datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
KnottedProteinsDemosick_nli_knotsknotprotSequencesDiffusion-Evodiff_knots
Dataset Card for "Diffusion-Evodiff_knots"
Dataset of proteins from Evodiff
Dataset of proteins generated through Evodiff
Contains knotted proteins (tested with omegafold and topoly) and unknotted proteins in ratio 1:4
The dataset is splitted into a train set (majority, 90 %) and evaluation set (only 10 %)
More Information needed
knotprotSequencesUniqueknots_AF_no_fragments
Dataset Card for "knots_AF_no_fragments"
More Information needed
Diffusion-all_knots
Dataset of knotted and unknotted proteins created by diffusion models
This dataset supports Unveiling the Entangled Landscape of Artificial Knotted Proteins ICLR poster and related GitHub repo.
The dataset contains a mixture of proteins generated by RFdiffusion+pMPNN, EvoDiff and a fraction of real proteins. For each of the three, the dataset contains 1k of knotted proteins and 4k of unknotted proteins.
Each protein has:
sequence
label with either 0 (unknotted protein) or 1… See the full description on the dataset page: https://huggingface.co/datasets/EvaKlimentova/Diffusion-all_knots.Diffusion-RFdiffusion_knots
Dataset Card for "Diffusion-RFdiffusion_knots"
More Information needed
knotprotSequencesClusteredknots_SPOUTxRossmann
Dataset description
Datataset containing SPOUT knotted (positive) and Rossmann unknotted (negative) proteins.
knots_AF
Dataset of knotted and unknotted proteins from AlphaFold
This dataset was created based on the whole UniProt database from where protein sequences were obtained, their 3D structure computed with AlphaFold
and their topology (knot vs. unknot) determined with Topoly. The obtained proteins were further processed by clustering with CD-HIT
and downsampling to ensure balanced sequence length distribution between knotted and unknotted samples.
The final dataset contains 98528 knotted… See the full description on the dataset page: https://huggingface.co/datasets/EvaKlimentova/knots_AF.Quazim0t0__Knot-CoT-14B-sce-details
Dataset Card for Evaluation run of Quazim0t0/Knot-CoT-14B-sce
Dataset automatically created during the evaluation run of model Quazim0t0/Knot-CoT-14B-sce
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Quazim0t0__Knot-CoT-14B-sce-details.knot-bakery-corpus