Determine the protein function is important to have greater understanding of different diseases that arise from the alteration in this function. However, proteins function characterization by laboratory experiments is an expensive and long-lasting procedure. SIFTER is a bioinformatic tool used to predict protein function based on data sets obtained by experimental procedures; SIFTER uses a Hidden Markov Model (HMM), and Expectation Maximization (EM) algorithm to estimate the parameters of the Markov Model. In this paper we propose a strategy based on genetic algorithms called GAPE (Genetic Algorithm for Parameter Estimation) as an alternative to estimate the parameters of the HMM implemented in SIFTER. With the implementation of the genetic algorithm SIFTER increases the accuracy of function prediction in three of four reference data sets; in addition, computational resources (execution time and RAM memory) consume necessary for estimating the parameters of the HMM are reduced.

MOTIVATION: PAR-CLIP, a CLIP-seq protocol, derives a transcriptome wide set of binding sites for RNA-binding proteins. Even though the protocol uses stringent washing to remove experimental noise, some of it remains. A recent study measured three sets of non-specific RNA backgrounds which are present in several PAR-CLIP datasets. However, a tool to identify the presence of common background in PAR-CLIP datasets is not yet available. RESULTS: We used the measured sets of non-specific RNA backgrounds to build a common background set. Each element from the common background set has a score that reflects its presence in several PAR-CLIP datasets. We present a tool that uses this score to identify the amount of common backgrounds present in a PAR-CLIP dataset, and we provide the user the option to use or remove it. We used the proposed strategy in 30 PAR-CLIP datasets from nine proteins. It is possible to identify the presence of common backgrounds in a dataset and identify differences in datasets for the same protein. This method is the first step in the process of completely removing such backgrounds. AVAILABILITY: The tool was implemented in python. The common background set and the supplementary data are available at https://github.com/phrh/BackCLIP. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.