MMSplice: modular modeling improves the predictions of genetic variant effects on splicing

Abstract

Predicting the effects of genetic variants on splicing is highly relevant for human genetics. We describe the framework MMSplice (modular modeling of splicing) with which we built the winning model of the CAGI5 exon skipping prediction challenge. The MMSplice modules are neural networks scoring exon, intron, and splice sites, trained on distinct large-scale genomics datasets. These modules are combined to predict effects of variants on exon skipping, splice site choice, splicing efficiency, and pathogenicity, with matched or higher performance than state-of-the-art. Our models, available in the repository Kipoi, apply to variants including indels directly from VCF files. Electronic supplementary material The online version of this article (10.1186/s13059-019-1653-z) contains supplementary material, which is available to authorized users.

Predicting the change of exon splicing caused by genetic variant using support vector regression

“…The group 3 (ranked 5 th) did not provide implementation details. On the other side, the group 5 made the best predictions by using their developed MMSplice method (Cheng et al, ). In their method, six deep neural networks have been trained to extract features of splice donor, splice acceptor, 5′ exon, 3′ exon, 5′intron, and 3′ intron, which were later combined by a simple linear regression to predict .…”

CAGI 5 splicing challenge: Improved exon skipping and intron retention predictions with MMSplice

“…It is probably difficult to train a model capturing much of the splicing regulatory elements directly from these data. Therefore, we used complementary data from different sources that are richer (Cheng et al, ). We used the GENCODE 24 annotation to train a module to score donor sites and similarly a module to score acceptor sites.…”

“…Although the two challenges have different measured quantities, we assumed that variant disrupting splicing could affect both Ψ and splicing efficiency. Therefore, we applied a modular modeling approach, MMSplice (Cheng et al, ), where the modules score different gene regions and are shared across challenges. The predictors proposed for each challenge differed only in how they combine the scores of the individual modules.…”

“…We have described MMSplice and the modular modeling strategy previously (Cheng et al, ). In this CAGI special issue, we focus on the application of MMSplice to the CAGI 5 challenges.…”

Assessing predictions of the impact of variants on splicing in CAGI5

“…While other aspects of their model could account for this superior performance, one unique feature of their model (MMsplice;Cheng et al, 2019) is the decomposition of sequence surrounding alternatively spliced exons into five distinct regions (upstream intron, acceptor site, exon, donor site, and downstream intron), each of which was evaluated by a distinct neural network. While other aspects of their model could account for this superior performance, one unique feature of their model (MMsplice;Cheng et al, 2019) is the decomposition of sequence surrounding alternatively spliced exons into five distinct regions (upstream intron, acceptor site, exon, donor site, and downstream intron), each of which was evaluated by a distinct neural network.…”