A Machine Discovery from Amino Acid Sequences by Decision Trees over Regular Patterns

Revised: September, 1991; Proc. FGCS\u2792, 618-625, 1992; New Generation Computing 11, 361-375, 1993This paper describes a machine learning system that discovered a \u22negative motif\u22, in transmembrane domain identification from amino acid sequences, and reports its experiments on protein data using PIR database. We introduce a decision tree whose node are labeled with regular patterns. As a hypothesis, the system produces such decision tree for a small number of randomly chosen positive and negative examples from PIR. Experiments show that our system finds reasonable hypotheses very successfully. As a theoretical foundation, we show that the class of languages defined by decision trees of depth at most d over k-variable regular patterns is polynomial time learnable in the sense of probably approximately correct (PAC) learning for any fixed d, $ k gep 0 $