Gene2vec: gene subsequence embedding for prediction of mammalian N⁶-methyladenosine sites from mRNA

Abstract

N 6 -Methyladenosine (m 6 A) refers to methylation modification of the adenosine nucleotide acid at the nitrogen-6 position. Many conventional computational methods for identifying N 6 -methyladenosine sites are limited by the small amount of data available. Taking advantage of the thousands of m 6 A sites detected by high-throughput sequencing, it is now possible to discover the characteristics of m 6 A sequences using deep learning techniques. To the best of our knowledge, our work is the first attempt to use word embedding and deep neural networks for m 6 A prediction from mRNA sequences. Using four deep neural networks, we developed a model inferred from a larger sequence shifting window that can predict m 6 A accurately and robustly. Four prediction schemes were built with various RNA sequence representations and optimized convolutional neural networks. The soft voting results from the four deep networks were shown to outperform all of the stateof-the-art methods. We evaluated these predictors mentioned above on a rigorous independent test data set and proved that our proposed method outperforms the state-of-the-art predictors. The training, independent, and cross-species testing data sets are much larger than in previous studies, which could help to avoid the problem of overfitting. Furthermore, an online prediction web server implementing the four proposed predictors has been built and is available at http://server. malab.cn/Gene2vec/.

TMP-SSurface: A Deep Learning-Based Predictor for Surface Accessibility of Transmembrane Protein Residues

“…Based on this consideration, we tried to describe the protein fragment with features as concise as possible to make the predictor simpler and more efficient. After a series of experiments, we selected two types of encoding schemes to represent the protein fragment: one-hot code [28][29][30] and a position-specific scoring matrix (PSSM), where the former one encodes the residues arrangement and the latter one reflect the evolutionary profile. However, reducing the number of features will inevitably result in less information that may get by the predictor and cause performance deterioration.…”

IMPContact: An Interhelical Residue Contact Prediction Method

“…As a representative branch of deep learning, CNN [34] had already made great achievements in various research fields, including protein sequence studies [35][36][37][38][39]. It can capture various nonlinear features by constructing neural networks consisting of convolution, pooling, and fully connected layers.…”

RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

“…As an alternative to costly and labor-intensive laboratory experiments, robust, swift, and inexpensive computational methods for RNA chemical modification prediction have emerged recently, owing to the increasing amount of data generated in this post-genomics era (Libbrecht and Noble, 2015). A large number of m6A (Chen et al, 2015(Chen et al, , 2018a(Chen et al, ,b, 2019aZhou et al, 2016;Zhao et al, 2019;Zou et al, 2019) and m5C (Feng et al, 2016;Qiu et al, 2017;Li et al, 2018;Sabooh et al, 2018;Zhang et al, 2018;Yin et al, 2019) site predictors based on traditional machine learning and emerging deep learning algorithms have been proposed. However, few computational tools have been developed to predict pseudouridine sites.…”