Пример #1
0
def name_or_none(taxid):
    """Return organism name for ncbi taxid or None if not found.
    """
    try:
        return taxonomy.name(taxid)
    except taxonomy.UnknownSpeciesIdentifier:
        return None
Пример #2
0
    def initialize(self):
        if self.__initialized:
            # Already initialized
            return
        self.__initialized = True

        self.organisms = sorted(
            set([
                name.split(".")[-2]
                for name in serverfiles.listfiles("NCBI_geneinfo")
            ] + gene.NCBIGeneInfo.common_taxids()))

        self.organismComboBox.addItems(
            [taxonomy.name(tax_id) for tax_id in self.organisms])
        if self.taxid in self.organisms:
            self.organism_index = self.organisms.index(self.taxid)
        else:
            self.organism_index = 0
            self.taxid = self.organisms[self.organism_index]

        self.altSourceCheck.setVisible(self.taxid == DICTY_TAXID)
        self.dictyExpressBox.setVisible(self.taxid == DICTY_TAXID)

        self.infoLabel.setText("No data on input\n")
        self.initfuture = None

        self.setBlocking(False)
        self.progressBarFinished(processEvents=None)
Пример #3
0
def name_or_none(taxid):
    """Return organism name for ncbi taxid or None if not found.
    """
    try:
        return taxonomy.name(taxid)
    except taxonomy.UnknownSpeciesIdentifier:
        return None
Пример #4
0
    def initialize(self):
        if self.__initialized:
            # Already initialized
            return
        self.__initialized = True

        self.organisms = sorted(
            set([name.split(".")[-2] for name in
                 serverfiles.listfiles("NCBI_geneinfo")] +
                gene.NCBIGeneInfo.common_taxids())
        )

        self.organismComboBox.addItems(
            [taxonomy.name(tax_id) for tax_id in self.organisms]
        )
        if self.taxid in self.organisms:
            self.organism_index = self.organisms.index(self.taxid)
        else:
            self.organism_index = 0
            self.taxid = self.organisms[self.organism_index]

        self.altSourceCheck.setVisible(self.taxid == DICTY_TAXID)
        self.dictyExpressBox.setVisible(self.taxid == DICTY_TAXID)

        self.infoLabel.setText("No data on input\n")
        self.initfuture = None

        self.setBlocking(False)
        self.progressBarFinished(processEvents=None)
Пример #5
0
 def setUp(self):
     self.listfiles = [
         fname for domain, fname in sf_local.listfiles("NCBI_geneinfo")
     ]
     self.taxonomy_IDs = sorted(
         set([name.split(".")[-2]
              for name in self.listfiles] + NCBIGeneInfo.common_taxids()))
     self.organisms = [(taxonomy.name(tax_id), tax_id)
                       for tax_id in self.taxonomy_IDs]
Пример #6
0
force = False  # force update

taxids = ppi.STRING.common_taxids()
desc = "STRING Protein interactions for {name} (Creative Commons Attribution 3.0 License)"

#Sorry, STRING does not know an organism named 'Mycoplasma pneumoniae M129', ' Candida albicans'.
#Note that the database only contains organisms with full sequenced and published genomes.

exclude = ['272634', '5476']
taxids = [idtax for idtax in taxids if idtax not in exclude]

for taxid in taxids:
    dbfilename = ppi.STRING.default_db_filename(taxid)
    basename = os.path.basename(dbfilename)

    TITLE = desc.format(name=taxonomy.name(taxid))
    TAGS = ["protein interaction", "STRING"]
    VERSION = ppi.STRING.VERSION

    if not force and version_id in sf_server.info("PPI", basename)["tags"]:
        continue

    ppi.STRING.init_db(version,
                       taxid,
                       dbfilename=dbfilename,
                       cache_dir=downloads)

    gzfile = gzip.GzipFile(os.path.join(temp_path, basename), "wb")
    shutil.copyfileobj(open(dbfilename, "rb"), gzfile)
    gzfile.close()
Пример #7
0
taxids = ppi.STRING.common_taxids()
desc = "STRING Protein interactions for {name} (Creative Commons Attribution 3.0 License)"


#Sorry, STRING does not know an organism named 'Mycoplasma pneumoniae M129', ' Candida albicans'.
#Note that the database only contains organisms with full sequenced and published genomes.

exclude = ['272634', '5476']
taxids = [idtax for idtax in taxids if idtax not in exclude]

for taxid in taxids:
    dbfilename = ppi.STRING.default_db_filename(taxid)
    basename = os.path.basename(dbfilename)

    TITLE = desc.format(name=taxonomy.name(taxid))
    TAGS = ["protein interaction", "STRING"]
    VERSION = ppi.STRING.VERSION

    if not force and version_id in sf_server.info("PPI", basename)["tags"]:
        continue

    ppi.STRING.init_db(version, taxid, dbfilename=dbfilename, cache_dir=downloads)

    gzfile = gzip.GzipFile(os.path.join(temp_path, basename), "wb")
    shutil.copyfileobj(open(dbfilename, "rb"), gzfile)
    gzfile.close()

    create_info_file(os.path.join(temp_path, basename), title=TITLE, tags=TAGS, version=VERSION,
                     compression='gz', uncompressed=file_size_bytes(dbfilename), dbversion=version_id)
Пример #8
0
 def setUp(self):
     self.common_ids = taxonomy.common_taxids()
     self.organisms = [(taxonomy.name(tax_id), tax_id) for tax_id in self.common_ids]
     self.taxon = taxonomy.Taxonomy()
Пример #9
0
 def setUp(self):
     self.listfiles = [fname for domain, fname in sf_local.listfiles("NCBI_geneinfo")]
     self.taxonomy_IDs = sorted(set([name.split(".")[-2] for name in self.listfiles] + NCBIGeneInfo.common_taxids()))
     self.organisms = [(taxonomy.name(tax_id), tax_id) for tax_id in self.taxonomy_IDs]