def load_methylation(pids,
ref_names=None,
norm_method='swan',
ref_name_filter=None,
units='beta'):
"""
Load and prepare the Illumina methylation data
"""
# patient data
obj = loader.load_by_patient(pids, norm_method=norm_method)
anno = loader.load_illumina_methylationepic_annotation()
# reference data
if ref_names is not None:
ref_obj = loader.load_reference(ref_names, norm_method=norm_method)
if ref_name_filter is not None:
ref_obj.filter_by_sample_name(ref_name_filter, exact=True)
obj = loader.loader.MultipleBatchLoader([obj, ref_obj])
me_data = obj.data.dropna()
if units == 'm':
me_data = process.m_from_beta(me_data)
# reduce anno and data down to common probes
common_probes = anno.index.intersection(me_data.index)
anno = anno.loc[common_probes]
# dmr.add_merged_probe_classes(anno)
me_data = me_data.loc[common_probes]
obj.data = me_data
return obj, anno
# 'ICb1299_shBMI1CHD7': 'shBMI1shCHD7',
# 'p62_3_shBmi1': 'shBMI1',
# 'p62_3_shChd7': 'shCHD7',
# 'p62_3_shB+C': 'shBMI1shCHD7',
# 'p62_3_Scr': 'scramble',
#
# })
# condition = condition.loc[meta.index]
# meta.insert(0, 'condition', condition)
#
# cell_line = pd.Series('3021', index=meta.index)
# cell_line[cell_line.index.str.contains('1299')] = 'ICb1299'
# cell_line[cell_line.index.str.contains('p62')] = 'ICb1299'
# meta.insert(0, 'cell_line', cell_line)
anno = loader.load_illumina_methylationepic_annotation()
me_data = obj.data.dropna()
me_data = process.m_from_beta(me_data)
# reduce anno and data down to common probes
common_probes = anno.index.intersection(me_data.index)
anno = anno.loc[common_probes]
# plot PCA
p = pca.PCA()
pca_dat = p.fit_transform(me_data.transpose())
fig = plt.figure()
df_row = df.loc[ix].tolist()
if pd.isna(row.UCSC_RefGene_Name):
gr = [('', '')]
else:
g = row.UCSC_RefGene_Name.split(';')
r = row.UCSC_RefGene_Group.split(';')
gr = sorted(set(zip(g, r)))
for t in gr:
this_res.append([ix] + df_row +
[row.CHR, row.Strand, row.MAPINFO, t[0], t[1]])
return pd.DataFrame(this_res,
columns=['probe_id'] + df.columns.tolist() + anno_cols)
if __name__ == '__main__':
anno = loader.load_illumina_methylationepic_annotation(split_genes=False)
# 1. Annotate DMPs and re-export to Excel
# dmp_fns = glob(os.path.join(GIT_LFS_DATA_DIR, 'mb_dmp', '*.xlsx'))
dmp_fns = glob(os.path.join(os.path.expanduser('~/temp'), '*.xlsx'))
print "Found %d relevant input (DMP) files: %s" % (len(dmp_fns),
', '.join(dmp_fns))
outdir = output.unique_output_dir("mb_dmps")
res = {}
for fn in dmp_fns:
base = os.path.splitext(os.path.basename(fn))[0]
res[base] = {}
dat = pd.read_excel(fn, sheet_name=None)
