2010 | OriginalPaper | Chapter
Transducer Inference by Assembling Specific Languages
Authors : Piedachu Peris, Damián López
Published in: Grammatical Inference: Theoretical Results and Applications
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Grammatical Inference has recently been applied successfully to bioinformatic tasks as protein domain prediction. In this work we present a new approach to infer regular languages. Although used in a biological task, our results may be useful not only in bioinformatics, but also in many applied tasks. To test the algorithm we consider the transmembrane domain prediction task. A preprocessing of the training sequences set allows us to use this heuristic to obtain a transducer. The transducer obtained is then used to label problem sequences. The experimentation carried out shows that this approach is suitable for the task.