Tablassert

Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution built in and optional quality control.

Tablassert turns biomedical spreadsheets (Excel, CSV, TSV) into knowledge graphs ready for NCATS Translator. Declare how your columns map to subject–predicate–object statements in YAML; Tablassert resolves free text to standard CURIEs, attaches provenance and statistical annotations, and emits KGX-compliant nodes and edges.

Full Documentation — installation guides, tutorial, configuration reference, and API docs.

Quick Start

pip install tablassert

Given a CSV of gene–disease associations with p-values and sample sizes, declare the mapping in a table config (table.yaml):

template:
  source:
    kind: text
    local: ./gene-disease.csv
    url: https://example.com/data.csv
    row_slice: [1, auto]
    delimiter: ","
  statement:
    subject: { method: column, encoding: A, prioritize: [Gene] }
    predicate: associated_with
    object: { method: column, encoding: B, prioritize: [Disease] }
  provenance: { repo: PMID, publication: "12345678" }
  annotations:
    - { annotation: p_value, method: column, encoding: C }
    - { annotation: supporting_study_size, method: column, encoding: D }

Wrap it in a graph config (graph.yaml) pointing at your fullmap entity-resolution database:

name: MY_KG
version: 1.0.0
description: Gene–disease associations extracted from tabular sources.
tables:
  - ./table.yaml
fullmap: /path/to/fullmap

Build the knowledge graph:

tablassert build-kg graph.yaml

Output is one JSON object per line — nodes with Biolink categories, edges with annotations:

{"id":"HGNC:11998","name":"TP53","category":["biolink:Gene"],"taxon":"NCBITaxon:9606"}
{"id":"MONDO:0008903","name":"lung cancer","category":["biolink:Disease"]}

{"subject":"HGNC:11998","predicate":"biolink:associated_with","object":"MONDO:0008903","p_value":"1.0000e-03","supporting_study_size":"450"}

See the Tutorial for the full walkthrough.

Key Features

• Declarative YAML configuration — define data transformations without writing code
• Built-in entity resolution — map free text to genes, diseases, and chemicals with standard CURIEs, taxonomic filtering, and provenance, backed by an embedded redb database
• Optional quality control — a three-stage audit (exact → fuzzy → BioBERT embeddings) flags low-confidence mappings
• KGX compliance — emits NCATS Translator-compatible node/edge NDJSON with Biolink categories and predicates
• Autonomous agent — tablassert agent derives, builds, and refines configs for whole papers
• Performance & reproducibility — lazy Polars pipelines and a deterministic UV-based development environment

Installation

pip install tablassert

Or with uv: uv tool install tablassert. The base install builds knowledge graphs from CSV/TSV/Excel sources; optional extras add runtime and pipeline capabilities:

Extra	Adds	Install
rt	CPU-compatible Polars runtime	pip install "tablassert[rt]"
qc	three-stage QC audit (exact → fuzzy → BioBERT embeddings)	pip install "tablassert[qc]"
agent	autonomous agent (smolagents, litellm, PDF context)	pip install "tablassert[agent]"
optimize	GEPA prompt optimization for agent --optimize (dspy)	pip install "tablassert[optimize]"

QC is opt-in at build time (build-kg --qc). See the Installation guide for the full matrix and the CLI Reference for every flag.

Entity Resolution API

from pathlib import Path
from tablassert.lib import resolve_many

results = resolve_many(
    col="gene",
    entities=["TP53", "BRCA1"],
    fullmap=Path("/path/to/fullmap"),
    taxon="9606",
)
# [{"original_gene": "TP53", "gene": "HGNC:11998", "gene_name": "TP53", ...}, ...]

Point resolve_many() at a fullmap database to resolve any iterable of entity strings to CURIEs — no LazyFrame setup or NLP preprocessing required. See the Batch Resolution API for the full reference.

Documentation

• Installation — install methods, extras, and development setup
• Tutorial — step-by-step example with synthetic data
• CLI Reference — complete command-line flag reference
• Use Case Gallery — real-world configuration patterns
• Configuration — graph and table configuration reference
• Agent — the autonomous agent pipeline
• API Reference — core functions documentation

Developing

uv sync --group dev --extra qc
uv run maturin develop --manifest-path rust/Cargo.toml
make check

See CONTRIBUTING.md for the full development loop, quality gates, and pull request guidelines.

Citation

If you use Tablassert, please cite it as described in CITATION.cff. The approach is described in:

Skye Lane Goetz, Alex K. Glen, and Gwênlyn Glusman. “MicrobiomeKG: bridging microbiome research and host health through knowledge graphs.” Frontiers in Systems Biology 5 (2025). doi:10.3389/fsysb.2025.1544432

License

Apache License 2.0

Contributors

• Skye Lane Goetz — Institute for Systems Biology
• Gwênlyn Glusman — Institute for Systems Biology
• Jared C. Roach — Institute for Systems Biology