def __init__(self, run, cancer, data_type, patients=None, drop_pc1=False,
create_real_features=True, create_meta_features=True,
filter_down=True, draw_figures=False):
'''
'''
Dataset.__init__(self, cancer.path, data_type, compressed=True)
self.df = IM.read_data(run.data_path, cancer.name, data_type,
tissue_code='All')
if patients is not None:
self.df = self.df.ix[:, patients].dropna(axis=1, how='all')
self.patients = patients
else:
self.patients = self.df.xs('01',1,1).columns
self.global_vars = pd.DataFrame(index=self.patients)
self.features = {}
self.global_loadings = pd.DataFrame(index=self.df.index)
self._calc_global_pcs(drop_pc1)
if create_real_features is True:
self._get_real_features()
if create_meta_features is True:
self._get_meta_features(run.gene_sets, filter_down)
self.features = pd.concat(self.features)
if draw_figures is True:
self._creat_pathway_figures()
def __init__(self, run, cancer, data_type, patients=None, drop_pc1=False,
create_real_features=True, create_meta_features=True,
filter_down=True, draw_figures=False):
'''
'''
Dataset.__init__(self, cancer.path, data_type, compressed=True)
self.df = IM.read_data(run.data_path, cancer.name, data_type,
tissue_code='All')
if patients is not None:
self.df = self.df.ix[:, patients].dropna(axis=1, how='all')
self.patients = patients
else:
self.patients = self.df.xs('01', 1, 1).columns
self.global_vars = pd.DataFrame(index=self.patients)
self.features = {}
self.global_loadings = pd.DataFrame(index=self.df.index)
self._calc_global_pcs(drop_pc1)
if create_real_features is True:
self._get_real_features()
if create_meta_features is True:
self._get_meta_features(run.gene_sets, filter_down)
self.features = pd.concat(self.features)
if draw_figures is True:
self._creat_pathway_figures()
def __init__(self, run, cancer, cn_type, patients=None):
Dataset.__init__(self, cancer.path, cn_type, compressed=False)
min_pat = run.parameters['min_patients']
if cn_type == 'CN_broad':
self.df = get_gistic(run.data_path, cancer.name,
min_patients=min_pat)
if patients is not None:
self.df = self.df.ix[:, patients].dropna(1, how='all')
self.features = self.df
def __init__(self, run, cancer, cn_type, patients=None):
'''
'''
Dataset.__init__(self, cancer.path, cn_type, compressed=False)
min_pat = run.parameters['min_patients']
if cn_type == 'CN_broad':
self.df = FH.get_gistic(run.data_path, cancer.name,
min_patients=min_pat)
if patients is not None:
self.df = self.df.ix[:, patients].dropna(1, how='all')
self.features = self.df
def __init__(self, run, cancer, patients=None,
create_features=True, draw_figures=False):
"""
"""
Dataset.__init__(self, cancer.path, 'Mutation', compressed=False)
self.df = FH.get_mutation_matrix(run.data_path, cancer.name)
if patients is not None:
self.df = self.df.ix[:, patients].dropna(1, how='all')
if create_features is True:
min_pat = run.parameters['min_patients']
self._create_feature_matrix(run.gene_sets, min_pat)
if draw_figures is True:
self._create_pathway_figures(run.gene_sets)
def __init__(self,
run,
cancer,
patients=None,
create_features=True,
draw_figures=False):
"""
"""
Dataset.__init__(self, cancer.path, 'Mutation', compressed=False)
self.df = FH.get_mutation_matrix(run.data_path, cancer.name)
if patients is not None:
self.df = self.df.ix[:, patients].dropna(1, how='all')
if create_features is True:
min_pat = run.parameters['min_patients']
self._create_feature_matrix(run.gene_sets, min_pat)
if draw_figures is True:
self._create_pathway_figures(run.gene_sets)
from pandas import Series, DataFrame
from matplotlib.pylab import savefig
import matplotlib.pyplot as plt
from Data.Containers import Dataset
from Reports.Figures import pathway_plot
report_path = sys.argv[1]
cancer_type = sys.argv[2]
data_type = 'MAF'
'''Load in run and mutation data'''
run = pickle.load(open(report_path + '/RunObject.p', 'rb'))
cancer = run.load_cancer(cancer_type)
mut = Dataset(cancer, run, data_type)
'''Create hit_matrix and meta_matrix, filter out genes for features'''
hit_matrix = mut.df.fillna(0).clip_upper(1.)
meta_matrix = DataFrame({p: mut.df.ix[g].sum() for p,g in
run.gene_sets.iteritems()}).T
meta_matrix = meta_matrix.fillna(0).clip_upper(1.)
def size_filter(s):
'''Make sure features covers a minimum number of patients'''
min_p = run.parameters['min_patients']
return s.sum(1).isin(range(min_p, meta_matrix.shape[1] - min_p))
def is_one_gene(p):
'''Test to see if most mutations are due to single gene'''
counts = hit_matrix.ix[run.gene_sets[p]].sum(1).dropna().order()
from Reports.Figures import pathway_plot
from Processing.Helpers import merge_redundant
report_path = sys.argv[1]
cancer_type = sys.argv[2]
data_type = sys.argv[3]
data_type = data_type[3:]
'''Load in run and CN data'''
run = pickle.load(open(report_path + '/RunObject.p', 'rb'))
cancer = run.load_cancer(cancer_type)
if data_type == 'broad':
data = Dataset(cancer, run, 'CN_broad')
data.features = data.df
data.save()
sys.exit(0)
data = Dataset(cancer, run, 'CN')
data.path = '_'.join([data.path, data_type])
if data_type == 'deletion':
data.hit_val = -2
elif data_type == 'amplification':
data.hit_val = 2
elif data_type == 'amplification_low':
data.df = data.df.replace(1,2)
data.hit_val = 2
