datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
rfam
Rfam
Rfam is a database of structure-annotated multiple sequence alignments, covariance models and family annotation for a number of non-coding RNA, cis-regulatory and self-splicing intron families.
The seed alignments are hand curated and aligned using available sequence and structure data, and covariance models are built from these alignments using the INFERNAL v1.1.4 software suite.
The full regions list is created by searching the RFAMSEQ database using the covariance model… See the full description on the dataset page: https://huggingface.co/datasets/multimolecule/rfam.rfam-taxonomy-lookuprfam_sample_padded_arraysrfam-standard