Read, manipulate, analyze, and fetch biomolecular structures and sequences in Python.
npx skills add https://github.com/LiorZ/protein-design-skills --skill biotite
Please help me install this Agent Skill. Skill: biotite Source: https://github.com/LiorZ/protein-design-skills/tree/main/skills/biotite Command: npx skills add https://github.com/LiorZ/protein-design-skills --skill biotite
Biotite provides a fast, NumPy-backed toolkit to read, manipulate, analyze, and fetch biomolecular structures and sequences, serving as the connective tissue between design predictors, structure analysis tools, and data sources.
Install Biotite and run a quick check: fetch a PDB by its id, load it, and compute a simple RMSD against a rotated copy.
High-intent search queries and answers about installing and using this skill.
Biotite reads and analyzes PDB and mmCIF structures in Python using a NumPy-backed AtomArray model, enabling fast structural manipulation, trajectory loading, and format conversion for biomolecular data.
Yes, you can fetch biomolecular sequences and structures directly from RCSB PDB, AlphaFold DB, UniProt, NCBI Entrez, and PubChem to populate AtomArray objects for downstream analysis and validation workflows.
Compute RMSD, lDDT, and TM-score for protein structure predictions by loading models into an AtomArray or AtomArrayStack, then applying built-in structural analysis functions to compare and align designs.
Yes, this protein-structure toolkit integrates with RDKit and OpenMM through optional bridges, allowing you to prepare inputs, refine models, and automate end-to-end structural analysis pipelines.
The best way to validate protein designs against structural predictions is to combine predictor outputs with structural analyses like RMSD and hydrogen bonds to rank survivors within a NumPy-based pipeline workflow.
Use BinaryCIF over mmCIF for structural data IO when you need faster read and write speeds for large biomolecular datasets, as both formats are fully supported within the NumPy-based structure model.
andikarachmanAudit Python version and installed DS/ML libraries for environment readiness.
InternScienceRun HDOCKlite docking to generate ranked protein–protein or protein–ligand complex models.
qinyan-aiSet up, run, and analyze molecular dynamics simulations with OpenMM and MDAnalysis.
omar-A-hassanRetrieves protein structure entries and metadata from the RCSB PDB via APIs.
