Bidirectional Long Short-Term Memory Networks for predicting the subcellular localization of eukaryotic proteins.
IEEE/ACM Trans Comput Biol Bioinform
; 4(3): 441-446, 2007.
Article
em En
| MEDLINE
| ID: mdl-17666763
ABSTRACT
An algorithm called Bidirectional Long Short-Term Memory Networks (BLSTM) for processing sequential data is introduced. This supervised learning method trains a special recurrent neural network to use very long ranged symmetric sequence context using a combination of nonlinear processing elements and linear feedback loops for storing long-range context. The algorithm is applied to the sequence-based prediction of protein localization and predicts 93.3 percent novel non-plant proteins and 88.4 percent novel plant proteins correctly, which is an improvement over feedforward and standard recurrent networks solving the same problem. The BLSTM system is available as a web-service (http//www.stepc.gr/~synaptic/blstm.html).
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Frações Subcelulares
/
Algoritmos
/
Alinhamento de Sequência
/
Redes Neurais de Computação
/
Proteoma
/
Análise de Sequência de Proteína
Tipo de estudo:
Prognostic_studies
/
Risk_factors_studies
Idioma:
En
Revista:
ACM Trans Comput Biol Bioinform
Assunto da revista:
BIOLOGIA
/
INFORMATICA MEDICA
Ano de publicação:
2007
Tipo de documento:
Article