June 02, 2011

Genetic Classification of Populations Using Supervised Learning

Supervised learning involves fitting a model on genetic data using the population labels of individuals. If one is interested in detecting the presence but without supposing the presence of meaningful and distinct clusters of individuals (as I do with the Galore approach), then using the population labels is a big no-no. However, if one adopts a more practical approach of trying to detect difference between actual populations, then using the labels adds value to the classification process.

A good way to see the added value of using the labels can be seen with the following simple example:

This looks pretty much like a random collection of individuals with not much structure visible. Now, let's add the labels:
It's pretty obvious now, that "red" and "blue" points differ systematically from each other, and one would be able to achieve fairly high classification accuracy among them.

PLoS ONE 6(5): e1402. doi:10.1371/journal.pone.0014802

Genetic Classification of Populations Using Supervised Learning

Michael Bridges et al.

There are many instances in genetics in which we wish to determine whether two candidate populations are distinguishable on the basis of their genetic structure. Examples include populations which are geographically separated, case–control studies and quality control (when participants in a study have been genotyped at different laboratories). This latter application is of particular importance in the era of large scale genome wide association studies, when collections of individuals genotyped at different locations are being merged to provide increased power. The traditional method for detecting structure within a population is some form of exploratory technique such as principal components analysis. Such methods, which do not utilise our prior knowledge of the membership of the candidate populations. are termed unsupervised. Supervised methods, on the other hand are able to utilise this prior knowledge when it is available.

In this paper we demonstrate that in such cases modern supervised approaches are a more appropriate tool for detecting genetic differences between populations. We apply two such methods, (neural networks and support vector machines) to the classification of three populations (two from Scotland and one from Bulgaria). The sensitivity exhibited by both these methods is considerably higher than that attained by principal components analysis and in fact comfortably exceeds a recently conjectured theoretical limit on the sensitivity of unsupervised methods. In particular, our methods can distinguish between the two Scottish populations, where principal components analysis cannot. We suggest, on the basis of our results that a supervised learning approach should be the method of choice when classifying individuals into pre-defined populations, particularly in quality control for large scale genome wide association studies.


No comments: