Python Entrez.email方法代码示例

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def get_ncbi_seq(email, db, rettype, accession):

    # fetch
    print("Fetching accession %s from GenBank\n" % (accession))

    Entrez.email = email

    try:
        handle = Entrez.efetch(
            db=db,
            rettype=rettype,
            retmode="text",
            id=accession
        )
        res = handle.read()

        # for testing only
        # pickle_item(res, accession)
        return res

    except Exception:
        sys.stderr.write("Error! Cannot fetch: %s        \n" % accession) 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def main():
    parser = argparse.ArgumentParser(
        description='Populate the phageParser database with data from NCBI'
    )
    parser.add_argument(
        'email',
        nargs=1,
        help=('your email address (does not need to be registered, '
              'just used to identify you)')
    )
    args = parser.parse_args()

    Entrez.email = args.email

    print("Starting organism population")
    populate_organism()
    print("Starting LSR population")
    populate_lsrpair()
    print("Starting AntiCRISPR population")
    populate_anticrispr() 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def fetch_chrom_name(id):
    try:
        if not id.startswith("NC_"):
            return id
        Entrez.email = "vcf-kit@vcf-kit.com"
        chrom = Entrez.read(Entrez.efetch(db="nuccore", id=id, rettype="gb", retmode="xml"))
        gb_feature_quals = chrom[0]["GBSeq_feature-table"][0]["GBFeature_quals"]
        features = dict([x.values() for x in gb_feature_quals])
        if "organelle" in features:
            if features["organelle"] == "mitochondrion":
                return "MtDNA"
        else:
            chrom_name = features["chromosome"]
            return chrom_name
    except:
        return id 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def __init__(self, prefix, datasource, outdb, options=None, ohost=None,
                 email=None):
        '''
        prefix - prefix used to recognise which annotation is being performed
        datasource - link used for API
        outdb - output database
        options - optional string to be parsed by the APIAnnotation subclass
        ohost - original species of interest used by some subclasses
        email - entrez requires an email address to use its API
        '''
        self.prefix = prefix
        self.datasource = datasource
        self.outdb = outdb
        self.options = options
        self.ohost = ohost
        self.email = email
        self.resultsz = dict()
        self.resultspd = dict() 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def get_species_from_taxid(self, taxid):
        #if it is an integer (a taxid), try to get the species name
        species = taxid
        if taxid.isdigit():
            Entrez.email = EMBL.PREVIOUS_VALUES["email"]
            # fetch the classification sufing the taxid
            logging.debug("Fetch The Lineage using Entrez.efetch")
            try:
                search = Entrez.efetch(id=taxid, db="taxonomy", retmode="xml")
                data = Entrez.read(search)
                species = data[0]['ScientificName']
            except IOError as e:
                logging.error("Could not get species from taxid: %s" % e)

        return "%s%s" % (species[0].upper(), species[1:].lower())

    #if species is a taxid we change by the species name 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def get_taxid_from_species(self, species):
        #if it is a species name try to get the taxid
        taxid = species
        if not species.isdigit():
            Entrez.email = EMBL.PREVIOUS_VALUES["email"]
            #fetch taxid from ncbi taxomomy
            logging.debug("Fetch the taxid from species name using Entrez.esearch")
            species =  species.replace(" ", "+").strip()
            try:
                search = Entrez.esearch(term=species, db="taxonomy", retmode="xml")
                record = Entrez.read(search)
                if not record['IdList']: #no taxid found
                    logging.warning("Please verify the species name. '%s' species is unknown into the NCBI taxonomy databse. Impossible to check the taxonomic classification. We will use the default value 'Life' to populate the OC line.",self.species)
                    taxid=None
                else:
                    taxid = record['IdList'][0]
            except IOError as e:
                logging.error("Could not get taxid from species: %s" % e)

        return taxid 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def parse(self, path, fname, ftype, email, **kwargs):
        if self.accessions is not None:
            accessions = [acc.strip() for acc in self.accessions.split(",")]
            self.entrez_email(email)
            gi = self.get_GIs(accessions)
            viruses, sequences = self.get_entrez_viruses(gi, **kwargs)
        elif ftype is not None and fname is not None:
            if ftype == 'genbank':
                viruses, sequences = self.parse_gb_file(path + fname, **kwargs)
            elif ftype == 'accession':
                accessions = self.parse_accession_file(path + fname, **kwargs)
                self.entrez_email(email)
                gi = self.get_GIs(accessions)
                viruses, sequences = self.get_entrez_viruses(gi, **kwargs)
            elif ftype == 'fasta':
                viruses, sequences = self.parse_fasta_file(path + fname, **kwargs)
            elif ftype == 'tsv':
                viruses, sequences = self.parse_tsv_file(path + fname, **kwargs)
                print("Parsed " + str(len(viruses)) + " viruses and " + str(len(sequences)) + " sequences from file " + path+fname)
        else:
            raise Exception("No input file name and type defined or accessions given")
        return (viruses, sequences) 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def get_args():
    """get command-line arguments"""
    parser = argparse.ArgumentParser(
        description='Filter FASTA by taxons',
        formatter_class=argparse.ArgumentDefaultsHelpFormatter)

    parser.add_argument('file', metavar='str', help='Input file')

    parser.add_argument('-t',
                        '--taxa',
                        help='Taxa ids/file',
                        metavar='str',
                        type=str,
                        required=True)

    parser.add_argument('-e',
                        '--email',
                        help='Email address for Entrez query',
                        metavar='str',
                        type=str,
                        default='kyclark@email.arizona.edu')

    parser.add_argument('-o',
                        '--outfile',
                        help='Output file',
                        metavar='str',
                        type=str,
                        default='seqs.fa')

    parser.add_argument('-d', '--debug', help='Debug', action='store_true')

    return parser.parse_args()


# -------------------------------------------------- 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def fetch_from_entrez(index, cache_dir=False):
    logger = logging.getLogger('build')

    # slugify the index for the cache filename (some indices have symbols not allowed in file names (e.g. /))
    index_slug= slugify(index)
    cache_file_path = '{}/{}'.format('/'.join(cache_dir), index_slug)

    # try fetching from cache
    if cache_dir:
        d = fetch_from_cache(cache_dir, index_slug)
        if d:
            logger.info('Fetched {} from cache'.format(cache_file_path))
            return d
    
    # if nothing is found in the cache, use the web API
    logger.info('Fetching {} from Entrez'.format(index))
    tries = 0
    max_tries = 5
    while tries < max_tries:
        if tries > 0:
            logger.warning('Failed fetching pubmed {}, retrying'.format(str(index)))
            
        try:
            Entrez.email = 'info@gpcrdb.org'
            handle = Entrez.efetch(
                db="pubmed", 
                id=str(index), 
                rettype="medline", 
                retmode="text"
            )
        except:
            tries += 1
            time.sleep(2)
        else:
            d = Medline.read(handle)

            # save to cache
            save_to_cache(cache_dir, index_slug, d)
            logger.info('Saved entry for {} in cache'.format(cache_file_path))
            return d 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def last_exception():
    """Return last exception as a string, or use in logging."""
    exc_type, exc_value, exc_traceback = sys.exc_info()
    return "".join(traceback.format_exception(exc_type, exc_value, exc_traceback))


# Set contact email for NCBI 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def set_ncbi_email(args: Namespace) -> None:
    """Set contact email for NCBI.

    :param args:  Namespace, command-line arguments
    """
    logger = logging.getLogger(__name__)

    Entrez.email = args.email
    logger.info("Set NCBI contact email to %s", args.email)
    Entrez.tool = "genbank_get_genomes_by_taxon.py"


# Create output directory if it doesn't exist 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def get_tax_id(self, query_name):
        """to get data from ncbi taxomomy, we need to have the taxid. we can
        get that by passing the species name to esearch, which will return
        the tax id"""
        query_name = query_name.replace(' ', "+").strip()
        Entrez.email = 'A.N.Other@example.com'
        search = Entrez.esearch(term=query_name, db="taxonomy", retmode="xml")
        record = Entrez.read(search)
        return record['IdList'][0] if record['IdList'] else None 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def get_tax_data(self, taxid):
        """once we have the taxid, we can fetch the record"""
        Entrez.email = 'A.N.Other@example.com'
        search = Entrez.efetch(id=taxid, db="taxonomy", retmode="xml")
        return Entrez.read(search) 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def fetSeqFromNCBI(self, id_array):
        batch_size = 20
        count = len(id_array)
        download_contents = ""
        for start in range(0, count, batch_size):
            if self.interrupt:
                return
            end = min(count, start + batch_size)
            print("Going to download record %i to %i" % (start + 1, end))
            if (start + batch_size) > count:
                batch_size = count - start
            Entrez.email = self.email if self.email else "A.N.Other@example.com"
            fetch_handle = Entrez.efetch(db="nucleotide", rettype=self.rettype, retmode="text",
                                         retstart=start, retmax=batch_size, id=id_array)
            download_contents += fetch_handle.read()
            self.progressDiologSig.emit(end * 100 / count)
        if self.rettype == "gb":
            self.inputContentSig.emit(
                download_contents, self.outputPath)
        else:
            with open(self.outputPath + os.sep + self.fasta_file_name, "w", encoding="utf-8") as f:
                f.write(download_contents)
            self.fastaDownloadFinishedSig.emit(self.outputPath)
        # result_handle = Entrez.efetch(
        #     db="nucleotide", rettype="gb",  id=id_array, retmode="text")
        # # with open(self.exportPath + os.sep + "new.gb", "w", encoding="utf-8") as f2:
        # #     f2.write(result_handle.read())
        # self.inputContentSig.emit(
        #     result_handle.read(), []) 

# 需要导入模块: from Bio import Entrez [as 别名]
# 或者: from Bio.Entrez import email [as 别名]
def on_toolButton_clicked(self):
        info = '''To make use of NCBI's E-utilities, NCBI requires you to specify your email address with each request.<br> 
In case of excessive usage of the E-utilities, NCBI will attempt to contact a user at the email address provided before blocking access to the E-utilities.'''
        QMessageBox.information(
            self,
            "Information",
            "<p style='line-height:25px; height:25px'>%s</p>"%info)