An MGI sequencing system and a sentinel machine learning model improve the calling accuracy of small variants of whole-genome sequencing data

DNAscope, a germline variant calling pipeline from San Jose-based Sentieon Analytics Inc., achieved superior SNP and indel accuracy compared to other standard datasets, according to Modern print From the company. The study authors coupled a DNAscope with MGI Standard MPS chemistry, and trained a new DNAscope model for the MGI DNBSEQ-G400* sequencing platform.

The high-accuracy Genome Analysis Toolkit (GATK) HaplotypeCaller is the industry standard small variant caller. However, short-read callers including HaplotypeCaller have incomplete matching of high-confidence variant calls, especially across complex, clinically relevant genomic regions. Improving accuracy at these sites is of increasing importance, the study authors said, as next-generation sequencing data sees greater use in the clinic.

Sentieon’s DNAscope combines established methods for haplotype-based diverse callers with machine learning for greater accuracy. The system improves active region detection and local aggregation to obtain higher levels of sensitivity and robustness, especially across regions of high complexity. DNAscope outputs candidate variants along with useful annotations, and the candidates are transferred to a machine learning model for variant genotyping.

DNAscope MGI Model v0.5 trained on the DNBSEQ-G400 sequencing platform

The researchers developed the MGI DNAscope model to analyze the accuracy of existing PE150 WGS reads generated on MGI’s DNBSEQ-G400 medium-throughput sequencer, which the researchers say was chosen for its comprehensiveness and flexibility.

Overview of the training model and measurement pipeline.

The platform, together with the trained DNAscope model, provided higher accuracy than previously published benchmarks and other major platforms. It also demonstrated faster processing speed, while enabling fewer false negative and false positive variant calls as Sentieon’s DNAscope was able to more accurately model systematic error patterns.

“MGI provides high-quality sequencing products, giving the genomics community more choice in sequencing platforms. We at Sentieon are very pleased to optimize the DNAscope for MGI sequences and jointly launch this secondary analysis solution for MGI customers,” said Jun Ye, CEO of Sentieon. This optimized pipeline helps MGI and its customers achieve high-performance computing efficiency, ease of use, and high accuracy. We look forward to continuing collaborations in the future to provide high quality solutions to the genomics industry. “

With its high accuracy and low cost, the DNBSEQ-G400 may make high-performance sequencing projects more accessible to researchers and clinicians, especially those working on human disease and population diversity using large sample sets. In combination with Sentieon’s DNAscope, the system can provide enhanced variant recall, including in complex clinically relevant genomic regions, facilitating more relevant clinical discoveries and treatment strategies.

The DNBSEQ-400 sequencer is shown on a table with a sign reading "MGI, providing the power of choice."
DNBSEQ-400 at ASHG.

As demonstrated by this study, MGI’s DNBSEQ-G400 improves daily sequencing while demonstrating higher accuracy in SNP and indel detection, according to Yongwei Zhang, CEO of MGI Americas. The system has a daily data output of up to 1440 GB with the option of one or two flow cell operation using two types of flow cells (550m/read vs 1800m/read) and different read length options from SE50 to SE400 or PE300. Designed with a new flow cell system and improved biochemical and optical systems, the DNBSEQ-G400 can flexibly and quickly support a variety of sequencing and analysis of various data in areas such as basic research, clinical research, forensics, and agriculture. With the DNBSEQ-G400 introduced in the US in August and the first few instruments in customer labs within a week, Zhang said MGI exemplifies its commitment to domestic customers and partners to make sequencing more accurate, flexible and affordable.

“MGI will compete based on the advantages of DNBSEQ technologies, complete workflow solutions including raw sampler/library automation, final BioIT solutions, excellent customer-centric services from our local team, and cost,” said Chang. “Our goal is to enable more and more customers to have higher data quality and lower cost options when they want to purchase sequencing platforms. We will help them do more cutting-edge research or offer more accurate and affordable clinical tests.”

* Unless otherwise notified, Standard MPS and CoolMPS serial reagents and serials are not available for use with these reagents in Germany, Spain, United Kingdom, Hong Kong, Sweden, Belgium, Italy, Finland, Czech Republic, Switzerland, Portugal, Austria and Romania. No orders for StandardMPS products will be accepted in the USA until after January 1, 2023.

Source

Leave a Reply

Your email address will not be published. Required fields are marked *

Exit mobile version