Download an NCBI genbank file for a subset of a nucleotide sequence

dl_subsequence_gbk.py

import requests
from pathlib import Path

def dl_subsequence_gbk(outdir, accession, n_start, n_stop):
    response = requests.post(
        "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi",
        params={
            "db": "nuccore",
            "rettype": "gb",
            "from": str(n_start),
            "to": str(n_stop),
        },
        files={"id": accession},
    )
    if not response.ok:
        print(f"Failed with response: {response.reason}")
    else:
        try:
            organism = [
                i.strip()
                for i in response.text.split("\n")
                if i.strip().startswith("ORGANISM")
            ][0]
            organism = organism.removeprefix("ORGANISM")
            organism = organism.strip()
            organism = organism.replace(" ", "-")
        except:
            organism = "NA"
        try:
            assembly = [
                i.strip()
                for i in response.text.split("\n")
                if i.strip().startswith("Assembly")
            ][0]
            assembly = assembly.removeprefix("Assembly:")
            assembly = assembly.strip()
            assembly = assembly.replace(" ", "_")
        except:
            assembly = "NA"
        filepath = Path(outdir, f"{assembly}_{accession}_{organism}.gbk")
        with open(filepath, "w") as file1:
            file1.writelines(response.text)

dl_subsequence_gbk(
    outdir="/home/chase/Downloads/test",
    accession="NZ_LFOD01000025.1",
    n_start=1,
    n_stop=10000,
)

Will result in the file:

/home/chase/Downloads/test/GCF_001077745.1_NZ_LFOD01000025.1_Mycolicibacterium-conceptionense.gbk