Photo by DeepMind on Unsplash

COVID-19 Genome Sequence Dataset 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/ncbi-covid-19-dataset")

fs.listdir("s3://sra-pub-sars-cov2")
Click on copy button to copy content

Description

A centralized sequence repository for all records containing sequence associated with the novel corona virus (SARS-CoV-2) submitted to the National Center for Biotechnology Information (NCBI) Sequence Read Archive (SRA). Included are both the original sequences submitted by the principal investigator as well as SRA-processed sequences that require the SRA Toolkit for analysis. Additionally, submitter provided metadata included in associated BioSample and BioProject records is available alongside NCBI calculated data, such k-mer based taxonomy analysis results, contiguous assemblies (contigs) and associated statistics such as contig length, blast results for the assembled contigs, contig annotation, blast databases of contigs and their annotated peptides, and VCF files generated for each record relative to the SARS-CoV-2 RefSeq record. Finally, metadata is additionally made available in parquet format to facilitate search and filtering using the AWS Athena Service.

Additional information

Update frequency

Hourly

Managed by

NLM

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