Learning a Hybrid Architecture for Sequence Regression and Annotation

TL;DR

This paper introduces a flexible hybrid model that jointly captures hidden sequence features and their relationship to continuous response variables, improving sequence annotation and prediction accuracy in biological data.

Contribution

It presents a novel framework combining HMMs with functional mappings for sequence regression and annotation, applicable to diverse domains.

Findings

Enhanced sequence annotation accuracy with additional response variables

Improved prediction performance on synthetic and real datasets

Flexible modeling of various mapping functions

Abstract

When learning a hidden Markov model (HMM), sequen- tial observations can often be complemented by real-valued summary response variables generated from the path of hid- den states. Such settings arise in numerous domains, includ- ing many applications in biology, like motif discovery and genome annotation. In this paper, we present a flexible frame- work for jointly modeling both latent sequence features and the functional mapping that relates the summary response variables to the hidden state sequence. The algorithm is com- patible with a rich set of mapping functions. Results show that the availability of additional continuous response vari- ables can simultaneously improve the annotation of the se- quential observations and yield good prediction performance in both synthetic data and real-world datasets.