VerySNP: VCF features to train SVM in crop SNP detection

Motivation: Several open-source tools have been recently developed to identify Single Nucleotide Polymorphisms (SNPs) in whole-genome data, the most popular being Samtools and GATK. Commonly, SNP predictors provide a VCF file as output, which contains a list of candidate SNPs with several informations such as SNP call quality, depth of coverage and many other parameters. Still this SNP list presents an unsatisfactory accuracy due to high false positive polymorphism prediction. Results: The VCF parameters are used to train a Support Vector Machine (SVM) that will classify the VCF SNP list in two groups: true SNPs and false positive results, with a prediction accuracy much more higher than the first predictor it-self.