Nature Methods Paper Leverages PacBio Sequencing Technology To Develop the Platinum Pedigree Benchmark
Complete the form below to unlock access to ALL audio articles.
PacBio (NASDAQ: PACB), announced the results of a study published in Nature Methods describing a new, comprehensive truth-set of genomic variation which characterizes simple and complex variation. These improved benchmarks were used to retrain Google’s DeepVariant, a popular AI-based variant calling tool, resulting in a 34% reduction in erroneously called variants. This resource (the Platinum Pedigree) was built by scientists from PacBio in collaboration with researchers at the University of Washington, the University of Utah, and several other institutions.
Combining inheritance-based validation with long-read sequencing, this benchmark accurately characterizes variants, even in difficult, repeat rich regions of the genome, producing the most complete view of validated genetic variation to date.
“Comprehensive benchmarking datasets that include all variant types are foundational to progress in genomics methods development and the application of AI-driven tools, as well as to our understanding of genomic variation for both research and diagnostic purposes,” said Zev Kronenberg, lead author and Senior Manager at PacBio. “The Platinum Pedigree benchmark doesn’t just include simple variants in easy-to-sequence regions, it includes variants from across the entire genome, including regions that were previously excluded from benchmarks due to their complex nature.”
The Platinum Pedigree dataset was developed using deep sequencing from three sequencing platforms across a 28-member, multi-generational family (CEPH-1463). By tracking the inheritance of genetic variants from parents to multiple children, the study confidently catalogs over 37 Mb of genetic variation segregating within the family from single nucleotide variants to large structural variants.
The dataset introduces the first large pedigree-validated tandem repeat and structural variant truth sets. It also adds more than 200 million bases extending the benchmark regions to 2.77 Gb, including difficult-to-map areas such as segmental duplications and low-complexity regions.
A Benchmark Built for the Dark Genome
As a demonstration of the value of improved benchmarks to improve AI and ML methods, the researchers retrained Google’s DeepVariant - a popular software tool that employs deep learning to identify genetic variants - using the Platinum Pedigree benchmark data. This updated DeepVariant model reduced errors by up to 34% genome-wide, including even higher gains in the most challenging regions of the genome.
“This benchmark pushes accuracy where it matters most,” said Michael Eberle, senior author and Vice President of Computational Biology at PacBio. “It enables better evaluation of variant calling pipelines and accelerates the development of methods that finally reach the full genome, including some of the complex regions that are important for human health.”
A New Standard for Clinical and Population Genomics
The Platinum Pedigree benchmark is freely available and already being used by scientists to develop new sequence analysis tools and validate clinical sequencing workflows. It also provides a roadmap for future benchmarking efforts, especially those involving more complete genomes like T2T-CHM13.
