Revealing protein–lncRNA interaction

Ferré, Fabrizio; Colantoni, Alessio; Helmer-Citterich, Manuela

doi:10.1093/bib/bbv031

Cited by 545 publications

(397 citation statements)

References 135 publications

(133 reference statements)

Supporting

Mentioning

374

Contrasting

Unclassified

Order By: Relevance

“…where h (1) and h (2) are hidden units for two hidden layers, and W (1) and W (2) are weight parameters for visible-to-hidden and hidden-to-hidden connection. DBN is able to capture high-level features from individual modalities, but it cannot interactively learn unified feature representations across them.…”

Section: Deep Belief Networkmentioning

confidence: 99%

RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach

Pan

Shen

2016

Preprint

View full text Add to dashboard Cite

Background: RNAs play key roles in cells through the interactions with proteins known as the RNA-binding proteins (RBP) and their binding motifs enable crucial understanding of the post-transcriptional regulation of RNAs. How the RBPs correctly recognize the target RNAs and why they bind specific positions is still far from clear. Machine learning-based algorithms are widely acknowledged to be capable of speeding up this process. Although many automatic tools have been developed to predict the RNA-protein binding sites from the rapidly growing multi-resource data, e.g. sequence, structure, their domain specific features and formats have posed significant computational challenges. One of current difficulties is that the cross-source shared common knowledge is at a higher abstraction level beyond the observed data, resulting in a low efficiency of direct integration of observed data across domains. The other difficulty is how to interpret the prediction results. Existing approaches tend to terminate after outputting the potential discrete binding sites on the sequences, but how to assemble them into the meaningful binding motifs is a topic worth of further investigation. Results: In viewing of these challenges, we propose a deep learning-based framework (iDeep) by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs. This new protocol is featured by transforming the original observed data into a high-level abstraction feature space using multiple layers of learning blocks, where the shared representations across different domains are integrated. To validate our iDeep method, we performed experiments on 31 large-scale CLIP-seq datasets, and our results show that by integrating multiple sources of data, the average AUC can be improved by 8% compared to the best single-source-based predictor; and through cross-domain knowledge integration at an abstraction level, it outperforms the state-of-the-art predictors by 6%. Besides the overall enhanced prediction performance, the convolutional neural network module embedded in iDeep is also able to automatically capture the interpretable binding motifs for RBPs.Large-scale experiments demonstrate that these mined binding motifs agree well with the experimentally verified results, suggesting iDeep is a promising approach in the real-world applications. Conclusion: The iDeep framework not only can achieve promising performance than the state-of-the-art predictors, but also easily capture interpretable binding motifs. iDeep is available at

show abstract

Section: Deep Belief Networkmentioning

confidence: 99%

RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach

Pan

Shen

2016

Preprint

View full text Add to dashboard Cite

show abstract

“…The core of EJC is built surrounding the RNA helicase eukaryotic initiation factor 4A3 (eIF4A3), a RBP that functions as ATP-dependent RNA remodeling enzymes so as to be implicated in several processes related to RNA (Linder & Jankowsky, 2011). Besides this, lncRNAs have also been revealed to regulate gene expression at the posttranscriptional or translational level through interacting with RBPs (Ferrè, Colantoni, & Helmer-Citterich, 2016;Noh et al, 2018). Also, lncRNAs have recently been discovered to modulate gene expression through interacting with eIF4A3.…”

Section: Discussionmentioning

confidence: 99%

Long noncoding RNA VCAN‐AS1 contributes to the progression of gastric cancer via regulating p53 expression

Fan

et al. 2019

Journal Cellular Physiology

View full text Add to dashboard Cite

Gastric cancer (GC) is one of the most frequent malignancies worldwide. Long noncoding RNAs (lncRNAs) are found to be largely implicated in various cancers, including GC. However, the function of lncRNA VCAN antisense RNA 1 (VCAN-AS1) in GC remains unclear. Herein, we observed a low level of VCAN-AS1 in normal gastric tissues through NCBI and UCSC, and that VCAN-AS1 upregulation in GC tissues was related to poor prognosis by TCGA. Furthermore, VCAN-AS1 was found markedly enhanced in GC tissues and cell lines, while its upregulation was related with clinical outcomes of GC patients. Besides this, silencing VCAN-AS1 represses cell proliferation, migration, and invasion but enhances apoptosis. More important, we discovered that VCAN-AS1 expression was negatively correlated with wild-type p53 levels in GC tissues and that p53 was negatively modulated by VCAN-AS1 in GC cells.Furthermore, p53 suppression reversed the repression of VCAN-AS1 silence on the biological processes of AGS cells. Intriguingly, we identified that both VCAN-AS1 and TP53 can bind with eIF4A3, one of the core proteins in the exon junction complex.Also, we confirmed that VCAN-AS1 negatively regulates TP53 expression by competitively binding with eIF4A3. Our findings disclosed that VCAN-AS1 contributes to GC progression through interacting with eIF4A3 to downregulate TP53 expression, indicating that VCAN-AS1 is a novel therapeutic strategy for GC treatment. K E Y W O R D S eIF4A3, EJC, GC progression, p53, VCAN-AS1

show abstract

“…Several tools are available to interrogate the lncRNA:protein interaction from a protein-centric view, but fewer methods have been available with lncRNA in focus. However, evolution in the field of immobilized oligonucleotide probes, affinity aptamers, and in vitro transcribed RNAs has allowed the capture of Xist:protein interactions in vivo [44,45] . One such assay is an extension of comprehensive identification of RNA-binding proteins by high-throughput sequencing (CHIRP-seq [46] ) that uses a proteomics approach to identify the Xist-bound proteome, called CHIRP-MS [47] .…”

Section: Rna:protein Interaction Coupled To Proteomics Screensmentioning

confidence: 99%

Novel molecular players of X chromosome inactivation: new technologies and new insights

Przanowski¹,

Wasko²,

Bhatnagar³

2018

JTGG

View full text Add to dashboard Cite

The dosage compensation in placental mammals is achieved by silencing of one copy of the X chromosomes in a female cell by a process called X chromosome inactivation (XCI). XCI ensures equal gene dosage for X-linked genes between the two genders. Although the choice of X chromosome to be silenced is random, once the silencing of the X chromosome has been established, this process is highly regulated and maintained throughout subsequent cell divisions. A long non-coding RNA, Xist , and its interacting proteins execute this multistep process, but several of these regulatory proteins remain unidentified. Recent technological advances based on the genetic and proteomics screening have identified several new regulatory factors as well as dissected the molecular details of XCI regulation. Moreover, identification of regulators of XCI offers an opportunity to explore reactivation of the inactive X chromosome (Xi ) as a potential therapeutic strategy to treat X-linked diseases, like Rett syndrome. Here, we summarize recent reports that identified new regulatory proteins and RNA species playing a crucial role in Xist localization and spreading, recruitment of silencing machinery to the Xi , Xist interaction with chromatin, and structural organization of the Xi in the nuclei.

show abstract

Revealing protein–lncRNA interaction

Cited by 545 publications

References 135 publications

RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach

RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach

Long noncoding RNA VCAN‐AS1 contributes to the progression of gastric cancer via regulating p53 expression

Novel molecular players of X chromosome inactivation: new technologies and new insights

Contact Info

Product

Resources

About