Discover non-obvious connections between materials, structures, and synthesis routes.
Knowledge Graph Explorer
The Lattice Graph subgraph endpoint links compositions to their crystal structures and synthesis recipes. BFS traversal surfaces unexpected material connections invisible to any single-source search. The live edge count is in the public health payload (api.latticegraph.com/v1/health, no key required). Endpoint: GET /v1/graph/subgraph.
Key outcomes
What goes in
Inputs this feature expects
- A seed composition
- Desired traversal depth
- Optional result limits for large neighborhoods
What comes out
Outputs your team can act on
- A subgraph of related compositions, structures, and recipes
- Non-obvious connection paths with evidence for each edge
- Export-ready adjacency data for visualization or downstream analysis
Workflow
How teams use Knowledge Graph Explorer
Seed the traversal
Start from any known composition as the graph entry point.
Explore connected subgraphs
BFS expands outward through structure and recipe relationships, surfacing adjacent materials the team may not have considered.
Export and act
The resulting subgraph feeds directly into screening, package generation, or IP exploration workflows.
Best fit
Where this feature fits best
- Discovery scientists looking beyond their current material family
- Program managers exploring adjacent opportunities in a new application domain
- AI and data teams building graph-augmented materials reasoning systems
Related features
More in Search & Discover
Formation Energy Predictor
A gradient-boosted model that ranks candidate chemistries for formation energy and relative stability before you spend simulation budget, falling back to warehouse DFT values when the model is unavailable. Performance on novel compositions may vary.
Cross-Source Confidence
Scores from 0-1 based on agreement across every indexed source that reports the formula.
Similarity Search
Find materials like NMC811 but without cobalt using compositional and property context.