def map_factor_sets(factor_sets): pssm_map = get_pssm_to_ensembl_map_min_range() return dict( (name, extract_ensembl(map_factors_to_ensembl(name, factor_names, pssm_map))) for name, factor_names in factor_sets.iteritems() )
def get_hit_counts(): if options.use_ucsc_seqs: import ucsc_promoters analysis = ucsc_promoters.get_analysis() else: raise RuntimeError('Do not know which sequences to use.') hit_counts = dict() logging.info('Using binding site threshold of %f to calculate hit counts.', options.hit_count_threshold) hit_counts.update(convert_analysis_to_counts(analysis, A.get_pssm_to_ensembl_map_min_range(), options.hit_count_threshold)) remove_empty_counts(hit_counts) return hit_counts.copy()
def get_hit_counts(): if options.use_ucsc_seqs: import ucsc_promoters analysis = ucsc_promoters.get_analysis() else: raise RuntimeError('Do not know which sequences to use.') hit_counts = dict() logging.info('Using binding site threshold of %f to calculate hit counts.', options.hit_count_threshold) hit_counts.update( convert_analysis_to_counts(analysis, A.get_pssm_to_ensembl_map_min_range(), options.hit_count_threshold)) remove_empty_counts(hit_counts) return hit_counts.copy()
def map_fn(key): "@return: The value for the key." return map[key] return map_fn if "__main__" == __name__: import ucsc_promoters, analysis, biopsy, shared tag = "lower" try: ucsc_analysis except NameError: ucsc_analysis = ucsc_promoters.get_analysis(tag) pssm_map = analysis.get_pssm_to_ensembl_map_min_range() ensembl_names = shared.get_all_ensembl_names() for gene in [ "ENSMUSG00000000581", "ENSMUSG00000035403", "ENSMUSG00000022184", "ENSMUSG00000061099", "ENSMUSG00000031949", "ENSMUSG00000037447", "ENSMUSG00000026753", "ENSMUSG00000022877", "ENSMUSG00000066273", "ENSMUSG00000031131", "ENSMUSG00000015305", "ENSMUSG00000061911", ]:
def map_factor_sets(factor_sets): pssm_map = get_pssm_to_ensembl_map_min_range() return dict( (name, extract_ensembl(map_factors_to_ensembl(name, factor_names, pssm_map))) for name, factor_names in factor_sets.iteritems())
def map_factors_to_ensembl(name, factor_names, pssm_map): result = dict( (factor_name, transfac_factors.ens_genes_for(factor_name, pssm_map)) for factor_name in factor_names) logging.info( '%s\n%s\n', name, '\n'.join('% 20s: %s' % (factor_name, ','.join(imap(str, ensembl))) for factor_name, ensembl in result.iteritems())) return result def extract_ensembl(factor_mapping): return set(chain(*[ensembl for ensembl in factor_mapping.values()])) def map_factor_sets(factor_sets): pssm_map = get_pssm_to_ensembl_map_min_range() return dict( (name, extract_ensembl(map_factors_to_ensembl(name, factor_names, pssm_map))) for name, factor_names in factor_sets.iteritems()) if '__main__' == __name__: tremor_liver_tfs = tf_sets_by_name['tremor-liver'] pssm_map = get_pssm_to_ensembl_map_min_range() tremor_liver_ensembl = map_factors_to_ensembl('tremor-liver', tremor_liver_tfs, pssm_map)
def map_fn(key): "@return: The value for the key." return map[key] return map_fn if '__main__' == __name__: import ucsc_promoters, analysis, biopsy, shared tag = 'lower' try: ucsc_analysis except NameError: ucsc_analysis = ucsc_promoters.get_analysis(tag) pssm_map = analysis.get_pssm_to_ensembl_map_min_range() ensembl_names = shared.get_all_ensembl_names() for gene in [ 'ENSMUSG00000000581', 'ENSMUSG00000035403', 'ENSMUSG00000022184', 'ENSMUSG00000061099', 'ENSMUSG00000031949', 'ENSMUSG00000037447', 'ENSMUSG00000026753', 'ENSMUSG00000022877', 'ENSMUSG00000066273', 'ENSMUSG00000031131', 'ENSMUSG00000015305', 'ENSMUSG00000061911', ]:
], } def map_factors_to_ensembl(name, factor_names, pssm_map): result = dict( (factor_name, transfac_factors.ens_genes_for(factor_name, pssm_map)) for factor_name in factor_names ) logging.info('%s\n%s\n', name, '\n'.join('% 20s: %s' % (factor_name, ','.join(imap(str, ensembl))) for factor_name, ensembl in result.iteritems())) return result def extract_ensembl(factor_mapping): return set(chain(*[ensembl for ensembl in factor_mapping.values()])) def map_factor_sets(factor_sets): pssm_map = get_pssm_to_ensembl_map_min_range() return dict( (name, extract_ensembl(map_factors_to_ensembl(name, factor_names, pssm_map))) for name, factor_names in factor_sets.iteritems() ) if '__main__' == __name__: tremor_liver_tfs = tf_sets_by_name['tremor-liver'] pssm_map = get_pssm_to_ensembl_map_min_range() tremor_liver_ensembl = map_factors_to_ensembl('tremor-liver', tremor_liver_tfs, pssm_map)