Fetch PDB protein structure abstracts via REST API
LlamaIndex reader that fetches publication abstracts for Protein Data Bank entries via RCSB or EBI REST APIs for structural bioinformatics research.
Why it matters
Retrieve publication abstracts and metadata from the Protein Data Bank for structural biology research, enabling researchers to load protein structure documentation into knowledge systems and RAG pipelines.
Outcomes
What it gets done
Query RCSB or EBI REST APIs with PDB entry identifiers
Extract abstract text from protein structure publications
Transform PDB metadata into structured document format
Load protein data bank entries into LlamaIndex for indexing
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-pdb | bash Overview
Protein Data Bank (PDB) publication Loader
The Protein Data Bank publication Loader is a LlamaIndex reader that fetches publication abstracts for PDB entries using RCSB or EBI REST APIs. It takes PDB identifiers as input and returns documents containing the associated publication abstracts. Use this loader when you need to fetch publication abstracts for specific PDB entries and load them into LlamaIndex.
What it does
The Protein Data Bank (PDB) publication Loader is a LlamaIndex reader that retrieves publication abstracts for PDB entries using REST APIs from RCSB (Research Collaboratory for Structural Bioinformatics) or EBI (European Bioinformatics Institute).
When to use - and when NOT to
Use this loader when you need to fetch publication abstracts for specific PDB entries by their IDs.
Do NOT use this loader if you need full-text articles (it only retrieves abstracts), or if you require 3D coordinate data, experimental methods, or other structural details beyond publication abstracts.
Inputs and outputs
You provide an array of PDB identifiers (e.g., ["1cbs"]) to the load_data method. The loader returns documents containing the publication abstracts associated with those PDB entries.
Integrations
This loader is designed to be used as a way to load data into LlamaIndex. It connects to RCSB and EBI REST APIs to fetch PDB publication data.
Who it's for
This tool serves users who need to fetch PDB publication abstracts and load them into LlamaIndex.
Installation and usage
pip install llama-index-readers-pdb
from llama_index.readers.pdb import PdbAbstractReader
loader = PdbAbstractReader()
documents = loader.load_data(pdb_id=["1cbs"])
Source README
Protein Data Bank (PDB) publication Loader
pip install llama-index-readers-pdb
This loader fetches the abstract of PDB entries using the RCSB (Research Collaboratory for Structural Bioinformatics) or EBI (European Bioinformatics Institute) REST api.
Usage
To use this loader, simply pass an array of PDB ids into load_data:
from llama_index.readers.pdb import PdbAbstractReader
loader = PdbAbstractReader()
documents = loader.load_data(pdb_id=["1cbs"])
This loader is designed to be used as a way to load data into LlamaIndex.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.