Gene Ontology term prediction based upon amino acid occurrence

Usually prediction of molecular functions of proteins from their amino acid sequences is based upon sequence similarity with proteins of known functions. However, it is well known that function is mainly dependent upon protein structures than sequences. Since structures are often independent of sequences, it is important to predict function without sequence similarities. Here we propose a method based upon amino acid occurrence for predicting Gene Ontology (GO) term. We have tested the method in a set of 3212 proteins in Protein Data Bank with less than 40% sequence identity. Our method achieved more than 50% sensitivity and 20% precision for c.a. 20 selected GO terms among the most frequent 557 GO terms. Mean sensitivity, specificity, precision, and accuracy for relatively rare (but majority) 402 GO terms among the 557 GO terms are 13%, 99%, 9% and 99%, respectively. They are significantly larger than expected values of less than 2% under assuming random selection.