def add_info_to_dict(data_dict, cpg_key='CpG'):
annotations_keys = [
'CHR', 'MAPINFO', 'UCSC_REFGENE_NAME', 'UCSC_REFGENE_GROUP',
'RELATION_TO_UCSC_CPG_ISLAND'
]
annotations_dict = load_annotations_dict()
for key in annotations_keys:
data_dict[key] = []
for cpg in data_dict[cpg_key]:
for key in annotations_keys:
data_dict[key].append(annotations_dict[key][cpg])
reject, pvals_corr, alphacSidak, alphacBonf = multipletests(
data_dict['Sex_P.Value'], 0.05, method='fdr_bh')
data_dict['Sex_P.Value_fdr_bh'] = pvals_corr
reject, pvals_corr, alphacSidak, alphacBonf = multipletests(
data_dict['Sex_P.Value'], 0.05, method='bonferroni')
data_dict['Sex_P.Value_bf'] = pvals_corr
reject, pvals_corr, alphacSidak, alphacBonf = multipletests(
data_dict['Age_P.Value'], 0.05, method='fdr_bh')
data_dict['Age_P.Value_fdr_bh'] = pvals_corr
reject, pvals_corr, alphacSidak, alphacBonf = multipletests(
data_dict['Age_P.Value'], 0.05, method='bonferroni')
data_dict['Age_P.Value_bf'] = pvals_corr
return data_dict
def get_cpg_dataset_save_dicts(sets, data_dicts, cpg_dicts, key='item'):
annotations_keys = [
'CHR', 'MAPINFO', 'UCSC_REFGENE_NAME', 'UCSC_REFGENE_GROUP',
'RELATION_TO_UCSC_CPG_ISLAND'
]
papers_keys = ['inoshita', 'singmann', 'yousefi']
annotations_dict = load_annotations_dict()
papers_dict = load_papers_dict()
save_dicts = {}
for set_key in sets:
save_dicts[set_key] = {}
for metrics_key in [key] + annotations_keys + papers_keys:
save_dicts[set_key][metrics_key] = []
curr_datasets = set_key.split('_')
for dataset in curr_datasets:
for ds_key in data_dicts[dataset]:
if ds_key not in save_dicts[set_key]:
save_dicts[set_key][ds_key + '_' + dataset] = []
for cpg in sets[set_key]:
save_dicts[set_key][key].append(cpg)
for dataset in curr_datasets:
for ds_key in data_dicts[dataset]:
if ds_key not in save_dicts[set_key]:
save_dicts[set_key][ds_key + '_' + dataset].append(
data_dicts[dataset][ds_key][cpg_dicts[dataset]
[cpg]])
for ann_key in annotations_keys:
save_dicts[set_key][ann_key].append(
annotations_dict[ann_key][cpg])
for paper_key in papers_keys:
if cpg in papers_dict[paper_key]:
save_dicts[set_key][paper_key].append(1)
else:
save_dicts[set_key][paper_key].append(0)
return save_dicts
def add_chars_to_dict(data_dict, item_key='item'):
annotations_keys = [
'CHR', 'MAPINFO', 'UCSC_REFGENE_NAME', 'UCSC_REFGENE_GROUP',
'RELATION_TO_UCSC_CPG_ISLAND'
]
papers_keys = ['inoshita', 'singmann', 'yousefi']
annotations_dict = load_annotations_dict()
papers_dict = load_papers_dict()
add_keys = annotations_keys + papers_keys
for key in add_keys:
data_dict[key] = []
for item in data_dict[item_key]:
for paper_key in papers_keys:
if item in papers_dict[paper_key]:
data_dict[paper_key].append(1)
else:
data_dict[paper_key].append(0)
for ann_key in annotations_keys:
data_dict[ann_key].append(annotations_dict[ann_key][item])
papers_keys = ['inoshita', 'singmann', 'yousefi']
path = 'E:/YandexDisk/Work/pydnameth/draft/fixes/materials_and_methods/update_4_bonferroni'
data_dicts_passed = {}
cpgs_dicts_passed = {}
R2s = {}
R2_percentiles = {}
data_dict = load_table_dict_xlsx(f'{path}/{name}.xlsx')
for key in annotations_keys:
data_dict[key] = []
for key in papers_keys:
data_dict[key] = []
annotations_dict = load_annotations_dict()
papers_dict = load_papers_dict()
for cpg in tqdm(data_dict[cpg_key], desc=f'intersection processing'):
for key in annotations_keys:
data_dict[key].append(annotations_dict[key][cpg])
for paper_key in papers_keys:
if cpg in papers_dict[paper_key]:
data_dict[paper_key].append(1)
else:
data_dict[paper_key].append(0)
save_table_dict_xlsx(f'{path}/{name}_with_added_info', data_dict)