def merge_comodules_task(
exp,
block,
cs_1,
cs_2,
cs_1_name,
cs_2_name,
base_filename,
):
if settings.CELERY_DEBUG:
import sys
sys.path.append(
'/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg'
)
import pydevd
pydevd.settrace('localhost',
port=6901,
stdoutToServer=True,
stderrToServer=True)
CS1 = cs_1.load_set()
CS2 = cs_2.load_set()
df = merge(CS1, CS2, left_index=True, right_index=True, how='outer')
df.columns = [cs_1_name, cs_2_name]
# df = CS1.join(CS2)
# df = pd.DataFrame({'genes':CS1.values, 'miRNAs':CS2.values}, index=CS1.index)
print(df.info())
cs = ComoduleSet(exp.get_data_folder(), base_filename)
cs.store_set(df)
return [cs], {}
def threshold_task(exp, block,
es,
T,
base_filename,
):
# def removeTemporaryNegativeFeatures(S, indicator_string = 'negative_feature___'):
# """Remove elements starting with the indicator_string and remove possible duplicates."""
# return S.apply(lambda list_element: set([s.replace(indicator_string, '') for s in list_element]))
"""Computes co-comodules from matrix H by given threshold T."""
if settings.CELERY_DEBUG:
import sys
sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg')
import pydevd
pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True)
H = es.get_assay_data_frame()
print(H)
# mu = np.mean(H, axis = 1)
# sigma = np.std(H, axis = 1)
# Z = H.apply(lambda z: (z-mu)/sigma, axis = 0)
# S = []
# S.append(removeTemporaryNegativeFeatures(Z.apply(lambda x: Z.columns[x >= T].tolist(), axis = 1)))
# S = pd.DataFrame(S)
# S = S.apply(lambda x: set.union(*x))
# result = pd.DataFrame(S)
from wrappers.snmnmf.evaluation import EnrichmentInGeneSets
z = 1
x = EnrichmentInGeneSets(z)
result = x.getGeneSet(H, T)
cs = ComoduleSet(exp.get_data_folder(), base_filename)
cs.store_set(result)
return [cs], {}
def merge_comodules_task(exp, block,
cs_1,
cs_2,
cs_1_name,
cs_2_name,
base_filename,
):
if settings.CELERY_DEBUG:
import sys
sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg')
import pydevd
pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True)
CS1 = cs_1.load_set()
CS2 = cs_2.load_set()
df = merge(CS1, CS2, left_index=True, right_index=True, how='outer')
df.columns = [cs_1_name, cs_2_name]
# df = CS1.join(CS2)
# df = pd.DataFrame({'genes':CS1.values, 'miRNAs':CS2.values}, index=CS1.index)
print(df.info())
cs = ComoduleSet(exp.get_data_folder(), base_filename)
cs.store_set(df)
return [cs], {}
def pattern_filter_task(exp, block,
m_rna_es,
mi_rna_es,
comodule_set,
metric,
n_best,
base_filename):
"""
@type m_rna_es: ExpressionSet
@type mi_rna_es: ExpressionSet
@type comodule_set: ComoduleSet
@type metric: metric
@type n_best: int
"""
if settings.CELERY_DEBUG:
import sys
sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg')
import pydevd
pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True)
mData = m_rna_es.get_assay_data_frame()
pheno = m_rna_es.get_pheno_data_frame()
classes = pheno['User_class'].values
data = mData
data.set_index(data.columns[0], inplace=True, drop=True)
# data = zscore(data)
com_set = comodule_set.load_set()
result = pattern_filter(com_set.values(), data, classes, n_best, metric)
result = {key: value for key, value in enumerate(result)}
cs = ComoduleSet(exp.get_data_folder(), base_filename)
cs.store_set(result)
return [cs], {}
def pattern_search(exp, block,
m_rna_es,
mi_rna_es,
gene2gene,
miRNA2gene,
# gene_platform,
# miRNA_platform,
radius,
min_imp,
metric,
base_filename):
"""
@type m_rna_es: ExpressionSet
@type mi_rna_es: ExpressionSet
@type gene2gene: BinaryInteraction
@type miRNA2gene: BinaryInteraction
@type radius: int
@type min_imp: double
"""
if settings.CELERY_DEBUG:
import sys
sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg')
import pydevd
pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True)
AllUpdated(
exp.pk,
comment=u"Initializing data...",
silent=False,
mode=NotifyMode.INFO
).send()
exp.log(block.uuid, "Initializing data...")
mData = m_rna_es.get_assay_data_frame()
gene_platform = list(mData.columns)
AllUpdated(
exp.pk,
comment=u"Transforming interaction matrix",
silent=False,
mode=NotifyMode.INFO
).send()
gene2gene = gene2gene.get_matrix_for_platform(exp, gene_platform)
AllUpdated(
exp.pk,
comment=u"Transforming interaction matrix done",
silent=False,
mode=NotifyMode.INFO
).send()
# TODO fix pattern search
# if miRNA2gene is not None:
# miRNA2gene = miRNA2gene.load_matrix().T
# miRNA2gene = sp.coo_matrix(miRNA2gene.values)
# if mi_rna_es is not None:
# miData = mi_rna_es.get_assay_data_frame()
# mir2gene = miRNA2gene
# mir2gene = sp.coo_matrix(mir2gene.values).T
# nw = mergeNetworks(gene2gene, mir2gene)
# else:
nw = gene2gene
# data = mData.ix[1:]
data = mData
data.set_index(data.columns[0], inplace=True, drop=True)
data = zscore(data)
pheno = m_rna_es.get_pheno_data_frame()
classes = pheno['User_class'].values
exp.log(block.uuid, "Data ready. Running Pattern Search")
# inicializace objektu metric=metric,
searcher = DifferentialPatternSearcher(nw, radius=radius, min_improve=min_imp,
base_dir="orig_interactions/", verbose=True)
#vlastni search
res = searcher.search(data, classes)
exp.log(block.uuid, "Pattern search finished.")
# res ... list patternu,
# tj. pro nase potreby:
comodule_set = map(lambda pattern: [gene_platform[gene] for gene in pattern.genes], res)
cs = ComoduleSet(exp.get_data_folder(), base_filename)
result = {key: value for key, value in enumerate(comodule_set)}
cs.store_set(result)
exp.log(block.uuid, "ComoduleSet stored.")
return [cs], {}
