Predicting enhancer activity and variant impact using gkm‐SVM

Abstract

We participated in the Critical Assessment of Genome Interpretation eQTL challenge to further test computational models of regulatory variant impact and their association with human disease. Our prediction model is based on a discriminative gapped-kmer SVM (gkm-SVM) trained on genome-wide chromatin accessibility data in the cell type of interest. The comparisons with Massively Parallel Reporter Assays (MPRA) in lymphoblasts show that gkm-SVM is among the most accurate prediction models even though all other models used the MPRA data for model training, while gkm-SVM did not. In addition, we compare to other MPRA datasets and show that gkm-SVM is a reliable predictor of expression and that deltaSVM is a reliable predictor of variant impact in K562 cells and mouse retina. We further show that DHS (DNase-I Hypersensitive Sites) and ATAC-seq (Assay for Transposase-Accessible Chromatin using sequencing) data are equally predictive substrates for training gkm-SVM, and that DHS regions flanked by H3K27Ac and H3K4me1 marks are more predictive than DHS regions alone.

Integration of multiple epigenomic marks improves prediction of variant impact in saturation mutagenesis reporter assay

“…The distinguishing feature of the top three performing methods is that they all used DNA sequence features derived from Deep Neural Networks (DNN) trained on ENCODE data (DeepSEA or similar network methods). Thus one of the main conclusions of this study is that machine learning‐based DNA sequence features are the best predictors of mutation impact in enhancers and promoters, consistent with our previous findings (Beer, ; Inoue et al, ; Kreimer et al, ; Lee et al, ). The top three groups all did particularly well on F9 and TERT‐GBM, which we will discuss below.…”

“…Blind community assessments provide the most principled way to gauge the performance of the leading computational prediction models. The 2016 Critical Assessment of Genome Interpretation (CAGI 4) eQTL challenge (Beer, ; Kreimer et al, ; Tewhey et al, ; Zeng, Edwards, Guo, & Gifford, ) assessed the effect of common human variation on the enhancer activity in lymphoblast cell lines. It established that the top performing state‐of‐the‐art models of the enhancer activity typically used machine learning methods e.g.…”

“…It established that the top performing state-of-the-art models of the enhancer activity typically used machine learning methods e.g. gkm-SVM (Ghandi, Lee, Mohammad-Noori, & Beer, 2014;Lee et al, 2015), DeepBind (Alipanahi, Delong, Weirauch, & Frey, 2015), and/or DeepSEA (Zhou & Troyanskaya, 2015)) using features learned from epigenomic chromatin state data (DHS-seq, Histone modification ChIP-seq, TF ChIP-seq, or ATAC-seq) to build models of TF binding specificity (Beer, 2017;Kreimer et al, 2017;Zeng et al, 2017). Here, we significantly extend the earlier CAGI 4 study, and report the results of the 2018 CAGI 5 regulation saturation challenge.…”

Reports from CAGI: The Critical Assessment of Genome Interpretation

“…CAGI challenges span a wide range of relationships between genetic variation and disease. For single base variants, there are challenges that address the problem of interpreting the impact of missense mutations on protein activity using a variety of molecular and cellular phenotypes, challenges that test the ability to predict the effect of mutations in cancer driver genes on cell growth, and challenges on the effect of single‐base variants on RNA expression levels and splicing (including Beer, ; Capriotti, Martelli, Fariselli, & Casadio, ; Carraro et al., ; Katsonis & Lichtarge, ; Kreimer et al., ; Niroula & Vihinen ; Pejaver et al., ; Tang et al., 2017; Tang & Fenton, ; Xu et al., ; Yin et al., ; Zeng, Edwards, Guo, & Gifford, ; Zhang et al., ). At the level of full exome and genome sequence, there are challenges that assess methods for assigning complex traits phenotypes and that evaluate the ability to associate genome sequence and an extensive profile of phenotypic traits (including Cai et al., 2017; Daneshjou et al., ; Daneshjou et al., ; Giollo et al., ; Laksshman, Bhat, Viswanath, & Li, ; Pal, Kundu, Yin, & Moult, ; Wang et al., ).…”

Deciphering regulatory DNA sequences and noncoding genetic variants using neural network models of massively parallel reporter assays

“…Recently, these approaches have been used to model regulatory activity measurements from MPRAs. An SVM-based model 23 was the top performer in a challenge that benchmarked several methods for predicting MPRA activity of DNA sequences flanking regulatory genetic variants 24 . Kalita et al 25 developed a statistical model to estimate allelic imbalance at regulatory variants based on MPRA measurements.…”