Download the DLD Dataset
The DLD dataset contains information on 2646 protein sequences, including labels for independent domain linkers (IDL), dependent domain linkers (DDL), intra-domain loops (L), structural domains (D), and termini (T). Below are the download options for both the JSON and CSV versions of the dataset and its associated files.
Main Dataset
domainLinker.chain: The main file containing all 2649 PDB chains with labels (reference). The labels are as follows: 1: IDL, 2: DDL, 3: L, 4: D, and 5: T.
Region Files
These files contain data on specific regions of the protein sequences (more detailed information):
- Download independent_domain_linker (JSON)
- Download independent_domain_linker (CSV)
- Download dependent_domain_linker (JSON)
- Download dependent_domain_linker (CSV)
- Download domain_dataset (JSON)
- Download domain_dataset (CSV)
- Download intra_domain_loops (JSON)
- Download intra_domain_loops (CSV)
- Download terminus (JSON)
- Download terminus (CSV)
- Download mapIdx_pdb_chain_unp (CSV)
Download All Files as a ZIP
If you prefer to download all the files in one go, click the button below to download a ZIP file containing all the dataset files.
Download All Files (ZIP)