Saluki Mouse mRNA Half-Life Benchmark (mRNABench): transcript sequences with half-life aggregated from 27 mouse datasets

Provider
Vikram Agarwal and David R. Kelley (Calico); packaged by the Morris lab (MSKCC) for mRNABench
License
CC-BY-4.0 (source)
Size
3 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/morrislab/rnahl-saluki-mouse)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.6326409
Category
Genomics & Bioinformatics
Source
https://doi.org/10.1186/s13059-022-02811-x

About this dataset

Mouse mRNA half-life, the time for a transcript's level to fall by half and a direct readout of mRNA degradation rate, aggregated by Agarwal and Kelley for the Saluki model from 27 transcriptome-wide mouse datasets (the companion human set combines 39). Half-lives were averaged per gene across studies and summarized by the first principal component of the gene by dataset half-life matrix, which is the regression target here. The Morris lab repackaged it for mRNABench: rnahl-saluki-mouse.parquet has 13,723 rows, one per gene transcript, with the mRNA sequence, a binary codon-start track over the coding sequence, a binary splice-site track and the half-life target; about 22 MB. Read with pandas, polars or Hugging Face datasets, or through the mrnabench package. Use for predicting mRNA stability from sequence, comparing RNA language models on a mouse task and studying UTR, codon and splice-junction determinants of decay. Source data are on Zenodo under CC BY 4.0 (DOI 10.5281/zenodo.6326409); cite Agarwal and Kelley, Genome Biology 23, 245 (2022), doi 10.1186/s13059-022-02811-x, and mRNABench.

How to load this dataset in Python

from datasets import load_dataset
ds = load_dataset("morrislab/rnahl-saluki-mouse")
print(ds)

Data structure

File types in sampled files: Parquet

Files

Example file: rnahl-saluki-mouse.parquet

Analyze this dataset without downloading it

On Scigantic, Saluki Mouse mRNA Half-Life Benchmark (mRNABench): transcript sequences with half-life aggregated from 27 mouse datasets opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Genomics & Bioinformatics datasets