PureCLIP: capturing target-specific protein–RNA interaction footprints from single-nucleotide CLIP-seq data

Krakau, Sabrina; Richard, Hugues; Marsico, Annalisa

doi:10.1186/s13059-017-1364-2

Cited by 131 publications

(121 citation statements)

References 34 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…While the top 6mers in the high ranking sites are in line with the corresponding RBP motif(s), this is not necessarily the case for low ranking sites specially for RBPs with low scores. As an example for CPSF6 with AP scores of 0.26 the high ranking binding sites contains mostly AAUAAA and UGUA elements while the low ranking sites are enriched in U-rich elements that have been previously reported as CLIP artifacts [Krakau et al, 2017]. This suggests that the RBP data used in our study may vary considerably in their quality, and indicates a potentially high rate of false positives in some of the (PAR-)CLIP datasets.…”

Section: Performancementioning

confidence: 63%

Deep neural networks for interpreting RNA binding protein target preferences

Ghanbari

Ohler

2019

Preprint

View full text Add to dashboard Cite

Deep learning has become a powerful paradigm to analyze the binding sites of regulatory factors including RNA-binding proteins (RBPs), owing to its strength to learn complex features from possibly multiple sources of raw data. However, the interpretability of these models, which is crucial to improve our understanding of RBP binding preferences and functions, has not yet been investigated in significant detail. We have designed a multitask and multimodal deep neural network for characterizing in vivo RBP binding preferences. The model incorporates not only the sequence but also the region type of the binding sites as input, which helps the model to boost the prediction performance. To interpret the model, we quantified the contribution of the input features to the predictive score of each RBP. Learning across multiple RBPs at once, we are able to avoid experimental biases and to identify the RNA sequence motifs and transcript context patterns that are the most important for the predictions of each individual RBP. Our findings are consistent with known motifs and binding behaviors of RBPs and can provide new insights about the regulatory functions of RBPs.

show abstract

Section: Performancementioning

confidence: 63%

Deep neural networks for interpreting RNA binding protein target preferences

Ghanbari

Ohler

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…As an example, the high-ranking binding sites for CPSF6 (AP of 0.26) contain mostly AAUAAA and UGUA elements, that is, the polyadenylation signal and up-stream motif recognized by the CFIm complex that CPSF6 is part of (Martin et al 2012). Low ranking CPSF6 sites are enriched in U-rich elements that have been previously reported as CLIP artifacts (Krakau et al 2017). This indicates that the RBP data used in our study vary in terms of the fraction of sequence-specific sites in them, indicating a potentially high rate of false positives in some of the (PAR-)CLIP data sets or, alternatively, specification of sites by features not accounted for in our DNNs.…”

Section: Performance Of Deepripementioning

confidence: 85%

Deep neural networks for interpreting RNA-binding protein target preferences

2020

View full text Add to dashboard Cite

Deep learning has become a powerful paradigm to analyze the binding sites of regulatory factors including RNA-binding proteins (RBPs), owing to its strength to learn complex features from possibly multiple sources of raw data. However, the interpretability of these models, which is crucial to improve our understanding of RBP binding preferences and functions, has not yet been investigated in significant detail. We have designed a multitask and multimodal deep neural network for characterizing in vivo RBP targets. The model incorporates not only the sequence but also the region type of the binding sites as input, which helps the model to boost the prediction performance. To interpret the model, we quantified the contribution of the input features to the predictive score of each RBP. Learning across multiple RBPs at once, we are able to avoid experimental biases and to identify the RNA sequence motifs and transcript context patterns that are the most important for the predictions of each individual RBP. Our findings are consistent with known motifs and binding behaviors and can provide new insights about the regulatory functions of RBPs.

show abstract

“…Besides the expression profile, matched IgG CLIP results have been used often to estimate background control, but they were unfavorably sparse and artificially over-amplified ( 31 ). Although sequencing of a size-matched input control prior to immunoprecipitation is informative to improve the peak calling process, shown in the eCLIP ( 31 ) and an HMM-based peak calling method with individual crosslink site detection (PureCLIP) ( 44 ), performing such matched experiments with CLIPper is neither always feasible nor so much beneficial in terms of accuracy and sensitivity as show in the comparison (Figure 5 and Supplementary Figure S8 ). This is likely due to relatively superior performance of CLIPick in refining peak signals from lowly expressed transcripts (Figure 5D and Supplementary Figure S9 ).…”

Section: Discussionmentioning

confidence: 99%

CLIPick: a sensitive peak caller for expression-based deconvolution of HITS-CLIP signals

Park

Ahn

Cho

et al. 2018

Nucleic Acids Research

View full text Add to dashboard Cite

High-throughput sequencing of RNAs isolated by crosslinking immunoprecipitation (HITS-CLIP, also called CLIP-Seq) has been used to map global RNA–protein interactions. However, a critical caveat of HITS-CLIP results is that they contain non-linear background noise—different extent of non-specific interactions caused by individual transcript abundance—that has been inconsiderately normalized, resulting in sacrifice of sensitivity. To properly deconvolute RNA–protein interactions, we have implemented CLIPick, a flexible peak calling pipeline for analyzing HITS-CLIP data, which statistically determines the signal-to-noise ratio for each transcript based on the expression-dependent background simulation. Comprising of streamlined Python modules with an easy-to-use standalone graphical user interface, CLIPick robustly identifies significant peaks and quantitatively defines footprint regions within which RNA–protein interactions were occurred. CLIPick outperforms other peak callers in accuracy and sensitivity, selecting the largest number of peaks particularly in lowly expressed transcripts where such marginal signals are hard to discriminate. Specifically, the application of CLIPick to Argonaute (Ago) HITS-CLIP data were sensitive enough to uncover extended features of microRNA target sites, and these sites were experimentally validated. CLIPick enables to resolve critical interactions in a wide spectrum of transcript levels and extends the scope of HITS-CLIP analysis. CLIPick is available at: http://clip.korea.ac.kr/clipick/

show abstract

PureCLIP: capturing target-specific protein–RNA interaction footprints from single-nucleotide CLIP-seq data

Cited by 131 publications

References 34 publications

Deep neural networks for interpreting RNA binding protein target preferences

Deep neural networks for interpreting RNA binding protein target preferences

Deep neural networks for interpreting RNA-binding protein target preferences

CLIPick: a sensitive peak caller for expression-based deconvolution of HITS-CLIP signals

Contact Info

Product

Resources

About