Deep learning predicts short non-coding RNA functions from only raw sequence data

Noviello, Teresa Maria Rosaria; Ceccarelli, Francesco; Ceccarelli, Michele; Cerulo, Luigi

doi:10.1371/journal.pcbi.1008415

Cited by 26 publications

(48 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We show that positional information improves classification accuracy. When tested on the same data set, global-local secondary structure fingerprints slightly outperform ncrnadeep [29], a state-of-the-art method.…”

Section: Contributions Of This Papermentioning

confidence: 97%

“…Based on this preliminary comparison that does not include the use of the "improved model" [29] with kmer encodings or the Monte Carlo dropouts; our approach (particularly with a combination of all secondary structure fingerprint types based on scores of best structural matches, and 6-mer), achieved a slightly higher classification performance on all metrics.…”

Section: Evaluation With New Sequences From Rfam 145mentioning

confidence: 99%

“…We compared the classification performance of our approach to a state-of-the-art method, ncrna-deep [29]. The scripts made available by the authors were utilized to build, train, and evaluate the models on the same data set used to evaluate our approach.…”

Section: Comparison With Ncrna-deepmentioning

confidence: 99%

See 2 more Smart Citations

Assessing Global-Local Secondary Structure Fingerprints to Classify RNA Sequences With Deep Learning

Sutanto¹,

Turcotte²

2023

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

RNA elements that are transcribed but not translated into proteins are called non-coding RNAs (ncRNAs). They play wide-ranging roles in biological processes and disorders. Just like proteins, their structure is often intimately linked to their function. Many examples have been documented where structure is conserved across taxa despite sequence divergence. Thus, structure is often used to identify function. Specifically, the secondary structure is predicted and ncRNAs with similar structures are assumed to have same or similar functions. However, a strand of RNA can fold into multiple possible structures, and some strands even fold differently in vivo and in vitro. Furthermore, ncRNAs often function as RNA-protein complexes, which can affect structure. Because of these, we hypothesized using one structure per sequence may discard information, possibly resulting in poorer classification accuracy. Therefore, we propose using secondary structure fingerprints, comprising two categories: a higher-level representation derived from RNA-As-Graphs (RAG), and free energy fingerprints based on a curated repertoire of small structural motifs. The fingerprints take into account the difference between global and local structural matches. We also evaluated our deep learning architecture with k -mers. By combining our global-local fingerprints with 6-mer, we achieved an accuracy, precision, and recall of 91.04%, 91.10%, and 91.00%.

show abstract

Section: Contributions Of This Papermentioning

confidence: 97%

Section: Evaluation With New Sequences From Rfam 145mentioning

confidence: 99%

See 1 more Smart Citation

Assessing Global-Local Secondary Structure Fingerprints to Classify RNA Sequences With Deep Learning

Sutanto¹,

Turcotte²

2023

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

show abstract

“…On the computational side, tools are being developed to help us to understand what the myriad of ncRNA sequences obtained by sequencing reveals about ncRNA function. Recent computational tools based on deep learning were developed to improve sequence classification into ncRNA classes or infer function of short ncRNAs transcripts based on the sequences alone [ 103 , 104 ].…”

Section: Advancing Our Understanding Of Ncrna Biology Through Rna Sequencingmentioning

confidence: 99%

Advances in Non-Coding RNA Sequencing

Micheel

Safrastyan

Wollny

2021

ncRNA

View full text Add to dashboard Cite

Non-coding RNAs (ncRNAs) comprise a set of abundant and functionally diverse RNA molecules. Since the discovery of the first ncRNA in the 1960s, ncRNAs have been shown to be involved in nearly all steps of the central dogma of molecular biology. In recent years, the pace of discovery of novel ncRNAs and their cellular roles has been greatly accelerated by high-throughput sequencing. Advances in sequencing technology, library preparation protocols as well as computational biology helped to greatly expand our knowledge of which ncRNAs exist throughout the kingdoms of life. Moreover, RNA sequencing revealed crucial roles of many ncRNAs in human health and disease. In this review, we discuss the most recent methodological advancements in the rapidly evolving field of high-throughput sequencing and how it has greatly expanded our understanding of ncRNA biology across a large number of different organisms.

show abstract

“…Instead of considering a secondary structure as a key determinant to determine small ncRNA function, Noviello et al [162] presented a deep learning methodology based on just raw sequence information. To extract discriminative high level features from small ncRNA sequences represented using k-mer binary encoding, they used a threelayer convolutional neural network (CNN) and showed that raw sequence information is enough to determine the function of small ncRNA.…”

Section: Family Classification Of Small Non-coding Rnasmentioning

confidence: 99%

Advances in Computational Methodologies for Classification and Sub-Cellular Locality Prediction of Non-Coding RNAs

Asim

Ibrahim

Malik

et al. 2021

IJMS

View full text Add to dashboard Cite

Apart from protein-coding Ribonucleic acids (RNAs), there exists a variety of non-coding RNAs (ncRNAs) which regulate complex cellular and molecular processes. High-throughput sequencing technologies and bioinformatics approaches have largely promoted the exploration of ncRNAs which revealed their crucial roles in gene regulation, miRNA binding, protein interactions, and splicing. Furthermore, ncRNAs are involved in the development of complicated diseases like cancer. Categorization of ncRNAs is essential to understand the mechanisms of diseases and to develop effective treatments. Sub-cellular localization information of ncRNAs demystifies diverse functionalities of ncRNAs. To date, several computational methodologies have been proposed to precisely identify the class as well as sub-cellular localization patterns of RNAs). This paper discusses different types of ncRNAs, reviews computational approaches proposed in the last 10 years to distinguish coding-RNA from ncRNA, to identify sub-types of ncRNAs such as piwi-associated RNA, micro RNA, long ncRNA, and circular RNA, and to determine sub-cellular localization of distinct ncRNAs and RNAs. Furthermore, it summarizes diverse ncRNA classification and sub-cellular localization determination datasets along with benchmark performance to aid the development and evaluation of novel computational methodologies. It identifies research gaps, heterogeneity, and challenges in the development of computational approaches for RNA sequence analysis. We consider that our expert analysis will assist Artificial Intelligence researchers with knowing state-of-the-art performance, model selection for various tasks on one platform, dominantly used sequence descriptors, neural architectures, and interpreting inter-species and intra-species performance deviation.

show abstract

Deep learning predicts short non-coding RNA functions from only raw sequence data

Cited by 26 publications

References 17 publications

Assessing Global-Local Secondary Structure Fingerprints to Classify RNA Sequences With Deep Learning

Assessing Global-Local Secondary Structure Fingerprints to Classify RNA Sequences With Deep Learning

Advances in Non-Coding RNA Sequencing

Advances in Computational Methodologies for Classification and Sub-Cellular Locality Prediction of Non-Coding RNAs

Contact Info

Product

Resources

About