A Two-Layer Computational Model for Discrimination of Enhancer and Their Types Using Hybrid Features Pace of Pseudo K-Tuple Nucleotide Composition

A comprehensive revisit of the machine-learning tools developed for the identification of enhancers in the human genome

Enhancers are non-coding DNA elements that play a crucial role in enhancing the transcription rate of a specific gene in the genome. Experiments for identifying enhancers can be restricted by their conditions and involve complicated, time-consuming, laborious, and costly steps. To overcome these challenges, computational platforms have been developed to complement experimental methods that enable high-throughput identification of enhancers. Over the last few years, the development of various enhancer computational tools has resulted in significant progress in predicting putative enhancers. Thus, researchers are now able to use a variety of strategies to enhance and advance enhancer study. In this review, an overview of machine learning (ML)-based prediction methods for enhancer identification and related databases has been provided. The existing enhancer-prediction methods have also been reviewed regarding their algorithms, feature selection processes, validation techniques, and software utility. In addition, the advantages and drawbacks of these ML approaches and guidelines for developing bioinformatic tools have been highlighted for a more efficient enhancer prediction. This review will serve as a useful resource for experimentalists in selecting the appropriate ML tool for their study, and for bioinformaticians in developing more accurate and advanced ML-based predictors.

A machine learning technique for identifying DNA enhancer regions utilizing CIS-regulatory element patterns

Enhancers regulate gene expression, by playing a crucial role in the synthesis of RNAs and proteins. They do not directly encode proteins or RNA molecules. In order to control gene expression, it is important to predict enhancers and their potency. Given their distance from the target gene, lack of common motifs, and tissue/cell specificity, enhancer regions are thought to be difficult to predict in DNA sequences. Recently, a number of bioinformatics tools were created to distinguish enhancers from other regulatory components and to pinpoint their advantages. However, because the quality of its prediction method needs to be improved, its practical application value must also be improved. Based on nucleotide composition and statistical moment-based features, the current study suggests a novel method for identifying enhancers and non-enhancers and evaluating their strength. The proposed study outperformed state-of-the-art techniques using fivefold and tenfold cross-validation in terms of accuracy. The accuracy from the current study results in 86.5% and 72.3% in enhancer site and its strength prediction respectively. The results of the suggested methodology point to the potential for more efficient and successful outcomes when statistical moment-based features are used. The current study's source code is available to the research community at https://github.com/csbioinfopk/enpred.

Enhancer-LSTMAtt: A Bi-LSTM and Attention-Based Deep Learning Method for Enhancer Recognition

Enhancers are short DNA segments that play a key role in biological processes, such as accelerating transcription of target genes. Since the enhancer resides anywhere in a genome sequence, it is difficult to precisely identify enhancers. We presented a bi-directional long-short term memory (Bi-LSTM) and attention-based deep learning method (Enhancer-LSTMAtt) for enhancer recognition. Enhancer-LSTMAtt is an end-to-end deep learning model that consists mainly of deep residual neural network, Bi-LSTM, and feed-forward attention. We extensively compared the Enhancer-LSTMAtt with 19 state-of-the-art methods by 5-fold cross validation, 10-fold cross validation and independent test. Enhancer-LSTMAtt achieved competitive performances, especially in the independent test. We realized Enhancer-LSTMAtt into a user-friendly web application. Enhancer-LSTMAtt is applicable not only to recognizing enhancers, but also to distinguishing strong enhancer from weak enhancers. Enhancer-LSTMAtt is believed to become a promising tool for identifying enhancers.

DeepPN: a deep parallel neural network based on convolutional neural network and graph convolutional network for predicting RNA-protein binding sites

Background

Addressing the laborious nature of traditional biological experiments by using an efficient computational approach to analyze RNA-binding proteins (RBPs) binding sites has always been a challenging task. RBPs play a vital role in post-transcriptional control. Identification of RBPs binding sites is a key step for the anatomy of the essential mechanism of gene regulation by controlling splicing, stability, localization and translation. Traditional methods for detecting RBPs binding sites are time-consuming and computationally-intensive. Recently, the computational method has been incorporated in researches of RBPs. Nevertheless, lots of them not only rely on the sequence data of RNA but also need additional data, for example the secondary structural data of RNA, to improve the performance of prediction, which needs the pre-work to prepare the learnable representation of structural data.

Results

To reduce the dependency of those pre-work, in this paper, we introduce DeepPN, a deep parallel neural network that is constructed with a convolutional neural network (CNN) and graph convolutional network (GCN) for detecting RBPs binding sites. It includes a two-layer CNN and GCN in parallel to extract the hidden features, followed by a fully connected layer to make the prediction. DeepPN discriminates the RBP binding sites on learnable representation of RNA sequences, which only uses the sequence data without using other data, for example the secondary or tertiary structure data of RNA. DeepPN is evaluated on 24 datasets of RBPs binding sites with other state-of-the-art methods. The results show that the performance of DeepPN is comparable to the published methods.

Conclusion

The experimental results show that DeepPN can effectively capture potential hidden features in RBPs and use these features for effective prediction of binding sites.

Prediction of N6-methyladenosine sites using convolution neural network model based on distributed feature representations

N⁶-methyladenosine (m⁶A) is a well-studied and most common interior messenger RNA (mRNA) modification that plays an important function in cell development. N⁶A is found in all kingdoms​ of life and many other cellular processes such as RNA splicing, immune tolerance, regulatory functions, RNA processing, and cancer. Despite the crucial role of m⁶A in cells, it was targeted computationally, but unfortunately, the obtained results were unsatisfactory. It is imperative to develop an efficient computational model that can truly represent m⁶A sites. In this regard, an intelligent and highly discriminative computational model namely: m6A-word2vec is introduced for the discrimination of m⁶A sites. Here, a concept of natural language processing in the form of word2vec is used to represent the motif of the target class automatically. These motifs (numerical descriptors) are automatically targeted from the human genome without any clear definition. Further, the extracted feature space is then forwarded to the convolution neural network model as input for prediction. The developed computational model obtained 83.17%, 92.69%, and 90.50% accuracy for benchmark datasets S₁, S₂, and S₃, respectively, using a 10-fold cross-validation test. The predictive outcomes validate that the developed intelligent computational model showed better performance compared to existing computational models. It is thus greatly estimated that the introduced computational model "m6A-word2vec" may be a supportive and practical tool for elementary and pharmaceutical research such as in drug design along with academia.

iPseU-CNN: Identifying RNA Pseudouridine Sites Using Convolutional Neural Networks

Pseudouridine is the most prevalent RNA modification and has been found in both eukaryotes and prokaryotes. Currently, pseudouridine has been demonstrated in several kinds of RNAs, such as small nuclear RNA, rRNA, tRNA, mRNA, and small nucleolar RNA. Therefore, its significance to academic research and drug development is understandable. Through biochemical experiments, the pseudouridine site identification has produced good outcomes, but these lab exploratory methods and biochemical processes are expensive and time consuming. Therefore, it is important to introduce efficient methods for identification of pseudouridine sites. In this study, an intelligent method for pseudouridine sites using the deep-learning approach was developed. The proposed prediction model is called iPseU-CNN (identifying pseudouridine by convolutional neural networks). The existing methods used handcrafted features and machine-learning approaches to identify pseudouridine sites. However, the proposed predictor extracts the features of the pseudouridine sites automatically using a convolution neural network model. The iPseU-CNN model yields better outcomes than the current state-of-the-art models in all evaluation parameters. It is thus highly projected that the iPseU-CNN predictor will become a helpful tool for academic research on pseudouridine site prediction of RNA, as well as in drug discovery.

iRNA-PseKNC(2methyl): Identify RNA 2'-O-methylation sites by convolution neural network and Chou's pseudo components

The 2'-O-methylation transferase is involved in the process of 2'-O-methylation. In catalytic processes, the 2-hydroxy group of the ribose moiety of a nucleotide accept a methyl group. This methylation process is a post-transcriptional modification, which occurs in various cellular RNAs and plays a vital role in regulation of gene expressions at the post-transcriptional level. Through biochemical experiments 2'-O-methylation sites produce good results but these biochemical process and exploratory techniques are very expensive. Thus, it is required to develop a computational method to identify 2'-O-methylation sites. In this work, we proposed a simple and precise convolution neural network method namely: iRNA-PseKNC(2methyl) to identify 2'-O-methylation sites. The existing techniques use handcrafted features, while the proposed method automatically extracts the features of 2'-O-methylation using the proposed convolution neural network model. The proposed prediction iRNA-PseKNC(2methyl) method obtained 98.27% of accuracy, 96.29% of sensitivity, 100% of specificity, and 0.965 of MCC on Home sapiens dataset. The reported outcomes present that our proposed method obtained better outcomes than existing method in terms of all evaluation parameters. These outcomes show that iRNA-PseKNC(2methyl) method might be beneficial for the academic research and drug design.