Probabilistic inference of biological networks via data integration.

Mark F Rogers,Colin Campbell,Yiming Ying

doi:10.1155/2015/707453

Mark F Rogers, Colin Campbell + Show 1 more

Open Access

https://doi.org/10.1155/2015/707453

Copy DOI

Abstract

There is significant interest in inferring the structure of subcellular networks of interaction. Here we consider supervised interactive network inference in which a reference set of known network links and nonlinks is used to train a classifier for predicting new links. Many types of data are relevant to inferring functional links between genes, motivating the use of data integration. We use pairwise kernels to predict novel links, along with multiple kernel learning to integrate distinct sources of data into a decision function. We evaluate various pairwise kernels to establish which are most informative and compare individual kernel accuracies with accuracies for weighted combinations. By associating a probability measure with classifier predictions, we enable cautious classification, which can increase accuracy by restricting predictions to high-confidence instances, and data cleaning that can mitigate the influence of mislabeled training instances. Although one pairwise kernel (the tensor product pairwise kernel) appears to work best, different kernels may contribute complimentary information about interactions: experiments in S. cerevisiae (yeast) reveal that a weighted combination of pairwise kernels applied to different types of data yields the highest predictive accuracy. Combined with cautious classification and data cleaning, we can achieve predictive accuracies of up to 99.6%.

Highlights

There is a significant interest in determining subcellular network structures, from metabolic and protein-protein interaction networks, through to signalling pathways
We have investigated supervised interactive network inference using multiple kernel learning
Our conclusion was that the pairwise kernel P1 (TPPK) worked best

Summary

Introduction

There is a significant interest in determining subcellular network structures, from metabolic and protein-protein interaction networks, through to signalling pathways. No prior knowledge of network linkage is assumed. One advantage of supervised inference is that there are a variety of pathways where the structure is fairly reliably determined and this prior structural knowledge could give a viable training set. A further advantage of supervised inference is that different types of data are informative about whether a functional link may exist, allowing practitioners to integrate data from diverse sources [1]. We can weight these different data sources according to their relative significance. With unsupervised learning, it is much more difficult integrating different types of data into a predictive model, though various schemes have been suggested. We will introduce a confidence measure associated with linkage prediction. The parameters A and B are found by minimizing the negative log likelihood of the training data via the cross entropy error function: min

Objectives

Methods

Results

Conclusion