An Empirical Analysis of Domain Adaptation Algorithms for Genomic Sequence Analysis

Abstract

We study the problem of domain transfer for a supervised classification task in\nmRNA splicing. We consider a number of recent domain transfer methods from\nmachine learning, including some that are novel, and evaluate them on genomic\nsequence data from model organisms of varying evolutionary distance. We find\nthat in cases where the organisms are not closely related, the use of domain adap-\ntation methods can help improve classification performance.