM (Support Vector Machine) and MLP (Multilayer Perceptron), and pattern discovery methods to develop a procedure which purpose is to predict the relation between a protein sequence and its functional class, using patterns of regular expression extracted from SPEXS (Sequence Pattern EXhaustive Search), a algorithm for discovery patterns into strings

ASSUNTO(S)

proteÃna gpcr classification protein svm svm patterns discovery padrÃes ciencia da computacao gpcr classificaÃÃo

Documentos Relacionados

• Modelos escondidos de Markov para classificaÃÃo de proteÃnas
• SegmentaÃÃo e classificaÃÃo de padrÃes visuais baseadas em campos receptivos e inibitÃrios
• ClassificaÃÃo automÃtica de modulaÃÃo digital de sinais de comunicaÃÃes utilizando reconhecimento de padrÃes.
• DetecÃÃo de ateromas com base em espectroscopia Raman utilizando ferramentas de seleÃÃo de variÃveis e classificaÃÃo de padrÃes.
• Descoberta de relacionamentos entre padrÃes de sofware utilizando semÃntica latente