A probabilistic method for small RNA flowgram matching

Abstract

The 454 pyrosequencing technology is gaining popularity as an alternative to traditional Sanger sequencing. While each method has comparative advantages over the other, certain properties of the 454 method make it particularly well suited for small RNA discovery. We here describe some of the details of the 454 sequencing technique, with an emphasis on the nature of the intrinsic sequencing errors and methods for mitigating their effect. We propose a probabilistic framework for small RNA discovery, based on matching 454 flowgrams against the target genome. We formulate flowgram matching as an analog of profile matching, and adapt several profile matching techniques for the task of matching flowgrams. As a result, we are able to recover some of the hits missed by existing methods and assign probability-based scores to them.

Figure 1

Distribution of signals for the A. thaliana pyrosequencing dataset

Figure 2

Comparison between the number of matches found for the four stress-induced A. thaliana small RNA libraries: A) cold, B) drought and AB, C) NaCl and copper, and D) heat and UV light.