nRC: non-coding RNA Classifier based on structural features

Fiannaca, Antonino; Rosa, Massimo La; Paglia, Laura La; Rizzo, Riccardo; Urso, Alfonso

doi:10.1186/s13040-017-0148-2

Cited by 66 publications

(86 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, tools focused on coding and non-coding characteristics are based on the properties of known transcripts to predict whether a transcript encodes or not for a protein. The coding potential can be estimated using automatic learning approaches such as CPAT [62], FEELnc [63], lncRScan-SVM [64] and NRC [65]. These exclude transcripts based on properties such as transcription length, length of open reading frame (ORF), ORF coverage, k-mer frequency, codon usage bias, in addition to being optimized for different techniques [47].…”

Section: Bioinformatics Tools In the Study Of Coding Rna Non-coding mentioning

confidence: 99%

Bioinformatics as a Tool for the Structural and Evolutionary Analysis of Proteins

Hernández-Domínguez¹,

Castillo-Ortega²,

García-Esquivel³

et al. 2020

Computational Biology and Chemistry

View full text Add to dashboard Cite

This chapter deals with the topic of bioinformatics, computational, mathematics, and statistics tools applied to biology, essential for the analysis and characterization of biological molecules, in particular proteins, which play an important role in all cellular and evolutionary processes of the organisms. In recent decades, with the next generation sequencing technologies and bioinformatics, it has facilitated the collection and analysis of a large amount of genomic, transcriptomic, proteomic, and metabolomic data from different organisms that have allowed predictions on the regulation of expression, transcription, translation, structure, and mechanisms of action of proteins as well as homology, mutations, and evolutionary processes that generate structural and functional changes over time. Although the information in the databases is greater every day, all bioinformatics tools continue to be constantly modified to improve performance that leads to more accurate predictions regarding protein functionality, which is why bioinformatics research remains a great challenge.

show abstract

Section: Bioinformatics Tools In the Study Of Coding Rna Non-coding mentioning

confidence: 99%

Bioinformatics as a Tool for the Structural and Evolutionary Analysis of Proteins

Hernández-Domínguez¹,

Castillo-Ortega²,

García-Esquivel³

et al. 2020

Computational Biology and Chemistry

View full text Add to dashboard Cite

show abstract

“…Besides sequence information, a few conventional lncRNA prediction methods also present the potential of discovering circRNA through the secondary structure. nRC [11] extracts features from the secondary structures of non-conding RNAs and adopts CNNs framework to classify different types of non-coding RNA. lncFinder [19] integrates both the sequence composition and structural information as features and employs random forests.…”

Section: Related Workmentioning

confidence: 99%

“…Baseline Methods. To evaluate the performance of JEDI, we compare with eight competitive baseline methods, including circDeep [6], PredcircRNA [37], DeepCirCode [48], nRC [11], Sup- [47] for backsplicing prediction. Attentive CNN and RNN as popular deep learning approaches utilize CNNs and RNNs with the attention mechanism [3] for sequence modeling, thereby predicting circRNAs based on a fully-connected hidden layer with the ReLU activation function [16].…”

Section: Experimental Settingsmentioning

confidence: 99%

“…Specifically, these deep learning algorithms provide powerful functionality to process large-scale data and automatically extract useful features for object tasks [31]. In the domain of circRNA prediction, the convolution neural network (CNN) is the architecture that has been widely explored to automatically learn the important features for prediction, either from the primary sequence [6,48] or secondary structure [11]. Although CNN is capable of capturing important local patterns on gene sequences for prediction, positional information and global context of each splice site cannot be recognized.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

JEDI: Circular RNA Prediction based on Junction Encoders and Deep Interaction among Splice Sites

Jiang

Hao

et al. 2020

Preprint

View full text Add to dashboard Cite

Circular RNA is a novel class of endogenous non-coding RNAs that have been largely discovered in eukaryotic transcriptome. The circular structure arises from a non-canonical splicing process, where the donor site backsplices to an upstream acceptor site. These circular form of RNAs are conserved across species, and often show tissue or cell-specific expression. Emerging evidences have suggested its vital roles in gene regulation, which are further associated with various types of diseases. As the fundamental effort to elucidate its function and mechanism, numerous efforts have been devoted to predicting circular RNA from its primary sequence. However, statistical learning methods are constrained by the information presented with explicit features, and the existing deep learning approach falls short on fully exploring the positional information of the splice sites and their deep interaction. We present an effective and robust end-to-end framework, JEDI, for circular RNA prediction using only the nucleotide sequence. Our framework first leverages the attention mechanism to encode each junction site based on deep bidirectional recurrent neural networks and then presents the novel cross-attention layer to model deep interaction among these sites for backsplicing. Finally, JEDI is capable of not only addressing the task of circular RNA prediction but also interpreting the relationships among splice sites to discover the hotspots for backsplicing within a gene region. Experimental evaluations demonstrate that JEDI significantly outperforms several state-of-the-art approaches in circular RNA prediction on both isoform-level and gene-level. Moreover, JEDI also shows promising results on zero-shot backsplicing discovery, where none of the existing approaches can achieve. The implementation of our framework is available at https://github.com/hallogameboy/ JEDI.

show abstract

“…Having explored a baseline deep learning architecture, we next sought to determine whether 10 training our dataset on higher-capacity convolutional neural networks (CNN) and long shortterm memory (LSTM) recurrent neural networks could increase our predictive ability. CNN and LSTM models have been applied to a variety of biological datasets in recent years, and have been cited as being particularly adept at recognizing motifs and long-range interactions in nucleotide sequence data (10,(17)(18)(19)(20)(34)(35)(36)(37)(38). We trained a CNN on a one-hot sequence input, an 15…”

Section: Predictive Performance Of Higher-capacity Deep Learning Modelsmentioning

confidence: 99%

Deep Learning for RNA Synthetic Biology

et al. 2019

Preprint

View full text Add to dashboard Cite

Engineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these tools remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep 30 learning. Thus, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesized and characterized in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperformed (R 2 =0.43-0.70) previous state-of-the-art thermodynamic and kinetic models (R 2 =0.04-0.15) and allowed 35for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This deep learning approach constitutes a major step forward in engineering and understanding of RNA synthetic biology. 40One Sentence Summary: Deep neural networks are used to improve functionality prediction and provide insights on toehold switches as a model for RNA synthetic biology tools.

show abstract

nRC: non-coding RNA Classifier based on structural features

Cited by 66 publications

References 55 publications

Bioinformatics as a Tool for the Structural and Evolutionary Analysis of Proteins

Bioinformatics as a Tool for the Structural and Evolutionary Analysis of Proteins

JEDI: Circular RNA Prediction based on Junction Encoders and Deep Interaction among Splice Sites

Deep Learning for RNA Synthetic Biology

Contact Info

Product

Resources

About