datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
sfm-midtraining-mix-dclm-long-context-passages-blocklist-filteredsfm-supplemental-alignment-literaturesfm-alignment-labeling-v3items_raw_fullitems_fullGenLoop
GenLoop — Designed Candidates
Designed small-molecule candidates from GenLoop (Reddy 2026, Generative Drug Design in a Loop with dtSFM), with their AlphaFold-3 structural-verification metrics.
Paper: Generative Drug Design in a Loop with dtSFM (Reddy 2026) · bioRxiv (DOI pending)
Code: github.com/Reddy-BIIE-ETHZ/GenLoop
Model: dtSFM v3
Contents
genloop_designed_candidates.tsv — 84 designs across three campaigns (Breadth 50, CFTR 12, GLP1R 22), including each… See the full description on the dataset page: https://huggingface.co/datasets/SFM-BIIE-ETHZ/GenLoop.items_raw_liteitems_lite