Skip to main content

Technical Background

FoodAtlas is an evidence-based knowledge graph linking foods, the chemicals they contain, the diseases those chemicals correlate with, and the bioactivities they express. Every edge in the graph is traceable to a public source or a peer-reviewed publication.

The graph is built from two pipelines: an information extraction pipeline that pulls food–chemical relations from PubMed / PMC literature, and a knowledge graph construction pipeline that ingests public databases, resolves entities, and stitches everything into the released graph. For the full study, see the npj Science of Food paper.

What's in the graph

Diagram of the FoodAtlas graph semantics: Food, Chemical, Disease, and Bioactivity nodes connected by CONTAINS, IS_A, WORSENS, IMPROVES, EXHIBITS, and MEASURED edges.

A node is a Food , Chemical , Disease , or Bioactivity . An edge informs about the relationship between two nodes.

Every edge carries an attestation — the supporting evidence, source, and any measurement metadata (concentration values, assay outcomes, Hill-curve fits).

CodeRelationBetweenDescription
r1CONTAINSFoodChemicalA food contains a chemical at a measured concentration. Values normalised to mg / 100g where the source unit allows.
r2IS_AAnyAny (same type)Ontology hierarchy. Ties into FoodOn, ChEBI, MeSH, and the bioactivity hierarchy so children inherit parent context.
r3WORSENSChemicalDiseasePeer-reviewed evidence that the chemical worsens the disease's health outcomes or increases risk of onset.
r4IMPROVESChemicalDiseasePeer-reviewed evidence that the chemical improves the disease's health outcomes or reduces risk of onset.
r5EXHIBITSFoodBioactivityA food exhibits a bioactivity — either from direct assay evidence or from a model inference over its composition.
r6MEASUREDChemicalBioactivityA chemical was measured against a bioactivity in an assay. Carries the raw measurement + a Hill-curve fit when the assay reports dose–response.

Where the data comes from

The knowledge graph integrates nine public sources spanning ontologies, composition tables, and bioassay repositories. The information extraction pipeline layers additional food–chemical relations on top by reading peer-reviewed literature from PubMed / PMC.

How it's built

Our pipeline uses state-of-the-art AI models to extract and quantify food connections. The two major steps are (a) knowledge extraction, i.e., converting literature into food–chemical relations, and (b) knowledge graph construction, which adds meta-information and new information to our knowledge base.

Step 1 — Information Extraction

From literature to structured triplets.

1
Corpus

Refresh a local BioC-PMC corpus and rebuild the PMC-ID index.

2
Search

Query PubMed for food terms; retrieve and fuzzy-match candidate sentences.

3
Filter

Binary classification with a fine-tuned BioBERT model — only sentences above a 0.99 confidence threshold pass through.

4
Extract

The remaining sentences are batched through OpenAI's Batch API using gpt-5.5 and structured extraction prompts.

Step 2 — Knowledge Graph Construction

From sources + triplets to the released graph.

1
Ingest

Parse each source into standardised parquet files (nodes / edges / cross-references).

2
Entities

Three-pass entity resolution → stable `foodatlas_id`s that survive across releases. Ambiguities are recorded on attestations, not silently collapsed.

3
Triplets

Build typed edges (r1–r6) from source data. Duplicates merge; ambiguous resolutions explode into candidates for later review.

4
Extraction fold-in

Concentration parser normalises the information extraction pipeline's output to mg/100g. Chemical + food names resolved through the entity registry.

5
Enrichment

Add derived metadata: chemical/food classifications, flavor descriptors, common names, display grouping.

6
Trust

Per-attestation plausibility signals from a Gemini 3.1 Flash-Lite LLM judge. Emits a 0–1 score and a short justification per triplet.

7
Evaluation

Diagnostics on the finished graph — orphan detection, unclassified entities, per-source coverage.

Bioactivity in detail

A bioactivity is a biological effect a chemical or food can exhibit — antibacterial, antioxidant, hepatotoxic, and so on. The graph organises 21 bioactivity concepts in a small hierarchy so queries roll up naturally (e.g. an antibacterial hit is also an antimicrobial hit).

Chemical → bioactivity evidence ( r6 ) comes in two flavors:

  • Experimental — assay measurements pulled from PubChem and ChEMBL, with outcome, potency (value + unit), and a four-parameter Hill-curve fit when the assay reports a dose response.
  • Predicted — random-forest model inferences (e.g. RF_antioxidant_v1 ) that score a chemical against a bioactivity based on structural features.

Food → bioactivity evidence ( r5 ) is either directly measured against the food or inferred from the bioactivities of its composed chemicals.

Trust signals

Every attestation in the graph carries a per-triplet trust signal. A Gemini 3.1 Flash-Lite LLM judge scores each (food, chemical, concentration) triplet on world-knowledge plausibility from 0 to 1, alongside a short justification. Low-trust rows aren't hidden — they're surfaced on the frontend so a curator can review them without losing the underlying evidence.

Trust signals are versioned and stored separately from the main attestations, so a rebuild of the graph doesn't lose the per-row judgements that were made against an earlier snapshot.

FoodAtlas was created and is maintained by AIFS at the University of California, Davis.

About AIFS

The AI Institute for Next Generation Food Systems, or AIFS aims to meet growing demands in our food supply by increasing efficiencies using Al and bioinformatics spanning the entire system–from growing crops through consumption. We are dedicated to creating AI applications for a healthier, more sustainable planet from farm to fork.

Connect with us

Subscribe to our newsletter to stay up-to-date on AIFS events, industry news, and AI research.

This work is supported by AFRI Competitive Grant no. 2020-67021-32855/project accession no. 1024262 from the USDA National Institute of Food and Agriculture.

2026 AIFS. All rights reserved.