Tablassert

Tablassert turns biomedical tables (Excel, CSV, TSV) into NCATS Translator-compliant KGX knowledge graphs — declaratively, with entity resolution built in and optional quality control. Installing? See Installation. First build? Follow the Tutorial. Automating? Use the CLI or the autonomous Agent.

Why Tablassert

• Declarative YAML configuration — define data transformations without code
• Entity resolution — map free text to biological entities (genes, diseases, chemicals) with taxonomic filtering and provenance, backed by an embedded redb database
• Optional quality control — 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
• Performance & reproducibility — lazy Polars pipelines and a UV-based, deterministic development environment

Quick Start

pip install tablassert          # or: uv tool install tablassert
tablassert build-kg config.yaml

Quality control and runtime-compatible Polars are opt-in extras. See Installation for the full install matrix, extras, and development setup.

Documentation Sections

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

Authors

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

License

See repository for license information.