Elman

Discovery you can trace to the figure.

An autonomous discovery engine for the life sciences
Elman · Knowledge Graph Engine Fig. 3 / 7

Figure 3

Discovery you can trace to the figure

Fig. 3. A single concept node — Discovery — connected to its grammatical neighbours under the Elman knowledge graph. Edges denote co-occurrence in the substantive sentence; weight reflects semantic proximity to the focal node.

Forthcoming · Cell · 2026

A collaboration with the Allen Institute for Brain Science — full architectural reveal of the discovery engine, validated against single-cell data in human substantia nigra.

253 Public datasets
ingested
170,000 Experimental facts
in the graph
112 End-to-end
discovery cycles

Full provenance

Every finding anchored to a specific experimental arm in a specific paper or in-silico run — never to a model's parametric memory.

Rational pruning

The reasoning agent chases specific questions through the graph one edge at a time, surfacing low-magnitude but significant signal where the tractable biology lives.

Compounding

A single schema across literature, in-silico and wet-lab evidence. Every result sharpens the substrate every future run consumes — across indications, not within one.

The discovery flow

Five steps, end-to-end.
Two production-grade today.

Each step lives on the same compounding knowledge graph. Two are sold as standalone services right now; the rest run end-to-end in beta.

01
Production

Ingest

Public datasets, literature, and in-silico runs land in a single Neo4j graph at arm-level resolution.

02
Beta

Generate

Multi-agent traversal proposes mechanistic hypotheses, each verified concurrently against the literature.

03
Production

Identify

Rational pruning surfaces candidate intervention points at sub-population resolution — for any indication.

04
Beta

Simulate

Propagate the intervention through the graph to predict cohort and sub-population response.

05
Production

Engineer

Freedom-to-operate, patent landscape, and engineering mitigation on the target, asset, or technology area.