def __init__(self, inputFnameLs=None, **keywords):
"""
2008-07-27
use option_default_dict
2008-07-06
use the firstline (header) of the fasta file to extract which chromosome. using filename is unreliable.
"""
AbstractDBInteractingJob.__init__(self, inputFnameLs=inputFnameLs, **keywords)
#self.connectDB() called within its __init__()
self.FigureOutTaxID_ins = FigureOutTaxID(db_user=self.db_user,
db_passwd=self.db_passwd, hostname=self.hostname, dbname=self.dbname)
if self.organism is not None:
from annot.bin.codense.common import org_short2long, org2tax_id
if org_short2long(self.organism):
self.tax_id = org2tax_id(org_short2long(self.organism))
else:
self.tax_id = self.FigureOutTaxID_ins.returnTaxIDGivenSentence(self.organism)
#self.p_chromosome = re.compile(r'[a-zA-Z]+_chr(\w+).fa')
self.p_chromosome = re.compile(r'chromosome (\w+)[,\n\r]?') #the last ? means [,\n\r] is optional
self.p_acc_ver = re.compile(r'(\w+)\.(\d+)')
self.parseFastaDescriptionDict = {1: self.parseFastaDescriptionForGenBank, \
2: self.parseFastaDescriptionForWUSTLVervetScaffolds,\
3: self.parseFastaDescriptionForFullVervetBACs,\
4: self.parseFastaDescriptionForWUSTLVervetChromosomeGenome}
def __init__(self, inputFnameLs=None, **keywords):
"""
2008-07-27
use option_default_dict
2008-07-06
use the firstline (header) of the fasta file to extract which chromosome. using filename is unreliable.
"""
AbstractDBInteractingJob.__init__(self, inputFnameLs=inputFnameLs, **keywords)
#self.connectDB() called within its __init__()
self.FigureOutTaxID_ins = FigureOutTaxID(db_user=self.db_user,
db_passwd=self.db_passwd, hostname=self.hostname, dbname=self.dbname)
if self.organism is not None:
from annot.bin.codense.common import org_short2long, org2tax_id
if org_short2long(self.organism):
self.tax_id = org2tax_id(org_short2long(self.organism))
else:
self.tax_id = self.FigureOutTaxID_ins.returnTaxIDGivenSentence(self.organism)
#self.p_chromosome = re.compile(r'[a-zA-Z]+_chr(\w+).fa')
self.p_chromosome = re.compile(r'chromosome (\w+)[,\n\r]?') #the last ? means [,\n\r] is optional
self.p_acc_ver = re.compile(r'(\w+)\.(\d+)')
self.parseFastaDescriptionDict = {1: self.parseFastaDescriptionForGenBank, \
2: self.parseFastaDescriptionForWUSTLVervetScaffolds,\
3: self.parseFastaDescriptionForFullVervetBACs,\
4: self.parseFastaDescriptionForWUSTLVervetChromosomeGenome}
def __init__(self, hostname='zhoudb', dbname='mdb', schema='', inputfile=None, \
organism='hs', type=1, debug=0, report=0, commit=0):
self.hostname = hostname
self.dbname = dbname
self.schema = schema
self.inputfile = inputfile
self.organism = organism
self.type = int(type)
self.debug = int(debug)
self.report = int(report)
self.commit = int(commit)
self.tax_id = org2tax_id(org_short2long(self.organism))
self.parser_dict = {1: self.harbison2004_parse,
2: self.cisred_parse,
3: self.sgd_regulatory_parse,
4: self.ucsc_tfbs_conserved_parse}
def __init__(self, hostname='dl324b-1', dbname='yhdb', schema='dbsnp', input_fname=None, \
output_table=None, strain_info_table='strain_info', snp_locus_table='snp_locus', \
organism='hs', type=1, debug=0, report=0, commit=0):
self.hostname = hostname
self.dbname = dbname
self.schema = schema
self.input_fname = input_fname
self.output_table = output_table
self.strain_info_table = strain_info_table
self.snp_locus_table = snp_locus_table
self.tax_id = org2tax_id(org_short2long(organism))
self.type = int(type)
self.debug = int(debug)
self.report = int(report)
self.commit = int(commit)
self.snp_acc_category_pattern = re.compile("([a-zA-Z]*[\-]*[a-zA-Z]+)[\-_ ]*[\w]+")
def __init__(self, hostname='dl324b-1', dbname='yhdb', schema='dbsnp', input_fname=None, \
output_table=None, strain_info_table='strain_info', snp_locus_table='snp_locus', \
organism='hs', type=1, debug=0, report=0, commit=0):
self.hostname = hostname
self.dbname = dbname
self.schema = schema
self.input_fname = input_fname
self.output_table = output_table
self.strain_info_table = strain_info_table
self.snp_locus_table = snp_locus_table
self.tax_id = org2tax_id(org_short2long(organism))
self.type = int(type)
self.debug = int(debug)
self.report = int(report)
self.commit = int(commit)
self.snp_acc_category_pattern = re.compile(
"([a-zA-Z]*[\-]*[a-zA-Z]+)[\-_ ]*[\w]+")
def __init__(self, hostname='zhoudb', dbname='mdb', schema='transfac', inputfile=None, \
output_table=None, sequence_type=1, organism='hs', type=1, debug=0, report=0, commit=0):
self.hostname = hostname
self.dbname = dbname
self.schema = schema
self.inputfile = inputfile
self.output_table = output_table
self.sequence_type = int(sequence_type)
self.organism = org_short2long(organism)
self.type = int(type)
self.debug = int(debug)
self.report = int(report)
self.commit = int(commit)
self.parser_dict = {
1: self.prom_seq_parse,
2: self.factor_parse,
3: self.matrix_parse,
4: self.binding_site_parse,
5: self.reference_parse,
6: self.site_parse,
7: self.cell_parse,
8: self.fragment_parse,
9: self.gene_parse,
10: self.class_parse,
11: self.binding_site_easy_parse
}
self.output_table_dict = {
1: 'prom_seq',
2: 'factor',
3: 'matrix',
4: 'binding_site',
5: 'reference',
6: 'site',
7: 'cell',
8: 'fragment',
9: 'gene',
10: 'class',
11: 'binding_site'
}
self.pwm_line_pattern = re.compile(r'\d\d ')
def __init__(self, hostname='zhoudb', dbname='mdb', schema='transfac', inputfile=None, \
output_table=None, sequence_type=1, organism='hs', type=1, debug=0, report=0, commit=0):
self.hostname = hostname
self.dbname = dbname
self.schema = schema
self.inputfile = inputfile
self.output_table = output_table
self.sequence_type = int(sequence_type)
self.organism = org_short2long(organism)
self.type = int(type)
self.debug = int(debug)
self.report = int(report)
self.commit = int(commit)
self.parser_dict = {1: self.prom_seq_parse,
2: self.factor_parse,
3: self.matrix_parse,
4: self.binding_site_parse,
5: self.reference_parse,
6: self.site_parse,
7: self.cell_parse,
8: self.fragment_parse,
9: self.gene_parse,
10: self.class_parse,
11: self.binding_site_easy_parse}
self.output_table_dict = {1: 'prom_seq',
2: 'factor',
3: 'matrix',
4: 'binding_site',
5: 'reference',
6: 'site',
7: 'cell',
8: 'fragment',
9: 'gene',
10: 'class',
11: 'binding_site'}
self.pwm_line_pattern = re.compile(r'\d\d ')
