A Batch-learning Self-organizing Map for Functional Classification of Proteins in Sequence Databases

Abstract

Homology searches have been used widely to predict functions of genes and proteins when genomes are newly decoded. As a result of decoding of genome sequences from a wide range of species, a large number of proteins whose function cannot be estimated by the homology search of amino acid sequences is progressively accumulated and remains of no use in science and industry. A method to estimate the protein function that does not depend on the sequence homology search is in urgent need. We previously developed a Batch-Learning SOM (BL-SOM) for genome informatics, which does not depend on the order of data input. The present study focused on BL-SOM analyses on di to tetra continuous amino acid frequencies. Concerning the oligopeptide frequencies in the 110,000 proteins which have been classified into 2,853 function-known COGs (clusters of orthologous groups of proteins), BL-SOMs that faithfully reproduced the COG classifications were obtained. This indicated that proteins, whose functions are presently unknown because of lack of significant homology with function-known proteins, can be related to function-known proteins with the BL-SOM.