def run_dmr_analyses(data, comparisons, anno, dmr_params, verbose=True):
"""
Compute DMRs for paired GBM-iNSC comparisons (defined in that order) for all patients
:param me_data: Pandas dataframe containing M values, columns are samples and rows are probes.
:param comparisons: Dictionary, each key is a title, each value is a 2-element iterable containing lists of
sample names. The comparison is run as group 1 - group 2 in each case.
:param anno:
:param pids:
:param dmr_params:
:return:
"""
dmr_res_obj = dmr.DmrResults(anno=anno)
dmr_res_obj.identify_clusters(**dmr_params)
dmr_res = {}
for the_ttl, the_samples in comparisons.items():
logger.info(
"Comparison %s. Group 1: %s. Group 2: %s.",
the_ttl,
','.join(the_samples[0]),
','.join(the_samples[1]),
)
the_obj = dmr_res_obj.copy()
the_obj.test_clusters(data,
samples=the_samples,
n_jobs=dmr_params['n_jobs'],
min_median_change=dmr_params['delta_m_min'],
method=dmr_params['dmr_test_method'],
alpha=dmr_params['alpha'],
**dmr_params['test_kwargs'])
dmr_res[the_ttl] = the_obj
return dmr.DmrResultCollection(**dmr_res)
def run_dmr(me_meta, me_data, dmr_clusters, str_contains_dict, type1='iPSC', type2='FB', **dmr_params):
"""
Run DMR as type1 - type2.
:param me_meta:
:param me_data:
:param dmr_clusters:
:param str_contains_dict: Dictionary. Keys will be used to identify results. Values are 2-tuples with the strings
used in the meta.index.str.contains() call that separates samples.
:param type1: Refers to the `type` column in meta.
:param type2:
:param dmr_params:
:return:
"""
res = {}
for k, (c1, c2) in str_contains_dict.items():
this = dmr_clusters.copy()
the_idx1 = me_meta.index.str.contains(c1) & (me_meta.loc[:, 'type'] == type1)
the_idx2 = me_meta.index.str.contains(c2) & (me_meta.loc[:, 'type'] == type2)
the_idx = the_idx1 | the_idx2
the_groups = me_meta.loc[the_idx, 'type'].values
the_samples = me_meta.index[the_idx].groupby(the_groups)
the_samples = [the_samples[type1], the_samples[type2]]
this.test_clusters(
me_data,
samples=the_samples,
n_jobs=dmr_params['n_jobs'],
min_median_change=dmr_params['delta_m_min'],
method=dmr_params['dmr_test_method'],
alpha=dmr_params['alpha'],
**dmr_params['test_kwargs']
)
res[k] = this
return dmr.DmrResultCollection(**res)
def compute_cross_dmr(me_data, me_meta, anno, pids, dmr_params, external_references=(('GIBCO', 'NSC'),)):
obj = dmr.DmrResults(anno=anno)
obj.identify_clusters(**dmr_params)
res = {}
# loop over GBM groups
for pid1 in pids:
res.setdefault(pid1, {})
the_idx1 = me_meta.index.str.contains(pid1) & (me_meta.loc[:, 'type'] == 'GBM')
# loop over iNSC groups
for pid2 in pids:
the_idx2 = me_meta.index.str.contains(pid2) & (me_meta.loc[:, 'type'] == 'iNSC')
the_idx = the_idx1 | the_idx2
the_groups = me_meta.loc[the_idx, 'type'].values
the_samples = me_meta.index[the_idx].groupby(the_groups).values()
the_obj = obj.copy()
the_obj.test_clusters(me_data,
samples=the_samples,
n_jobs=dmr_params['n_jobs'],
min_median_change=dmr_params['delta_m_min'],
method=dmr_params['dmr_test_method'],
**dmr_params['test_kwargs']
)
res[pid1][pid2] = the_obj
# loop over external reference NSC groups
for er, er_type in external_references:
the_idx2 = me_meta.index.str.contains(er) & (me_meta.loc[:, 'type'] == er_type)
the_idx = the_idx1 | the_idx2
the_groups = me_meta.loc[the_idx, 'type'].values
the_samples = me_meta.index[the_idx].groupby(the_groups).values()
the_obj = obj.copy()
the_obj.test_clusters(me_data,
samples=the_samples,
n_jobs=dmr_params['n_jobs'],
min_median_change=dmr_params['delta_m_min'],
method=dmr_params['dmr_test_method'],
**dmr_params['test_kwargs']
)
res[pid1][er] = the_obj
return dmr.DmrResultCollection(**res)
def paired_dmr(me_data, me_meta, anno, pids, dmr_params):
"""
Compute DMRs for paired GBM-iNSC comparisons (defined in that order) for all patients
:param me_data:
:param me_meta:
:param anno:
:param pids:
:param dmr_params:
:return:
"""
dmr_res_obj = dmr.DmrResults(anno=anno)
dmr_res_obj.identify_clusters(**dmr_params)
dmr_res = {}
for pid in pids:
the_idx1 = me_meta.index.str.contains(pid) & (me_meta.loc[:, 'type'] == 'GBM')
the_idx2 = me_meta.index.str.contains(pid) & (me_meta.loc[:, 'type'] == 'iNSC')
# control comparison order
the_samples = [
me_meta.index[the_idx1],
me_meta.index[the_idx2],
]
# the_idx = the_idx1 | the_idx2
# the_groups = me_meta.loc[the_idx, 'type'].values
# the_samples = me_meta.index[the_idx].groupby(the_groups).values()
the_obj = dmr_res_obj.copy()
the_obj.test_clusters(me_data,
samples=the_samples,
n_jobs=dmr_params['n_jobs'],
min_median_change=dmr_params['delta_m_min'],
method=dmr_params['dmr_test_method'],
alpha=dmr_params['alpha'],
**dmr_params['test_kwargs']
)
dmr_res[pid] = the_obj
return dmr.DmrResultCollection(**dmr_res)