ontology-explorer

Ontology Explorer

Goal

Enable an agent to understand, navigate, and query the structure of materials science ontologies without loading verbose OWL/XML files directly. Provides fast access to class hierarchies, property definitions, and domain-range relationships through pre-processed JSON summaries.

Requirements

• Python 3.10+
• No external dependencies (Python standard library only)
• Internet access required only for owl_parser.py and ontology_summarizer.py when fetching remote OWL files

Inputs to Gather

Input	Description	Example
Ontology name	Registered ontology to query	cmso
Class name	A specific class to inspect	Material, UnitCell
Property name	A specific property to look up	hasMaterial, hasSpaceGroupNumber
Search term	Keyword to search across labels	crystal, lattice
OWL source	Path or URL to an OWL/XML file (for parsing/summarizing)	https://raw.githubusercontent.com/OCDO/cmso/main/cmso.owl

Decision Guidance

What do you need?
├── Understand overall ontology structure
│   └── class_browser.py --ontology cmso --list-roots
├── Inspect a specific class
│   └── class_browser.py --ontology cmso --class <name>
├── Find properties for a class
│   └── property_lookup.py --ontology cmso --class <name>
├── Look up a specific property
│   └── property_lookup.py --ontology cmso --property <name>
├── Search for a concept
│   ├── class_browser.py --ontology cmso --search <term>
│   └── property_lookup.py --ontology cmso --search <term>
├── Parse a new/updated OWL file
│   └── owl_parser.py --source <path-or-url>
└── Generate/refresh a summary JSON
    └── ontology_summarizer.py --source <url> --output <path>

Script Outputs (JSON Fields)

Script	Key Outputs
scripts/owl_parser.py	results.metadata, results.classes, results.object_properties, results.data_properties, results.class_hierarchy
scripts/ontology_summarizer.py	results.output_file, results.statistics
scripts/class_browser.py	results.class_info, results.subtree, results.properties, results.path_to_root, results.roots, results.search_results
scripts/property_lookup.py	results.property_info, results.class_properties, results.search_results

Workflow

1. Identify which ontology the user is working with (default: CMSO).
2. Use class_browser.py --list-roots to see the top-level concepts.
3. Drill into specific classes with class_browser.py --class <name> to see hierarchy, children, and applicable properties.
4. Look up individual properties with property_lookup.py --property <name>.
5. If the user mentions a concept but not its ontology name, use --search to find matching classes or properties.
6. For a new or updated ontology, run owl_parser.py to parse the raw OWL, then ontology_summarizer.py to generate a summary JSON.

Conversational Workflow Example

User: I have an FCC copper simulation. What CMSO classes should I use to describe it?

Agent: Let me explore the CMSO ontology to find the relevant classes. I'll run
a few targeted searches and property lookups (the answer below is synthesized
from several commands, per the Workflow section).

[Runs: class_browser.py --ontology cmso --search "crystal" --json]
  → Crystalline Material, Crystal Structure (among others)
[Runs: class_browser.py --ontology cmso --search "sample" --json]
  → Computational Sample, Atomic Scale Sample
[Runs: class_browser.py --ontology cmso --search "unit cell" --json]
  → Unit Cell
[Runs: class_browser.py --ontology cmso --search "space group" --json]
  → Space Group
[Runs: class_browser.py --ontology cmso --search "element" --json]
  → Chemical Element
[Runs: property_lookup.py --ontology cmso --property "has material" --json]
  → domain Computational Sample → range Material
[Runs: property_lookup.py --ontology cmso --property "has structure" --json]
  → domain Material → range Structure
[Runs: property_lookup.py --ontology cmso --property "has unit cell" --json]
  → domain Crystal Structure → range Unit Cell

For an FCC copper simulation, the relevant CMSO classes are:

- **Computational Sample** → **Atomic Scale Sample**: your simulation is an atomic-scale sample
- **Material** → **Crystalline Material**: copper is crystalline
- **Crystal Structure**: describes the FCC arrangement
- **Unit Cell**: the repeating FCC unit cell (a=b=c=3.615 Å, α=β=γ=90°)
- **Space Group**: FCC copper is space group 225 (Fm-3m)
- **Chemical Element**: Cu

The key relationship chain (from the property domains/ranges above):
  Computational Sample → has material → Material → has structure → Structure
  → (Crystal Structure) → has unit cell → Unit Cell

Shall I look up the specific properties for any of these classes?

CLI Examples

# List root classes in CMSO
python3 skills/ontology/ontology-explorer/scripts/class_browser.py \
  --ontology cmso --list-roots --json

# Inspect the Material class hierarchy
python3 skills/ontology/ontology-explorer/scripts/class_browser.py \
  --ontology cmso --class Material --json

# Search for crystal-related classes
python3 skills/ontology/ontology-explorer/scripts/class_browser.py \
  --ontology cmso --search crystal --json

# Find all properties for UnitCell
python3 skills/ontology/ontology-explorer/scripts/property_lookup.py \
  --ontology cmso --class UnitCell --json

# Look up a specific property
python3 skills/ontology/ontology-explorer/scripts/property_lookup.py \
  --ontology cmso --property "has space group" --json

# Parse a remote OWL file
python3 skills/ontology/ontology-explorer/scripts/owl_parser.py \
  --source https://raw.githubusercontent.com/OCDO/cmso/main/cmso.owl --json

# Generate a summary JSON from an OWL file
python3 skills/ontology/ontology-explorer/scripts/ontology_summarizer.py \
  --source https://raw.githubusercontent.com/OCDO/cmso/main/cmso.owl \
  --output summary.json --json

Error Handling

Error	Cause	Resolution
Ontology 'X' not in registry	Ontology name not registered	Check references/ontology_registry.json for available names
Class 'X' not found	Class label doesn't match any entry	Use --search to find similar names, or --list-roots to see available classes
Property 'X' not found	Property label doesn't match	Use --search to find similar properties
Cannot parse OWL source	Invalid XML or unreachable URL	Check file path or URL; ensure the file is valid OWL/XML
Summary file not found	Summary JSON hasn't been generated	Run ontology_summarizer.py first

Interpretation Guidance

• Class hierarchy: root classes are the broadest concepts; leaf classes are the most specific. A class inherits all properties from its ancestors.
• Object properties: show how classes relate to each other (domain → range). A property with domain UnitCell and range Basis means a unit cell has a basis.
• Data properties: show what literal values a class carries. A property with domain ChemicalElement and range xsd:string means an element has a string-valued attribute.
• Union domains: a property can apply to more than one class. When it does, the domain is shown as the classes joined with a pipe, e.g. A | B. (The bundled CMSO/ASMO summaries currently contain no union-domain properties.)
• Search relevance: 1.0 = label match, 0.5 = description match only.

Verification checklist

Before presenting any class, property, or relationship as fact, confirm and record:

• Resolved the target via class_browser.py --class <name> (or property_lookup.py) and recorded the exact canonical label returned in results.class_info.label / results.property_info.name — do not quote a name the agent typed; quote the label the tool resolved (e.g. UnitCell → Unit Cell).
• For every relationship chain stated, cited the actual domain and range from a property_lookup.py --property <name> call (recorded results.property_info.domain and .range), rather than inferring the link from class names.
• When a property's domain contains a pipe (A | B), reported it as a union (applies to each listed class) and confirmed the class in question matches one normalized member — did not silently assume single-class domain.
• For --search results, recorded each match's relevance and stated whether it was a label match (1.0) or description-only match (0.5); did not present a 0.5 description hit as a confirmed term match.
• Identified the ontology by its registry key (cmso or asmo) and confirmed it exists in references/ontology_registry.json; did not query an unregistered ontology or conflate CMSO and ASMO terms.
• When relying on a generated/refreshed summary, recorded its metadata.source_url and metadata.generated_at and the statistics (num_classes, num_object_properties, num_data_properties) so the result is traceable to a specific OWL source.
• Treated absent parents, descriptions, or domain/range as missing data (not as "no such relationship"), since the parser extracts only simple rdfs:subClassOf and declared domains/ranges and does no reasoning.

Common pitfalls & rationalizations

Tempting shortcut	Why it's wrong / what to do
"The class name UnitCell returned nothing, so the term doesn't exist."	Labels carry spaces (Unit Cell). The tools resolve exact → case-insensitive → space-normalized; if a direct guess fails, run --search and use the canonical label the tool returns, not the typed string.
"These two classes are obviously related, so I'll state the link."	Relationships exist only where an object property declares them. Verify with property_lookup.py --property <name> and quote the recorded domain → range; never infer a triple from class names alone.
"The script ran and printed results, so the answer is complete."	Run success ≠ completeness. A missing parent, description, or domain/range means the OWL lacked that annotation — the parser does no inference and ignores complex OWL restrictions. State what is absent.
"--search crystal matched it, so it's the right term."	A match may be relevance 0.5 (description-only), not a label match. Check the relevance field and prefer 1.0 label matches; report 0.5 hits as "mentioned in the description," not as the canonical term.
"A property has one domain class."	Domains can be unions (`A
"Any OCDO ontology will work / CMSO and ASMO are interchangeable."	Only cmso and asmo are registered; CDCO/PODO/PLDO/LDO are planned, not available. Pick the correct registry key and don't mix terms across ontologies.
"I'll point the parser at this http:// OWL URL."	owl_parser.py/ontology_summarizer.py reject non-https:// URLs by design. Use an https:// source or a local file path.

Security

Input Validation

• --ontology is validated against registered ontology names in ontology_registry.json (fixed allowlist)
• --class and --property names are validated against a safe-character pattern to prevent injection
• --search terms are length-limited and used only for substring matching against pre-processed labels (never interpolated into queries or code)
• --source for owl_parser.py accepts file paths or URLs; URLs are validated against https:// scheme only

File Access

• class_browser.py and property_lookup.py read pre-processed JSON summary files from the references/ directory (read-only)
• owl_parser.py reads a single OWL/XML file from a local path or HTTPS URL; remote fetches have a 30-second timeout
• ontology_summarizer.py writes a single JSON summary file to the path specified by --output
• No scripts modify or delete existing files

Tool Restrictions

• Read: Used to inspect script source, reference files, and ontology summaries
• Bash: Used to execute the four Python scripts (owl_parser.py, ontology_summarizer.py, class_browser.py, property_lookup.py) with explicit argument lists; URL fetching is contained within the Python scripts with timeout limits

Safety Measures

• No eval(), exec(), or dynamic code generation
• All subprocess calls use explicit argument lists (no shell=True)
• OWL/XML parsing uses Python's xml.etree.ElementTree which does not resolve external entities by default, mitigating XXE attacks
• Remote URL fetching is limited to HTTPS with a 30-second timeout to prevent abuse
• Search results are capped in count to prevent output flooding

Limitations

• Only supports OWL/XML format (not Turtle, JSON-LD, or N-Triples)
• Does not support OWL reasoning or inference (e.g., does not compute transitive closures)
• Class hierarchy extraction handles simple rdfs:subClassOf only (not complex OWL restrictions)
• Descriptions may be missing for classes that lack rdfs:comment, skos:definition, or IAO annotations
• URL fetching requires internet access and may time out (30-second limit)

References

• OWL/RDF Primer — brief introduction to OWL concepts
• CMSO Guide — narrative guide to the CMSO ontology
• Ontology Registry — registered ontologies and their metadata
• CMSO Summary — pre-processed CMSO structure
• CMSO Documentation — official CMSO docs
• CMSO Repository — source OWL file and development

Version History

Date	Version	Changes
2026-06-24	1.2.2	Added a Verification checklist (evidence-based, tied to canonical-label resolution, recorded domain/range, union domains, search relevance, registry keys, and summary provenance) and a Common pitfalls & rationalizations table.
2026-06-23	1.2.0	Fixed property_lookup --class to resolve canonical labels (spaceless names like UnitCell now match), made class/property domain matching consistent across tools, enforced documented security controls (safe-character pattern, length caps, search-result caps, HTTPS-only URLs), corrected union-domain doc example and eval assertions, scoped description to CMSO/ASMO.
2026-02-25	1.0	Initial release with CMSO support