datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
vepyr_116_GRCh38_plugin_alphamissense
vepyr plugin cache — AlphaMissense (GRCh38, VEP 116)
A prebuilt, frequency-tiered Parquet cache of AlphaMissense pathogenicity
predictions for use with vepyr, the Rust/DataFusion
VEP-compatible variant annotation engine. It reproduces the CSQ output of Ensembl
VEP 116's --plugin AlphaMissense without requiring the upstream TSV or the Perl plugin
at annotation time.
Source version
This is the fact you most likely came here for.
Source file… See the full description on the dataset page: https://huggingface.co/datasets/biodatageeks/vepyr_116_GRCh38_plugin_alphamissense.allelix-alphamissense
Allelix AlphaMissense Pathogenicity Cache
Pre-built SQLite cache of missense variant pathogenicity predictions from DeepMind's AlphaMissense for use with Allelix.
What's in the file
alphamissense.sqlite.gz is a gzipped SQLite database containing the alphamissense_scores table with all ~71M missense variant predictions from AlphaMissense, 7.5M of which carry rsID mappings via a gnomAD v4.1 coordinate join.
Schema
CREATE TABLE alphamissense_scores (… See the full description on the dataset page: https://huggingface.co/datasets/allelix/allelix-alphamissense.dm_alphamissenseNote: this database has been uploaded by Hugging Face staff. Please see the original paper, repo, and hosted database below for any questions.
Google DeepMind AlphaMissense Database
Paper: https://www.science.org/doi/10.1126/science.adg7492
Github Repo: https://github.com/google-deepmind/alphamissense
Original Database: https://console.cloud.google.com/storage/browser/dm_alphamissense
File descriptions
AlphaMissense_hg19.tsv.gz, AlphaMissense_hg38.tsv.gz:… See the full description on the dataset page: https://huggingface.co/datasets/katielink/dm_alphamissense.