A method to predict the impact of regulatory variants from DNA sequence

By Dongwon Lee, David U. Gorkin, Maggie Baker, B. Strober, Alessandro L. Asoni, A. McCallion, Michael A. Beer. 2015

455 citations recorded by the source corpus.

Most variants implicated in common human disease by genome-wide association studies (GWAS) lie in noncoding sequence intervals. Despite the suggestion that regulatory element disruption represents a common theme, identifying causal risk variants within implicated genomic regions remains a major challenge. Here we present a new sequence-based computational method to predict the effect of regulatory variation, using a classifier (gkm-SVM) that encodes cell type–specific regulatory sequence vocabularies. The induced change in the gkm-SVM score, deltaSVM, quantifies the effect of variants. We show that deltaSVM accurately predicts the impact of SNPs on DNase I sensitivity in their native genomic contexts and accurately predicts the results of dense mutagenesis of several enhancers in reporter assays. Previously validated GWAS SNPs yield large deltaSVM scores, and we predict new risk-conferring SNPs for several autoimmune diseases. Thus, deltaSVM provides a powerful computational approach to systematically identify functional regulatory variants.

Subfields: Genetics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Genetics

In Molecular Biology

Citations in the corpus

Convolutional Kitchen Sinks for Transcription Factor Binding Site Prediction (2017, unknown): “Speciﬁcally, Fletez-Brant et al. and Lee et al. [5, 6] have applied string kernel methods to the prediction of transcription factor binding sites.”
Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks (2015, methodology): “We trained Basset and a recently published advance based on gapped k-mer support vector machines called gkm-SVM (Lee et al. 2015) to predict the accessibility of a set of test sequences in 164 cell types (see Methods).”
Sequential regulatory activity prediction across chromosomes with convolutional neural networks (2017, methodology): “To better understand the model prediction, we performed an in silico saturation mutagenesis (Kelley et al. 2016; Lee et al. 2015) in several affected cell types.”
Gkmexplain: Fast and Accurate Interpretation of Nonlinear Gapped k-mer SVMs Using Integrated Gradients (2018, methodology): “…to quantify the functional impact of regulatory genetic variants, we used the same benchmarking dataset of DNase I–sensitivity quantitative trait loci (dsQTLs) in lymphomablastoid cell lines (LCLs) that was used in the deltaSVM paper [9, 5], consisting of 579 dsQTL SNPs and 28,950 control SNPs.”
The Polygenic and Monogenic Basis of Blood Traits and Diseases (2020, methodology): “We used deltaSVM, a supportvector machine classifier, to train genomic sequence features of the ATAC-seq from 18 hematopoietic cell populations (Figures S3B and S3C), and then applied the model to predict the allelespecific, cell type-specific impact of FM variants on chromatin accessibility (Lee et”
Variation Interpretation Predictors: Principles, Types, Performance, and Choice (2016, methodology): “…largely focus on coding regions and protein sequences, some methods have been developed to predict the impact of variations in noncoding regions including regulatory regions [Macintyre et al., 2010; Manke et al., 2010; Ritchie et al., 2014; Lee et al., 2015; Zhou and Troyanskaya, 2015](Supp.”
DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences (2015, methodology): “To predict the effect of regulatory variation, both gkm-SVM (9) and DeepSEA use a similar strategy of predicting the function”
SBSM-Pro: support bio-sequence machine for proteins (2023, unknown): “Both iLearnPlus and Biological Seq-Analysis 2.0 oﬀer a rich array of feature extraction and analysis methods, making them more commonly employed in biological sequence classiﬁcation research compared to traditional tools.”