A multi-task convolutional deep neural network for variant calling in single molecule sequencing

• Published in: Nature communications Vol. 10; no. 1; pp. 998 - 11
• Main Authors: Luo, Ruibang, Sedlazeck, Fritz J., Lam, Tak-Wah, Schatz, Michael C.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01-03-2019; Nature Publishing Group; Nature Portfolio
• Subjects: 45/23; 631/114/1305; 631/114/2164; 631/114/2785; Artificial neural networks; Base Sequence; Computational Biology - instrumentation; Computational Biology - methods; Deoxyribonucleic acid; DNA; DNA Mutational Analysis; DNA sequencing; Genome, Human; Genome-Wide Association Study; Genomics; Genotype; Genotyping Techniques - instrumentation; Genotyping Techniques - methods; Humanities and Social Sciences; Humans; INDEL Mutation; multidisciplinary; Nanopores; Neural networks; Neural Networks, Computer; Nucleotide sequence; Polymorphism, Single Nucleotide; Porosity; Science; Science (multidisciplinary); Sequence Analysis, DNA; Single-nucleotide polymorphism; Software; Zygosity
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-019-09025-z

The accurate identification of DNA sequence variants is an important, but challenging task in genomics. It is particularly difficult for single molecule sequencing, which has a per-nucleotide error rate of ~5–15%. Meeting this demand, we developed Clairvoyante, a multi-task five-layer convolutional neural network model for predicting variant type (SNP or indel), zygosity, alternative allele and indel length from aligned reads. For the well-characterized NA12878 human sample, Clairvoyante achieves 99.67, 95.78, 90.53% F1-score on 1KP common variants, and 98.65, 92.57, 87.26% F1-score for whole-genome analysis, using Illumina, PacBio, and Oxford Nanopore data, respectively. Training on a second human sample shows Clairvoyante is sample agnostic and finds variants in less than 2 h on a standard server. Furthermore, we present 3,135 variants that are missed using Illumina but supported independently by both PacBio and Oxford Nanopore reads. Clairvoyante is available open-source (
https://github.com/aquaskyline/Clairvoyante
), with modules to train, utilize and visualize the model.
Single Molecule Sequencing (SMS) technologies generate long but noisy reads data. Here, the authors develop Clairvoyante, a deep neural network-based method for variant calling with SMS reads such as PacBio and ONT data.