Identification of RNA pseudouridine sites using deep learning approaches

Aziz, Abu Zahid Bin; Hasan, Md. Al Mehedi; Shin, Jungpil

doi:10.1371/journal.pone.0247511

Cited by 9 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RNA secondary structure depends not only on the primary sequence, but also on other factors such as RNA modifications [ 66 ] which are known to be identifiable by neural networks [ 67 , 68 ]. While it is difficult to combine such factors with secondary structure constraints in model-based approaches, neural networks provide an attractive model-free alternative.…”

Section: Discussionmentioning

confidence: 99%

Inverse folding based pre-training for the reliable identification of intrinsic transcription terminators

Brandenburg

Narberhaus²,

Mosig³

2022

PLoS Comput Biol

View full text Add to dashboard Cite

It is well-established that neural networks can predict or identify structural motifs of non-coding RNAs (ncRNAs). Yet, the neural network based identification of RNA structural motifs is limited by the availability of training data that are often insufficient for learning features of specific ncRNA families or structural motifs. Aiming to reliably identify intrinsic transcription terminators in bacteria, we introduce a novel pre-training approach that uses inverse folding to generate training data for predicting or identifying a specific family or structural motif of ncRNA. We assess the ability of neural networks to identify secondary structure by systematic in silico mutagenesis experiments. In a study to identify intrinsic transcription terminators as functionally well-understood RNA structural motifs, our inverse folding based pre-training approach significantly boosts the performance of neural network topologies, which outperform previous approaches to identify intrinsic transcription terminators. Inverse-folding based pre-training provides a simple, yet highly effective way to integrate the well-established thermodynamic energy model into deep neural networks for identifying ncRNA families or motifs. The pre-training technique is broadly applicable to a range of network topologies as well as different types of ncRNA families and motifs.

show abstract

Section: Discussionmentioning

confidence: 99%

Inverse folding based pre-training for the reliable identification of intrinsic transcription terminators

Brandenburg

Narberhaus²,

Mosig³

2022

PLoS Comput Biol

View full text Add to dashboard Cite

show abstract

“…Howard and Eran introduced the PARS method to anticipate the RNA secondary organization. It uses protein sequences to break the human always double portions of the RNA, resulting in a collection of two RNA pieces that then segment independently to produce an RNA secondary framework [4][5]. On the other hand, Restriction enzymes cannot enter the cell barrier.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Convolute Neural Approach in the Prediction of RNA Structure

Ashok,

Narayana,

et al. 2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

Obtaining RNA secondary image data seems to have been increasingly significant in RNA and genetic analysis interest in recent decades. Even though some RNA secondary structures may be discovering approaches, many RNA secondary structure predictions require adequate and reliable analytical modeling. Present RNA robust estimation algorithms were typically focused on the minimal free power approach, which uses an ongoing method to identify the optimum RNA packing condition in vivo while meeting the lowest power and other such limitations. Due to the ecological atmosphere's intricacy, a real RNA architecture constantly provides a good balance of living potential power position instead of the ideal retractable prestige that fulfills the lowest power requirements. Because the RNA compact individual's responsibility for maintaining order position was similar to the minimal free power position for simple sequence RNA, the lowest free power method for forecasting RNA secondary structure does have greater precision. Continuous packing, however, leads the total bioelectrical energy of a lengthier chain RNA to stray significantly from either the simple or cost level of energy. These discrepancies were due to its complicated design, which caused a significant drop in the secondary structure's demand forecasting Convolutional Neural Network (CNN). Researchers present a unique RNA secondary structure prediction approach that combines a deep learning algorithm with a stochastic optimization approach to conformity with huge RNA sequence and an example based throughout this research. We build an extensive convolutionary neural network using present investigation variants plus knowledge construction. We would then derive implied characteristics of accurate processing from huge forecasting of the coupling likelihood of every character in an RNA sequence. An upgraded stochastic optimization analysis is used to identify the best RNA secondary structure based on RNA sequence foundation matching probability. Their multiple access outperforms standard RNA standard biochemical methods in identifying three reference RNA groups, according to the findings.

show abstract