An extensive comparison of feature ranking aggregation techniques in bioinformatics

Univariate feature rankers have been frequently used to order genes (features) in terms of their importance to a given bioinformatics challenge. Unfortunately, the resulting feature subsets tend to differ when applied to related (but distinct) datasets, or when applied to datasets which have been varied or corrupted in some fashion. As a result, a research focus has recently been on methods to measure or improve the stability of these feature subsets. One such method is called rank aggregation. Rank aggregation is the process of combining the information from several ranked lists (or in this case ordered gene lists) into a single more stable list. While there has been work on the creation of these methods, very little work has gone into comparing the lists generated by these techniques. Such a comparison allows for grouping the techniques into families, both for understanding how the families affect rank aggregation and for using less-computationally-expensive members of a given family. This paper is an extensive study on nine rank aggregation techniques across twenty-six bioinformatics datasets. Our results show that certain aggregation techniques are very similar to each other, while others are quite unique in that they are not similar to the other techniques. Additionally, it was found that as the size of the feature subset increases, the similarity between the techniques increases. To our knowledge this is the first study which examines this many rank aggregation techniques within the domain of bioinformatics.