VEF: a variant filtering tool based on ensemble methods

Abstract

Motivation Variants identified by current genomic analysis pipelines contain many incorrectly called variants. These can be potentially eliminated by applying state-of-the-art filtering tools, such as Variant Quality Score Recalibration (VQSR) or Hard Filtering (HF). However, these methods are very user-dependent and fail to run in some cases. We propose VEF, a variant filtering tool based on decision tree ensemble methods that overcomes the main drawbacks of VQSR and HF. Contrary to these methods, we treat filtering as a supervised learning problem, using variant call data with known ‘true’ variants, i.e. gold standard, for training. Once trained, VEF can be directly applied to filter the variants contained in a given Variants Call Format (VCF) file (we consider training and testing VCF files generated with the same tools, as we assume they will share feature characteristics). Results For the analysis, we used whole genome sequencing (WGS) Human datasets for which the gold standards are available. We show on these data that the proposed filtering tool VEF consistently outperforms VQSR and HF. In addition, we show that VEF generalizes well even when some features have missing values, when the training and testing datasets differ in coverage, and when sequencing pipelines other than GATK are used. Finally, since the training needs to be performed only once, there is a significant saving in running time when compared with VQSR (4 versus 50 min approximately for filtering the single nucleotide polymorphisms of a WGS Human sample). Availability and Implementation Code and scripts available at: github.com/ChuanyiZ/vef. Supplementary information Supplementary data are available at Bioinformatics online.

EMVC-2: an efficient single-nucleotide variant caller based on expectation maximization

“…Secondly, EMVC-2 uses a Decision Tree Classifier (DTC) ( Pedregosa et al 2011 ) to filter the untrue SNV candidates identified in the first step. A DTC is chosen as models based on DTs have been shown to discriminate well between true and false called variants in similar settings ( Zhang and Ochoa 2020 , Cooke et al 2021 ). Moreover, we refrain from using more complex models such as neural networks due to overfitting concerns.…”

Improving the filtering of false positive single nucleotide variations by combining genomic features with quality metrics

“…They use features related to the genomic position in which the call was made, such as GC content and proximity to homopolymers as well as quality metrics associated with variant calling. Other studies that use quality metrics extracted from VCF files include ( Zhang and Ochoa 2020 ) and ( Holt et al 2021 ), which use methods such as Gradient Boosting, EasyEnsemble, Random Forest, and AdaBoost. Both studies use Genome in a Bottle Consortium (GIAB) truth sets and train separate models for insertion/deletion variants (Indels) and Single Nucleotide Variations (SNVs).…”

FVC as an adaptive and accurate method for filtering variants from popular NGS analysis pipelines

“…Current state-of-the-art filtering methods include Frequency 25 , Hard-Filter 20 , VQSR 26 , GARFIELD 27 , VEF 28 , ForestQC 29 and so on, which employ different strategies in addressing the filtering task. The Frequency model defines variant calls with the variant allelic frequency (VAF) less than 20% or the allelic depth (AD) less than 5 as false variants.…”

“…ForestQC cannot be utilized on single-sample sequencing data. Five of these filtering methods (Frequency, VQSR, Hard-Filter, GARFIELD, and VEF) are available for quality control of variants from single-sample sequencing data and showed high performance in F1-major and accuracy 28 . However, these state-of-the-art methods were unsatisfactory when measured with the Matthews correlation coefficient (MCC) metric 27 , which is a highly suggested measurement for imbalanced data 34 , i.e., the WGS variant calls.…”