def add_ds_ma(norm_exprs_file,
tax_id,
symbol_type,
pheno_file,
name,
normalization,
description,
xref):
name = get_or_guess_name(name, norm_exprs_file)
print("Adding microarray data set '%s' ..." % name)
from roger.persistence import db
import roger.logic.dge
import roger.persistence.dge
from roger.persistence.schema import MicroArrayDataSet
session = db.session()
print("Parsing and annotating data ...")
ds_prop = roger.logic.dge.create_ds(session,
MicroArrayDataSet,
norm_exprs_file,
tax_id,
symbol_type,
pheno_file,
name,
normalization,
description,
xref)
print("Persisting data set ...")
roger.persistence.dge.add_ds(session,
flask.current_app.config['ROGER_DATA_FOLDER'],
ds_prop)
print("Done - added data set with name '%s'" % name)
def add_design(session,
design_file,
dataset_name,
name=None,
description=None,
sample_groups_file=None,
sample_group_levels_file=None,
sample_group_pheno_column=None):
ds = get_ds(session, dataset_name)
name = get_or_guess_name(name, design_file)
design = query_design(session, name, dataset_name).one_or_none()
if design is not None:
raise ROGERUsageError(
"Design of data set '%s' with name '%s' already exist" %
(dataset_name, name))
design_data = create_design_data(
read_table(design_file, sep='\t',
index_col=0), ds.pheno_data, name, description,
read_array(sample_groups_file, nullable=True),
read_array(sample_group_levels_file, nullable=True),
sample_group_pheno_column)
design_data.design.DataSetID = ds.ID
session.add(design_data.design)
session.flush()
design_data.sample_subset["DesignID"] = design_data.design.ID
insert_data_frame(session, design_data.sample_subset,
SampleSubset.__table__)
session.commit()
return name
def add_contrast(session,
contrast_file,
design_name,
dataset_name,
name=None,
description=None):
design = get_design(session, design_name, dataset_name)
name = get_or_guess_name(name, contrast_file)
if query_contrast(session, name, design_name,
dataset_name).one_or_none() is not None:
raise ROGERUsageError("Contrast '%s' already exist in '%s'" %
(name, design_name))
contrast = Contrast(DesignID=design.ID,
Name=name,
Description=description,
CreatedBy=get_current_user_name(),
CreationTime=get_current_datetime())
session.add(contrast)
session.flush()
contrast_data = read_table(contrast_file, sep='\t', index_col=0)
check_contrast_matrix(design.design_matrix.columns, contrast_data)
contrast_cols = contrast_data.columns
contrast_table = DataFrame({
"ContrastID":
contrast.ID,
"DesignID":
design.ID,
"Name":
contrast_cols,
"Description":
contrast_cols,
"ColumnData": [
contrast_data[col_name].values.tolist()
for col_name in contrast_cols
]
})
insert_data_frame(session, contrast_table, ContrastColumn.__table__)
session.commit()
return name
def add_contrast(contrast_matrix,
design,
dataset,
name,
description):
name = get_or_guess_name(name, contrast_matrix)
print("Adding contrast '%s' to data set '%s' ..." % (name, dataset))
from roger.persistence import db
import roger.persistence.dge
name = roger.persistence.dge.add_contrast(db.session(),
contrast_matrix,
design,
dataset,
name,
description)
print("Done - added contrast with name '%s'" % name)
def add_design(design_matrix,
dataset,
name,
description,
sample_groups,
sample_group_levels,
sample_group_column):
name = get_or_guess_name(name, design_matrix)
print("Adding design '%s' to data set '%s' ..." % (name, dataset))
from roger.persistence import db
import roger.persistence.dge
name = roger.persistence.dge.add_design(db.session(),
design_matrix,
dataset,
name,
description,
sample_groups,
sample_group_levels,
sample_group_column)
print("Done - added design with name '%s'" % name)
def create_ds(session,
ds_type: Type[DataSet],
exprs_file,
tax_id,
symbol_type,
pheno_file=None,
name=None,
normalization_method=None,
description=None,
xref=None):
name = get_or_guess_name(name, exprs_file)
# Input checking
species_list = list_species(session)
if species_list[species_list.TaxID == tax_id].empty:
raise ROGERUsageError('Unknown taxon id: %s' % tax_id)
if session.query(DataSet).filter(
DataSet.Name == name).one_or_none() is not None:
raise ROGERUsageError("Data set with name '%s' already exists" % name)
exprs_data = parse_gct(file_path=exprs_file)
(annotation_data, annotation_version) = annotate(session, exprs_data,
tax_id, symbol_type)
pheno_data = pd.DataFrame()
if pheno_file is not None:
pheno_data = read_df(pheno_file)
annotated_pheno_data = annotate_ds_pheno_data(exprs_data, pheno_data)
return DataSetProperties(ds_type, tax_id, exprs_file, pheno_file,
exprs_data, annotated_pheno_data, annotation_data,
annotation_version, name, normalization_method,
description, xref)