Improving the Quantification of DNA Sequences Using Evolutionary Information Based on Deep Learning

Abstract

It is known that over 98% of the human genome is non-coding, and 93% of disease associated variants are located in these regions. Therefore, understanding the function of these regions is important. However, this task is challenging as most of these regions are not well understood in terms of their functions. In this paper, we introduce a novel computational model based on deep neural networks, called DQDNN, for quantifying the function of non-coding DNA regions. This model combines convolution layers for capturing regularity motifs at multiple scales and recurrent layers for capturing long term dependencies between the captured motifs. In addition, we show that integrating evolutionary information with raw genomic sequences improves the performance of the predictor significantly. The proposed model outperforms the state-of-the-art ones using raw genomics sequences only and also by integrating evolutionary information with raw genomics sequences. More specifically, the proposed model improves 96.9% and 98% of the targets in terms of area under the receiver operating characteristic curve and the precision-recall curve, respectively. In addition, the proposed model improved the prioritization of functional variants of expression quantitative trait loci (eQTLs) compared with the state-of-the-art models.

DNA sequences performs as natural language processing by exploiting deep learning algorithm for the identification of N4-methylcytosine

“…The proposed CNN model was trained and tested k intervals. There are four metrics to evaluate the performance of the model such as Accuracy (ACC), Mathew’s correlation coefficient (MCC), Specificity (Sp), and Sensitivity (Sn) with the given mathematical formulation 49 – 51 . Where TN and TP represent as true negative and true positive having the correct number of identified sequences related to 4mC and non-4mC, respectively.…”

XG-ac4C: identification of N4-acetylcytidine (ac4C) in mRNA using eXtreme gradient boosting with electron-ion interaction pseudopotentials

“…Because the benchmark datasets are imbalanced, PRC is the best choice for studying the performance of the proposed model 12 . Moreover, the accuracy (ACC), specificity (Sp), sensitivity (Sn), and Matthews correlation coefficient (MCC) were utilized in various recent published studies to evaluate classifier quality in the field of bioinformatics [30][31][32][33][34][35][36][37] . Thus, we also use them to evaluate the performance of the proposed model.…”

DNC4mC-Deep: Identification and Analysis of DNA N4-Methylcytosine Sites Based on Different Encoding Schemes By Using Deep Learning

“…The model was trained and tested k times, recorded performance each time, and concised by taking the mean score for the performance evaluation. The most common criteria which is used to evaluate the performance of the predicted models are four metrics; Mathew’s correlation coefficient (MCC), accuracy (ACC), sensitivity (Sn) and specificity (Sp) with the following mathematical formulations [ 60 , 61 , 62 ]. where TP and TN as true positive and true negative indicate the correct numbers of predicted samples for 4mCs and non-4mCs, respectively.…”