def extract_pc_filtered(df, pc_threshold=.2, filter_down=True):
'''
First pre-filters for patients with no tumor/normal change.
Then normalizes by normals.
'''
if ('11' in df.columns.levels[1]) and filter_down:
tt = df.xs('11', axis=1, level=1)
rr = df.apply(exp_change, 1).sort('p')
m, s = tt.mean(1), tt.std(1)
df_n = df.xs('01', axis=1, level=1)
df_n = ((df_n.T - m) / s).T
df_n = df_n.ix[true_index(rr.p < .05)]
else: # No matched normals
df_n = df.xs('01', axis=1, level=1)
df_n = ((df_n.T - df_n.mean(1)) / df_n.std(1)).T
pc = extract_pc(df_n, pc_threshold, standardize=False)
return pc
def extract_pc_filtered(df, pc_threshold=.2, filter_down=True):
'''
First pre-filters for patients with no tumor/normal change.
Then normalizes by normals.
'''
if ('11' in df.columns.levels[1]) and filter_down:
tt = df.xs('11', axis=1, level=1)
rr = df.apply(exp_change, 1).sort('p')
m, s = tt.mean(1), tt.std(1)
df_n = df.xs('01', axis=1, level=1)
df_n = ((df_n.T - m) / s).T
df_n = df_n.ix[true_index(rr.p < .05)]
else: #No matched normals
df_n = df.xs('01', axis=1, level=1)
df_n = ((df_n.T - df_n.mean(1)) / df_n.std(1)).T
pc = extract_pc(df_n, pc_threshold, standardize=False)
return pc
def _get_real_features(self):
binary, singles, real = extract_features(self.df)
background_df = real.ix[real.index.diff(singles.index)].dropna()
background = extract_pc(background_df, 0)
ss = screen_feature(background['pat_vec'], pearson_pandas, singles)
singles = singles.ix[ss.p > 10e-5]
singles = ((singles.T - singles.mean(1)) / singles.std(1)).T
U, S, pc = frame_svd(singles)
self.features['binary'] = binary
self.features['real'] = singles
self.global_vars['background'] = background['pat_vec']
self.global_vars['filtered_pc1'] = pc[0]
self.global_vars['filtered_pc2'] = pc[1]
self.global_loadings['background'] = background['gene_vec']
self.global_loadings['filtered_pc1'] = U[0]
self.global_loadings['filtered_pc2'] = U[1]
def peel_pc(df):
'''
Wrapper around extract_pc.
Flips the PC slightly differently based on correlation with the mean.
Does not standardize data for PCA due to underlying distribution of
beta values.
'''
try:
r = extract_pc(df-.5)
l,r,p = r['gene_vec'], r['pat_vec'], r['pct_var']
mean = df.mean(1)
if l.corr(mean) < 0:
l = l*-1
r = r*-1
return l,r,p
except:
r = df.mean()
return np.nan, r, np.nan
def _get_real_features(self):
binary, singles, real = extract_features(self.df)
background_df = real.ix[real.index.diff(singles.index)].dropna()
background = extract_pc(background_df, 0)
ss = screen_feature(background['pat_vec'], pearson_pandas, singles)
singles = singles.ix[ss.p > 10e-5]
singles = ((singles.T - singles.mean(1)) / singles.std(1)).T
U, S, pc = frame_svd(singles)
self.features['binary'] = binary
self.features['real'] = singles
self.global_vars['background'] = background['pat_vec']
self.global_vars['filtered_pc1'] = pc[0]
self.global_vars['filtered_pc2'] = pc[1]
self.global_loadings['background'] = background['gene_vec']
self.global_loadings['filtered_pc1'] = U[0]
self.global_loadings['filtered_pc2'] = U[1]
def peel_pc(df):
'''
Wrapper around extract_pc.
Flips the PC slightly differently based on correlation with the mean.
Does not standardize data for PCA due to underlying distribution of
beta values.
'''
try:
r = extract_pc(df - .5)
l, r, p = r['gene_vec'], r['pat_vec'], r['pct_var']
mean = df.mean(1)
if l.corr(mean) < 0:
l = l * -1
r = r * -1
return l, r, p
except:
r = df.mean()
return np.nan, r, np.nan
def run_clinical_real(cancer, clinical, data_path, gene_sets,
survival_tests, real_variables, binary_variables,
data_type='expression', drop_pc=False):
if data_type == 'expression':
data_matrix = read_rnaSeq(cancer, data_path)
data_matrix = data_matrix.groupby(by=lambda n: n.split('|')[0]).mean()
elif data_type == 'expression_array':
data_matrix = read_mrna(cancer, data_path)
elif data_type == 'methylation':
data_matrix = read_methylation(cancer, data_path)
if drop_pc:
data_matrix = drop_first_norm_pc(data_matrix)
pc = dict((p, extract_pc(data_matrix.ix[g])) for p, g in
gene_sets.iteritems())
pc = DataFrame(dict((p, (v - v.mean()) / v.std()) for p,v in pc.iteritems() if
type(v) != type(None))).T
#clinical['pc'] = extract_pc(data_matrix.dropna(), pc_threshold=0)
tests = get_tests(clinical, survival_tests, real_variables,
binary_variables, var_type='real')
#return locals()
p_pathways, q_pathways = run_tests(tests, pc)
return locals()
