Interpretable prioritization of splice variants in diagnostic next-generation sequencing

Abstract

A critical challenge in genetic diagnostics is the computational assessment of candidate splice variants, specifically the interpretation of nucleotide changes located outside of the highly conserved dinucleotide sequences at the 5′ and 3′ ends of introns. To address this gap, we developed the Super Quick Informationcontent Random-forest Learning of Splice variants (SQUIRLS) algorithm. SQUIRLS generates a small set of interpretable features for machine learning by calculating the information-content (IC) of wildtype and variant sequences of canonical and cryptic splice sites, assessing changes in candidate splicing regulatory sequences, and incorporating characteristics of the sequence such as exon length, disruptions of the AG exclusion zone, and conservation. We curated a comprehensive collection of disease-associated splicealtering variants at positions outside of the highly conserved AG/GT dinucleotides at the termini of introns. SQUIRLS trains two random-forest classifiers for the donor and for the acceptor and combines their outputs by logistic regression to yield a final score. We show that SQUIRLS transcends previous state of the art accuracy in classifying splice variants as assessed by rank analysis in simulated exomes and is significantly faster than competing methods. SQUIRLS provides tabular output files for incorporation into diagnostic pipelines for exome and genome analysis, as well as visualizations that contextualize predicted effects of variants on splicing to make it easier to interpret splice variants in diagnostic settings

Comparison of in silico strategies to prioritize rare genomic variants impacting RNA splicing for the diagnosis of genomic disorders

“…Our findings demonstrate the opportunity to expand bioinformatics analysis to the pre-mRNA regions of known disease genes and provide immediate increases to diagnostic yield. Further, a wide variety of bioinformatics prediction tools continue to be developed, as seen with the recent release of CADD-Splice 34 , and SQUIRLS 35 . As such tools continue to become available, careful analysis of their utility using a framework as described here will allow integration with maximum effect.…”

Combining genetic constraint with predictions of alternative splicing to prioritize deleterious splicing in rare disease studies

“…ConSpliceML uses a Random Forest (RF) classifier to combine regional splicing constraint measures with per-nucleotide alternative splicing predictions from SpliceAI and SQUIRLS ( Methods ). We chose to use both SpliceAI and SQUIRLS since they each perform well at predicting alternative splicing, 77 yet also capture variants missed by the other.…”

“…Similarly, SQUIRLS uses a Random Forest approach to predict whether a variant causes alternative splicing with similar performance as SpliceAI. 77 SQUIRLS differs in that it uses various features such as conservation scores from phyloP 78 , sequence context parameters such as local distance from an exon and canonical splice sites, models of changes in spliceosome free energy binding, and other prediction tools such as ESRSeq. 79 However, these and other existing approaches provide little to no guidance as to whether or not the variant is deleterious.…”

SvAnna: efficient and accurate pathogenicity prediction for coding and regulatory structural variants in long-read genome sequencing

“…Although details vary from tool to tool, in general, variant pathogenicity is assessed on the basis of variant allele population frequencies, evolutionary conservation, and functional impact prediction for missense, splice, and regulatory variants. [29][30][31] Disease genes can be prioritized based on functional and genomic data, 32 or on the basis of phenotypic similarity of patient phenotype definitions with computational disease models of the HPO project. 16,33 There is a need to extend these algorithms for LRS.…”