def pca_agg_task_cv(exp, block,
train_es, test_es, gene_sets,
base_filename,
):
"""
@type train_es, test_es: ExpressionSet
@type gene_sets: GeneSets
"""
df_train = train_es.get_assay_data_frame()
df_test = test_es.get_assay_data_frame()
src_gs = gene_sets.get_gs()
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)
df_train, src_gs_train = preprocess_df_gs(df_train, src_gs)
df_test, src_gs_test = preprocess_df_gs(df_test, src_gs)
result_df_train, result_df_test = pca_agg_cv(df_train, df_test, src_gs_train.genes)
result_train = train_es.clone(base_filename + "_train")
result_train.store_assay_data_frame(result_df_train)
result_train.store_pheno_data_frame(train_es.get_pheno_data_frame())
result_test = test_es.clone(base_filename + "_test")
result_test.store_assay_data_frame(result_df_test)
result_test.store_pheno_data_frame(test_es.get_pheno_data_frame())
return [result_train, result_test], {}
def gt_basic(es, gene_sets, pheno_class_column,
model="logistic",
permutations=100):
"""
@param es: Expression set with defined user class in pheno
@type es: ExpressionSet
@type gene_sets: environment.structures.GeneSets
@param pheno_class_column: Column name of target classes in phenotype table
@type pheno_class_column: string or None
"""
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)
src_gs = gene_sets.get_gs()
# GlobalTest.gt_init()
df = es.get_assay_data_frame()
df, gs_filtered = preprocess_df_gs(df, src_gs)
dataset = com.convert_to_r_matrix(df.T)
response = es.get_pheno_column_as_r_obj(pheno_class_column)
ds_r = R.r['t'](dataset)
gs_r = gs_filtered.to_r_obj()
try:
R.r['library']("globaltest")
gt = R.r['gt']
gt_instance = gt(
response,
ds_r,
subsets=gs_r,
# model=model,
# permutations=permutations
)
except:
import sys
log.error("Unexpected error: %s" % sys.exc_info()[0])
raise
result = gt_instance.do_slot('result')
result_df = com.convert_robj(result)
return result_df
def pca_agg_task(exp, block,
es, gene_sets,
base_filename,
):
"""
@type es: ExpressionSet
@type gene_sets: GeneSets
"""
df = es.get_assay_data_frame()
src_gs = gene_sets.get_gs()
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)
df, src_gs = preprocess_df_gs(df, src_gs)
result_df = pca_agg(df, src_gs.genes)
result = es.clone(base_filename)
result.store_assay_data_frame(result_df)
result.store_pheno_data_frame(es.get_pheno_data_frame())
return [result], {}