seqsearch.databases.ncbi_16s

 1#!/usr/bin/env python3
 2# -*- coding: utf-8 -*-
 3
 4"""
 5Written by Lucas Sinclair.
 6MIT Licensed.
 7Contact at www.sinclair.bio
 8"""
 9
10# Built-in modules #
11import os
12
13# First party modules #
14from seqsearch.databases import Database
15
16# Third party modules #
17
18# Constants #
19home = os.environ.get('HOME', '~') + '/'
20
21###############################################################################
22class NCBI16S(Database):
23    """
24    The NCBI provides a database of 16S ribosomal sequences.
25    The exact title is "Bacteria and Archaea: 16S ribosomal RNA project".
26    More information is available at:
27
28    https://www.ncbi.nlm.nih.gov/refseq/targetedloci/16S_process/
29
30    To install:
31
32        >>> from seqsearch.databases.ncbi_16s import ncbi_16s
33        >>> ncbi_16s.download()
34        >>> ncbi_16s.untargz()
35
36    It will place the resulting files in "~/databases/ncbi_16s/".
37    """
38
39    tag        = "ncbi_16s"
40    short_name = "ncbi_16s"
41    long_name  = 'The NCBI 16S RNA database'
42
43    base_url   = "ftp://ftp.ncbi.nlm.nih.gov/blast/db/"
44    ftp_url    = "ftp.ncbi.nlm.nih.gov"
45    ftp_dir    = "/blast/db/"
46    files      = ['16S_ribosomal_RNA.tar.gz']
47    db_name    = '16S_ribosomal_RNA'
48
49###############################################################################
50ncbi_16s = NCBI16S('nucl')