Learn More
Calcification-associated peptide (CAP)-1 isolated from the exoskeleton of the crayfish, Procambarus clarkii, has anti-calcification activity and chitin-binding ability and is, therefore, considered to be associated with calcification. In this study, a cDNA encoding CAP-1 was cloned and characterized. An open reading frame encoded a pre-propeptide of 99(More)
The mollusc shell is a hard tissue consisting of calcium carbonate and organic matrices. The organic matrices are believed to play important roles in shell formation. In the present study, we extracted and purified a novel matrix protein, named Prismalin-14, from the acid-insoluble fraction of the prismatic layer of the shell of the Japanese pearl oyster(More)
Recently, multiple classifier systems (MCS) have been used for practical applications to improve classification accuracy. Self-generating neural networks (SGNN) are one of the suitable base-classifiers for MCS because of their simple setting and fast learning. However, the computation cost of the MCS increases in proportion to the number of SGNN. In this(More)
A novel peptide named calcification-associated peptide (CAP)-2 was isolated from the exoskeleton of the crayfish, Procambarus clarkii. CAP-2 consists of 65 amino acid residues and has a 44% sequence identity with CAP-1 characterized previously. It has a chitin-binding domain observed in many arthropod cuticle proteins. CAP-2 showed inhibitory activity on(More)
Negative Correlation Learning (NCL) has been successfully applied to construct neu-ral network ensembles. It encourages the neural networks that compose the ensemble to be different from each other and, at the same time, accurate. The difference among the neural networks that compose an ensemble is a desirable feature to perform incremental learning, for(More)
Calcification-associated peptide (CAP)-1 is considered to play an important role in calcification of the exoskeleton of the crayfish, Procambarus clarkii. In this study, in order to clarify the molecular mechanism of calcification, we constructed expression systems of recombinant molecules of CAP-1 and its related peptides in Escherichia coli, and verified(More)
We propose an efficient hybrid neural network for chaotic time series prediction. The hybrid neural network is constructed by a traditional feed-forward network, which is learned by using the backpropa-gation and a local model, which is implemented as a time delay embedding. The feed-forward network performs as the global approximation and the local model(More)