Using the Gene Ontology Hierarchy when Predicting Gene Function

TL;DR

This paper introduces two methods that leverage the hierarchical structure of the Gene Ontology to improve gene function prediction, demonstrating that hierarchy-aware approaches outperform reconciliation-based methods.

Contribution

The paper presents two novel hierarchy-aware algorithms for gene function prediction that directly incorporate ontology structure, enhancing prediction accuracy over existing reconciliation methods.

Findings

Hierarchy-based methods outperform reconciliation approaches

Using prior annotation information improves prediction accuracy

Linear system solutions enable efficient hierarchy-aware learning

Abstract

The problem of multilabel classification when the labels are related through a hierarchical categorization scheme occurs in many application domains such as computational biology. For example, this problem arises naturally when trying to automatically assign gene function using a controlled vocabularies like Gene Ontology. However, most existing approaches for predicting gene functions solve independent classification problems to predict genes that are involved in a given function category, independently of the rest. Here, we propose two simple methods for incorporating information about the hierarchical nature of the categorization scheme. In the first method, we use information about a gene's previous annotation to set an initial prior on its label. In a second approach, we extend a graph-based semi-supervised learning algorithm for predicting gene function in a hierarchy. We show that we can efficiently solve this problem by solving a linear system of equations. We compare these approaches with a previous label reconciliation-based approach. Results show that using the hierarchy information directly, compared to using reconciliation methods, improves gene function prediction.