Photo by DeepMind on Unsplash

1000 Genomes Phase 3 Reanalysis with DRAGEN 3.5 and 3.7 Dataset for Machine Learning

Install DagsHub:

pip install dagshub
Click on copy button to copy content

To stream this data directly on DagsHub

from dagshub.streaming import DagsHubFilesystem

fs = DagsHubFilesystem(".", repo_url="https://dagshub.com/DagsHub-Datasets/ilmn-dragen-1kgp-dataset")

fs.listdir("s3://1000genomes-dragen")
Click on copy button to copy content

Description

This dataset contains alignment files and short nucleotide, copy number, repeat expansion (STR) and structural variant call files from the 1000 Genomes Project Phase 3 dataset (n=3202) using Illumina DRAGEN v3.5.7b and v3.7.6 software. The v3.7.6 dataset also includes results from joint small variant, de novo structural variant, de novo copy number variant and repeat expansion calls on 602 trio families comprised of members from the 1000 Genomes Project Phase 3 dataset, as well as DRAGEN gVCF Genotyper (v3.8.3) analysis on the entire dataset (n=3202). Improvements and new features in the v3.7.6 individual samples analyses include CYP2D6 variant calling and joint detection (see ‘DRAGEN 3.7 User Guide’ for details on these features) and use of graph-based hg19 and hg38 reference hash tables (see ‘DRAGEN Wins at PrecisionFDA Truth Challenge V2 Showcase Accuracy Gains from Alt-aware Mapping and Graph Reference Genomes’ for details).

Additional information

Documentation

Update frequency

Files may be updated subsequent to changes to the 1000 Genomes Project data set or select new DRAGEN features or offerings.

Related datasets

Allen Brain Observatory – Visual Coding AWS Public Data Set

Allen Cell Imaging Collections

Biological and Physical Sciences (BPS) Microscopy Benchmark Training Dataset

Cancer Cell Line Encyclopedia (CCLE)

Launch your ML development to new heights with DagsHub

Back to top