Search and fetch sequences,
pinned to accession.
NCBI's Nucleotide and Protein databases are the archive of record for sequence — RefSeq genes, mRNAs, GenBank entries. ncbi_sequence_search finds records and ncbi_fetch_sequence returns FASTA or GenBank, each pinned to its accession so a sequence is never floating free of its source.
What the instrument does
NCBI hosts the primary nucleotide (nuccore) and protein sequence databases — RefSeq curated records, GenBank submissions, RefSeqGene entries — the authoritative store for a sequence and its provenance.
On the console, ncbi_sequence_search queries either database and returns accessions with titles and lengths; ncbi_fetch_sequence retrieves the FASTA or GenBank record for one.
Tools this powers on the console
ncbi_sequence_search · ncbi_fetch_sequence
Research use only. Service names belong to their owners; no partnership or endorsement is implied.
How Perslis integrates NCBI
NCBI is where a raw sequence keeps its identity. A search for hemoglobin's gene returns NG_059186.1 — a RefSeqGene with an accession, a length, an organism — not an anonymous string of bases a model could have hallucinated. The accession is the receipt.
It sits beside Ensembl, which anchors the annotated genome, and UniProt, which anchors the protein: NCBI provides the underlying sequence records that back both, so a nucleotide or protein sequence on the console can always be traced to a submitted, accessioned entry.
Ask
One question at the console — no per-service query language, no tab-hopping.
Route
Lois calls this instrument alongside the others and gathers what returns.
Pin
Every field keeps its source: database, accession, URL. A result that cannot name its source is refused by construction.
Admit
The PEEL gate decides what enters the lab record. Reported values stay verbatim; unsupported claims stay out.
A real, source-pinned result
Pulled live from the service and pinned to its identifier — the same contract every answer on the console is held to.
| Top accession | NG_059186.1 |
|---|---|
| Title | Homo sapiens hemoglobin subunit alpha 1 (HBA1), RefSeqGene |
| Locus | LRG_1225, chromosome 16 |
| Length | 7,872 bp |
| Databases | nuccore (nucleotide) · protein |
| Fetch | ncbi_fetch_sequence → FASTA / GenBank |
Source: ncbi nuccore · NG_059186.1 · retrieved 2026-09-18
Why route NCBI through one console
Sequence, callable
An agent searches and fetches nucleotide or protein records without EDirect scripting.
Backs the genome and protein
NCBI's accessioned records underpin the Ensembl and UniProt anchors on the same console.
A sequence keeps its receipt
Every FASTA carries an accession — a sequence on the console is never free-floating or invented.
Instruments NCBI talks to
A sequence underlies a gene and a protein. NCBI answers next to Ensembl, UniProt and the variant records.
