import pydnameth as pdm
from scripts.develop.routines import *
f = open('cpgs.txt', 'r')
items = f.read().splitlines()
reverses = ['no'] * len(items)
x_ranges = ['auto'] * len(items)
y_ranges = ['auto'] * len(items)
data = pdm.Data(
base='unn_epic'
)
annotations = pdm.Annotations(
name='annotations',
type='850k',
exclude='bad_cpgs_from_ChAMP',
select_dict={
'CHR': ['-X', '-Y']
}
)
observables = pdm.Observables(
name='observables',
types={}
)
cells = pdm.Cells(
name='',
types='any'
)
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(
#path='E:/YandexDisk/Work/pydnameth/tissues/brain(DLPFC)',
path='',
base='GSE87571'
)
annotations = pdm.Annotations(
name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={
'CHR': ['-X', '-Y']
}
)
cells = pdm.Cells(
name='',
types='any'
)
observables = pdm.Observables(
name='observables',
types={}
)
attributes = pdm.Attributes(
target='age',
observables=observables,
tmp_dict = df.to_dict()
for key in tmp_dict:
curr_dict = tmp_dict[key]
table_dict[key] = list(curr_dict.values())
items = table_dict['i']
x_ranges = [[5, 105]] * len(items)
y_ranges = []
for index in range(0, len(items)):
y_ranges.append([table_dict['begin'][index], table_dict['end'][index]])
data_bases = ['GSE87571_TEST']
for data_base in data_bases:
data = pdm.Data(path='', base='GSE43414')
annotations = pdm.Annotations(name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={'CHR': ['-X', '-Y']})
observables = pdm.Observables(name='observables', types={})
cells = pdm.Cells(name='cells', types='any')
target = get_target(data.base)
observables_list = get_observables_list(data.base)
data_params = get_data_params(data.base)
attributes = pdm.Attributes(target=target,
import pydnameth as pdm
data_sets = ['GSE87571']
for data_set in data_sets:
cell_types = ['Bcell', 'CD4T', 'NK', 'CD8T', 'Gran']
cell_name = 'cells_horvath_calculator'
data = pdm.Data(path='', base=data_set)
annotations = pdm.Annotations(name='annotations',
exclude='bad_cpgs',
cross_reactive='any',
snp='any',
chr='NS',
gene_region='any',
geo='any',
probe_class='any')
observables = pdm.Observables(name='observables', types={})
cells = pdm.Cells(name=cell_name, types=cell_types)
attributes = pdm.Attributes(target='age',
observables=observables,
cells=cells)
if data.base == 'GSE55763':
observables_list = [{
'gender': 'F',
import pydnameth as pdm
items = ['entropy']
x_ranges = [[5, 105]] * len(items)
y_ranges = ['auto'] * len(items)
data_bases = ['GSE87571']
for data_base in data_bases:
data = pdm.Data(
path='',
base=data_base
)
annotations = pdm.Annotations(
name='annotations',
exclude='bad_cpgs',
cross_reactive='any',
snp='any',
chr='NS',
gene_region='any',
geo='any',
probe_class='any'
)
observables = pdm.Observables(
name='observables',
types={}
)
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(
path='',
base='unn_epic'
)
annotations = pdm.Annotations(
name='annotations',
type='850k',
exclude='none',
select_dict={}
)
observables = pdm.Observables(
name='observables_part(v1)',
types={'COVID': ['no', 'before'],
'Sample_Chronology': [0, 1]}
)
cells = pdm.Cells(
name='cell_counts_part(v1)',
types='any'
)
target = 'Group'
attributes = pdm.Attributes(
target=target,
observables=observables,
import pydnameth as pdm
data = pdm.Data(
path=
'E:/YandexDisk/Work/pydnameth/script_datasets/GPL13534/filtered/blood(whole)',
base='GSE87571')
data_params = {
'norm': 'fun',
'part': 'wo_missedFeatures',
}
chip_type = '450k'
fn = 'observables_part(wo_missedFeatures)'
pdm.betas_horvath_calculator_create_regular(chip_type=chip_type,
observables_fn=fn,
data=data,
data_params=data_params)
tmp_dict = df.to_dict()
for key in tmp_dict:
curr_dict = tmp_dict[key]
cols_dict[key] = list(curr_dict.values())
data_bases = cols_dict['data_bases']
data_list = []
annotations_list = []
attributes_list = []
observables_list = []
data_params_list = []
for data_base in data_bases:
data = pdm.Data(path='E:/YandexDisk/Work/pydnameth/epityper/FIGN',
base=data_base)
data_list.append(data)
annotations = pdm.Annotations(name='annotations',
type='epityper',
exclude='none',
select_dict={})
annotations_list.append(annotations)
observables = pdm.Observables(name='observables', types={})
cells = pdm.Cells(name='cells', types='any')
target = get_target(data.base)
obs = get_observables_list(data.base)
data_params = get_data_params(data.base)
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(path='', base='EPIC')
annotations = pdm.Annotations(name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={'CHR': ['-X', '-Y']})
observables = pdm.Observables(name='observables', types={})
cells = pdm.Cells(name='cells_horvath_calculator', types='any')
target = get_target(data.base)
observables_list = get_observables_list(data.base)
data_params = get_data_params(data.base)
data_params['cells'] = ['Bcell', 'CD4T', 'CD8T', 'Gran', 'NK']
attributes = pdm.Attributes(target=target,
observables=observables,
cells=cells)
pdm.residuals_table_approach_4(data=data,
annotations=annotations,
attributes=attributes,
observables_list=observables_list,
data_params=data_params)
import pydnameth as pdm
from scripts.develop.routines import *
f = open('cpgs.txt', 'r')
items = f.read().splitlines()
x_ranges = ['auto'] * len(items)
y_ranges = ['auto'] * len(items)
data = pdm.Data(
path='E:/YandexDisk/Work/pydnameth/epityper/PRR4',
base='control'
)
annotations = pdm.Annotations(
name='annotations',
type='epityper',
exclude='none',
select_dict={}
)
observables = pdm.Observables(
name='observables',
types={}
)
cells = pdm.Cells(
name='cells',
types='any'
)
target = get_target(data.base)
import pydnameth as pdm
f = open('genes.txt', 'r')
items = f.read().splitlines()
x_ranges = [[5, 105]] * len(items)
y_ranges = ['auto'] * len(items)
data = pdm.Data(
path='',
base='E-MTAB-7309-FILTERED'
)
annotations = pdm.Annotations(
name='annotations',
exclude='bad_cpgs',
cross_reactive='any',
snp='any',
chr='NS',
gene_region='any',
geo='islands_shores',
probe_class='any'
)
observables = pdm.Observables(
name='observables',
types={}
)
cells = pdm.Cells(
name='cells_horvath_calculator',
import pydnameth as pdm
data = pdm.Data(name='cpg_beta', path='', base='EPIC')
annotations = pdm.Annotations(name='annotations',
exclude='none',
cross_reactive='ex',
snp='ex',
chr='NS',
gene_region='yes',
geo='any',
probe_class='any')
observables = pdm.Observables(name='observables', types={})
cells = pdm.Cells(name='cells', types='any')
attributes = pdm.Attributes(target='age', observables=observables, cells=cells)
observables_list = [{'gender': 'F'}, {'gender': 'M'}]
pdm.cpg_proc_table_z_test_linreg(data=data,
annotations=annotations,
attributes=attributes,
observables_list=observables_list)
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(
path='',
base='GSE40279'
)
annotations = pdm.Annotations(
name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={
'CHR': ['-X', '-Y']
}
)
observables = pdm.Observables(
name='observables',
types={}
)
cells = pdm.Cells(
name='cells_horvath_calculator',
types='any'
)
target = get_target(data.base)
observables_list = get_observables_list(data.base)
data_params = get_data_params(data.base)
import pydnameth as pdm
from scripts.develop.routines import *
from tqdm import tqdm
import numpy as np
from scipy.stats import pearsonr, pointbiserialr
from statsmodels.stats.multitest import multipletests
from paper.routines.infrastructure.save.table import save_table_dict_xlsx
save_path = 'E:/YandexDisk/Work/pydnameth/unn_epic/comparison'
data_unn_epic = pdm.Data(
path='',
base='unn_epic'
)
annotations_unn_epic = pdm.Annotations(
name='annotations',
type='850k',
exclude='bad_cpgs_from_ChAMP',
select_dict={
'CHR': ['-X', '-Y']
}
)
target_unn_epic = 'Age'
observables_unn_epic = pdm.Observables(
name='observables',
types={}
)
cells_unn_epic = pdm.Cells(
name='cell_counts_horvath_filtered_normalized',
types='any'
)
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(
path='',
base='GSE55763'
)
annotations = pdm.Annotations(
name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={
'CHR': ['-X', '-Y']
}
)
observables = pdm.Observables(
name='observables',
types={}
)
cells = pdm.Cells(
name='cells_horvath_calculator',
types='any'
)
target = get_target(data.base)
observables_list = get_observables_list(data.base)
data_params = get_data_params(data.base)
import pydnameth as pdm
data = pdm.Data(name='cpg_beta', path='', base='GSE87571')
annotations = pdm.Annotations(name='annotations',
exclude='none',
cross_reactive='ex',
snp='ex',
chr='NS',
gene_region='yes',
geo='any',
probe_class='any')
observables = pdm.Observables(name='observables', types={})
cells = pdm.Cells(name='cells', types='any')
attributes = pdm.Attributes(target='age', observables=observables, cells=cells)
observables_list = [{'smoke': 0}, {'smoke': [1, 2, 3, 4]}]
pdm.cpg_proc_table_polygon(data=data,
annotations=annotations,
attributes=attributes,
observables_list=observables_list)
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(
path='',
#path='E:/YandexDisk/Work/pydnameth/tissues/brain(DLPFC)',
base='GSE87571'
#base='liver'
#base='GSE74193'
)
annotations = pdm.Annotations(name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={'CHR': ['-X', '-Y']})
cells = pdm.Cells(name='cells_horvath_calculator', types='any')
target = get_target(data.base)
data_params = get_data_params(data.base)
if data.base == 'GSE55763':
observables_list = [
{
'gender': 'any',
'is_duplicate': '0',
'age': (35, 100)
},
]
else:
# observables_list = [
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(path='', base='liver')
annotations = pdm.Annotations(name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={'CHR': ['-X', '-Y']})
cells = pdm.Cells(name='cells_horvath_calculator', types='any')
target = 'age'
observables_list = [
{
'gender': 'any'
},
]
data_params = get_data_params(data.base)
data_params['cells'] = ['CD8T', 'CD4T', 'NK', 'Bcell', 'Gran']
data_params['observables'] = ['gender']
for obs in observables_list:
observables = pdm.Observables(name='observables', types=obs)
attributes = pdm.Attributes(target=target,
observables=observables,
cells=cells)
pdm.residuals_table_oma(data=data,
import pydnameth as pdm
from scripts.develop.routines import *
data = pdm.Data(path='', base='GSE87571')
annotations = pdm.Annotations(name='annotations',
type='450k',
exclude='bad_cpgs',
select_dict={'CHR': ['-X', '-Y']})
cells = pdm.Cells(name='cells_horvath_calculator', types='any')
target = get_target(data.base)
data_params = get_data_params(data.base)
data_params['cells'] = ['CD8T', 'CD4T', 'NK', 'Bcell', 'Gran']
if data.base == 'GSE55763':
observables_list = [
{
'gender': 'any',
'is_duplicate': '0',
'age': (35, 100)
},
]
else:
observables_list = [
{
'gender': 'any'
},
]
if '(' in filter_list[1] and ')' in filter_list[1]:
filter_values_str = filter_list[1][1::-1]
filter_value = filter_values_str.split(',')
else:
filter_value = filter_list[1]
ds_filter[ds][filter_key] = filter_value
ololo = 1
f.close()
data = pdm.Data(
path='E:/YandexDisk/Work/pydnameth/script_datasets/GPL13534/filtered/airway_epithelial_cells',
base='GSE85566'
)
annotations = None
cells = None
observables = pdm.Observables(
name='observables',
types={}
)
attributes = pdm.Attributes(
target='age',
observables=observables,
cells=cells
