Structure prediction of protein-ligand complexes from sequence information with Umol
posebusters_benchmark_set.tar.zst - files for the prediction (features to Umol) and scoring of the pose busters benchmark posebusters_pred_native.tar.zst - pdb and sdf files of proteins and ligands. Includes native structures, predicted structures and relaxed predicted structures with plDDT in the B factor column. posebusters_scores.csv - contains ligand RMSD and other metrics for the unrelaxed structures predicted with Umol. PDBBind_processed.tar.zst - files for the training (features to Umol) using PDBbind version 2020 Zenodo record 10060894, published 2023-11-01, 4 file(s) totalling 8246.1 MB (3 archive, 1 tabular).
- Category
- Drug Discovery
- Provider
- Patrick Bryant
- License
- CC-BY-4.0
- DOI
- 10.5281/zenodo.10060894
- Hosted on
- Zenodo
- Access
- Free and public. No account with the data provider is needed.
- Source
- https://doi.org/10.5281/zenodo.10060894
Data structure and loading code
Fields
id | string |
protein_pocket_rmsd | float |
ligand_rmsd | float |
dmat_err | float |
pocket_size | integer |
protein_plddt | float |
protein_pocket_plddt | float |
protein_pocket_lddt | float |
ligand_lddt | float |
ligand_plddt | float |
num_ligand_atoms | integer |
protein_length | integer |
l_plDDT_bin | string |
ligand_lddt_CA | float |
protein_pocket_lddt_CA | float |
Load the data
import pandas as pd
# posebusters_scores.csv (0.1 MB) streamed straight from Zenodo.
df = pd.read_csv("https://zenodo.org/api/records/10060894/files/posebusters_scores.csv/content", sep=",", low_memory=False)
print(df.shape)
df.head()Written for a Scigantic notebook, where /mnt/archive is the mounted dataset.
Analyze this dataset without downloading it
On Scigantic, Structure prediction of protein-ligand complexes from sequence information with Umol opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
Related Drug Discovery datasets
- OpenBind on Fragalysis: FatA and DENV-2/ZIKV RdRp fragment-screen structures
- PubChem: compound identifier, name and mass registry
- Structures of FDA-approved drugs and their active metabolites and data sets of experimental PD and PK properties
- Benchmarking of PROTAC docking and virtual screening tools - dataset
- 829 drug-like molecules intrinsic solubility dataset
- Data from: Poor adherence to guidelines for preventing central line-associated bloodstream infections (CLABSI): results of a worldwide survey
- Improved Detection of Drug-Induced Liver Injury by Integrating Predicted in vivo and in vitro Data
- CompTox Zebrafish developmental toxicity processed data