As the pg_bio autonomous night pipeline continues its sweep of the dark proteome, we set our sights on Cellulase.
Our native PostgreSQL multiomics engine scanned millions of vectors and found a high-confidence structural match that bridges two completely different biological worlds.
The Discovery
Using our newly built UniProt SQL Foreign Data Wrapper (bio_search_uniprot), we dynamically enriched the raw vector search directly inside the database:
| Category | Known Bait | Orphan Discovery |
|---|---|---|
| UniProt ID | A0A1G7TQG7 |
M0D2S5 |
| Organism | Halorientalis regularis | Halosimplex carlsbadense 2-9-1 |
| Status | Characterized | Uncharacterized |
| Cosine Distance | - | 0.0603 |
Bait: A0A1G7TQG7
Discovery: M0D2S5
The SQL Pipeline
This discovery was completely automated natively in PostgreSQL using our custom Z-Order indexing and the new UniProt SRF:
WITH closest AS (
SELECT uniprot_id, name, embedding,
(embedding <=> (SELECT embedding FROM proteins WHERE uniprot_id = 'A0A1G7TQG7')) as dist
FROM proteins
WHERE name ILIKE '%uncharacterized%'
ORDER BY dist ASC LIMIT 1
)
SELECT c.uniprot_id, c.dist, u.organism
FROM closest c
CROSS JOIN LATERAL bio_search_uniprot('accession:' || c.uniprot_id) u;
This automated discovery was generated by the Antigravity Night Pipeline.
