Protein Structure Data Retrieval
Retrieve protein structures with disambiguation, quality assessment, and comprehensive metadata.
IMPORTANT: Always use English terms in tool calls. Respond in the user's language.
LOOK UP DON'T GUESS: Never assume PDB IDs, resolution, or availability. Always query RCSB/PDBe and AlphaFold to confirm.
Domain Reasoning
Not all structures are equal. X-ray <2 A is high-quality for drug design. Cryo-EM 3-4 A is good for fold but not side chains. AlphaFold is excellent for well-folded domains but unreliable for disordered regions. Always check pLDDT (AlphaFold) or resolution (experimental) before drawing conclusions.
Workflow
Phase 0: Clarify (if needed) → Phase 1: Disambiguate Protein → Phase 2: Retrieve Structures → Phase 3: Report
Phase 0: Clarification (When Needed)
Ask ONLY if: protein name ambiguous (e.g., "kinase"), organism not specified, unclear if experimental vs AlphaFold needed.
Skip for: specific PDB IDs, UniProt accessions, unambiguous protein+organism.
Phase 1: Protein Disambiguation
# By PDB ID: direct retrieval
# By UniProt: get AlphaFold + search experimental structures
af_structure = tu.tools.alphafold_get_prediction(uniprot_id=uniprot_id)
# By protein name: search
result = tu.tools.PDBeSearch_search_structures(protein_name=protein_name)
Identity Checklist
- Protein name/gene identified, organism confirmed
- UniProt accession (if available), isoform/variant specified (if relevant)
Phase 2: Data Retrieval (Internal)
Retrieve silently. Do NOT narrate the process.
pdb_id = "4INS"
# Search, metadata, quality, ligands, similar structures
result = tu.tools.PDBeSearch_search_structures(protein_name=name)
metadata = tu.tools.get_protein_metadata_by_pdb_id(pdb_id=pdb_id)
exp = tu.tools.RCSBData_get_entry(pdb_id=pdb_id)
quality = tu.tools.PDBeValidation_get_quality_scores(pdb_id=pdb_id)
ligands = tu.tools.PDBe_KB_get_ligand_sites(pdb_id=pdb_id)
similar = tu.tools.PDBeSIFTS_get_all_structures(pdb_id=pdb_id, cutoff=2.0)
# PDBe additional data
summary = tu.tools.pdbe_get_entry_summary(pdb_id=pdb_id)
molecules = tu.tools.pdbe_get_entry_molecules(pdb_id=pdb_id)
# AlphaFold (when no experimental structure, or for comparison)
af = tu.tools.alphafold_get_prediction(uniprot_id=uniprot_id)
Fallback Chains
| Primary |
Fallback |
| RCSB search |
PDBe search |
| get_protein_metadata |
pdbe_get_entry_summary |
| Experimental structure |
AlphaFold prediction |
| get_protein_ligands |
PDBe_KB_get_ligand_sites |
Phase 3: Report Structure Profile
Present as a Structure Profile Report. Hide search process. Include:
- Search Summary: query, organism, experimental + AlphaFold structure counts
- Best Structure: PDB ID, UniProt, organism, method, resolution, date, quality assessment
- Experimental Details: method, resolution, R-factor, R-free, space group
- Composition: chains, residues (coverage%), ligands, waters, metals
- Bound Ligands: ligand ID, name, type, binding site
- Binding Site Details (for drug discovery): location, key residues, druggability
- Alternative Structures: ranked by quality with resolution, method, ligands
- AlphaFold Prediction: UniProt, model version, pLDDT confidence distribution, use cases
- Structure Comparison: resolution, completeness, ligands across structures
- Download Links: PDB/mmCIF/AlphaFold formats, database URLs
Quality Assessment
Experimental Structures
| Tier |
Criteria |
| Excellent |
X-ray <1.5A, complete, R-free <0.22 |
| High |
X-ray <2.0A OR Cryo-EM <3.0A |
| Good |
X-ray 2.0-3.0A OR Cryo-EM 3.0-4.0A |
| Moderate |
X-ray >3.0A OR NMR ensemble |
| Low |
>4.0A, incomplete, or problematic |
Resolution Use Cases
<1.5A: atomic detail, H-bond analysis. 1.5-2.0A: drug design. 2.0-2.5A: structure-based design. 2.5-3.5A: overall architecture. >3.5A: domain arrangement only.
AlphaFold Confidence (pLDDT)
90: very high, experimental-like. 70-90: good backbone. 50-70: uncertain/flexible. <50: likely disordered.
Error Handling
| Error |
Response |
| "PDB ID not found" |
Verify 4-char format, check if obsoleted |
| "No structures" |
Offer AlphaFold, suggest similar proteins |
| "Download failed" |
Retry once, provide alternative link |
| "Resolution unavailable" |
Likely NMR/model, note in assessment |
Tool Reference
RCSB PDB: PDBeSearch_search_structures (search), get_protein_metadata_by_pdb_id (basic info), RCSBData_get_entry (details), PDBeValidation_get_quality_scores (quality), PDBe_KB_get_ligand_sites (ligands), PDBeSIFTS_get_all_structures (homologs)
PDBe: pdbe_get_entry_summary (overview), pdbe_get_entry_molecules (entities), pdbe_get_entry_experiment (experimental), PDBe_KB_get_ligand_sites (pockets)
AlphaFold: alphafold_get_prediction (get prediction), alphafold_get_summary (search)
1---
2name: tooluniverse-protein-structure-retrieval
3description: Protein structure retrieval from RCSB PDB, PDBe, and AlphaFold with disambiguation, quality assessment (resolution, R-factor, pLDDT), and metadata. Distinguishes high-quality experimental (X-ray under 2 Angstrom) vs predicted vs medium-quality structures. Use for fetching protein structures, structure-quality comparison, and selecting structures for drug design or modeling.
4disable-model-invocation: true
5---
6
7# Protein Structure Data Retrieval
8
9Retrieve protein structures with disambiguation, quality assessment, and comprehensive metadata.
10
11**IMPORTANT**: Always use English terms in tool calls. Respond in the user's language.
12
13**LOOK UP DON'T GUESS**: Never assume PDB IDs, resolution, or availability. Always query RCSB/PDBe and AlphaFold to confirm.
14
15## Domain Reasoning
16
17Not all structures are equal. X-ray <2 A is high-quality for drug design. Cryo-EM 3-4 A is good for fold but not side chains. AlphaFold is excellent for well-folded domains but unreliable for disordered regions. Always check pLDDT (AlphaFold) or resolution (experimental) before drawing conclusions.
18
19## Workflow
20
21```
22Phase 0: Clarify (if needed) → Phase 1: Disambiguate Protein → Phase 2: Retrieve Structures → Phase 3: Report
23```
24
25---
26
27## Phase 0: Clarification (When Needed)
28
29Ask ONLY if: protein name ambiguous (e.g., "kinase"), organism not specified, unclear if experimental vs AlphaFold needed.
30Skip for: specific PDB IDs, UniProt accessions, unambiguous protein+organism.
31
32---
33
34## Phase 1: Protein Disambiguation
35
36```python
37# By PDB ID: direct retrieval
38# By UniProt: get AlphaFold + search experimental structures
39af_structure = tu.tools.alphafold_get_prediction(uniprot_id=uniprot_id)
40# By protein name: search
41result = tu.tools.PDBeSearch_search_structures(protein_name=protein_name)
42```
43
44### Identity Checklist
45- Protein name/gene identified, organism confirmed
46- UniProt accession (if available), isoform/variant specified (if relevant)
47
48---
49
50## Phase 2: Data Retrieval (Internal)
51
52Retrieve silently. Do NOT narrate the process.
53
54```python
55pdb_id = "4INS"
56
57# Search, metadata, quality, ligands, similar structures
58result = tu.tools.PDBeSearch_search_structures(protein_name=name)
59metadata = tu.tools.get_protein_metadata_by_pdb_id(pdb_id=pdb_id)
60exp = tu.tools.RCSBData_get_entry(pdb_id=pdb_id)
61quality = tu.tools.PDBeValidation_get_quality_scores(pdb_id=pdb_id)
62ligands = tu.tools.PDBe_KB_get_ligand_sites(pdb_id=pdb_id)
63similar = tu.tools.PDBeSIFTS_get_all_structures(pdb_id=pdb_id, cutoff=2.0)
64
65# PDBe additional data
66summary = tu.tools.pdbe_get_entry_summary(pdb_id=pdb_id)
67molecules = tu.tools.pdbe_get_entry_molecules(pdb_id=pdb_id)
68
69# AlphaFold (when no experimental structure, or for comparison)
70af = tu.tools.alphafold_get_prediction(uniprot_id=uniprot_id)
71```
72
73### Fallback Chains
74
75| Primary | Fallback |
76|---------|----------|
77| RCSB search | PDBe search |
78| get_protein_metadata | pdbe_get_entry_summary |
79| Experimental structure | AlphaFold prediction |
80| get_protein_ligands | PDBe_KB_get_ligand_sites |
81
82---
83
84## Phase 3: Report Structure Profile
85
86Present as a **Structure Profile Report**. Hide search process. Include:
87
881. **Search Summary**: query, organism, experimental + AlphaFold structure counts
892. **Best Structure**: PDB ID, UniProt, organism, method, resolution, date, quality assessment
903. **Experimental Details**: method, resolution, R-factor, R-free, space group
914. **Composition**: chains, residues (coverage%), ligands, waters, metals
925. **Bound Ligands**: ligand ID, name, type, binding site
936. **Binding Site Details** (for drug discovery): location, key residues, druggability
947. **Alternative Structures**: ranked by quality with resolution, method, ligands
958. **AlphaFold Prediction**: UniProt, model version, pLDDT confidence distribution, use cases
969. **Structure Comparison**: resolution, completeness, ligands across structures
9710. **Download Links**: PDB/mmCIF/AlphaFold formats, database URLs
98
99---
100
101## Quality Assessment
102
103### Experimental Structures
104
105| Tier | Criteria |
106|------|----------|
107| Excellent | X-ray <1.5A, complete, R-free <0.22 |
108| High | X-ray <2.0A OR Cryo-EM <3.0A |
109| Good | X-ray 2.0-3.0A OR Cryo-EM 3.0-4.0A |
110| Moderate | X-ray >3.0A OR NMR ensemble |
111| Low | >4.0A, incomplete, or problematic |
112
113### Resolution Use Cases
114<1.5A: atomic detail, H-bond analysis. 1.5-2.0A: drug design. 2.0-2.5A: structure-based design. 2.5-3.5A: overall architecture. >3.5A: domain arrangement only.
115
116### AlphaFold Confidence (pLDDT)
117>90: very high, experimental-like. 70-90: good backbone. 50-70: uncertain/flexible. <50: likely disordered.
118
119---
120
121## Error Handling
122
123| Error | Response |
124|-------|----------|
125| "PDB ID not found" | Verify 4-char format, check if obsoleted |
126| "No structures" | Offer AlphaFold, suggest similar proteins |
127| "Download failed" | Retry once, provide alternative link |
128| "Resolution unavailable" | Likely NMR/model, note in assessment |
129
130---
131
132## Tool Reference
133
134**RCSB PDB**: `PDBeSearch_search_structures` (search), `get_protein_metadata_by_pdb_id` (basic info), `RCSBData_get_entry` (details), `PDBeValidation_get_quality_scores` (quality), `PDBe_KB_get_ligand_sites` (ligands), `PDBeSIFTS_get_all_structures` (homologs)
135
136**PDBe**: `pdbe_get_entry_summary` (overview), `pdbe_get_entry_molecules` (entities), `pdbe_get_entry_experiment` (experimental), `PDBe_KB_get_ligand_sites` (pockets)
137
138**AlphaFold**: `alphafold_get_prediction` (get prediction), `alphafold_get_summary` (search)
mims-harvard