While massive identification of sequence variants in each patient sample became available thanks to the development of next generation sequencing technology, the need for in silico prediction of the functional consequences of a diverse range of variations was also increased.
However, the effect of deep intronic sequence variants at the mRNA level through altered binding to RNA-binding proteins is difficult to predict in silico as existing tools’ predictions of functional outcomes of splicing are primarily based on the analysis of point mutations within or near exons. Although some existing binding site prediction tools can work on sequences of any type, there is an unmet need for improved modeling of contextual dependencies other than structure that are crucial for correctly predicting the effects of sequence variations.
Dr. Brage Andresen’s team published the paper “DeepCLIP:predicting the effect of mutations on protein–RNA binding with deep learning” in Nucleic Acids Research on June 19, presenting a novel method for context-aware modeling and predicting protein binding to RNA nucleic acids (Nucleic Acids, 2020). In the paper, the researchers show that DeepCLIP outperforms existing methods for modeling RNA-protein binding. Importantly, they demonstrate that DeepCLIP predictions correlate with the functional outcomes of nucleotide variants in independent wet lab experiments. Furthermore, they show how DeepCLIP binding profiles can be used in the design of therapeutically relevant antisense oligonucleotides, and to uncover possible position-dependent regulation in a tissue-specific manner.
Boxplot of comparative analyses of DeepCLIP classification performance against other state-of-the-art tools.
DeepCLIP allows analysis of sequences and sequence variants with multiple
models in one analysis, as many RNA-binding proteins compete for binding site positions on RNA
molecules, and identifying the most likely change or binding partner is
important for further experimental analysis.
DeepCLIP is freely available, both as a stand-alone application and as a webtool at:
More free tools
MolecularCloud provides a tool box of frequently used bioinformatics tools, to assist researchers' daily design work, including qPCR primer and probe design, DNA construct design, gRNA design and codon optimization. Click the anchor texts below to try any of those free tools or visit the DeepCLIP website above and create a post on MolecularCloud to share your feedbacks. Participants with the best posts will have a chance to win a canvas bag, hoodie or $20 Amazon gift card!
GenSmart™ Codon Optimization- With one click, MAXIMIZE the chance to obtain functional proteins
WoLF PSORT- Advanced protein subcellular localization prediction tool
PSORT- Free computational prediction tool for protein subcellular localization
Peptide Library Design Tools- Choose the most efficient peptide library for your specific application
*MolecularCloud reserves the right of final explanation for details of this campaign. If there's any further question, please feel free to contact us at firstname.lastname@example.org.
MolecularCloud October Newsletter: Novel Base Editors Induce Efficient and Specific Editing with Low DDR
MolecularCloud September Newsletter: Winners Announced of 2020 Distinguished Research Awards
MolecularCloud August Newsletter: Glycosylase base editors enable C-to-A and C-to-G base changes