ShapeGTB: The role of local DNA shape in prioritization of functional variants in human promoters with machine learning

, , ,
1 Laboratory of Bioinformatics and Biostatistics, Maria Sklodowska-Curie Memorial Cancer Centre and Institute of Oncology, Warsaw, Poland
2 Laboratory of Functional and Structural Genomics, Centre of New Technologies, University of Warsaw, Warsaw, Poland
3 Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
DOI
10.7287/peerj.preprints.27199v1
Published
Accepted
Subject Areas
Bioinformatics, Genomics, Data Mining and Machine Learning
Keywords
single-nucleotide polymorphism, DNA shape, DNA sequence variation, promoter, variant prioritization, machine learning
Copyright
© 2018 Malkowska et al.
Licence
This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
Cite this article
Malkowska M, Zubek J, Plewczynski D, Wyrwicz LS. 2018. ShapeGTB: The role of local DNA shape in prioritization of functional variants in human promoters with machine learning. PeerJ Preprints 6:e27199v1

Abstract

Motivation: The identification of functional sequence variations in regulatory DNA regions is one of the major challenges of modern genetics. Here, we report results of a combined multifactor analysis of properties characterizing functional sequence variants located in promoter regions of genes.

Results: We demonstrate that GC-content of the local sequence fragments and local DNA shape features play significant role in prioritization of functional variants and outscore features related to histone modifications, transcription factors binding sites, or evolutionary conservation descriptors. Those observations allowed us to build specialized machine learning classifier identifying functional SNPs within promoter regions – ShapeGTB. We compared our method with more general tools predicting pathogenicity of all non-coding variants. ShapeGTB outperformed them by a wide margin (AUC ROC 0.97 vs. 0.57-0.59). On the external validation set based on ClinVar database it displayed only slightly worse performance (AUC ROC 0.92 vs. 0.74-0.81). Such results suggest unique characteristics of mutations located within promoter regions and are a promising signal for the development of more accurate variant prioritization tools in the future.

Availability and implementation: The datasets and source code are publicly available at: https://github.com/zubekj/ShapeGTB.

Author Comment

This is a submission to PeerJ for review.

Supplemental Information

ROC curves for random train-test split

DOI: 10.7287/peerj.preprints.27199v1/supp-5