scholarly journals NanoCaller for accurate detection of SNPs and indels in difficult-to-map regions from long-read sequencing by haplotype-aware deep neural networks

2019 ◽  
Author(s):  
Umair Ahsan ◽  
Qian Liu ◽  
Li Fang ◽  
Kai Wang
Keyword(s):  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Variant Calling ◽  
Sequencing Data ◽  
Long Reads ◽  
Novel Variants ◽  
Long Read ◽  
Variant Detection ◽  
Genomic Regions ◽  
Haplotype Information

AbstractVariant (SNPs/indels) detection from high-throughput sequencing data remains an important yet unresolved problem. Long-read sequencing enables variant detection in difficult-to-map genomic regions that short-read sequencing cannot reliably examine (for example, only ~80% of genomic regions are marked as “high-confidence region” to have SNP/indel calls in the Genome In A Bottle project); however, the high per-base error rate poses unique challenges in variant detection. Existing methods on long-read data typically rely on analyzing pileup information from neighboring bases surrounding a candidate variant, similar to short-read variant callers, yet the benefits of much longer read length are not fully exploited. Here we present a deep neural network called NanoCaller, which detects SNPs by examining pileup information solely from other nonadjacent candidate SNPs that share the same long reads using long-range haplotype information. With called SNPs by NanoCaller, NanoCaller phases long reads and performs local realignment on two sets of phased reads to call indels by another deep neural network. Extensive evaluation on 5 human genomes (sequenced by Nanopore and PacBio long-read techniques) demonstrated that NanoCaller greatly improved performance in difficult-to-map regions, compared to other long-read variant callers. We experimentally validated 41 novel variants in difficult-to-map regions in a widely-used benchmarking genome, which cannot be reliably detected previously. We extensively evaluated the run-time characteristics and the sensitivity of parameter settings of NanoCaller to different characteristics of sequencing data. Finally, we achieved the best performance in Nanopore-based variant calling from MHC regions in the PrecisionFDA Variant Calling Challenge on Difficult-to-Map Regions by ensemble calling. In summary, by incorporating haplotype information in deep neural networks, NanoCaller facilitates the discovery of novel variants in complex genomic regions from long-read sequencing data.

scholarly journals NanoCaller for accurate detection of SNPs and indels in difficult-to-map regions from long-read sequencing by haplotype-aware deep neural networks

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Mian Umair Ahsan ◽  
Qian Liu ◽  
Li Fang ◽  
Kai Wang
Keyword(s):  
Deep Neural Networks ◽  
Short Read Sequencing ◽  
Human Genomes ◽  
Long Reads ◽  
Novel Variants ◽  
Long Read ◽  
Local Realignment ◽  
Variant Detection ◽  
Genomic Regions ◽  
Haplotype Information

AbstractLong-read sequencing enables variant detection in genomic regions that are considered difficult-to-map by short-read sequencing. To fully exploit the benefits of longer reads, here we present a deep learning method NanoCaller, which detects SNPs using long-range haplotype information, then phases long reads with called SNPs and calls indels with local realignment. Evaluation on 8 human genomes demonstrates that NanoCaller generally achieves better performance than competing approaches. We experimentally validate 41 novel variants in a widely used benchmarking genome, which could not be reliably detected previously. In summary, NanoCaller facilitates the discovery of novel variants in complex genomic regions from long-read sequencing.

scholarly journals LRSDAY: Long-read Sequencing Data Analysis for Yeasts

2017 ◽  
Author(s):  
Jia-Xing Yue ◽  
Gianni Liti
Keyword(s):  
Genome Assembly ◽  
Model Organism ◽  
Sequencing Data ◽  
Protein Coding ◽  
Sequencing Technologies ◽  
Long Reads ◽  
Long Read ◽  
Downstream Analysis ◽  
Eukaryotic Organisms ◽  
Genomic Regions

AbstractLong-read sequencing technologies have become increasingly popular in genome projects due to their strengths in resolving complex genomic regions. As a leading model organism with small genome size and great biotechnological importance, the budding yeast, Saccharomyces cerevisiae, has many isolates currently being sequenced with long reads. However, analyzing long-read sequencing data to produce high-quality genome assembly and annotation remains challenging. Here we present LRSDAY, the first one-stop solution to streamline this process. LRSDAY can produce chromosome-level end-to-end genome assembly and comprehensive annotations for various genomic features (including centromeres, protein-coding genes, tRNAs, transposable elements and telomere-associated elements) that are ready for downstream analysis. Although tailored for S. cerevisiae, we designed LRSDAY to be highly modular and customizable, making it adaptable for virtually any eukaryotic organisms. Applying LRSDAY to a S. cerevisiae strain takes ∼43 hrs to generate a complete and well-annotated genome from ∼100X Pacific Biosciences (PacBio) reads using four threads.

scholarly journals Evaluation of Germline Structural Variant Calling Methods for Nanopore Sequencing Data

2021 ◽  
Vol 12 ◽  
Author(s):  
Davide Bolognini ◽  
Alberto Magi
Keyword(s):  
Variant Calling ◽  
Research Report ◽  
Nanopore Sequencing ◽  
Sequencing Data ◽  
Factors Affecting ◽  
Sequencing Technologies ◽  
Long Reads ◽  
Oxford Nanopore ◽  
Sequencing Studies ◽  
Long Read

Structural variants (SVs) are genomic rearrangements that involve at least 50 nucleotides and are known to have a serious impact on human health. While prior short-read sequencing technologies have often proved inadequate for a comprehensive assessment of structural variation, more recent long reads from Oxford Nanopore Technologies have already been proven invaluable for the discovery of large SVs and hold the potential to facilitate the resolution of the full SV spectrum. With many long-read sequencing studies to follow, it is crucial to assess factors affecting current SV calling pipelines for nanopore sequencing data. In this brief research report, we evaluate and compare the performances of five long-read SV callers across four long-read aligners using both real and synthetic nanopore datasets. In particular, we focus on the effects of read alignment, sequencing coverage, and variant allele depth on the detection and genotyping of SVs of different types and size ranges and provide insights into precision and recall of SV callsets generated by integrating the various long-read aligners and SV callers. The computational pipeline we propose is publicly available at https://github.com/davidebolo1993/EViNCe and can be adjusted to further evaluate future nanopore sequencing datasets.

scholarly journals HELLO: improved neural network architectures and methodologies for small variant calling

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Anand Ramachandran ◽  
Steven S. Lumetta ◽  
Eric W. Klee ◽  
Deming Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Recognition ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Method Development ◽  
Variant Calling ◽  
Network Architectures ◽  
Sequencing Data ◽  
Neural Network Architectures

Abstract Background Modern Next Generation- and Third Generation- Sequencing methods such as Illumina and PacBio Circular Consensus Sequencing platforms provide accurate sequencing data. Parallel developments in Deep Learning have enabled the application of Deep Neural Networks to variant calling, surpassing the accuracy of classical approaches in many settings. DeepVariant, arguably the most popular among such methods, transforms the problem of variant calling into one of image recognition where a Deep Neural Network analyzes sequencing data that is formatted as images, achieving high accuracy. In this paper, we explore an alternative approach to designing Deep Neural Networks for variant calling, where we use meticulously designed Deep Neural Network architectures and customized variant inference functions that account for the underlying nature of sequencing data instead of converting the problem to one of image recognition. Results Results from 27 whole-genome variant calling experiments spanning Illumina, PacBio and hybrid Illumina-PacBio settings suggest that our method allows vastly smaller Deep Neural Networks to outperform the Inception-v3 architecture used in DeepVariant for indel and substitution-type variant calls. For example, our method reduces the number of indel call errors by up to 18%, 55% and 65% for Illumina, PacBio and hybrid Illumina-PacBio variant calling respectively, compared to a similarly trained DeepVariant pipeline. In these cases, our models are between 7 and 14 times smaller. Conclusions We believe that the improved accuracy and problem-specific customization of our models will enable more accurate pipelines and further method development in the field. HELLO is available at https://github.com/anands-repo/hello

scholarly journals A Long-Read Sequencing Approach for Direct Haplotype Phasing in Clinical Settings

2020 ◽  
Vol 21 (23) ◽  
pp. 9177
Author(s):  
Simone Maestri ◽  
Maria Giovanna Maturo ◽  
Emanuela Cosentino ◽  
Luca Marcolungo ◽  
Barbara Iadarola ◽  
...  
Keyword(s):  
Diagnostic Testing ◽  
Variant Calling ◽  
Clinical Settings ◽  
Sequencing Data ◽  
Sequencing Platform ◽  
Variant Discovery ◽  
Long Reads ◽  
Oxford Nanopore ◽  
Long Read ◽  
Second Generation Sequencing

The reconstruction of individual haplotypes can facilitate the interpretation of disease risks; however, high costs and technical challenges still hinder their assessment in clinical settings. Second-generation sequencing is the gold standard for variant discovery but, due to the production of short reads covering small genomic regions, allows only indirect haplotyping based on statistical methods. In contrast, third-generation methods such as the nanopore sequencing platform developed by Oxford Nanopore Technologies (ONT) generate long reads that can be used for direct haplotyping, with fewer drawbacks. However, robust standards for variant phasing in ONT-based target resequencing efforts are not yet available. In this study, we presented a streamlined proof-of-concept workflow for variant calling and phasing based on ONT data in a clinically relevant 12-kb region of the APOE locus, a hotspot for variants and haplotypes associated with aging-related diseases and longevity. Starting with sequencing data from simple amplicons of the target locus, we demonstrated that ONT data allow for reliable single-nucleotide variant (SNV) calling and phasing from as little as 60 reads, although the recognition of indels is less efficient. Even so, we identified the best combination of ONT read sets (600) and software (BWA/Minimap2 and HapCUT2) that enables full haplotype reconstruction when both SNVs and indels have been identified previously using a highly-accurate sequencing platform. In conclusion, we established a rapid and inexpensive workflow for variant phasing based on ONT long reads. This allowed for the analysis of multiple samples in parallel and can easily be implemented in routine clinical practice, including diagnostic testing.

scholarly journals precisionFDA Truth Challenge V2: Calling variants from short- and long-reads in difficult-to-map regions

2020 ◽  
Author(s):  
Nathan D. Olson ◽  
Justin Wagner ◽  
Jennifer McDaniel ◽  
Sarah H. Stephens ◽  
Samuel T. Westreich ◽  
...  
Keyword(s):  
Machine Learning ◽  
Variant Calling ◽  
Learning Approaches ◽  
Sequencing Technologies ◽  
Innovative Methods ◽  
Long Reads ◽  
Oxford Nanopore ◽  
Long Read ◽  
Recent Developments ◽  
Genomic Regions

SummaryThe precisionFDA Truth Challenge V2 aimed to assess the state-of-the-art of variant calling in difficult-to-map regions and the Major Histocompatibility Complex (MHC). Starting with FASTQ files, 20 challenge participants applied their variant calling pipelines and submitted 64 variant callsets for one or more sequencing technologies (~35X Illumina, ~35X PacBio HiFi, and ~50X Oxford Nanopore Technologies). Submissions were evaluated following best practices for benchmarking small variants with the new GIAB benchmark sets and genome stratifications. Challenge submissions included a number of innovative methods for all three technologies, with graph-based and machine-learning methods scoring best for short-read and long-read datasets, respectively. New methods out-performed the 2016 Truth Challenge winners, and new machine-learning approaches combining multiple sequencing technologies performed particularly well. Recent developments in sequencing and variant calling have enabled benchmarking variants in challenging genomic regions, paving the way for the identification of previously unknown clinically relevant variants.

scholarly journals Application of long-read sequencing to elucidate complex pharmacogenomic regions: a proof of principle

2021 ◽  
Author(s):  
Maaike van der Lee ◽  
William J. Rowell ◽  
Roberta Menafra ◽  
Henk-Jan Guchelaar ◽  
Jesse J. Swen ◽  
...  
Keyword(s):  
Genetic Variation ◽  
Clinical Practice ◽  
Variant Calling ◽  
Standard Of Care ◽  
Sequencing Data ◽  
Haplotype Phasing ◽  
Long Reads ◽  
Long Read ◽  
Genetic Makeup ◽  
Proof Of Principle

AbstractThe use of pharmacogenomics in clinical practice is becoming standard of care. However, due to the complex genetic makeup of pharmacogenes, not all genetic variation is currently accounted for. Here, we show the utility of long-read sequencing to resolve complex pharmacogenes by analyzing a well-characterised sample. This data consists of long reads that were processed to resolve phased haploblocks. 73% of pharmacogenes were fully covered in one phased haploblock, including 9/15 genes that are 100% complex. Variant calling accuracy in the pharmacogenes was high, with 99.8% recall and 100% precision for SNVs and 98.7% precision and 98.0% recall for Indels. For the majority of gene-drug interactions in the DPWG and CPIC guidelines, the associated genes could be fully resolved (62% and 63% respectively). Together, these findings suggest that long-read sequencing data offers promising opportunities in elucidating complex pharmacogenes and haplotype phasing while maintaining accurate variant calling.

scholarly journals Clair: Exploring the limit of using a deep neural network on pileup data for germline variant calling

2019 ◽  
Author(s):  
Ruibang Luo ◽  
Chak-Lim Wong ◽  
Yat-Sing Wong ◽  
Chi-Ian Tang ◽  
Chi-Man Liu ◽  
...  
Keyword(s):  
Single Molecule ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
New Technologies ◽  
Variant Calling ◽  
Epigenetic Mark ◽  
Sequencing Data ◽  
Single Molecule Sequencing ◽  
Sequencing Technologies ◽  
Complex Genome

AbstractSingle-molecule sequencing technologies have emerged in recent years and revolutionized structural variant calling, complex genome assembly, and epigenetic mark detection. However, the lack of a highly accurate small variant caller has limited the new technologies from being more widely used. In this study, we present Clair, the successor to Clairvoyante, a program for fast and accurate germline small variant calling, using single molecule sequencing data. For ONT data, Clair achieves the best precision, recall and speed as compared to several competing programs, including Clairvoyante, Longshot and Medaka. Through studying the missed variants and benchmarking intentionally overfitted models, we found that Clair may be approaching the limit of possible accuracy for germline small variant calling using pileup data and deep neural networks. Clair requires only a conventional CPU for variant calling and is an open source project available at https://github.com/HKU-BAL/Clair.

scholarly journals Ratatosk: hybrid error correction of long reads enables accurate variant calling and assembly

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Guillaume Holley ◽  
Doruk Beyter ◽  
Helga Ingimundardottir ◽  
Peter L. Møller ◽  
Snædis Kristmundsdottir ◽  
...  
Keyword(s):  
Error Correction ◽  
Human Genome ◽  
Error Rate ◽  
Variant Calling ◽  
High Error Rate ◽  
Sequencing Data ◽  
Short Read ◽  
Long Reads ◽  
Median Error ◽  
Long Read

AbstractA major challenge to long read sequencing data is their high error rate of up to 15%. We present Ratatosk, a method to correct long reads with short read data. We demonstrate on 5 human genome trios that Ratatosk reduces the error rate of long reads 6-fold on average with a median error rate as low as 0.22 %. SNP calls in Ratatosk corrected reads are nearly 99 % accurate and indel calls accuracy is increased by up to 37 %. An assembly of Ratatosk corrected reads from an Ashkenazi individual yields a contig N50 of 45 Mbp and less misassemblies than a PacBio HiFi reads assembly.

scholarly journals Fast and sensitive mapping of error-prone nanopore sequencing reads with GraphMap

2015 ◽  
Author(s):  
Ivan Sovic ◽  
Mile Sikic ◽  
Andreas Wilm ◽  
Shannon Nicole Fenlon ◽  
Swaine Chen ◽  
...  
Keyword(s):  
Human Genome ◽  
Variant Calling ◽  
Error Rates ◽  
Nanopore Sequencing ◽  
Structural Variants ◽  
Specific Identification ◽  
Long Reads ◽  
Long Read ◽  
Specific Error ◽  
Very High

Exploiting the power of nanopore sequencing requires the development of new bioinformatics approaches to deal with its specific error characteristics. We present the first nanopore read mapper (GraphMap) that uses a read-funneling paradigm to robustly handle variable error rates and fast graph traversal to align long reads with speed and very high precision (>95%). Evaluation on MinION sequencing datasets against short and long-read mappers indicates that GraphMap increases mapping sensitivity by at least 15-80%. GraphMap alignments are the first to demonstrate consensus calling with <1 error in 100,000 bases, variant calling on the human genome with 76% improvement in sensitivity over the next best mapper (BWA-MEM), precise detection of structural variants from 100bp to 4kbp in length and species and strain-specific identification of pathogens using MinION reads. GraphMap is available open source under the MIT license at https://github.com/isovic/graphmap.

Sign in / Sign up

Export Citation Format

Share Document