Fusion of BLAST and Ensemble of Classifiers for Protein Secondary Structure Prediction

Autor(es)

de Oliveira, Gabriel Bianchin ; Pedrini, Helio ; Dias, Zanoni ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2020 33RD SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2020); v. N/A, p. 8-pg., 2020-01-01.

Resumo

The prediction of protein secondary structure has great relevance in the analysis of global protein folding. In this work, we present a method for protein secondary structure prediction using the fusion of BLAST and the ensemble of local and global classifiers. We used the amino acid sequence and sequence similarity information available in the datasets and we explored other amino acid characteristics. In order to evaluate our method, we used the files from PDB (only from the year 2018), as well as CB6133 and CB513 datasets. We achieved 87.7%, 82.4% and 85.6% Q8 accuracy on PDB 2018, CB6133 and CB513 proteins using the amino acid sequence and amino acid biological properties, 84.7% and 87.5% Q8 accuracy on CB6133 and CB513 proteins using the amino acid sequence and similarity sequence information and 92.5% Q3 accuracy on PDB 2018 proteins using the amino acid sequence and amino acid biological properties. Our method presented competitive results using only BLAST and only the ensemble of classifiers. The fusion of both approaches achieved superior results compared to state-of-the-art approaches. (AU)

• Processo FAPESP: 17/12646-3 - Déjà vu: coerência temporal, espacial e de caracterização de dados heterogêneos para análise e interpretação de integridade
• Beneficiário: Anderson de Rezende Rocha
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 19/20875-8 - Classificação de imagens de radiografias de tórax utilizando redes neurais profundas
• Beneficiário: Vinicius Teixeira de Melo
• Modalidade de apoio: Bolsas no Brasil - Mestrado
• Processo FAPESP: 15/11937-9 - Investigação de problemas difíceis do ponto de vista algorítmico e estrutural
• Beneficiário: Flávio Keidi Miyazawa
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 17/16246-0 - Análise de mídias sensíveis usando arquiteturas de aprendizado profundo
• Beneficiário: Sandra Eliza Fontes de Avila
• Modalidade de apoio: Auxílio à Pesquisa - Regular