filenames = [
'1134_and_Cho.txt',
'1134_not_Cho.txt',
'cho_not_1134.txt',
]
references = dict()
for file in filenames:
print '****************** %s ********************' % file
references[os.path.splitext(file)[0]] = set(yield_refs(file))
# get all the HS unigenes from all the files
cell_cycle_hs_unigene = list(chain(*references.values()))
# translate them to ensembl HS genes using the Synergizer
translated = S.translate('ensembl', 'H**o sapiens', 'unigene',
'ensembl_gene_id', cell_cycle_hs_unigene)
print 'Ensembl translated: %d' % S.how_many_have_translations(translated)
ensembl_hs_genes = S.get_translations(translated)
def yield_mouse_orthologs(hs_genes):
# map into mouse orthologs using biomart
query = B.new_query()
dataset = B.add_dataset(query, 'hsapiens_gene_ensembl')
B.add_attribute(dataset, 'ensembl_gene_id')
B.add_attribute(dataset, 'mouse_ensembl_gene')
filter = B.add_filter(dataset, name='ensembl_gene_id', value='')
filter.set('value', ','.join(ensembl_hs_genes))
for chunk in B.split_big_list(ensembl_hs_genes, 50):
#logging.info('Querying Ensembl biomart for chunk of %d genes', len(chunk))
filter.set('value', ','.join(chunk))
'1134_not_Cho.txt',
'cho_not_1134.txt',
]
references = dict()
for file in filenames:
print '****************** %s ********************' % file
references[os.path.splitext(file)[0]] = set(yield_refs(file))
# get all the HS unigenes from all the files
cell_cycle_hs_unigene = list(chain(*references.values()))
# translate them to ensembl HS genes using the Synergizer
translated = S.translate('ensembl', 'H**o sapiens', 'unigene', 'ensembl_gene_id', cell_cycle_hs_unigene)
print 'Ensembl translated: %d' % S.how_many_have_translations(translated)
ensembl_hs_genes = S.get_translations(translated)
def yield_mouse_orthologs(hs_genes):
# map into mouse orthologs using biomart
query = B.new_query()
dataset = B.add_dataset(query, 'hsapiens_gene_ensembl')
B.add_attribute(dataset, 'ensembl_gene_id')
B.add_attribute(dataset, 'mouse_ensembl_gene')
filter = B.add_filter(dataset, name='ensembl_gene_id', value='')
filter.set('value', ','.join(ensembl_hs_genes))
for chunk in B.split_big_list(ensembl_hs_genes, 50):
#logging.info('Querying Ensembl biomart for chunk of %d genes', len(chunk))
filter.set('value', ','.join(chunk))
for row in B.yield_csv_query_results(query):
"""
muscle_tfs = [
'MEF2c', # MEF2
'SP1',
'SRF',
'MyoD1', # EBOX (MyoD)
'TEF',
]
"""
Muscle study TFBS (based on work by Wasserman and Fickett, 1998)
"""
tf_sets = {
'Haematopoietic': haematopoietic_tfs,
'Liver': liver_tfs,
'Muscle': muscle_tfs
}
import biopsy.identifiers.synergizer as S
import biopsy.identifiers.biomart as B
for tag, tfs in tf_sets.iteritems():
translated = S.translate('ensembl', 'Mus musculus', 'mgi_symbol',
'ensembl_gene_id', tfs)
print translated
print 'Ensembl translated: %d/%d' % (
S.how_many_have_translations(translated), len(tfs))
ensembl_genes = S.get_translations(translated)
open('%s-ensembl.txt' % tag, 'w').write('\n'.join(ensembl_genes))
"PAX5",
"SP1",
]
"""
Haematopoietic TFBS
"""
liver_tfs = ["HNF1a", "Foxe3", "HNF4a", "CEBPa"] # HNF1 # HNF3 # HNF4 # CEBP
"""
Liver study TFBS (based on work by Krivan and Wasserman, 2001)
"""
muscle_tfs = ["MEF2c", "SP1", "SRF", "MyoD1", "TEF"] # MEF2 # EBOX (MyoD)
"""
Muscle study TFBS (based on work by Wasserman and Fickett, 1998)
"""
tf_sets = {"Haematopoietic": haematopoietic_tfs, "Liver": liver_tfs, "Muscle": muscle_tfs}
import biopsy.identifiers.synergizer as S
import biopsy.identifiers.biomart as B
for tag, tfs in tf_sets.iteritems():
translated = S.translate("ensembl", "Mus musculus", "mgi_symbol", "ensembl_gene_id", tfs)
print translated
print "Ensembl translated: %d/%d" % (S.how_many_have_translations(translated), len(tfs))
ensembl_genes = S.get_translations(translated)
open("%s-ensembl.txt" % tag, "w").write("\n".join(ensembl_genes))
# Copyright John Reid 2009
#
"""
Targets of liver specific transcription factors in Wasserman's predictive model for liver paper
"""
from utils import *
from itertools import imap
import biopsy.identifiers.synergizer as S
liver_targets = ["G6PC", "IGF1", "PAH", "IGFBP1", "CFB", "FABP2", "GUCA2B", "HOXA4", "SLC34A1"] # BF
translated = S.translate("ensembl", "Mus musculus", "mgi_symbol", "ensembl_gene_id", liver_targets)
print translated
print "Ensembl translated: %d/%d" % (S.how_many_have_translations(translated), len(liver_targets))
ensembl_genes = S.get_translations(translated)
open("liver-targets.txt", "w").write("\n".join(ensembl_genes))
liver_ensembl_targets = {
"G6PC": "ENSMUSG00000078650",
"IGF1": "ENSMUSG00000020053",
"PAH": "ENSMUSG00000020051",
"IGFBP1": "ENSMUSG00000020429",
"CFB": "ENSMUSG00000024371",
"FABP2": "ENSMUSG00000023057",
"GUCA2B": "ENSMUSG00000032978",
"HOXA4": "ENSMUSG00000000942",
from itertools import imap
import biopsy.identifiers.synergizer as S
liver_targets = [
'G6PC',
'IGF1',
'PAH',
'IGFBP1',
'CFB', # BF
'FABP2',
'GUCA2B',
'HOXA4',
'SLC34A1'
]
translated = S.translate('ensembl', 'Mus musculus', 'mgi_symbol',
'ensembl_gene_id', liver_targets)
print translated
print 'Ensembl translated: %d/%d' % (S.how_many_have_translations(translated),
len(liver_targets))
ensembl_genes = S.get_translations(translated)
open('liver-targets.txt', 'w').write('\n'.join(ensembl_genes))
liver_ensembl_targets = {
'G6PC': 'ENSMUSG00000078650',
'IGF1': 'ENSMUSG00000020053',
'PAH': 'ENSMUSG00000020051',
'IGFBP1': 'ENSMUSG00000020429',
'CFB': 'ENSMUSG00000024371',
'FABP2': 'ENSMUSG00000023057',
'GUCA2B': 'ENSMUSG00000032978',
'HOXA4': 'ENSMUSG00000000942',
