Prediction of MicroRNA Subcellular Localization by Using a Sequence-to-Sequence Model

Xiao, Yiqun; Cai, Jiaxun; Yang, Yang; Zhao, Hai; Shen, Hong‐Bin

doi:10.1109/icdm.2018.00181

Cited by 22 publications

(49 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through utilizing various sources such as RNALocate meta-thesaurus [45], ENCODE project [7], and Ensembl database [1], in last two years, three LncRNA [19,36,10], one mRNA [42] and one miRNA [42] sub-cellular localization classification methodologies have been proposed. While the performance of lncRNA [19], and mRNA [43] methodologies fall in 70s, miRNA methodology performance is even lower [42], in just 50s. In addition, predicting miRNA sub-cellular locality is way different than predicting locality for mRNA, and lncRNA sequences as miRNA sequences are quite shorter than mRNA, and lncRNA sequences.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, predicting miRNA sub-cellular locality is way different than predicting locality for mRNA, and lncRNA sequences as miRNA sequences are quite shorter than mRNA, and lncRNA sequences. A very minor change in position, and length of nucleotides of a sequence may produce different location at sub-cellular level [42]. Moreover, according to the statistics of RNALocate Metathesaurus [45], almost 49% miRNA sequences may present in multiple compartments which indicate their ample localization patterns at sub-cellular level [42].…”

Section: Introductionmentioning

confidence: 99%

“…A very minor change in position, and length of nucleotides of a sequence may produce different location at sub-cellular level [42]. Moreover, according to the statistics of RNALocate Metathesaurus [45], almost 49% miRNA sequences may present in multiple compartments which indicate their ample localization patterns at sub-cellular level [42]. This indicates that miRNA sub-cellular localization is a multi-label classification problem.…”

Section: Introductionmentioning

confidence: 99%

“…One of the most eminent reason behind deficient work is the distinct sub-cellular localization properties of miRNAs, lack of prior knowledge-based features (e.g ontology), and their functional annotation in public datasets. According to our best knowledge, so far, there exists only one methodology for microRNA sub-cellular localization namely MIRLocator presented by Xiao et al [42]. MIRLocator utilized a sequence-to-sequence model which used non-arbitrary label order.…”

Section: Introductionmentioning

confidence: 99%

“…Most of the existing DNA and RNA sequence analysis approaches generally rely on k-mers of DNA or RNA sequences which are generated by sliding a fixed size window over the sequences with a particular stride size [42,37,34]. As K-mers are just chunk of characters, thus, they are usually treated as standard words in Natural Language Processing (NLP) [6].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A convNet based multi label microRNA sub cellular location predictor, by incorporating k-mer positional encoding

Asim

Dengel

Ahmed

2020

Preprint

View full text Add to dashboard Cite

MicroRNAs are special RNA sequences containing 22 nucleotides and are capable of regulating almost 60% of highly complex mammalian transcriptome. Presently, there exists very limited approaches capable of visualizing miRNA locations inside cell to reveal the hidden pathways, and mechanisms behind miRNA functionality, transport, and biogenesis. State-of-the-art miRNA sub-cellular location prediction MIRLocatar approach makes use of sequence to sequence model along with pre-train k-mer embeddings. Existing pre-train k-mer embedding generation methodologies focus on the extraction of semantics of k-mers. In RNA sequences, rather than semantics, positional information of nucleotides is more important because distinct positions of four basic nucleotides actually define the functionality of RNA molecules. Considering the dynamicity and importance of nucleotides positions, instead of learning representation on the basis of k-mers semantics, we propose a novel kmerRP2vec feature representation approach that fuses positional information of k-mers to randomly initialized neural k-mer embeddings. Effectiveness of proposed feature representation approach is evaluated with two deep learning based convolutional neural network CNN and recurrent neural network RNN methodologies using 8 evaluation measures. Experimental results on a public benchmark miRNAsubloc dataset prove that proposed kmerRP2vec approach along with a simple CNN model outperforms state-of-the-art MirLocator approach with a significant margin of 18% and 19% in terms of precision and recall.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A convNet based multi label microRNA sub cellular location predictor, by incorporating k-mer positional encoding

Asim

Dengel

Ahmed

2020

Preprint

View full text Add to dashboard Cite

show abstract

Recent methodology progress of deep learning for RNA–protein interaction prediction

et al. 2019

Self Cite

View full text Add to dashboard Cite

Interactions between RNAs and proteins play essential roles in many important biological processes. Benefitting from the advances of next generation sequencing technologies, hundreds of RNA-binding proteins (RBP) and their associated RNAs have been revealed, which enables the large-scale prediction of RNA-protein interactions using machine learning methods. Till now, a wide range of computational tools and pipelines have been developed, including deep learning models, which have achieved remarkable performance on the identification of RNA-protein binding affinities and sites. In this review, we provide an overview of the successful implementation of various deep learning approaches for predicting RNA-protein interactions, mainly focusing on the prediction of RNA-protein interaction pairs and RBP-binding sites on RNAs. Furthermore, we discuss the advantages and disadvantages of these approaches, and highlight future perspectives on how to design better deep learning models. Finally, we suggest some promising future directions of computational tasks in the study of RNA-protein interactions, especially the interactions between noncoding RNAs and proteins. deep learning, feature representation, machine learning, motif discovery, RNA-protein interactions *The first two authors are co-first authors.

show abstract

Computational Methods and Deep Learning for Elucidating Protein Interaction Networks

Vora¹,

Kalakoti²,

Sundar³

2022

Methods in Molecular Biology

View full text Add to dashboard Cite

Prediction of MicroRNA Subcellular Localization by Using a Sequence-to-Sequence Model

Cited by 22 publications

References 15 publications

A convNet based multi label microRNA sub cellular location predictor, by incorporating k-mer positional encoding

A convNet based multi label microRNA sub cellular location predictor, by incorporating k-mer positional encoding

Recent methodology progress of deep learning for RNA–protein interaction prediction

Computational Methods and Deep Learning for Elucidating Protein Interaction Networks

Contact Info

Product

Resources

About