Improvement in the prediction of the translation initiation site through balancing methods, inclusion of acquired knowledge and addition of features to sequences of mRNA

Abstract

BackgroundThe accurate prediction of the initiation of translation in sequences of mRNA is an important activity for genome annotation. However, obtaining an accurate prediction is not always a simple task and can be modeled as a problem of classification between positive sequences (protein codifiers) and negative sequences (non-codifiers). The problem is highly imbalanced because each molecule of mRNA has a unique translation initiation site and various others that are not initiators. Therefore, this study focuses on the problem from the perspective of balancing classes and we present an undersampling balancing method, M-clus, which is based on clustering. The method also adds features to sequences and improves the performance of the classifier through the inclusion of knowledge obtained by the model, called InAKnow.ResultsThrough this methodology, the measures of performance used (accuracy, sensitivity, specificity and adjusted accuracy) are greater than 93% for the Mus musculus and Rattus norvegicus organisms, and varied between 72.97% and 97.43% for the other organisms evaluated: Arabidopsis thaliana, Caenorhabditis elegans, Drosophila melanogaster, Homo sapiens, Nasonia vitripennis. The precision increases significantly by 39% and 22.9% for Mus musculus and Rattus norvegicus, respectively, when the knowledge obtained by the model is included. For the other organisms, the precision increases by between 37.10% and 59.49%. The inclusion of certain features during training, for example, the presence of ATG in the upstream region of the Translation Initiation Site, improves the rate of sensitivity by approximately 7%. Using the M-Clus balancing method generates a significant increase in the rate of sensitivity from 51.39% to 91.55% (Mus musculus) and from 47.45% to 88.09% (Rattus norvegicus).ConclusionsIn order to solve the problem of TIS prediction, the results indicate that the methodology proposed in this work is adequate, particularly when using the concept of acquired knowledge which increased the accuracy in all databases evaluated.

IRES-dependent translated genes in fungi: computational prediction, phylogenetic conservation and functional association

“…However, in real data sets imbalances ranging from 100:1 up to 10,000:1 have been reported [ 125 ]. This type of datasets are common in biological studies as well, for example, in the prediction of translation initiation sites [ 126 ] and pre-miRNA classification [ 127 ]. The dataset used in this work is imbalanced because the number of A-rich IRESs in S. cerevisiae used in the training of our SVM (9 sequences) is very small compared to all possible genes containing IRESs (nearly 100,000 for the 20 selected organisms).…”

Extraction of Conservative Rules for Translation Initiation Site Prediction using Formal Concept Analysis

“…The size of the nucleotide sequence used in training has a direct influence on the quality of the prediction model (Silva et al, 2011;LIU and WONG, 2003). Extraction windows can be symmetric, with the same number of nucleotides in the upstream regions ( region of the sequence before TIS ) and downstream (region after of TIS), or asymmetric, with a number other than nucleotides for each region.…”

“…Extraction windows can be symmetric, with the same number of nucleotides in the upstream regions ( region of the sequence before TIS ) and downstream (region after of TIS), or asymmetric, with a number other than nucleotides for each region. Preliminary studies indicate that asymmetric-sized windows provide greater accuracy (Silva et al, 2011). We will adopt asymmetric windows in this work being the region upstream with the lowest number of nucleotides.…”

“…SVM is a machine learning technique capable of solving linear and non-linear classification problems. It separates examples using a linear decision surface and increasing the distance between training points (Silva et al, 2011). The efficiency of SVM classifier depends on the proper selection of the parameters of the kernel function used and the smoothing parameter of the optimal hyperplane separation margin, represented by symbol C. In this work, the Gaussian RBF (Radial Basis Function) kernel function was used, which acts as a structural regulator.…”