Protein classification

S Pietrokovski, JG Hemkoff, S Henikoff. The BLOCKS database—A system for protein classification. Nucleic Acids Res 24 197-200, 1996. 

Hofmann, K., Protein classification and functional assignment. Trends... 

The property of annotation inheritance along chemical and protein classification schemes provides a computationally efficient means of... 

The direct sequence encoding methods preserve the order of residues along the sequence string and encode primarily local information. They are, however, not suitable when global sequence features or information content is more important to the application, or when variable length sequences are to be analyzed. This is evident in the intron/exon sequence discrimination (e.g., Uberbacher Mural, 1991 Snyder Stormo, 1993) and protein classification (e.g., Wu et al., 1992 Ferran Ferrara, 1992) problems. 

Current trends in neural networks favor smaller networks with minimal architecture. Two major advantages of smaller networks previously discussed are better generalization capability (8.4) and easier rule extraction (13.2). Another advantage is better predictive accuracy, seen when a large network is replaced by many smaller networks, each for a subtask or a subset of data. A typical example is the protein classification problem, where n individual networks can be used to classify n different protein families and increase the prediction accuracy obtained by one large network with n output units. The improvement is especially significant when there is sufficient data for fine-tuning individual neural networks to the particularity of the data subsets. The use of ensembles of small, customized neural networks to improve predictive accuracy has been shown in numerous cases. 

How have neural networks been used in genome informatics applications In Part II, we have summarized them based on the types of applications for DNA sequence analysis, protein structure prediction and protein sequence analysis. Indeed, the development of neural network applications over the years has resulted in many successful and widely used systems. Current state-of-the-art systems include those for gene recognition, secondary structure prediction, protein classification, signal peptide recognition, and peptide design, to name just a few. 

Leicester, S.E., Finney, J.L. and Bywater, R.P. (1994b). A Quantitative Representation of Molecular Surface Shape. 11 Protein Classification Using Fourier Shape Descriptors and Classical Scaling. J.Math.Chem., 16,343-365. 

Dali structure comparison and FSSP Protein classification via structural alignment, Dali http //www2.ebi.ac.uk/dali/ [102, 293,... 

Marchler-Bauer, A., J. B. Anderson, P F. Cherukuri, C. DeWeese-Scott, L. Y. Geer, M. Gwadz, S. He, et al. 2005. CDD A Conserved Domain Database for protein classification. Nucleic Acids Res 33, Database Issue D192-6. 

---