Multiple instance learning for sequence data with across bag dependencies

TL;DR

This paper introduces two novel multiple instance learning methods, ABClass and ABSim, for sequence data classification that incorporate across-bag dependencies, demonstrated on bacterial radiation resistance prediction.

Contribution

The work presents new MIL approaches that account for relations between instances across different bags, improving sequence data classification.

Findings

Both approaches achieved satisfactory results in bacterial radiation resistance prediction.

ABClass effectively extracts motifs for sequence encoding.

ABSim utilizes similarity measures to discriminate related instances.

Abstract

In Multiple Instance Learning (MIL) problem for sequence data, the instances inside the bags are sequences. In some real world applications such as bioinformatics, comparing a random couple of sequences makes no sense. In fact, each instance may have structural and/or functional relations with instances of other bags. Thus, the classification task should take into account this across bag relation. In this work, we present two novel MIL approaches for sequence data classification named ABClass and ABSim. ABClass extracts motifs from related instances and use them to encode sequences. A discriminative classifier is then applied to compute a partial classification result for each set of related sequences. ABSim uses a similarity measure to discriminate the related instances and to compute a scores matrix. For both approaches, an aggregation method is applied in order to generate the final classification result. We applied both approaches to solve the problem of bacterial Ionizing Radiation Resistance prediction. The experimental results of the presented approaches are satisfactory.