DeepCLIP: predicting the effect of mutations on protein-RNA binding with deep learning.

Nucleotide variants can cause functional changes by altering protein-RNA binding in various ways that are not easy to predict. This can affect processes such as splicing, nuclear shuttling, and stability of the transcript. Therefore, correct modeling of protein-RNA binding is critical when predicting the effects of sequence variations. Many RNA-binding proteins recognize a diverse set of motifs and binding is typically also dependent on the genomic context, making this task particularly challenging. Here, we present DeepCLIP, the first method for context-aware modeling and predicting protein binding to RNA nucleic acids using exclusively sequence data as input. We show that DeepCLIP outperforms existing methods for modeling RNA-protein binding. Importantly, we demonstrate that DeepCLIP predictions correlate with the functional outcomes of nucleotide variants in independent wet lab experiments. Furthermore, we 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. DeepCLIP is freely available as a stand-alone application and as a webtool at http://deepclip.compbio.sdu.dk.

The Splicing Efficiency of Activating HRAS Mutations Can Determine Costello Syndrome Phenotype and Frequency in Cancer.

Costello syndrome (CS) may be caused by activating mutations in codon 12/13 of the HRAS proto-oncogene. HRAS p.Gly12Val mutations have the highest transforming activity, are very frequent in cancers, but very rare in CS, where they are reported to cause a severe, early lethal, phenotype. We identified an unusual, new germline p.Gly12Val mutation, c.35_36GC>TG, in a 12-year-old boy with attenuated CS. Analysis of his HRAS cDNA showed high levels of exon 2 skipping. Using wild type and mutant HRAS minigenes, we confirmed that c.35_36GC>TG results in exon 2 skipping by simultaneously disrupting the function of a critical Exonic Splicing Enhancer (ESE) and creation of an Exonic Splicing Silencer (ESS). We show that this vulnerability of HRAS exon 2 is caused by a weak 3' splice site, which makes exon 2 inclusion dependent on binding of splicing stimulatory proteins, like SRSF2, to the critical ESE. Because the majority of cancer- and CS- causing mutations are located here, they affect splicing differently. Therefore, our results also demonstrate that the phenotype in CS and somatic cancers is not only determined by the different transforming potentials of mutant HRAS proteins, but also by the efficiency of exon 2 inclusion resulting from the different HRAS mutations. Finally, we show that a splice switching oligonucleotide (SSO) that blocks access to the critical ESE causes exon 2 skipping and halts proliferation of cancer cells. This unravels a potential for development of new anti-cancer therapies based on SSO-mediated HRAS exon 2 skipping.