ncbi_sequence

Name: ncbi_sequence
Author: ai4protein

244stars35forks

How to install ncbi_sequence?

ai4protein/venusfactory2/ncbi_sequence

$npx -y skills add ai4protein/VenusFactory2 --skill ncbi_sequence

Installs into the current project.

Summary

NCBI E-utilities for biological sequences — fetch protein/nucleotide FASTA by accession, run BLAST, translate CDS to protein, search NCBI Protein by gene+organism. Use when the user provides an NCBI accession (NP_, XP_, NM_, NR_, etc.), asks for a sequence by gene name + species,

Files · 1

View on GitHub

SKILL.md

1	# NCBI Sequence Tools
2
3	## Overview
4
5	Wraps NCBI E-utilities (`efetch`, `esearch`) for sequence-centric workflows. Honors `NCBI_API_KEY` env var to raise the QPS limit from 3 → 10. Set `USER_EMAIL` env var to identify yourself to NCBI as a good citizen.
6
7	## Project Tools (VenusFactory2)
8
9	\| Tool \| Args \| Returns \| Description \|
10	\|------\|------\|---------\|--------------\|
11	\| download_ncbi_sequence \| `ncbi_id`, `out_dir`, `db` (default `protein`) \| rich JSON envelope; FASTA file \| Fetch a single sequence by accession from `protein` or `nuccore`. \|
12	\| download_ncbi_metadata \| `ncbi_id`, `out_path`, `db` \| rich JSON envelope; metadata JSON \| Fetch GenBank-style metadata for an accession. \|
13	\| download_ncbi_blast \| (see existing schema) \| rich JSON envelope \| NCBI-hosted BLAST. Prefer `download_mmseqs2_homologs_by_sequence` (faster) or `download_blast_homologs_by_sequence` (EBI mirror) for protein-protein searches. \|
14	\| translate_ncbi_cds_to_protein \| `accession` (nuccore, e.g. `NM_000518` for HBB mRNA), `out_dir`, `target_length` (default `0` = longest), `timeout` \| rich JSON envelope; FASTA at `<out_dir>/<accession>_protein.fasta`; `biological_metadata.method="fasta_cds_aa"` \| Use `efetch(rettype=fasta_cds_aa)` to get the CDS-translated protein, pick the translation closest to `target_length` (or longest). \|
15	\| search_ncbi_protein_by_gene_and_organism \| `gene` (e.g. `TP53`), `organism` (`"Homo sapiens"`), `out_dir`, `target_length` (default `0` = no length filter; non-zero filters to ±25 aa window), `retmax` (default `10`), `timeout` \| rich JSON envelope; multi-FASTA + `<stem>.json` summary; `biological_metadata.summary_path` for the per-hit JSON \| Search NCBI Protein DB with `<gene>[Gene Name] AND <organism>[Organism]`, fetch all hits as multi-FASTA. \|
16
17	## Workflow: "Get the protein sequence for gene X in species Y"
18
19	1. Try `search_ncbi_protein_by_gene_and_organism` first — if it finds 1-5 hits, pick the canonical one.
20	2. If you know the mRNA accession (e.g. from a Gene record), use `translate_ncbi_cds_to_protein` for the canonical CDS-derived protein (no ambiguity from isoforms).
21	3. Fallback: keyword search via `download_ncbi_metadata` to find an accession, then `download_ncbi_sequence`.
22
23	## Workflow: "Translate this mRNA to protein"
24
25	- Direct: `translate_ncbi_cds_to_protein(accession=..., target_length=expected_aa_count)`. The tool uses NCBI's pre-translated CDS protein when available — no client-side translation needed, no codon-table issues.
26
27	## Common Mistakes
28
29	- Confusing `protein` and `nuccore` DBs: protein accessions (NP_, XP_, AAA-style) go to `db=protein`; mRNA/genomic (NM_, NC_, etc.) go to `db=nuccore`. `translate_ncbi_cds_to_protein` always uses `nuccore` internally.
30	- Mismatched gene+organism: NCBI is strict; `TP53 AND Homo sapiens` works, `tp53 AND human` may not.
31	- Forgetting `NCBI_API_KEY`: at 3 QPS you'll hit rate limits with batch operations. Set the env var to bump to 10 QPS.
32	- target_length too narrow: `search_ncbi_protein_by_gene_and_organism` applies ±25 aa filter; if your target_length is uncertain, pass 0 and pick from results.
33
34	## References
35
36	- [E-utilities](https://www.ncbi.nlm.nih.gov/books/NBK25501/)
37	- [Get an NCBI API key](https://www.ncbi.nlm.nih.gov/account/settings/) (free)
38	- [Entrez query syntax](https://www.ncbi.nlm.nih.gov/books/NBK3837/)

People who liked this also viewed

6 picks

Type

ncbi_sequence

244stars35forks

View on GitHub

How to install ncbi_sequence?

ai4protein/venusfactory2/ncbi_sequence

$npx -y skills add ai4protein/VenusFactory2 --skill ncbi_sequence

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# NCBI Sequence Tools
2
3	## Overview
4
5	Wraps NCBI E-utilities (`efetch`, `esearch`) for sequence-centric workflows. Honors `NCBI_API_KEY` env var to raise the QPS limit from 3 → 10. Set `USER_EMAIL` env var to identify yourself to NCBI as a good citizen.
6
7	## Project Tools (VenusFactory2)
8
9	\| Tool \| Args \| Returns \| Description \|
10	\|------\|------\|---------\|--------------\|
11	\| download_ncbi_sequence \| `ncbi_id`, `out_dir`, `db` (default `protein`) \| rich JSON envelope; FASTA file \| Fetch a single sequence by accession from `protein` or `nuccore`. \|
12	\| download_ncbi_metadata \| `ncbi_id`, `out_path`, `db` \| rich JSON envelope; metadata JSON \| Fetch GenBank-style metadata for an accession. \|
13	\| download_ncbi_blast \| (see existing schema) \| rich JSON envelope \| NCBI-hosted BLAST. Prefer `download_mmseqs2_homologs_by_sequence` (faster) or `download_blast_homologs_by_sequence` (EBI mirror) for protein-protein searches. \|
14	\| translate_ncbi_cds_to_protein \| `accession` (nuccore, e.g. `NM_000518` for HBB mRNA), `out_dir`, `target_length` (default `0` = longest), `timeout` \| rich JSON envelope; FASTA at `<out_dir>/<accession>_protein.fasta`; `biological_metadata.method="fasta_cds_aa"` \| Use `efetch(rettype=fasta_cds_aa)` to get the CDS-translated protein, pick the translation closest to `target_length` (or longest). \|
15	\| search_ncbi_protein_by_gene_and_organism \| `gene` (e.g. `TP53`), `organism` (`"Homo sapiens"`), `out_dir`, `target_length` (default `0` = no length filter; non-zero filters to ±25 aa window), `retmax` (default `10`), `timeout` \| rich JSON envelope; multi-FASTA + `<stem>.json` summary; `biological_metadata.summary_path` for the per-hit JSON \| Search NCBI Protein DB with `<gene>[Gene Name] AND <organism>[Organism]`, fetch all hits as multi-FASTA. \|
16
17	## Workflow: "Get the protein sequence for gene X in species Y"
18
19	1. Try `search_ncbi_protein_by_gene_and_organism` first — if it finds 1-5 hits, pick the canonical one.
20	2. If you know the mRNA accession (e.g. from a Gene record), use `translate_ncbi_cds_to_protein` for the canonical CDS-derived protein (no ambiguity from isoforms).
21	3. Fallback: keyword search via `download_ncbi_metadata` to find an accession, then `download_ncbi_sequence`.
22
23	## Workflow: "Translate this mRNA to protein"
24
25	- Direct: `translate_ncbi_cds_to_protein(accession=..., target_length=expected_aa_count)`. The tool uses NCBI's pre-translated CDS protein when available — no client-side translation needed, no codon-table issues.
26
27	## Common Mistakes
28
29	- Confusing `protein` and `nuccore` DBs: protein accessions (NP_, XP_, AAA-style) go to `db=protein`; mRNA/genomic (NM_, NC_, etc.) go to `db=nuccore`. `translate_ncbi_cds_to_protein` always uses `nuccore` internally.
30	- Mismatched gene+organism: NCBI is strict; `TP53 AND Homo sapiens` works, `tp53 AND human` may not.
31	- Forgetting `NCBI_API_KEY`: at 3 QPS you'll hit rate limits with batch operations. Set the env var to bump to 10 QPS.
32	- target_length too narrow: `search_ncbi_protein_by_gene_and_organism` applies ±25 aa filter; if your target_length is uncertain, pass 0 and pick from results.
33
34	## References
35
36	- [E-utilities](https://www.ncbi.nlm.nih.gov/books/NBK25501/)
37	- [Get an NCBI API key](https://www.ncbi.nlm.nih.gov/account/settings/) (free)
38	- [Entrez query syntax](https://www.ncbi.nlm.nih.gov/books/NBK3837/)

People who liked this also viewed

6 picks

Type