예제 #1
0
파일: __init__.py 프로젝트: kaspermunch/sap
def _encode_options(ecitmatch, params):
    # Open a handle to Entrez.
    options = _urlencode(params, doseq=True)
    # _urlencode encodes pipes, which NCBI expects in ECitMatch
    if ecitmatch:
        options = options.replace("%7C", "|")
    return options
예제 #2
0
파일: __init__.py 프로젝트: cbirdlab/sap
def _encode_options(ecitmatch, params):
    # Open a handle to Entrez.
    options = _urlencode(params, doseq=True)
    # _urlencode encodes pipes, which NCBI expects in ECitMatch
    if ecitmatch:
        options = options.replace('%7C', '|')
    return options
예제 #3
0
파일: ScanProsite.py 프로젝트: cbirdlab/sap
def scan(seq="", mirror='http://www.expasy.org', output='xml', **keywords):
    """Execute a ScanProsite search.

    mirror:      The ScanProsite mirror to be used
                 (default: http://www.expasy.org).
    seq:         The query sequence, or UniProtKB (Swiss-Prot,
                 TrEMBL) accession
    output:      Format of the search results
                 (default: xml)

    Further search parameters can be passed as keywords; see the
    documentation for programmatic access to ScanProsite at
    http://www.expasy.org/tools/scanprosite/ScanPrositeREST.html
    for a description of such parameters.

    This function returns a handle to the search results returned by
    ScanProsite. Search results in the XML format can be parsed into a
    Python object, by using the Bio.ExPASy.ScanProsite.read function.
    """
    parameters = {'seq': seq,
                  'output': output}
    for key, value in keywords.items():
        if value is not None:
            parameters[key] = value
    command = _urlencode(parameters)
    url = "%s/cgi-bin/prosite/PSScan.cgi?%s" % (mirror, command)
    handle = _urlopen(url)
    return handle
예제 #4
0
파일: __init__.py 프로젝트: kaspermunch/sap
def sprot_search_de(text, swissprot=1, trembl=None, cgi="http://www.expasy.ch/cgi-bin/sprot-search-de"):
    """sprot_search_de(text, swissprot=1, trembl=None,
    cgi='http://www.expasy.ch/cgi-bin/sprot-search-de') -> handle

    Search SwissProt by name, description, gene name, species, or
    organelle.

    """
    variables = {"SEARCH": text}
    if swissprot:
        variables["S"] = "on"
    if trembl:
        variables["T"] = "on"
    options = _urlencode(variables)
    fullcgi = "%s?%s" % (cgi, options)
    handle = _urlopen(fullcgi)
    return handle
예제 #5
0
파일: __init__.py 프로젝트: kaspermunch/sap
def sprot_search_ful(
    text, make_wild=None, swissprot=1, trembl=None, cgi="http://www.expasy.ch/cgi-bin/sprot-search-ful"
):
    """sprot_search_ful(text, make_wild=None, swissprot=1, trembl=None,
    cgi='http://www.expasy.ch/cgi-bin/sprot-search-ful') -> handle

    Search SwissProt by full text.

    """
    variables = {"SEARCH": text}
    if make_wild:
        variables["makeWild"] = "on"
    if swissprot:
        variables["S"] = "on"
    if trembl:
        variables["T"] = "on"
    options = _urlencode(variables)
    fullcgi = "%s?%s" % (cgi, options)
    handle = _urlopen(fullcgi)
    return handle
예제 #6
0
def sprot_search_de(text,
                    swissprot=1,
                    trembl=None,
                    cgi='http://www.expasy.ch/cgi-bin/sprot-search-de'):
    """sprot_search_de(text, swissprot=1, trembl=None,
    cgi='http://www.expasy.ch/cgi-bin/sprot-search-de') -> handle

    Search SwissProt by name, description, gene name, species, or
    organelle.

    """
    variables = {'SEARCH': text}
    if swissprot:
        variables['S'] = 'on'
    if trembl:
        variables['T'] = 'on'
    options = _urlencode(variables)
    fullcgi = "%s?%s" % (cgi, options)
    handle = _urlopen(fullcgi)
    return handle
예제 #7
0
def sprot_search_ful(text,
                     make_wild=None,
                     swissprot=1,
                     trembl=None,
                     cgi='http://www.expasy.ch/cgi-bin/sprot-search-ful'):
    """sprot_search_ful(text, make_wild=None, swissprot=1, trembl=None,
    cgi='http://www.expasy.ch/cgi-bin/sprot-search-ful') -> handle

    Search SwissProt by full text.

    """
    variables = {'SEARCH': text}
    if make_wild:
        variables['makeWild'] = 'on'
    if swissprot:
        variables['S'] = 'on'
    if trembl:
        variables['T'] = 'on'
    options = _urlencode(variables)
    fullcgi = "%s?%s" % (cgi, options)
    handle = _urlopen(fullcgi)
    return handle
예제 #8
0
파일: NCBIWWW.py 프로젝트: cbirdlab/sap
def qblast(program, database, sequence,
           auto_format=None, composition_based_statistics=None,
           db_genetic_code=None, endpoints=None, entrez_query='(none)',
           expect=10.0, filter=None, gapcosts=None, genetic_code=None,
           hitlist_size=50, i_thresh=None, layout=None, lcase_mask=None,
           matrix_name=None, nucl_penalty=None, nucl_reward=None,
           other_advanced=None, perc_ident=None, phi_pattern=None,
           query_file=None, query_believe_defline=None, query_from=None,
           query_to=None, searchsp_eff=None, service=None, threshold=None,
           ungapped_alignment=None, word_size=None,
           alignments=500, alignment_view=None, descriptions=500,
           entrez_links_new_window=None, expect_low=None, expect_high=None,
           format_entrez_query=None, format_object=None, format_type='XML',
           ncbi_gi=None, results_file=None, show_overview=None, megablast=None,
           ):
    """Do a BLAST search using the QBLAST server at NCBI.

    Supports all parameters of the qblast API for Put and Get.
    Some useful parameters:
    program        blastn, blastp, blastx, tblastn, or tblastx (lower case)
    database       Which database to search against (e.g. "nr").
    sequence       The sequence to search.
    ncbi_gi        TRUE/FALSE whether to give 'gi' identifier.
    descriptions   Number of descriptions to show.  Def 500.
    alignments     Number of alignments to show.  Def 500.
    expect         An expect value cutoff.  Def 10.0.
    matrix_name    Specify an alt. matrix (PAM30, PAM70, BLOSUM80, BLOSUM45).
    filter         "none" turns off filtering.  Default no filtering
    format_type    "HTML", "Text", "ASN.1", or "XML".  Def. "XML".
    entrez_query   Entrez query to limit Blast search
    hitlist_size   Number of hits to return. Default 50
    megablast      TRUE/FALSE whether to use MEga BLAST algorithm (blastn only)
    service        plain, psi, phi, rpsblast, megablast (lower case)

    This function does no checking of the validity of the parameters
    and passes the values to the server as is.  More help is available at:
    http://www.ncbi.nlm.nih.gov/BLAST/Doc/urlapi.html

    """
    import time

    assert program in ['blastn', 'blastp', 'blastx', 'tblastn', 'tblastx']

    # Format the "Put" command, which sends search requests to qblast.
    # Parameters taken from http://www.ncbi.nlm.nih.gov/BLAST/Doc/node5.html on 9 July 2007
    # Additional parameters are taken from http://www.ncbi.nlm.nih.gov/BLAST/Doc/node9.html on 8 Oct 2010
    # To perform a PSI-BLAST or PHI-BLAST search the service ("Put" and "Get" commands) must be specified
    # (e.g. psi_blast = NCBIWWW.qblast("blastp", "refseq_protein", input_sequence, service="psi"))
    parameters = [
        ('AUTO_FORMAT', auto_format),
        ('COMPOSITION_BASED_STATISTICS', composition_based_statistics),
        ('DATABASE', database),
        ('DB_GENETIC_CODE', db_genetic_code),
        ('ENDPOINTS', endpoints),
        ('ENTREZ_QUERY', entrez_query),
        ('EXPECT', expect),
        ('FILTER', filter),
        ('GAPCOSTS', gapcosts),
        ('GENETIC_CODE', genetic_code),
        ('HITLIST_SIZE', hitlist_size),
        ('I_THRESH', i_thresh),
        ('LAYOUT', layout),
        ('LCASE_MASK', lcase_mask),
        ('MEGABLAST', megablast),
        ('MATRIX_NAME', matrix_name),
        ('NUCL_PENALTY', nucl_penalty),
        ('NUCL_REWARD', nucl_reward),
        ('OTHER_ADVANCED', other_advanced),
        ('PERC_IDENT', perc_ident),
        ('PHI_PATTERN', phi_pattern),
        ('PROGRAM', program),
        #('PSSM',pssm), - It is possible to use PSI-BLAST via this API?
        ('QUERY', sequence),
        ('QUERY_FILE', query_file),
        ('QUERY_BELIEVE_DEFLINE', query_believe_defline),
        ('QUERY_FROM', query_from),
        ('QUERY_TO', query_to),
        #('RESULTS_FILE',...), - Can we use this parameter?
        ('SEARCHSP_EFF', searchsp_eff),
        ('SERVICE', service),
        ('THRESHOLD', threshold),
        ('UNGAPPED_ALIGNMENT', ungapped_alignment),
        ('WORD_SIZE', word_size),
        ('CMD', 'Put'),
        ]
    query = [x for x in parameters if x[1] is not None]
    message = _as_bytes(_urlencode(query))

    # Send off the initial query to qblast.
    # Note the NCBI do not currently impose a rate limit here, other
    # than the request not to make say 50 queries at once using multiple
    # threads.
    request = _Request("http://blast.ncbi.nlm.nih.gov/Blast.cgi",
                       message,
                       {"User-Agent":"BiopythonClient"})
    handle = _urlopen(request)

    # Format the "Get" command, which gets the formatted results from qblast
    # Parameters taken from http://www.ncbi.nlm.nih.gov/BLAST/Doc/node6.html on 9 July 2007
    rid, rtoe = _parse_qblast_ref_page(handle)
    parameters = [
        ('ALIGNMENTS', alignments),
        ('ALIGNMENT_VIEW', alignment_view),
        ('DESCRIPTIONS', descriptions),
        ('ENTREZ_LINKS_NEW_WINDOW', entrez_links_new_window),
        ('EXPECT_LOW', expect_low),
        ('EXPECT_HIGH', expect_high),
        ('FORMAT_ENTREZ_QUERY', format_entrez_query),
        ('FORMAT_OBJECT', format_object),
        ('FORMAT_TYPE', format_type),
        ('NCBI_GI', ncbi_gi),
        ('RID', rid),
        ('RESULTS_FILE', results_file),
        ('SERVICE', service),
        ('SHOW_OVERVIEW', show_overview),
        ('CMD', 'Get'),
        ]
    query = [x for x in parameters if x[1] is not None]
    message = _as_bytes(_urlencode(query))

    # Poll NCBI until the results are ready.  Use a backoff delay from 2 - 120 second wait
    delay = 2.0
    previous = time.time()
    while True:
        current = time.time()
        wait = previous + delay - current
        if wait > 0:
            time.sleep(wait)
            previous = current + wait
        else:
            previous = current
        if delay + .5*delay <= 120:
            delay += .5*delay
        else:
            delay = 120

        request = _Request("http://blast.ncbi.nlm.nih.gov/Blast.cgi",
                           message,
                           {"User-Agent":"BiopythonClient"})
        handle = _urlopen(request)
        results = _as_string(handle.read())

        # Can see an "\n\n" page while results are in progress,
        # if so just wait a bit longer...
        if results=="\n\n":
            continue
        # XML results don't have the Status tag when finished
        if "Status=" not in results:
            break
        i = results.index("Status=")
        j = results.index("\n", i)
        status = results[i+len("Status="):j].strip()
        if status.upper() == "READY":
            break

    return StringIO(results)