datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
biomap-research-metal_ion_binding
metal_ion_binding
Sourced from biomap-research/metal_ion_binding and prepared for Hugging Face datasets usage.
Data files
Parquet files are stored under data/ using Hugging Face split naming conventions
(train-*, validation-*, test-*).
Preparation
Preprocess mode: minimal.
Seed: 1957723.
No max sequence length filter was applied.
Renamed source columns: label -> targets, seq -> sequence.
Columns: id, sequence, targets, split.
Validation handling:… See the full description on the dataset page: https://huggingface.co/datasets/swhitfield/biomap-research-metal_ion_binding.metal_ion_binding
Dataset Card for Metal Ion Binding Dataset
Dataset Summary
Metal ion binding sites within proteins play a crucial role across a spectrum of processes, spanning from physiological to pathological, toxicological, pharmaceutical, and diagnostic. Consequently, the development of precise and efficient methods to identify and characterize these metal ion binding sites in proteins has become an imperative and intricate task for bioinformatics and structural biology.… See the full description on the dataset page: https://huggingface.co/datasets/biomap-research/metal_ion_binding.uniprot_binding_sites_multiple
Dataset Details
Dataset Description
Binding sites of a molecule in protein sequences.
Curated by:
License: MIT
Dataset Sources
data source
Citation
BibTeX:
@article{10.1093/nar/gkac1052,
author = {The UniProt Consortium},
title = {UniProt - the Universal Protein Knowledgebase in 2023},
journal = {Nucleic Acids Research},
volume = {51},
number = {D1},
pages = {D523-D531},
year = {2022},
month = {11},
issn = {0305-1048},
doi =… See the full description on the dataset page: https://huggingface.co/datasets/jablonkagroup/uniprot_binding_sites_multiple.Binding-Affinity
SupraBench Binding Affinity — Comprehensive Anchor Dataset
📄 Paper: arXiv:2606.13477
💻 Code: https://github.com/Tianyi-Billy-Ma/SupraBench
Each row is a host–guest binding-affinity record from SupraBench, enriched with
full molecular-structure data for both the host and the guest (SMILES, a 2D
depiction, and a 3D conformer) plus the experimental environment (solvent,
temperature, pH). It is the structure-complete companion to the
SupraBench/bap task split.… See the full description on the dataset page: https://huggingface.co/datasets/SupraBench/Binding-Affinity.bindingdb
BindingDB Processed Dataset
This dataset is derived from BindingDB, specifically from BindingDB_All_2D_202503_sdf.zip.
The dataset creation code can be found here.
dataset_info:
features:
- name: ligand
dtype: string
- name: protein
dtype: string
- name: ic50
dtype: float64
splits:
- name: train
num_bytes: 568898862
num_examples: 972285
- name: test
num_bytes: 142171753
num_examples: 243072
download_size: 393836446… See the full description on the dataset page: https://huggingface.co/datasets/vladak/bindingdb.sarscov2-binding-prediction
SARS-CoV-2 binding dataset
Dataset of 104972 antibodies screened for binding the SARS-CoV-2 HR peptide, described in Engelhart et al. (2022), were obtained from Zenodo.
Average predicted logKD values were used for classifying sequences as binders and non-binders:
logKD<3 = binders
logKD>=4 = non-binders
logKD>=3 and logKD = ambiguous; removed.
Using these criteria, we have 51590 sequences remaining; these were stratified into an 80:10:10 ratio for training, test, validation… See the full description on the dataset page: https://huggingface.co/datasets/alchemab/sarscov2-binding-prediction.il6-binding-prediction
Human IL-6 binding dataset
Nanobodies binding IL-6 were obtained from the Github repo for Tsuruta et al. (2023). Labels for antibody sequences were provided from the Github repo as-is.
Briefly, we first removed any nanobody sequence having lower than 75%; human germline sequence identity was determined using ANARCI.
Among the remaining 232084 sequences, we only use antibodies that have confirmed binding to one IL-6 variant or has no binding to any IL-6 variant, leading to 211920… See the full description on the dataset page: https://huggingface.co/datasets/alchemab/il6-binding-prediction.her2-binding-prediction
HER2 binding dataset
HER2 binding antibodies have been obtained from the Github repo for Mason et al. (2021).
Labels for antibody sequences were generated using scripts in the above Github repo. The number of negatives and positives were balanced through random undersampling using imbalanced-learn, and sequences were deduplicated.
The dataset has:
39108 antibodies in total
22779 antibodies after undersampling and deduplication
18223 in the training set, 2278 in the evaluation set… See the full description on the dataset page: https://huggingface.co/datasets/alchemab/her2-binding-prediction.metal_ion_binding
Dataset Card for Metal Ion Binding Dataset
Dataset Summary
Metal ion binding sites within proteins play a crucial role across a spectrum of processes, spanning from physiological to pathological, toxicological, pharmaceutical, and diagnostic. Consequently, the development of precise and efficient methods to identify and characterize these metal ion binding sites in proteins has become an imperative and intricate task for bioinformatics and structural biology.… See the full description on the dataset page: https://huggingface.co/datasets/proteinglm/metal_ion_binding.clustered_jglaser_binding_affinityuniprot_binding_sites_multiple-multimodaluniprot_binding_single
Dataset Details
Dataset Description
Binding sites of a molecule in protein sequences.
Curated by:
License: MIT
Dataset Sources
data source
Citation
BibTeX:
@article{10.1093/nar/gkac1052,
author = {The UniProt Consortium},
title = {UniProt - the Universal Protein Knowledgebase in 2023},
journal = {Nucleic Acids Research},
volume = {51},
number = {D1},
pages = {D523-D531},
year = {2022},
month = {11},
issn = {0305-1048},
doi =… See the full description on the dataset page: https://huggingface.co/datasets/jablonkagroup/uniprot_binding_single.bindingdb_molwt_300-750_50k_featurestoretoy_binding_affinity
Dataset Card for "toy_binding_affinity"
More Information needed
binding_512_SELFIES
From the jglaser/binding_affinity database, converted to SELFIES
Steps to prepare the database:
Download the jglaser/binding_affinity database
from datasets import load_dataset
binding_data = load_dataset('parquet', split='train', data_files="https://huggingface.co/datasets/jglaser/binding_affinity/resolve/main/data/all_512.parquet")
Convert SMILES to SELFIES
import selfies
def smiles_to_selfies(dataset):
try:
return {"selfies": selfies.encoder(dataset["smiles_can"])}… See the full description on the dataset page: https://huggingface.co/datasets/introvoyz041/binding_512_SELFIES.ligand_protein_binding_datasetentity_bindingmodel-raising-persona-binding-sft