Skip to content

SKILL.md

Latest commit

 

History

History
171 lines (131 loc) · 7.68 KB

SKILL.md

File metadata and controls

171 lines (131 loc) · 7.68 KB
Raw
name ontology-mapper
description Map materials science terms, crystal structures, and sample descriptions to ontology classes and properties. Supports any ontology registered in ontology_registry.json. Use when translating natural-language material descriptions to ontology terms, annotating simulation inputs with ontology metadata, or mapping crystal parameters (space group, Bravais lattice, lattice constants) to standardized ontology representations.
allowed-tools Read, Bash

Ontology Mapper

Goal

Translate real-world materials science descriptions into standardized ontology annotations. Given terms like "FCC copper" or structured data like {"material": "iron", "structure": "BCC", "lattice_a": 2.87}, produce the corresponding ontology classes and properties for any registered ontology.

Requirements

  • Python 3.8+
  • No external dependencies (Python standard library only)
  • Requires ontology-explorer's summary JSON and ontology_registry.json
  • Per-ontology mapping config (<name>_mappings.json) for ontology-specific synonyms and labels

Inputs to Gather

Input Description Example
Ontology Ontology name from registry cmso, asmo
Term(s) Natural-language materials concept(s) "unit cell", "FCC,copper,lattice"
Crystal system One of the 7 crystal systems cubic, hexagonal
Bravais lattice Lattice type (symbol or common name) FCC, cF, BCC
Space group Space group number (1-230) 225
Lattice parameters a, b, c in angstroms; alpha, beta, gamma in degrees a=3.615
Sample description JSON dict with material properties {"material":"copper","structure":"FCC"}

Decision Guidance

What do you need to map?
├── A concept or term to find its ontology class
│   └── concept_mapper.py --ontology <name> --term "<term>"
├── Crystal structure parameters to ontology terms
│   └── crystal_mapper.py --ontology <name> --bravais <type> --space-group <N> --a <val>
├── A full sample description to ontology annotations
│   └── sample_annotator.py --ontology <name> --sample '<json>'
└── Multiple terms at once
    └── concept_mapper.py --ontology <name> --terms "term1,term2,term3"

Script Outputs (JSON Fields)

Script Key Outputs
scripts/concept_mapper.py results.matches, results.unmatched, results.suggestions
scripts/crystal_mapper.py results.ontology_classes, results.ontology_properties, results.effective_system, results.bravais_lattice, results.validation_warnings
scripts/sample_annotator.py results.annotations, results.sample_type, results.material_type, results.unmapped_fields, results.suggested_properties

Workflow

  1. If the user provides natural-language terms, use concept_mapper.py to find matching ontology classes.
  2. If the user describes crystal structure parameters, use crystal_mapper.py to map them and validate constraints.
  3. For a complete sample description, use sample_annotator.py to produce full ontology annotations.
  4. Review any validation warnings (e.g., lattice parameter mismatches for the crystal system).
  5. Check unmapped_fields and suggested_properties for completeness.

Conversational Workflow Example

User: I'm setting up an MD simulation of BCC iron with lattice parameter 2.87 angstroms.
      What CMSO terms should I use?

Agent: Let me map your iron sample to CMSO ontology terms.

[Runs: sample_annotator.py --ontology cmso --sample '{"material":"iron","structure":"BCC","lattice_a":2.87,"space_group":229}' --json]

Your BCC iron simulation maps to these CMSO annotations:

- **Sample**: Atomic Scale Sample (subclass of Computational Sample)
- **Material**: Crystalline Material
- **Unit Cell**: Bravais lattice = "cI" (body-centered cubic)
- **Space Group**: number = 229 (Im-3m)
- **Lattice**: a = 2.87 Å
- **Element**: Fe

Suggested additions:
- Number of atoms in the simulation cell
- Simulation cell vectors and angles

CLI Examples

# Map a single concept
python3 skills/ontology/ontology-mapper/scripts/concept_mapper.py \
  --ontology cmso --term "space group" --json

# Map multiple terms
python3 skills/ontology/ontology-mapper/scripts/concept_mapper.py \
  --ontology cmso --terms "FCC,copper,lattice constant" --json

# Map crystal parameters (with ontology-specific labels)
python3 skills/ontology/ontology-mapper/scripts/crystal_mapper.py \
  --ontology cmso --bravais FCC --space-group 225 --a 3.615 --json

# Map crystal parameters (generic labels, no ontology specified)
python3 skills/ontology/ontology-mapper/scripts/crystal_mapper.py \
  --bravais FCC --space-group 225 --a 3.615 --json

# Annotate a full sample
python3 skills/ontology/ontology-mapper/scripts/sample_annotator.py \
  --ontology cmso \
  --sample '{"material":"copper","structure":"FCC","space_group":225,"lattice_a":3.615}' \
  --json

Adding a New Ontology

To support a new ontology (e.g., ASMO), create a <name>_mappings.json in references/:

{
  "ontology": "asmo",
  "synonyms": { "simulation method": "Simulation Method", ... },
  "property_synonyms": { "timestep": "has timestep", ... },
  "material_type_rules": { "keyword_rules": [...], "default": "Material" },
  "sample_schema": { "sample_class": "Simulation", ... },
  "crystal_output": { "base_classes": [...], "property_map": {...} },
  "annotation_routing": { "unit_cell_indicators": [...], ... }
}

Then add "mappings_file": "asmo_mappings.json" to the ontology's entry in ontology_registry.json. No code changes needed.

Error Handling

Error Cause Resolution
space_group must be between 1 and 230 Invalid space group number Use a valid space group number
a must be positive Non-positive lattice parameter Provide positive values in angstroms
Sample must be a non-empty dict Empty or missing sample data Provide a valid JSON sample dict
Validation warnings Lattice parameters inconsistent with crystal system Check that a=b=c for cubic, etc.

Interpretation Guidance

  • Confidence scores: 1.0 = exact match, 0.9 = synonym match, 0.7 = substring match, 0.5 = description match
  • Validation warnings: indicate potential mistakes (e.g., specifying a!=b for cubic). These are warnings, not errors — the mapping still proceeds.
  • Unmapped fields: input keys that the annotator doesn't recognize. These may need manual mapping.
  • Suggested properties: additional ontology properties that would make the annotation more complete.

Limitations

  • Concept mapping uses string matching and a per-ontology synonym table; it does not understand arbitrary natural language
  • Crystal system validation checks basic constraints only (not all crystallographic rules)
  • The element resolver recognizes common element names and symbols but may miss unusual spellings
  • Bravais lattice aliases cover common usage (FCC, BCC, HCP) but not all crystallographic notation variants

References

Version History

Date Version Changes
2026-02-25 1.1 Refactored for multi-ontology support: externalized CMSO-specific knowledge to config
2026-02-25 1.0 Initial release with CMSO mapping support