ncbi_urlprediction.py

"""
From Luiz Irber.
Takes an SRA accession and determines the location of the .sra data file for automated or downloading.
Follows this format: ftp://ftp-trace.ncbi.nih.gov/sra/sra-instant/reads/ByRun/sra/{SRR|ERR|DRR}/<first 6 characters of accession>/<accession>/<accession>.sra
Format according to NCBI utility handbook: https://www.ncbi.nlm.nih.gov/books/NBK158899/
"""

def sra_url(accession):
    """Returns predicted URL given SRA accession as input."""
    accession = accession.upper()
    return "ftp://ftp-trace.ncbi.nih.gov/sra/sra-instant/reads/ByRun/sra/{}/{}/{}/{}.sra".format(
           accession[0:3], accession[0:6], accession, accession)

def test_sra_url():
    """Test for the sra_url function."""
    assert sra_url('DRR053698') == 'ftp://ftp-trace.ncbi.nih.gov/sra/sra-instant/reads/ByRun/sra/DRR/DRR053/DRR053698/DRR053698.sra'