AD
Data & Repro
Adaptyv
Adaptyv is a cloud laboratory platform that provides automated protein testing and validation services. Submit protein sequences via API or…
K-Dense-AI/claude-scientific-skillsView
Data & Repro
BI
bio-structural-biology-alphafold-predictions
Maintainer FreedomIntelligence · Last updated April 1, 2026
Access and analyze AlphaFold protein structure predictions. Use when predicted structures are needed for proteins without experimental structures, or for confidence scores (pLDDT).
Original source
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-structural-biology-alphafold-predictions
- Maintainer
- FreedomIntelligence
- License
- MIT
- Last updated
- April 1, 2026
Skill Snapshot
Key Details From SKILL.md
Key Notes
- Python: requests.get(f'https://alphafold.ebi.ac.uk/files/AF-{uniprot}-F1-model_v4.pdb').
- Get the AlphaFold predicted structure for my protein" → Download pre-computed AlphaFold structures by UniProt ID and assess prediction quality via per-residue pLDDT confidence scores. Python: requests.get(f'https://alphafold.ebi.ac.uk/files/AF-{uniprot}-F1-model_v4.pdb').
- Download and analyze AlphaFold predicted protein structures from the AlphaFold Protein Structure Database.
- Goal: Retrieve pre-computed AlphaFold protein structure predictions and assess prediction quality via pLDDT confidence scores.
- Approach: Query the AlphaFold Protein Structure Database API by UniProt accession to download PDB/CIF files, then extract per-residue pLDDT scores from B-factor columns to identify high-confidence and disordered regions.
Source Doc
Excerpt From SKILL.md
File Types Available
Database version v4 (current as of 2025). The version number refers to the database release, not the AlphaFold model version.
| File | URL Pattern | Description |
|---|---|---|
| PDB | AF-{id}-F1-model_v4.pdb | Structure coordinates |
| mmCIF | AF-{id}-F1-model_v4.cif | Structure with metadata |
| PAE JSON | AF-{id}-F1-predicted_aligned_error_v4.json | Predicted aligned error |
Extract from PDB B-factors
AlphaFold stores pLDDT scores in the B-factor column.
Confidence Interpretation
| pLDDT | Confidence | Interpretation |
|---|---|---|
| >90 | Very high | High accuracy, can be used as experimental |
| 70-90 | Confident | Good backbone, may have sidechain errors |
| 50-70 | Low | Caution, may be disordered |
| <50 | Very low | Likely disordered or wrong |
Use cases
- Use when predicted structures are needed for proteins without experimental structures, or for confidence scores (pLDDT).
Not for
- Do not rely on this catalog entry alone for installation or maintenance details.
Upstream Related Skills
- structural-biology/structure-io - Load and parse PDB/mmCIF files
- structural-biology/geometric-analysis - RMSD, superimposition
- database-access/uniprot-access - Get UniProt IDs for proteins
- structural-biology/structure-navigation - Navigate structure hierarchy
Related skills
Related skills
AL
Data & Repro
alphafold
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) P…
FreedomIntelligence/OpenClaw-Medical-SkillsView
AL
Data & Repro
AlphaFold DB
AlphaFold DB is a public repository of AI-predicted 3D protein structures for over 200 million proteins, maintained by DeepMind and EMBL-EBI…
K-Dense-AI/claude-scientific-skillsView
AN
Data & Repro
antibody-design-agent
Antibody design: epitope mapping, CDR engineering, bispecific construction.
FreedomIntelligence/OpenClaw-Medical-SkillsView