Information-theoretic evaluation of predicted ontological annotations

By Wyatt Travis Clark, Predrag Radivojac. 2013

136 citations recorded by the source corpus.

Motivation: The development of effective methods for the prediction of ontological annotations is an important goal in computational biology, with protein function prediction and disease gene prioritization gaining wide recognition. Although various algorithms have been proposed for these tasks, evaluating their performance is difficult owing to problems caused both by the structure of biomedical ontologies and biased or incomplete experimental annotations of genes and gene products. Results: We propose an information-theoretic framework to evaluate the performance of computational protein function prediction. We use a Bayesian network, structured according to the underlying ontology, to model the prior probability of a protein’s function. We then define two concepts, misinformation and remaining uncertainty, that can be seen as information-theoretic analogs of precision and recall. Finally, we propose a single statistic, referred to as semantic distance, that can be used to rank classification models. We evaluate our approach by analyzing the performance of three protein function predictors of Gene Ontology terms and provide evidence that it addresses several weaknesses of currently used metrics. We believe this framework provides useful insights into the performance of protein function prediction tools. Contact: predrag@indiana.edu Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Genetics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Genetics

In Molecular Biology

Citations in the corpus

DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier (2017, methodology): “In the future, additional weights based on information content of GO classes (Resnik, 1999) should be assigned to more specific functions which contain more information (Clark and Radivojac, 2013; Radivojac et al., 2013); using these weights during training of our model may improve performance for m”
Extensive complementarity between gene function prediction methods (2016, methodology): “We estimated the total information in gene function annotations contributed by different predictors using the information accretion (IA) measure (Clark and Radivojac, 2013).”
GOLabeler: Improving Sequence-based Large-scale Protein Function Prediction by Learning to Rank (2017, background): “where Pr(Gi|parents of Gi in GO) is the conditional probability of Gi given its parents of the GO structure (see [5] for more details).”