Takashi Ishikawa [1] (takashi@j.kisarazu.ac.jp)
Shigeki Mitaku [2] (mitaku@cc.tuat.ac.jp)
Takao Terano [3] (terano@gssm.otsuka.tsukuba.ac.jp)
Makiko Suwa [2] (suwa@cc.tuat.ac.jp)
Takatsugu Hirokawa [2] (hirokawa@cc.tuat.ac.jp)
[1] Kisarazu National College of Technology
2-11-1 Kiyomidai-higashi, Kisarazu, Chiba 292, Japan
[2] Tokyo University of Agriculture and Technology
2-24-16 Naka-cho, Koganei-shi, Tokyo 184, Japan
[3] University of Tsukuba
3-29-1 Otsuka, Bunkyo-ku, Tokyo 112, Japan
This research develops a method for discovering functional sites of amino acid s equences using an Inductive Logic Programming (ILP) method with sorte d variable generalization. Functional sites provide clues to building a knowled ge base for prediction of protein functions from amino acid sequences. The propo sed method generates hypotheses of functional sites directly from aligned amino acid sequences using an ILP method extended with sorted variable generaliza tion. The proposed method is shown to be useful for discovering functional site s by an example application to the case of bacteriorhodopsin-like proteins.