def __init__(self, config):
self.callback_url = config['SDK_CALLBACK_URL']
self.scratch = config['scratch']
self.token = config['KB_AUTH_TOKEN']
self.dfu = DataFileUtil(self.callback_url)
self.data_util = DataUtil(config)
self.matrix_types = [x.split(".")[1].split('-')[0]
for x in self.data_util.list_generic_types()]
def __init__(self, config):
self.callback_url = config['SDK_CALLBACK_URL']
self.scratch = config['scratch']
self.token = config['KB_AUTH_TOKEN']
self.dfu = DataFileUtil(self.callback_url)
self.data_util = DataUtil(config)
self.attr_util = AttributesUtil(config)
self.matrix_util = MatrixUtil(config)
self.matrix_types = [x.split(".")[1].split('-')[0]
for x in self.data_util.list_generic_types()]
self.taxon_wsname = config['taxon-workspace-name']
self.kbse = KBaseSearchEngine(config['search-url'])
def __init__(self, config):
self.ws_url = config["workspace-url"]
self.callback_url = config['SDK_CALLBACK_URL']
self.token = config['KB_AUTH_TOKEN']
self.shock_url = config['shock-url']
self.srv_wiz_url = config['srv-wiz-url']
self.scratch = config['scratch']
self.dfu = DataFileUtil(self.callback_url)
self.kbse = KBaseSearchEngine(config['search-url'])
self.data_util = DataUtil(config)
self.wsClient = workspaceService(self.ws_url, token=self.token)
self.DEFAULT_ONTOLOGY_ID = "Custom:Term"
self.DEFAULT_UNIT_ID = "Custom:Unit"
self.ONT_LABEL_DEL = " - "
self.ONT_TERM_DEL = ":"
def __init__(self, config):
self.ws_url = config["workspace-url"]
self.callback_url = config['SDK_CALLBACK_URL']
self.token = config['KB_AUTH_TOKEN']
self.scratch = config['scratch']
self.data_util = DataUtil(config)
self.dfu = DataFileUtil(self.callback_url)
plt.switch_backend('agg')
def __init__(self, config):
#BEGIN_CONSTRUCTOR
self.config = config
self.config['SDK_CALLBACK_URL'] = os.environ['SDK_CALLBACK_URL']
self.config['KB_AUTH_TOKEN'] = os.environ['KB_AUTH_TOKEN']
self.scratch = config['scratch']
self.attr_util = AttributesUtil(self.config)
self.matrix_util = MatrixUtil(self.config)
self.corr_util = CorrelationUtil(self.config)
self.data_util = DataUtil(self.config)
self.network_util = NetworkUtil(self.config)
self.biom_util = BiomUtil(self.config)
self.pca_util = PCAUtil(self.config)
self.data_table_util = DataTableUtil(self.config)
logging.basicConfig(format='%(created)s %(levelname)s: %(message)s',
level=logging.INFO)
#END_CONSTRUCTOR
pass
class MatrixUtil:
def _validate_import_matrix_from_excel_params(self, params):
"""
_validate_import_matrix_from_excel_params:
validates params passed to import_matrix_from_excel method
"""
logging.info('start validating import_matrix_from_excel params')
# check for required parameters
for p in ['obj_type', 'matrix_name', 'workspace_name', 'scale']:
if p not in params:
raise ValueError(
'"{}" parameter is required, but missing'.format(p))
obj_type = params.get('obj_type')
if obj_type not in self.matrix_types:
raise ValueError('Unknown matrix object type: {}'.format(obj_type))
scale = params.get('scale')
if scale not in SCALE_TYPES:
raise ValueError('Unknown scale type: {}'.format(scale))
if params.get('input_file_path'):
file_path = params.get('input_file_path')
elif params.get('input_shock_id'):
file_path = self.dfu.shock_to_file({
'shock_id':
params['input_shock_id'],
'file_path':
self.scratch
}).get('file_path')
elif params.get('input_staging_file_path'):
file_path = self.dfu.download_staging_file({
'staging_file_subdir_path':
params.get('input_staging_file_path')
}).get('copy_file_path')
else:
error_msg = "Must supply either a input_shock_id or input_file_path "
error_msg += "or input_staging_file_path"
raise ValueError(error_msg)
refs = {k: v for k, v in params.items() if "_ref" in k}
return (obj_type, file_path, params.get('workspace_name'),
params.get('matrix_name'), refs, scale)
def _upload_to_shock(self, file_path):
"""
_upload_to_shock: upload target file to shock using DataFileUtil
"""
logging.info('Start uploading file to shock: {}'.format(file_path))
file_to_shock_params = {'file_path': file_path, 'pack': 'zip'}
shock_id = self.dfu.file_to_shock(file_to_shock_params).get('shock_id')
return shock_id
@staticmethod
def _mkdir_p(path):
"""
_mkdir_p: make directory for given path
"""
if not path:
return
try:
os.makedirs(path)
except OSError as exc:
if exc.errno == errno.EEXIST and os.path.isdir(path):
pass
else:
raise
@staticmethod
def _find_between(s, start, end):
"""
_find_between: find string in between start and end
"""
return re.search('{}(.*){}'.format(start, end), s).group(1)
@staticmethod
def _write_mapping_sheet(file_path, sheet_name, mapping, index):
"""
_write_mapping_sheet: write mapping to sheet
"""
df_dict = collections.OrderedDict()
df_dict[index[0]] = []
df_dict[index[1]] = []
for key, value in mapping.items():
df_dict.get(index[0]).append(key)
df_dict.get(index[1]).append(value)
df = pd.DataFrame.from_dict(df_dict)
with pd.ExcelWriter(file_path, engine='openpyxl') as writer:
writer.book = load_workbook(file_path)
df.to_excel(writer, sheet_name=sheet_name)
def _generate_report(self, matrix_obj_ref, workspace_name):
"""
_generate_report: generate summary report
"""
report_params = {
'message':
'',
'objects_created': [{
'ref': matrix_obj_ref,
'description': 'Imported Matrix'
}],
'workspace_name':
workspace_name,
'report_object_name':
'import_matrix_from_excel_' + str(uuid.uuid4())
}
kbase_report_client = KBaseReport(self.callback_url, token=self.token)
output = kbase_report_client.create_extended_report(report_params)
report_output = {
'report_name': output['name'],
'report_ref': output['ref']
}
return report_output
@staticmethod
def _process_mapping_sheet(file_path, sheet_name):
"""
_process_mapping: process mapping sheet
"""
try:
df = pd.read_excel(file_path, sheet_name=sheet_name, dtype='str')
except XLRDError:
return dict()
else:
mapping = {value[0]: value[1] for value in df.values.tolist()}
return mapping
def _process_attribute_mapping_sheet(self, file_path, sheet_name,
matrix_name, workspace_id):
"""
_process_attribute_mapping_sheet: process attribute_mapping sheet
"""
try:
df = pd.read_excel(file_path, sheet_name=sheet_name)
except XLRDError:
return ''
else:
obj_name = f'{matrix_name}_{sheet_name}'
result_directory = os.path.join(self.scratch, str(uuid.uuid4()))
self._mkdir_p(result_directory)
file_path = os.path.join(result_directory,
'{}.xlsx'.format(obj_name))
df.to_excel(file_path)
import_attribute_mapping_params = {
'output_obj_name': obj_name,
'output_ws_id': workspace_id,
'input_file_path': file_path
}
ref = self.attr_util.file_to_attribute_mapping(
import_attribute_mapping_params)
return ref.get('attribute_mapping_ref')
@staticmethod
def _file_to_df(file_path):
logging.info('start parsing file content to data frame')
try:
df = pd.read_excel(file_path, sheet_name='data', index_col=0)
except XLRDError:
try:
df = pd.read_excel(file_path, index_col=0)
logging.warning(
'WARNING: A sheet named "data" was not found in the attached file,'
' proceeding with the first sheet as the data sheet.')
except XLRDError:
try:
reader = pd.read_csv(file_path, sep=None, iterator=True)
inferred_sep = reader._engine.data.dialect.delimiter
df = pd.read_csv(file_path, sep=inferred_sep, index_col=0)
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide tsv, excel or csv file'
)
df.index = df.index.astype('str')
df.columns = df.columns.astype('str')
# fill NA with "None" so that they are properly represented as nulls in the KBase Object
df = df.where((pd.notnull(df)), None)
return df
def _file_to_data(self, file_path, refs, matrix_name, workspace_id):
logging.info('Start reading and converting excel file data')
data = refs
df = self._file_to_df(file_path)
matrix_data = {
'row_ids': df.index.tolist(),
'col_ids': df.columns.tolist(),
'values': df.values.tolist()
}
data.update({'data': matrix_data})
data.update(
self._get_axis_attributes('col', matrix_data, refs, file_path,
matrix_name, workspace_id))
data.update(
self._get_axis_attributes('row', matrix_data, refs, file_path,
matrix_name, workspace_id))
# processing metadata
metadata = self._process_mapping_sheet(file_path, 'metadata')
data['attributes'] = {}
data['search_attributes'] = []
for k, v in metadata.items():
k = k.strip()
v = v.strip()
if k in TYPE_ATTRIBUTES:
data[k] = v
else:
data['attributes'][k] = v
data['search_attributes'].append(" | ".join((k, v)))
return data
def _get_axis_attributes(self, axis, matrix_data, refs, file_path,
matrix_name, workspace_id):
"""Get the row/col_attributemapping and mapping of ids, validating as needed"""
# Parameter specified mappings should take precedence over tabs in excel so only process
# if attributemapping_ref is missing:
attr_data = {}
if refs.get(f'{axis}_attributemapping_ref'):
attributemapping_ref = refs[f'{axis}_attributemapping_ref']
else:
attributemapping_ref = self._process_attribute_mapping_sheet(
file_path, f'{axis}_attribute_mapping', matrix_name,
workspace_id)
if attributemapping_ref:
attr_data[f'{axis}_attributemapping_ref'] = attributemapping_ref
# col/row_mappings may not be supplied
id_mapping = self._process_mapping_sheet(file_path, f'{axis}_mapping')
if id_mapping:
attr_data[f'{axis}_mapping'] = id_mapping
# if no mapping, axis ids must match the attribute mapping
elif attributemapping_ref:
am_data = self.dfu.get_objects(
{'object_refs': [attributemapping_ref]})['data'][0]['data']
axis_ids = matrix_data[f'{axis}_ids']
unmatched_ids = set(axis_ids) - set(am_data['instances'].keys())
if unmatched_ids:
name = "Column" if axis == 'col' else "Row"
raise ValueError(
f"The following {name} IDs from the uploaded matrix do not match "
f"the supplied {name} attribute mapping: {', '.join(unmatched_ids)}"
f"\nPlease verify the input data or upload an excel file with a"
f"{name} mapping tab.")
else:
# just gen the IDs in this matrix
attr_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
return attr_data
@staticmethod
def _build_header_str(attribute_names): #not going to be used
header_str = ''
width = 100.0 / len(attribute_names)
header_str += '<tr class="header">'
header_str += '<th style="width:{0:.2f}%;">Feature ID</th>'.format(
width)
for attribute_name in attribute_names:
header_str += '<th style="width:{0:.2f}%;"'.format(width)
header_str += '>{}</th>'.format(attribute_name)
header_str += '</tr>'
return header_str
def _build_html_str(self, row_mapping, attributemapping_data,
row_ids): #not going to be used
logging.info('Start building html replacement')
attribute_names = [
attributes.get('attribute')
for attributes in attributemapping_data.get('attributes')
]
header_str = self._build_header_str(attribute_names)
table_str = ''
instances = attributemapping_data.get('instances')
for feature_id, attribute_id in row_mapping.items():
if feature_id in row_ids:
feature_instances = instances.get(attribute_id)
table_str += '<tr>'
table_str += '<td>{}</td>'.format(feature_id)
for feature_instance in feature_instances:
table_str += '<td>{}</td>'.format(feature_instance)
table_str += '</tr>'
return header_str, table_str
def _generate_search_html_report(self, header_str,
table_str): #generate search html report
html_report = list()
output_directory = os.path.join(self.scratch, str(uuid.uuid4()))
self._mkdir_p(output_directory)
result_file_path = os.path.join(output_directory, 'search.html')
shutil.copy2(
os.path.join(os.path.dirname(__file__), 'templates',
'kbase_icon.png'), output_directory)
shutil.copy2(
os.path.join(os.path.dirname(__file__), 'templates',
'search_icon.png'), output_directory)
with open(result_file_path, 'w') as result_file:
with open(
os.path.join(os.path.dirname(__file__), 'templates',
'search_template.html'),
'r') as report_template_file:
report_template = report_template_file.read()
report_template = report_template.replace(
'//HEADER_STR', header_str)
report_template = report_template.replace(
'//TABLE_STR', table_str)
result_file.write(report_template)
report_shock_id = self.dfu.file_to_shock({
'file_path': output_directory,
'pack': 'zip'
})['shock_id']
html_report.append({
'shock_id':
report_shock_id,
'name':
os.path.basename(result_file_path),
'label':
os.path.basename(result_file_path),
'description':
'HTML summary report for Search Matrix App'
})
return html_report
def _generate_search_report(self, header_str, table_str, workspace_name):
logging.info('Start creating report')
output_html_files = self._generate_search_html_report(
header_str, table_str)
report_params = {
'message': '',
'workspace_name': workspace_name,
'html_links': output_html_files,
'direct_html_link_index': 0,
'html_window_height': 366,
'report_object_name':
'kb_matrix_filter_report_' + str(uuid.uuid4())
}
kbase_report_client = KBaseReport(self.callback_url, token=self.token)
output = kbase_report_client.create_extended_report(report_params)
report_output = {
'report_name': output['name'],
'report_ref': output['ref']
}
return report_output
@staticmethod
def _filter_value_data(value_data, remove_ids, dimension):
"""Filters a value matrix based on column or row ids"""
def _norm_id(_id):
return _id.replace(" ", "_")
val_df = pd.DataFrame(value_data['values'],
index=value_data['row_ids'],
columns=value_data['col_ids'],
dtype='object')
if dimension == 'row':
filtered_df = val_df.drop(remove_ids, axis=0, errors='ignore')
filtered_df = filtered_df.drop([_norm_id(x) for x in remove_ids],
axis=0,
errors='ignore')
elif dimension == 'col':
filtered_df = val_df.drop(remove_ids, axis=1, errors='ignore')
filtered_df = filtered_df.drop([_norm_id(x) for x in remove_ids],
axis=1,
errors='ignore')
else:
raise ValueError('Unexpected dimension: {}'.format(dimension))
filtered_value_data = {
"values": filtered_df.values.tolist(),
"col_ids": list(filtered_df.columns),
"row_ids": list(filtered_df.index),
}
return filtered_value_data
def _standardize_df(self, df, with_mean=True, with_std=True):
logging.info("Standardizing matrix data")
df.fillna(0, inplace=True)
x_train = df.values
scaler = preprocessing.StandardScaler(with_mean=with_mean,
with_std=with_std).fit(x_train)
standardized_values = scaler.transform(x_train)
standardize_df = pd.DataFrame(index=df.index,
columns=df.columns,
data=standardized_values)
return standardize_df
def __init__(self, config):
self.callback_url = config['SDK_CALLBACK_URL']
self.scratch = config['scratch']
self.token = config['KB_AUTH_TOKEN']
self.dfu = DataFileUtil(self.callback_url)
self.data_util = DataUtil(config)
self.attr_util = AttributesUtil(config)
self.matrix_types = [
x.split(".")[1].split('-')[0]
for x in self.data_util.list_generic_types()
]
def standardize_matrix(self, params):
"""
standardize a matrix
"""
input_matrix_ref = params.get('input_matrix_ref')
workspace_name = params.get('workspace_name')
new_matrix_name = params.get('new_matrix_name')
with_mean = params.get('with_mean', 1)
with_std = params.get('with_std', 1)
if not isinstance(workspace_name, int):
workspace_id = self.dfu.ws_name_to_id(workspace_name)
else:
workspace_id = workspace_name
input_matrix_obj = self.dfu.get_objects(
{'object_refs': [input_matrix_ref]})['data'][0]
input_matrix_info = input_matrix_obj['info']
input_matrix_name = input_matrix_info[1]
input_matrix_data = input_matrix_obj['data']
if not new_matrix_name:
current_time = time.localtime()
new_matrix_name = input_matrix_name + time.strftime(
'_%H_%M_%S_%Y_%m_%d', current_time)
data_matrix = self.data_util.fetch_data({
'obj_ref': input_matrix_ref
}).get('data_matrix')
df = pd.read_json(data_matrix)
standardize_df = self._standardize_df(df, with_mean, with_std)
new_matrix_data = {
'row_ids': df.index.tolist(),
'col_ids': df.columns.tolist(),
'values': standardize_df.values.tolist()
}
input_matrix_data['data'] = new_matrix_data
logging.info("Saving new standardized matrix object")
info = self.dfu.save_objects({
"id":
workspace_id,
"objects": [{
"type": input_matrix_info[2],
"data": input_matrix_data,
"name": new_matrix_name
}]
})[0]
new_matrix_obj_ref = "%s/%s/%s" % (info[6], info[0], info[4])
objects_created = [{
'ref': new_matrix_obj_ref,
'description': 'Standardized Matrix'
}]
report_params = {
'message': '',
'objects_created': objects_created,
'workspace_name': workspace_name,
'report_object_name':
'import_matrix_from_biom_' + str(uuid.uuid4())
}
kbase_report_client = KBaseReport(self.callback_url, token=self.token)
output = kbase_report_client.create_extended_report(report_params)
return {
'new_matrix_obj_ref': new_matrix_obj_ref,
'report_name': output['name'],
'report_ref': output['ref']
}
def filter_matrix(self, params): #not going to be used
"""
filter_matrix: create sub-matrix based on input feature_ids
arguments:
matrix_obj_ref: object reference of a matrix
workspace_name: workspace name
feature_ids: string of feature ids that result matrix contains
filtered_matrix_name: name of newly created filtered matrix object
"""
matrix_obj_ref = params.get('matrix_obj_ref')
workspace_name = params.get('workspace_name')
remove_ids = params.get('remove_ids')
dimension = params.get('dimension')
filtered_matrix_name = params.get('filtered_matrix_name')
matrix_source = self.dfu.get_objects({"object_refs":
[matrix_obj_ref]})['data'][0]
matrix_info = matrix_source.get('info')
matrix_data = matrix_source.get('data')
matrix_type = self._find_between(matrix_info[2], '\.', '\-')
value_data = matrix_data.get('data')
remove_ids = [x.strip() for x in remove_ids.split(',')]
filtered_value_data = self._filter_value_data(value_data, remove_ids,
dimension)
# if the matrix has changed shape, update the mappings
if len(filtered_value_data['row_ids']) < len(
matrix_data['data']['row_ids']):
if matrix_data.get('row_mapping'):
matrix_data['row_mapping'] = {
k: matrix_data['row_mapping'][k]
for k in filtered_value_data['row_ids']
}
if matrix_data.get('feature_mapping'):
matrix_data['feature_mapping'] = {
k: matrix_data['feature_mapping'][k]
for k in filtered_value_data['row_ids']
}
if len(filtered_value_data['col_ids']) < len(
matrix_data['data']['col_ids']):
if matrix_data.get('col_mapping'):
matrix_data['col_mapping'] = {
k: matrix_data['col_mapping'][k]
for k in filtered_value_data['col_ids']
}
matrix_data['data'] = filtered_value_data
if not isinstance(workspace_name, int):
workspace_id = self.dfu.ws_name_to_id(workspace_name)
else:
workspace_id = workspace_name
filtered_matrix_obj_ref = self.data_util.save_object({
'obj_type':
'KBaseMatrices.{}'.format(matrix_type),
'obj_name':
filtered_matrix_name,
'data':
matrix_data,
'workspace_name':
workspace_id
})['obj_ref']
returnVal = {'matrix_obj_refs': [filtered_matrix_obj_ref]}
report_output = self._generate_report(filtered_matrix_obj_ref,
workspace_name)
returnVal.update(report_output)
return returnVal
def search_matrix(self, params): #not going to be used
"""
search_matrix: generate a HTML report that allows users to select feature ids
arguments:
matrix_obj_ref: object reference of a matrix
workspace_name: workspace name
"""
matrix_obj_ref = params.get('matrix_obj_ref')
workspace_name = params.get('workspace_name')
matrix_source = self.dfu.get_objects({"object_refs":
[matrix_obj_ref]})['data'][0]
matrix_data = matrix_source.get('data')
row_mapping = matrix_data.get('row_mapping')
row_attributemapping_ref = matrix_data.get('row_attributemapping_ref')
row_ids = matrix_data['data']['row_ids']
if not (row_mapping and row_attributemapping_ref):
raise ValueError(
'Matrix obejct is missing either row_mapping or row_attributemapping_ref'
)
attributemapping_data = self.dfu.get_objects(
{"object_refs": [row_attributemapping_ref]})['data'][0]['data']
header_str, table_str = self._build_html_str(row_mapping,
attributemapping_data,
row_ids)
returnVal = self._generate_search_report(header_str, table_str,
workspace_name)
return returnVal
def import_matrix_from_excel(self, params):
"""
import_matrix_from_excel: import matrix object from excel
arguments:
obj_type: one of ExpressionMatrix, FitnessMatrix, DifferentialExpressionMatrix
matrix_name: matrix object name
workspace_name: workspace name matrix object to be saved to
input_shock_id: file shock id
or
input_file_path: absolute file path
or
input_staging_file_path: staging area file path
optional arguments:
col_attributemapping_ref: column AttributeMapping reference
row_attributemapping_ref: row AttributeMapping reference
genome_ref: genome reference
matrix_obj_ref: Matrix reference
"""
(obj_type, file_path, workspace_name, matrix_name, refs,
scale) = self._validate_import_matrix_from_excel_params(params)
if not isinstance(workspace_name, int):
workspace_id = self.dfu.ws_name_to_id(workspace_name)
else:
workspace_id = workspace_name
data = self._file_to_data(file_path, refs, matrix_name, workspace_id)
data['scale'] = scale
if params.get('description'):
data['description'] = params['description']
matrix_obj_ref = self.data_util.save_object({
'obj_type':
'KBaseMatrices.{}'.format(obj_type),
'obj_name':
matrix_name,
'data':
data,
'workspace_name':
workspace_id
})['obj_ref']
returnVal = {'matrix_obj_ref': matrix_obj_ref}
report_output = self._generate_report(matrix_obj_ref, workspace_name)
returnVal.update(report_output)
return returnVal
def export_matrix(self, params):
"""
export_matrix: univeral downloader for matrix data object
arguments:
obj_ref: generics object reference
optional arguments:
generics_module: select the generics data to be retrieved from
e.g. for an given data type like below:
typedef structure {
FloatMatrix2D data;
condition_set_ref condition_set_ref;
} SomeGenericsMatrix;
and only data is needed
generics_module should be
{'data': 'FloatMatrix2D'}
"""
logging.info('Start exporting matrix')
if 'input_ref' in params:
params['obj_ref'] = params.pop('input_ref')
obj_source = self.dfu.get_objects(
{"object_refs": [params.get('obj_ref')]})['data'][0]
obj_data = obj_source.get('data')
result_directory = os.path.join(self.scratch, str(uuid.uuid4()))
self._mkdir_p(result_directory)
file_path = os.path.join(result_directory,
'{}.xlsx'.format(obj_source.get('info')[1]))
data_matrix = self.data_util.fetch_data(params).get('data_matrix')
df = pd.read_json(data_matrix)
df.to_excel(file_path, sheet_name='data')
if obj_data.get('col_mapping'):
self._write_mapping_sheet(file_path, 'col_mapping',
obj_data.get('col_mapping'),
['col_name', 'instance_name'])
obj_data.pop('col_mapping')
if obj_data.get('row_mapping'):
self._write_mapping_sheet(file_path, 'row_mapping',
obj_data.get('row_mapping'),
['row_name', 'instance_name'])
obj_data.pop('row_mapping')
try:
obj_data.pop('data')
except KeyError:
logging.warning('Missing key [data]')
obj_data.update(obj_data.get('attributes', {})) # flatten for printing
self._write_mapping_sheet(file_path, 'metadata', obj_data,
['name', 'value'])
shock_id = self._upload_to_shock(file_path)
return {'shock_id': shock_id}
class BiomUtil:
def _mkdir_p(self, path):
"""
_mkdir_p: make directory for given path
"""
if not path:
return
try:
os.makedirs(path)
except OSError as exc:
if exc.errno == errno.EEXIST and os.path.isdir(path):
pass
else:
raise
def _process_params(self, params):
logging.info('start validating import_matrix_from_biom params')
# check for required parameters
for p in [
'obj_type', 'matrix_name', 'workspace_id', 'scale',
'amplicon_type', 'sequencing_technology',
'sequencing_instrument', 'target_gene', 'target_subfragment',
'taxon_calling'
]:
if p not in params:
raise ValueError(
'"{}" parameter is required, but missing'.format(p))
# check sequencing_technology and sequencing_instrument matching
sequencing_technology = params.get('sequencing_technology')
sequencing_instrument = params.get('sequencing_instrument')
if sequencing_technology not in SEQ_INSTRUMENTS_MAP:
raise ValueError('Unexpected sequencing technology: {}'.format(
sequencing_technology))
expected_instruments = SEQ_INSTRUMENTS_MAP.get(sequencing_technology)
if sequencing_instrument not in expected_instruments:
raise ValueError(
'Please select sequencing instrument among {} for {}'.format(
expected_instruments, sequencing_technology))
# check target_gene and target_subfragment matching
target_gene = params.get('target_gene')
target_subfragment = list(set(params.get('target_subfragment')))
params['target_subfragment'] = target_subfragment
if target_gene not in TARGET_GENE_SUBFRAGMENT_MAP:
raise ValueError('Unexpected target gene: {}'.format(target_gene))
expected_subfragments = TARGET_GENE_SUBFRAGMENT_MAP.get(target_gene)
if not set(target_subfragment) <= set(expected_subfragments):
raise ValueError(
'Please select target subfragments among {} for {}'.format(
expected_subfragments, target_gene))
# check taxon_calling
taxon_calling = params.get('taxon_calling')
taxon_calling_method = list(
set(taxon_calling.get('taxon_calling_method')))
params['taxon_calling_method'] = taxon_calling_method
if 'denoising' in taxon_calling_method:
denoise_method = taxon_calling.get('denoise_method')
sequence_error_cutoff = taxon_calling.get('sequence_error_cutoff')
if not (denoise_method and sequence_error_cutoff):
raise ValueError(
'Please provide denoise_method and sequence_error_cutoff')
params['denoise_method'] = denoise_method
params['sequence_error_cutoff'] = sequence_error_cutoff
if 'clustering' in taxon_calling_method:
clustering_method = taxon_calling.get('clustering_method')
clustering_cutoff = taxon_calling.get('clustering_cutoff')
if not (clustering_method and clustering_cutoff):
raise ValueError(
'Please provide clustering_method and clustering_cutoff')
params['clustering_method'] = clustering_method
params['clustering_cutoff'] = clustering_cutoff
obj_type = params.get('obj_type')
if obj_type not in self.matrix_types:
raise ValueError('Unknown matrix object type: {}'.format(obj_type))
scale = params.get('scale')
if scale not in SCALE_TYPES:
raise ValueError('Unknown scale type: {}'.format(scale))
biom_file = None
tsv_file = None
fasta_file = None
metadata_keys = DEFAULT_META_KEYS
input_local_file = params.get('input_local_file', False)
if params.get('taxonomic_abundance_tsv') and params.get(
'taxonomic_fasta'):
tsv_file = params.get('taxonomic_abundance_tsv')
fasta_file = params.get('taxonomic_fasta')
if not (tsv_file and fasta_file):
raise ValueError('missing TSV or FASTA file')
if not input_local_file:
tsv_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
tsv_file
}).get('copy_file_path')
fasta_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
fasta_file
}).get('copy_file_path')
metadata_keys_str = params.get('metadata_keys')
if metadata_keys_str:
metadata_keys += [
x.strip() for x in metadata_keys_str.split(',')
]
mode = 'tsv_fasta'
elif params.get('biom_fasta'):
biom_fasta = params.get('biom_fasta')
biom_file = biom_fasta.get('biom_file_biom_fasta')
fasta_file = biom_fasta.get('fasta_file_biom_fasta')
if not (biom_file and fasta_file):
raise ValueError('missing BIOM or FASTA file')
if not input_local_file:
biom_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
biom_file
}).get('copy_file_path')
fasta_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
fasta_file
}).get('copy_file_path')
mode = 'biom_fasta'
elif params.get('tsv_fasta'):
tsv_fasta = params.get('tsv_fasta')
tsv_file = tsv_fasta.get('tsv_file_tsv_fasta')
fasta_file = tsv_fasta.get('fasta_file_tsv_fasta')
if not (tsv_file and fasta_file):
raise ValueError('missing TSV or FASTA file')
if not input_local_file:
tsv_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
tsv_file
}).get('copy_file_path')
fasta_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
fasta_file
}).get('copy_file_path')
metadata_keys_str = tsv_fasta.get('metadata_keys_tsv_fasta')
if metadata_keys_str:
metadata_keys += [
x.strip() for x in metadata_keys_str.split(',')
]
mode = 'tsv_fasta'
else:
raise ValueError('missing valide file group type in parameters')
return (biom_file, tsv_file, fasta_file, mode,
list(set(metadata_keys)))
def _validate_fasta_file(self, df, fasta_file):
logging.info('start validating FASTA file')
try:
fastq_dict = SeqIO.index(fasta_file, "fasta")
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide FASTA file')
matrix_ids = df.index
file_ids = fastq_dict.keys()
unmatched_ids = set(matrix_ids) - set(file_ids)
if unmatched_ids:
raise ValueError(
'FASTA file does not have [{}] OTU id'.format(unmatched_ids))
def _file_to_amplicon_data(self,
biom_file,
tsv_file,
fasta_file,
mode,
refs,
matrix_name,
workspace_id,
scale,
description,
metadata_keys=None):
amplicon_data = refs
if mode.startswith('biom'):
logging.info('start parsing BIOM file for matrix data')
table = biom.load_table(biom_file)
observation_metadata = table._observation_metadata
sample_metadata = table._sample_metadata
matrix_data = {
'row_ids': table._observation_ids.tolist(),
'col_ids': table._sample_ids.tolist(),
'values': table.matrix_data.toarray().tolist()
}
logging.info('start building attribute mapping object')
amplicon_data.update(
self.get_attribute_mapping("row", observation_metadata,
matrix_data, matrix_name, refs,
workspace_id))
amplicon_data.update(
self.get_attribute_mapping("col", sample_metadata, matrix_data,
matrix_name, refs, workspace_id))
amplicon_data['attributes'] = {}
for k in ('create_date', 'generated_by'):
val = getattr(table, k)
if not val:
continue
if isinstance(val, bytes):
amplicon_data['attributes'][k] = val.decode('utf-8')
else:
amplicon_data['attributes'][k] = str(val)
elif mode.startswith('tsv'):
observation_metadata = None
sample_metadata = None
try:
logging.info('start parsing TSV file for matrix data')
reader = pd.read_csv(tsv_file, sep=None, iterator=True)
inferred_sep = reader._engine.data.dialect.delimiter
df = pd.read_csv(tsv_file, sep=inferred_sep, index_col=0)
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide tsv file')
else:
self._validate_fasta_file(df, fasta_file)
metadata_df = None
if metadata_keys:
shared_metadata_keys = list(
set(metadata_keys) & set(df.columns))
if mode == 'tsv' and 'consensus_sequence' not in shared_metadata_keys:
raise ValueError(
'TSV file does not include consensus_sequence')
if shared_metadata_keys:
metadata_df = df[shared_metadata_keys]
df.drop(columns=shared_metadata_keys, inplace=True)
try:
df = df.astype(float)
except ValueError:
err_msg = 'Found some non-float values. Matrix contains only numeric values\n'
err_msg += 'Please list any non-numeric column names in Metadata Keys field'
raise ValueError(err_msg)
df.fillna(0, inplace=True)
df.index = df.index.astype('str')
df.columns = df.columns.astype('str')
matrix_data = {
'row_ids': df.index.tolist(),
'col_ids': df.columns.tolist(),
'values': df.values.tolist()
}
logging.info('start building attribute mapping object')
amplicon_data.update(
self.get_attribute_mapping("row",
observation_metadata,
matrix_data,
matrix_name,
refs,
workspace_id,
metadata_df=metadata_df))
amplicon_data.update(
self.get_attribute_mapping("col", sample_metadata, matrix_data,
matrix_name, refs, workspace_id))
amplicon_data['attributes'] = {}
else:
raise ValueError(
'error parsing _file_to_amplicon_data, mode: {}'.format(mode))
amplicon_data.update({'data': matrix_data})
amplicon_data['search_attributes'] = [
f'{k}|{v}' for k, v in amplicon_data['attributes'].items()
]
amplicon_data['scale'] = scale
if description:
amplicon_data['description'] = description
return amplicon_data
def get_attribute_mapping(self,
axis,
metadata,
matrix_data,
matrix_name,
refs,
workspace_id,
metadata_df=None):
mapping_data = {}
axis_ids = matrix_data[f'{axis}_ids']
if refs.get('sample_set_ref') and axis == 'col':
name = matrix_name + "_{}_attributes".format(axis)
mapping_data[
f'{axis}_attributemapping_ref'] = self._sample_set_to_attribute_mapping(
axis_ids, refs.get('sample_set_ref'), name, workspace_id)
mapping_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
elif refs.get(f'{axis}_attributemapping_ref'):
am_data = self.dfu.get_objects(
{'object_refs':
[refs[f'{axis}_attributemapping_ref']]})['data'][0]['data']
unmatched_ids = set(axis_ids) - set(am_data['instances'].keys())
if unmatched_ids:
name = "Column" if axis == 'col' else "Row"
raise ValueError(
f"The following {name} IDs from the uploaded matrix do not match "
f"the supplied {name} attribute mapping: {', '.join(unmatched_ids)}"
f"\nPlease verify the input data or upload an excel file with a"
f"{name} mapping tab.")
else:
mapping_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
elif metadata:
name = matrix_name + "_{}_attributes".format(axis)
mapping_data[
f'{axis}_attributemapping_ref'] = self._metadata_to_attribute_mapping(
axis_ids, metadata, name, workspace_id)
# if coming from biom file, metadata and axis IDs are guaranteed to match
mapping_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
elif metadata_df is not None:
name = matrix_name + "_{}_attributes".format(axis)
mapping_data[
f'{axis}_attributemapping_ref'] = self._meta_df_to_attribute_mapping(
axis_ids, metadata_df, name, workspace_id)
mapping_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
return mapping_data
def _meta_df_to_attribute_mapping(self, axis_ids, metadata_df, obj_name,
ws_id):
data = {'ontology_mapping_method': "TSV file", 'instances': {}}
metadata_df = metadata_df.astype(str)
attribute_keys = metadata_df.columns.tolist()
data['attributes'] = [{
'attribute': key,
'source': 'upload'
} for key in attribute_keys]
if 'taxonomy' in attribute_keys:
data['attributes'].append({
'attribute': 'parsed_user_taxonomy',
'source': 'upload'
})
for axis_id in axis_ids:
data['instances'][axis_id] = metadata_df.loc[axis_id].tolist()
if 'taxonomy' in attribute_keys:
parsed_user_taxonomy = None
taxonomy_index = attribute_keys.index('taxonomy')
taxonomy_str = metadata_df.loc[axis_id].tolist(
)[taxonomy_index]
parsed_user_taxonomy = self.taxon_util.process_taxonomic_str(
taxonomy_str)
data['instances'][axis_id].append(parsed_user_taxonomy)
logging.info(
'start saving AttributeMapping object: {}'.format(obj_name))
info = self.dfu.save_objects({
"id":
ws_id,
"objects": [{
"type": "KBaseExperiments.AttributeMapping",
"data": data,
"name": obj_name
}]
})[0]
return f'{info[6]}/{info[0]}/{info[4]}'
def _sample_set_to_attribute_mapping(self, axis_ids, sample_set_ref,
obj_name, ws_id):
am_data = self.sampleservice_util.sample_set_to_attribute_mapping(
sample_set_ref)
unmatched_ids = set(axis_ids) - set(am_data['instances'].keys())
if unmatched_ids:
name = "Column"
raise ValueError(
f"The following {name} IDs from the uploaded matrix do not match "
f"the supplied {name} attribute mapping: {', '.join(unmatched_ids)}"
f"\nPlease verify the input data or upload an excel file with a"
f"{name} mapping tab.")
logging.info(
'start saving AttributeMapping object: {}'.format(obj_name))
info = self.dfu.save_objects({
"id":
ws_id,
"objects": [{
"type": "KBaseExperiments.AttributeMapping",
"data": am_data,
"name": obj_name
}]
})[0]
return f'{info[6]}/{info[0]}/{info[4]}'
def _metadata_to_attribute_mapping(self, instances, metadata, obj_name,
ws_id):
data = {'ontology_mapping_method': "BIOM file", 'instances': {}}
sample_set = metadata[0:min(len(metadata), 25)]
metadata_keys = sorted(
set((k for m_dict in sample_set for k in m_dict)))
data['attributes'] = [{
'attribute': key,
'source': 'upload'
} for key in metadata_keys]
for inst, meta in zip(instances, metadata):
data['instances'][inst] = [
str(meta[attr]) for attr in metadata_keys
]
logging.info(
'start saving AttributeMapping object: {}'.format(obj_name))
info = self.dfu.save_objects({
"id":
ws_id,
"objects": [{
"type": "KBaseExperiments.AttributeMapping",
"data": data,
"name": obj_name
}]
})[0]
return f'{info[6]}/{info[0]}/{info[4]}'
def _generate_visualization_content(self, output_directory, heatmap_dir,
data_df, top_heatmap_dir, top_percent,
display_count):
row_data_summary = data_df.T.describe().round(2).to_string()
col_data_summary = data_df.describe().round(2).to_string()
tab_def_content = ''
tab_content = ''
viewer_name = 'data_summary'
tab_def_content += '''\n<div class="tab">\n'''
tab_def_content += '''\n<button class="tablinks" '''
tab_def_content += '''onclick="openTab(event, '{}')"'''.format(
viewer_name)
tab_def_content += ''' id="defaultOpen"'''
tab_def_content += '''>Matrix Statistics</button>\n'''
tab_content += '''\n<div id="{}" class="tabcontent" style="overflow:auto">'''.format(
viewer_name)
tab_content += '''\n<h5>Amplicon Matrix Size: {} x {}</h5>'''.format(
len(data_df.index), len(data_df.columns))
tab_content += '''\n<h5>Row Aggregating Statistics</h5>'''
html = '''\n<pre class="tab">''' + str(row_data_summary).replace(
"\n", "<br>") + "</pre>"
tab_content += html
tab_content += '''\n<br>'''
tab_content += '''\n<hr style="height:2px;border-width:0;color:gray;background-color:gray">'''
tab_content += '''\n<br>'''
tab_content += '''\n<h5>Column Aggregating Statistics</h5>'''
html = '''\n<pre class="tab">''' + str(col_data_summary).replace(
"\n", "<br>") + "</pre>"
tab_content += html
tab_content += '\n</div>\n'
if top_heatmap_dir:
viewer_name = 'TopHeatmapViewer'
tab_def_content += '''\n<button class="tablinks" '''
tab_def_content += '''onclick="openTab(event, '{}')"'''.format(
viewer_name)
tab_def_content += '''>Top {}% ({} Rows) Heatmap</button>\n'''.format(
round(top_percent, 2), display_count)
heatmap_report_files = os.listdir(top_heatmap_dir)
heatmap_index_page = None
for heatmap_report_file in heatmap_report_files:
if heatmap_report_file.endswith('.html'):
heatmap_index_page = heatmap_report_file
shutil.copy2(
os.path.join(top_heatmap_dir, heatmap_report_file),
output_directory)
if heatmap_index_page:
tab_content += '''\n<div id="{}" class="tabcontent">'''.format(
viewer_name)
msg = 'Top {} percent of matrix sorted by sum of abundance values.'.format(
round(top_percent, 2))
tab_content += '''<p style="color:red;" >{}</p>'''.format(msg)
tab_content += '\n<iframe height="1300px" width="100%" '
tab_content += 'src="{}" '.format(heatmap_index_page)
tab_content += 'style="border:none;"></iframe>'
tab_content += '\n</div>\n'
else:
tab_content += '''\n<div id="{}" class="tabcontent">'''.format(
viewer_name)
tab_content += '''\n<p style="color:red;" >'''
tab_content += '''Heatmap is too large to be displayed.</p>\n'''
tab_content += '\n</div>\n'
viewer_name = 'MatrixHeatmapViewer'
tab_def_content += '''\n<button class="tablinks" '''
tab_def_content += '''onclick="openTab(event, '{}')"'''.format(
viewer_name)
tab_def_content += '''>Matrix Heatmap</button>\n'''
heatmap_report_files = os.listdir(heatmap_dir)
heatmap_index_page = None
for heatmap_report_file in heatmap_report_files:
if heatmap_report_file.endswith('.html'):
heatmap_index_page = heatmap_report_file
shutil.copy2(os.path.join(heatmap_dir, heatmap_report_file),
output_directory)
if heatmap_index_page:
tab_content += '''\n<div id="{}" class="tabcontent">'''.format(
viewer_name)
tab_content += '\n<iframe height="1300px" width="100%" '
tab_content += 'src="{}" '.format(heatmap_index_page)
tab_content += 'style="border:none;"></iframe>'
tab_content += '\n</div>\n'
else:
tab_content += '''\n<div id="{}" class="tabcontent">'''.format(
viewer_name)
tab_content += '''\n<p style="color:red;" >'''
tab_content += '''Heatmap is too large to be displayed.</p>\n'''
tab_content += '\n</div>\n'
tab_def_content += '\n</div>\n'
return tab_def_content + tab_content
def _generate_heatmap_html_report(self, data):
logging.info('Start generating heatmap report page')
data_df = pd.DataFrame(data['values'],
index=data['row_ids'],
columns=data['col_ids'])
result_directory = os.path.join(self.scratch, str(uuid.uuid4()))
self._mkdir_p(result_directory)
tsv_file_path = os.path.join(
result_directory, 'heatmap_data_{}.tsv'.format(str(uuid.uuid4())))
data_df.to_csv(tsv_file_path)
if data_df.index.size < 10000:
heatmap_dir = self.report_util.build_heatmap_html({
'tsv_file_path':
tsv_file_path,
'cluster_data':
True
})['html_dir']
else:
logging.info(
'Original matrix is too large. Skip clustering data in report.'
)
heatmap_dir = self.report_util.build_heatmap_html({
'tsv_file_path':
tsv_file_path,
'cluster_data':
False
})['html_dir']
top_heatmap_dir = None
top_percent = 100
display_count = 200 # roughly count for display items
if len(data_df.index) > 1000:
top_percent = min(display_count / data_df.index.size * 100, 100)
top_heatmap_dir = self.report_util.build_heatmap_html({
'tsv_file_path':
tsv_file_path,
'sort_by_sum':
True,
'top_percent':
top_percent
})['html_dir']
output_directory = os.path.join(self.scratch, str(uuid.uuid4()))
logging.info(
'Start generating html report in {}'.format(output_directory))
html_report = list()
self._mkdir_p(output_directory)
result_file_path = os.path.join(output_directory,
'matrix_viewer_report.html')
visualization_content = self._generate_visualization_content(
output_directory, heatmap_dir, data_df, top_heatmap_dir,
top_percent, display_count)
with open(result_file_path, 'w') as result_file:
with open(
os.path.join(os.path.dirname(__file__), 'templates',
'matrix_template.html'),
'r') as report_template_file:
report_template = report_template_file.read()
report_template = report_template.replace(
'<p>Visualization_Content</p>', visualization_content)
result_file.write(report_template)
report_shock_id = self.dfu.file_to_shock({
'file_path': output_directory,
'pack': 'zip'
})['shock_id']
html_report.append({
'shock_id':
report_shock_id,
'name':
os.path.basename(result_file_path),
'label':
os.path.basename(result_file_path),
'description':
'HTML summary report for Import Amplicon Matrix App'
})
return html_report
def _generate_report(self,
matrix_obj_ref,
new_row_attr_ref,
new_col_attr_ref,
workspace_id,
data=None):
"""
_generate_report: generate summary report
"""
objects_created = [{
'ref': matrix_obj_ref,
'description': 'Imported Amplicon Matrix'
}]
if new_row_attr_ref:
objects_created.append({
'ref':
new_row_attr_ref,
'description':
'Imported Amplicons(Row) Attribute Mapping'
})
if new_col_attr_ref:
objects_created.append({
'ref':
new_col_attr_ref,
'description':
'Imported Samples(Column) Attribute Mapping'
})
if data:
output_html_files = self._generate_heatmap_html_report(data)
report_params = {
'message':
'',
'objects_created':
objects_created,
'workspace_id':
workspace_id,
'html_links':
output_html_files,
'direct_html_link_index':
0,
'html_window_height':
1400,
'report_object_name':
'import_matrix_from_biom_' + str(uuid.uuid4())
}
else:
report_params = {
'message':
'',
'objects_created':
objects_created,
'workspace_id':
workspace_id,
'report_object_name':
'import_matrix_from_biom_' + str(uuid.uuid4())
}
kbase_report_client = KBaseReport(self.callback_url, token=self.token)
output = kbase_report_client.create_extended_report(report_params)
report_output = {
'report_name': output['name'],
'report_ref': output['ref']
}
return report_output
def __init__(self, config):
self.callback_url = config['SDK_CALLBACK_URL']
self.scratch = config['scratch']
self.token = config['KB_AUTH_TOKEN']
self.dfu = DataFileUtil(self.callback_url)
self.report_util = kb_GenericsReport(self.callback_url)
self.data_util = DataUtil(config)
self.sampleservice_util = SampleServiceUtil(config)
self.attr_util = AttributesUtil(config)
self.matrix_util = MatrixUtil(config)
self.taxon_util = TaxonUtil(config)
self.matrix_types = [
x.split(".")[1].split('-')[0]
for x in self.data_util.list_generic_types()
]
self.taxon_wsname = config['taxon-workspace-name']
self.kbse = KBaseSearchEngine(config['search-url'])
self.taxon_cache = dict()
def fetch_sequence(self, matrix_ref):
logging.info('start to fetch consensus sequence')
input_matrix_obj = self.dfu.get_objects({'object_refs':
[matrix_ref]})['data'][0]
input_matrix_info = input_matrix_obj['info']
matrix_name = input_matrix_info[1]
matrix_type = input_matrix_info[2]
matrix_data = input_matrix_obj['data']
if 'KBaseMatrices.AmpliconMatrix' not in matrix_type:
raise ValueError('Unexpected data type: {}'.format(matrix_type))
handle = matrix_data.get('sequencing_file_handle')
if not handle:
raise ValueError(
'Missing sequencing_file_handle from the matrix object')
output_directory = os.path.join(self.scratch, str(uuid.uuid4()))
logging.info('Start generating consensus sequence file in {}'.format(
output_directory))
self._mkdir_p(output_directory)
matrix_fasta_file = self.dfu.shock_to_file({
'handle_id': handle,
'file_path': self.scratch
}).get('file_path')
try:
logging.info('start parsing FASTA file')
fastq_dict = SeqIO.index(matrix_fasta_file, "fasta")
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide FASTA file')
row_ids = matrix_data['data']['row_ids']
fasta_file_path = os.path.join(
output_directory, matrix_name + 'consensus_sequence.fasta')
with open(fasta_file_path, 'w') as f:
for row_id in row_ids:
consensus_sequence = str(fastq_dict.get(row_id).seq)
f.write('>' + str(row_id) + '\n')
f.write(consensus_sequence + '\n')
return fasta_file_path
def import_matrix_from_biom(self, params):
"""
arguments:
obj_type: one of ExpressionMatrix, FitnessMatrix, DifferentialExpressionMatrix
matrix_name: matrix object name
workspace_id: workspace id matrix object to be saved to
input_shock_id: file shock id
or
input_file_path: absolute file path
or
input_staging_file_path: staging area file path
optional arguments:
col_attributemapping_ref: column AttributeMapping reference
row_attributemapping_ref: row AttributeMapping reference
genome_ref: genome reference
matrix_obj_ref: Matrix reference
"""
(biom_file, tsv_file, fasta_file, mode,
metadata_keys) = self._process_params(params)
workspace_id = params.get('workspace_id')
matrix_name = params.get('matrix_name')
obj_type = params.get('obj_type')
scale = params.get('scale')
description = params.get('description')
refs = {k: v for k, v in params.items() if "_ref" in k}
amplicon_data = self._file_to_amplicon_data(biom_file, tsv_file,
fasta_file, mode, refs,
matrix_name, workspace_id,
scale, description,
metadata_keys)
for key in [
'amplicon_type', 'amplification', 'extraction', 'target_gene',
'target_subfragment', 'pcr_primers', 'library_kit',
'library_layout', 'library_screening_strategy',
'sequencing_center', 'sequencing_date',
'sequencing_technology', 'sequencing_instrument',
'sequencing_quality_filter_cutoff', 'read_length_cutoff',
'read_pairing', 'barcode_error_rate',
'chimera_detection_and_removal', 'taxon_calling_method',
'denoise_method', 'sequence_error_cutoff', 'clustering_method',
'clustering_cutoff', 'sample_set_ref', 'reads_set_ref'
]:
if params.get(key):
amplicon_data[key] = params[key]
new_row_attr_ref = None
if not params.get('row_attributemapping_ref'):
new_row_attr_ref = amplicon_data.get('row_attributemapping_ref')
new_col_attr_ref = None
if not params.get('col_attributemapping_ref'):
new_col_attr_ref = amplicon_data.get('col_attributemapping_ref')
if fasta_file:
logging.info(
'start saving consensus sequence file to shock: {}'.format(
fasta_file))
handle_id = self.dfu.file_to_shock({
'file_path': fasta_file,
'make_handle': True
})['handle']['hid']
amplicon_data['sequencing_file_handle'] = handle_id
logging.info('start saving Matrix object: {}'.format(matrix_name))
matrix_obj_ref = self.data_util.save_object({
'obj_type':
'KBaseMatrices.{}'.format(obj_type),
'obj_name':
matrix_name,
'data':
amplicon_data,
'workspace_id':
workspace_id
})['obj_ref']
if params.get('sample_set_ref'):
self.matrix_util._link_matrix_to_samples(matrix_obj_ref,
amplicon_data,
params['sample_set_ref'])
returnVal = {'matrix_obj_ref': matrix_obj_ref}
report_output = self._generate_report(matrix_obj_ref,
new_row_attr_ref,
new_col_attr_ref,
workspace_id,
data=amplicon_data['data'])
returnVal.update(report_output)
return returnVal
class DataTableUtil:
def _mkdir_p(self, path):
"""
_mkdir_p: make directory for given path
"""
if not path:
return
try:
os.makedirs(path)
except OSError as exc:
if exc.errno == errno.EEXIST and os.path.isdir(path):
pass
else:
raise
def _build_table_content(self, output_directory, matrix_df):
"""
_build_table_content: generate HTML table content for FloatMatrix2D object
"""
logging.info('Start generating table content page')
page_content = """\n"""
table_file_name = 'matrix_data_viewer_{}.html'.format(str(uuid.uuid4()))
data_file_name = 'matrix_data_{}.json'.format(str(uuid.uuid4()))
page_content += """<iframe height="900px" width="100%" """
page_content += """src="{}" """.format(table_file_name)
page_content += """style="border:none;"></iframe>\n"""
table_headers = matrix_df.columns.tolist()
table_content = """\n"""
# build header and footer
table_content += """\n<thead>\n<tr>\n"""
for table_header in table_headers:
table_content += """\n <th>{}</th>\n""".format(table_header)
table_content += """\n</tr>\n</thead>\n"""
table_content += """\n<tfoot>\n<tr>\n"""
for table_header in table_headers:
table_content += """\n <th>{}</th>\n""".format(table_header)
table_content += """\n</tr>\n</tfoot>\n"""
logging.info('start generating table json file')
data_array = matrix_df.values.tolist()
total_rec = len(data_array)
json_dict = {'draw': 1,
'recordsTotal': total_rec,
'recordsFiltered': total_rec,
'data': data_array}
with open(os.path.join(output_directory, data_file_name), 'w') as fp:
json.dump(json_dict, fp)
logging.info('start generating table html')
with open(os.path.join(output_directory, table_file_name), 'w') as result_file:
with open(os.path.join(os.path.dirname(__file__), 'templates',
'matrix_table_viewer_template.html'),
'r') as report_template_file:
report_template = report_template_file.read()
report_template = report_template.replace('<p>table_header</p>',
table_content)
report_template = report_template.replace('ajax_file_path',
data_file_name)
report_template = report_template.replace('deferLoading_size',
str(total_rec))
result_file.write(report_template)
#exit(page_content)
'''
<iframe height="900px" width="100%" src="matrix_data_viewer_f3dac561-d9a3-4b05-a79c-d5ce454a36e8.html" style="border:none;"></iframe>
'''
return page_content
def _generate_visualization_content(self, output_directory, matrix_df):
#exit(matrix_df)
'''
ID ... taxonomy
0 GG_OTU_1 ... ['k__Bacteria', 'p__Proteobacteria', 'c__Gamma...
1 GG_OTU_2 ... ['k__Bacteria', 'p__Cyanobacteria', 'c__Nostoc...
2 GG_OTU_3 ... ['k__Archaea', 'p__Euryarchaeota', 'c__Methano...
3 GG_OTU_4 ... ['k__Bacteria', 'p__Firmicutes', 'c__Clostridi...
4 GG_OTU_5 ... ['k__Bacteria', 'p__Proteobacteria', 'c__Gamma...
[5 rows x 8 columns]
'''
tab_def_content = ''
tab_content = ''
tab_def_content += """\n<div class="tab">\n"""
tab_def_content += """
<button class="tablinks" onclick="openTab(event, 'MatrixData')" id="defaultOpen">Matrix Data</button>
"""
corr_table_content = self._build_table_content(output_directory, matrix_df)
tab_content += """\n<div id="MatrixData" class="tabcontent">{}</div>\n""".format(
corr_table_content)
tab_def_content += """\n</div>\n"""
#exit(tab_def_content + tab_content)
'''
<div class="tab">
<button class="tablinks" onclick="openTab(event, 'MatrixData')" id="defaultOpen">Matrix Data</button>
</div>
<div id="MatrixData" class="tabcontent">
<iframe height="900px" width="100%" src="matrix_data_viewer_273ab8bc-b5bf-4708-87c6-5fe01208be55.html" style="border:none;"></iframe>
</div>
'''
return tab_def_content + tab_content
def _generate_matrix_html_report(self, matrix_df):
"""
_generate_matrix_html_report: generate html summary report for matrix
"""
logging.info('Start generating html report')
html_report = list()
output_directory = os.path.join(self.scratch, str(uuid.uuid4()))
self._mkdir_p(output_directory)
result_file_path = os.path.join(output_directory, 'matrix_report.html')
visualization_content = self._generate_visualization_content(output_directory, matrix_df)
with open(result_file_path, 'w') as result_file:
with open(os.path.join(os.path.dirname(__file__), 'templates', 'matrix_template.html'),
'r') as report_template_file:
report_template = report_template_file.read()
report_template = report_template.replace('<p>Visualization_Content</p>',
visualization_content)
result_file.write(report_template)
report_shock_id = self.dfu.file_to_shock({'file_path': output_directory,
'pack': 'zip'})['shock_id']
html_report.append({'shock_id': report_shock_id,
'name': os.path.basename(result_file_path),
'label': os.path.basename(result_file_path),
'description': 'HTML summary report for Compute Correlation App'
})
return html_report
def _generate_corr_report(self, workspace_name, matrix_df):
"""
_generate_report: generate summary report
"""
logging.info('Start creating report')
output_html_files = self._generate_matrix_html_report(matrix_df)
report_params = {'message': '',
'workspace_name': workspace_name,
'html_links': output_html_files,
'direct_html_link_index': 0,
'html_window_height': 666,
'report_object_name': 'matrix_viewer_report_' + str(uuid.uuid4())}
kbase_report_client = KBaseReport(self.callback_url, token=self.token)
output = kbase_report_client.create_extended_report(report_params)
report_output = {'report_name': output['name'], 'report_ref': output['ref']}
return report_output
def _fetch_matrix_df(self, input_matrix_ref, with_attribute_info):
#exit(input_matrix_ref) 44071/21/229
logging.info('Start fetch matrix content')
matrix_obj = self.dfu.get_objects({'object_refs': [input_matrix_ref]})['data'][0]
matrix_info = matrix_obj['info']
matrix_data = matrix_obj['data']
matrix_type = matrix_info[2].split('-')[0].split('.')[-1]
if matrix_type not in self.matrix_types:
raise ValueError('Unexpected matrix type: {}'.format(matrix_type))
data_matrix = self.data_util.fetch_data({'obj_ref': input_matrix_ref}).get('data_matrix')
matrix_df = pd.read_json(data_matrix)
matrix_df = matrix_df.reindex(index=natsorted(matrix_df.index))
row_am_ref = matrix_data.get('row_attributemapping_ref')
if with_attribute_info and row_am_ref:
am_data = self.dfu.get_objects({'object_refs': [row_am_ref]})['data'][0]['data']
instances = am_data['instances']
columns = [x['attribute'] for x in am_data['attributes']]
row_am_df = pd.DataFrame(list(instances.values()), index=instances.keys(), columns=columns)
# row_am = self.data_util.fetch_data({'obj_ref': row_am_ref}).get('data_matrix')g
# row_am_df = pd.read_json(row_am)
matrix_df = matrix_df.join(row_am_df)
matrix_df.index.name = 'ID'
matrix_df.reset_index(inplace=True)
matrix_df = matrix_df.astype(str)
#exit(matrix_df)
'''
SystemExit: ID ... taxonomy
0 GG_OTU_1 ... ['k__Bacteria', 'p__Proteobacteria', 'c__Gamma...
1 GG_OTU_2 ... ['k__Bacteria', 'p__Cyanobacteria', 'c__Nostoc...
2 GG_OTU_3 ... ['k__Archaea', 'p__Euryarchaeota', 'c__Methano...
3 GG_OTU_4 ... ['k__Bacteria', 'p__Firmicutes', 'c__Clostridi...
4 GG_OTU_5 ... ['k__Bacteria', 'p__Proteobacteria', 'c__Gamma...
'''
return matrix_df
def __init__(self, config):
self.callback_url = config['SDK_CALLBACK_URL']
self.scratch = config['scratch']
self.token = config['KB_AUTH_TOKEN']
self.dfu = DataFileUtil(self.callback_url)
self.data_util = DataUtil(config)
self.matrix_types = [x.split(".")[1].split('-')[0]
for x in self.data_util.list_generic_types()]
def view_matrix_as_table(self, params):
input_matrix_ref = params.get('input_matrix_ref')
workspace_name = params.get('workspace_name')
with_attribute_info = params.get('with_attribute_info', True)
matrix_df = self._fetch_matrix_df(input_matrix_ref, with_attribute_info)
returnVal = dict()
report_output = self._generate_corr_report(workspace_name, matrix_df)
returnVal.update(report_output)
return returnVal
class AttributesUtil:
def __init__(self, config):
self.ws_url = config["workspace-url"]
self.callback_url = config['SDK_CALLBACK_URL']
self.token = config['KB_AUTH_TOKEN']
self.shock_url = config['shock-url']
self.srv_wiz_url = config['srv-wiz-url']
self.scratch = config['scratch']
self.dfu = DataFileUtil(self.callback_url)
self.kbse = KBaseSearchEngine(config['search-url'])
self.data_util = DataUtil(config)
self.wsClient = workspaceService(self.ws_url, token=self.token)
self.DEFAULT_ONTOLOGY_ID = "Custom:Term"
self.DEFAULT_UNIT_ID = "Custom:Unit"
self.ONT_LABEL_DEL = " - "
self.ONT_TERM_DEL = ":"
@staticmethod
def validate_params(params, expected, opt_param=set()):
"""Validates that required parameters are present. Warns if unexpected parameters appear"""
expected = set(expected)
opt_param = set(opt_param)
pkeys = set(params)
if expected - pkeys:
raise ValueError(
"Required keys {} not in supplied parameters".format(
", ".join(expected - pkeys)))
defined_param = expected | opt_param
for param in params:
if param not in defined_param:
logging.warning(
"Unexpected parameter {} supplied".format(param))
def file_to_attribute_mapping(self, params):
"""Convert a user supplied file to a compound set"""
if 'input_file_path' in params:
scratch_file_path = params['input_file_path']
elif 'input_shock_id' in params:
scratch_file_path = self.dfu.shock_to_file({
'shock_id':
params['input_shock_id'],
'file_path':
self.scratch
}).get('file_path')
else:
raise ValueError(
"Must supply either a input_shock_id or input_file_path")
attr_mapping = self._file_to_am_obj(scratch_file_path)
info = self.dfu.save_objects({
"id":
params['output_ws_id'],
"objects": [{
"type": "KBaseExperiments.AttributeMapping",
"data": attr_mapping,
"name": params['output_obj_name']
}]
})[0]
return {
"attribute_mapping_ref": "%s/%s/%s" % (info[6], info[0], info[4])
}
def append_file_to_attribute_mapping(self,
staging_file_subdir_path,
old_am_ref,
output_ws_id,
new_am_name=None):
"""append an attribute mapping file to existing attribute mapping object
"""
download_staging_file_params = {
'staging_file_subdir_path': staging_file_subdir_path
}
scratch_file_path = self.dfu.download_staging_file(
download_staging_file_params).get('copy_file_path')
append_am_data = self._file_to_am_obj(scratch_file_path)
old_am_obj = self.dfu.get_objects({'object_refs':
[old_am_ref]})['data'][0]
old_am_info = old_am_obj['info']
old_am_name = old_am_info[1]
old_am_data = old_am_obj['data']
new_am_data = self._check_and_append_am_data(old_am_data,
append_am_data)
if not new_am_name:
current_time = time.localtime()
new_am_name = old_am_name + time.strftime('_%H_%M_%S_%Y_%m_%d',
current_time)
info = self.dfu.save_objects({
"id":
output_ws_id,
"objects": [{
"type": "KBaseExperiments.AttributeMapping",
"data": new_am_data,
"name": new_am_name
}]
})[0]
return {
"attribute_mapping_ref": "%s/%s/%s" % (info[6], info[0], info[4])
}
def update_matrix_attribute_mapping(self, params):
dimension = params.get('dimension')
if dimension not in ['col', 'row']:
raise ValueError('Please use "col" or "row" for input dimension')
workspace_name = params.get('workspace_name')
old_matrix_ref = params.get('input_matrix_ref')
old_matrix_obj = self.dfu.get_objects(
{'object_refs': [old_matrix_ref]})['data'][0]
old_matrix_info = old_matrix_obj['info']
old_matrix_data = old_matrix_obj['data']
old_am_ref = old_matrix_data.get(
'{}_attributemapping_ref'.format(dimension))
if not isinstance(workspace_name, int):
workspace_id = self.dfu.ws_name_to_id(workspace_name)
else:
workspace_id = workspace_name
if not old_am_ref:
raise ValueError(
'Matrix object does not have {} attribute mapping'.format(
dimension))
new_am_ref = self.append_file_to_attribute_mapping(
params['staging_file_subdir_path'], old_am_ref, workspace_id,
params['output_am_obj_name'])['attribute_mapping_ref']
old_matrix_data['{}_attributemapping_ref'.format(
dimension)] = new_am_ref
info = self.dfu.save_objects({
"id":
workspace_id,
"objects": [{
"type": old_matrix_info[2],
"data": old_matrix_data,
"name": params['output_matrix_obj_name']
}]
})[0]
new_matrix_obj_ref = "%s/%s/%s" % (info[6], info[0], info[4])
objects_created = [{
'ref': new_am_ref,
'description': 'Updated Attribute Mapping'
}, {
'ref': new_matrix_obj_ref,
'description': 'Updated Matrix'
}]
report_params = {
'message': '',
'objects_created': objects_created,
'workspace_name': workspace_name,
'report_object_name':
'import_matrix_from_biom_' + str(uuid.uuid4())
}
kbase_report_client = KBaseReport(self.callback_url, token=self.token)
output = kbase_report_client.create_extended_report(report_params)
return {
'new_matrix_obj_ref': new_matrix_obj_ref,
'new_attribute_mapping_ref': new_am_ref,
'report_name': output['name'],
'report_ref': output['ref']
}
def _check_and_append_am_data(self, old_am_data, append_am_data):
exclude_keys = {'attributes', 'instances'}
new_am_data = {
k: old_am_data[k]
for k in set(list(old_am_data.keys())) - exclude_keys
}
old_attrs = old_am_data.get('attributes')
old_insts = old_am_data.get('instances')
append_attrs = append_am_data.get('attributes')
append_insts = append_am_data.get('instances')
# checking duplicate attributes
old_attrs_names = [old_attr.get('attribute') for old_attr in old_attrs]
append_attrs_names = [
append_attr.get('attribute') for append_attr in append_attrs
]
duplicate_attrs = set(old_attrs_names).intersection(append_attrs_names)
if duplicate_attrs:
error_msg = 'Duplicate attribute mappings: [{}]'.format(
duplicate_attrs)
raise ValueError(error_msg)
# checking missing instances
missing_inst = old_insts.keys() - append_insts.keys()
if missing_inst:
error_msg = 'Appended attribute mapping misses [{}] instances'.format(
missing_inst)
raise ValueError(error_msg)
new_attrs = old_attrs + append_attrs
new_am_data['attributes'] = new_attrs
new_insts = deepcopy(old_insts)
for inst_name, val in new_insts.items():
append_val = append_insts.get(inst_name)
val.extend(append_val)
new_am_data['instances'] = new_insts
return new_am_data
def _am_data_to_df(self, data):
"""
Converts a compound set object data to a dataframe
"""
attributes = pd.DataFrame(data['attributes'])
attributes.rename(columns=lambda x: x.replace("ont", "ontology").
capitalize().replace("_", " "))
instances = pd.DataFrame(data['instances'])
am_df = attributes.join(instances)
return am_df
def _clusterset_data_to_df(self, data):
"""
Converts a cluster set object data to a dataframe
"""
original_matrix_ref = data.get('original_data')
data_matrix = self.data_util.fetch_data({
'obj_ref': original_matrix_ref
}).get('data_matrix')
data_df = pd.read_json(data_matrix)
clusters = data.get('clusters')
id_name_list = [
list(cluster.get('id_to_data_position').keys())
for cluster in clusters
]
id_names = [item for sublist in id_name_list for item in sublist]
if set(data_df.columns.tolist()) == set(
id_names): # cluster is based on columns
data_df = data_df.T
cluster_names = [None] * data_df.index.size
cluster_id = 0
for cluster in clusters:
item_ids = list(cluster.get('id_to_data_position').keys())
item_idx = [data_df.index.get_loc(item_id) for item_id in item_ids]
for idx in item_idx:
cluster_names[idx] = cluster_id
cluster_id += 1
data_df['cluster'] = cluster_names
return data_df
def _ws_obj_to_df(self, input_ref):
"""Converts workspace obj to a DataFrame"""
res = self.dfu.get_objects({'object_refs': [input_ref]})['data'][0]
name = res['info'][1]
obj_type = res['info'][2]
if "KBaseExperiments.AttributeMapping" in obj_type:
cs_df = self._am_data_to_df(res['data'])
elif "KBaseExperiments.ClusterSet" in obj_type:
cs_df = self._clusterset_data_to_df(res['data'])
else:
err_msg = 'Ooops! [{}] is not supported.\n'.format(obj_type)
err_msg += 'Please supply KBaseExperiments.AttributeMapping or KBaseExperiments.ClusterSet'
raise ValueError("err_msg")
return name, cs_df, obj_type
def _file_to_am_obj(self, scratch_file_path):
try:
df = pd.read_excel(scratch_file_path, dtype='str')
except XLRDError:
df = pd.read_csv(scratch_file_path, sep=None, dtype='str')
df = df.replace('nan', '')
if df.columns[1].lower() == "attribute ontology id":
am_obj = self._df_to_am_obj(df)
else:
am_obj = self._isa_df_to_am_object(df)
return am_obj
def _df_to_am_obj(self, am_df):
"""Converts a dataframe from a user file to a compound set object"""
if not len(am_df):
raise ValueError("No attributes in supplied files")
attribute_df = am_df.filter(regex="[Uu]nit|[Aa]ttribute")
instance_df = am_df.drop(attribute_df.columns, axis=1)
if not len(instance_df.columns):
raise ValueError(
"Unable to find any instance columns in supplied file")
attribute_df.rename(
columns=lambda x: x.lower().replace(" ontology ", "_ont_").strip(),
inplace=True)
if "attribute" not in attribute_df.columns:
raise ValueError(
"Unable to find a 'attribute' column in supplied file")
attribute_df['source'] = 'upload'
attribute_fields = ('attribute', 'unit', 'attribute_ont_id',
'unit_ont_id', 'source')
attributes = attribute_df.filter(
items=attribute_fields).to_dict('records')
print(attributes)
self._validate_attribute_values(
am_df.set_index(attribute_df.attribute).iterrows())
attribute_mapping = {
'ontology_mapping_method': "User Curation",
'attributes': [self._add_ontology_info(f) for f in attributes],
'instances': instance_df.to_dict('list')
}
return attribute_mapping
def _isa_df_to_am_object(self, isa_df):
skip_columns = {
'Raw Data File', 'Derived Data File', 'Array Data File',
'Image File'
}
if 'Sample Name' in isa_df.columns and not any(
isa_df['Sample Name'].duplicated()):
isa_df.set_index('Sample Name', inplace=True)
elif 'Assay Name' in isa_df.columns and not any(
isa_df['Assay Name'].duplicated()):
isa_df.set_index('Assay Name', inplace=True)
elif not any(isa_df[isa_df.columns[0]].duplicated()):
logging.warning(f'Using {isa_df.columns[0]} as ID column')
isa_df.set_index(isa_df.columns[0], inplace=True)
else:
raise ValueError(
"Unable to detect an ID column that was unigue for each row. "
f"Considered 'Sample Names', 'Assay Names' and {isa_df.columns[0]}"
)
self._validate_attribute_values(isa_df.iteritems())
attribute_mapping = {
'ontology_mapping_method': "User Curation - ISA format"
}
attribute_mapping[
'attributes'], new_skip_cols = self._get_attributes_from_isa(
isa_df, skip_columns)
reduced_isa = isa_df.drop(columns=new_skip_cols, errors='ignore')
attribute_mapping['instances'] = reduced_isa.T.to_dict('list')
return attribute_mapping
def _validate_attribute_values(self, attribute_series):
errors = {}
for attr, vals in attribute_series:
try:
validator = getattr(AttributeValidation, attr)
attr_errors = validator(vals)
if attr_errors:
errors[attr] = attr_errors
except AttributeError:
continue
if errors:
for attr, attr_errors in errors.items():
logging.error(
f'Attribute {attr} had the following validation errors:\n'
"\n".join(attr_errors) + '\n')
raise ValueError(
f'The following attributes failed validation: {", ".join(errors)}'
f'\n See the log for details')
def _get_attributes_from_isa(self, isa_df, skip_columns):
attributes = []
# associate attribute columns with the other columns that relate to them
for i, col in enumerate(isa_df.columns):
if col.startswith('Term Source REF'):
skip_columns.add(col)
last_attr = attributes[-1]
if '_unit' in last_attr:
last_attr['_unit_ont'] = col
else:
last_attr['_val_ont'] = col
elif col.startswith('Term Accession Number'):
# If the term Accession is a web link only grab the last bit
# Similarly, sometimes the number is prefixed with the term source e.x. UO_0000012
isa_df[col] = isa_df[col].map(
lambda x: x.split("/")[-1].split("_")[-1])
skip_columns.add(col)
last_attr = attributes[-1]
if '_unit' in last_attr:
last_attr['_unit_accession'] = col
else:
last_attr['_val_accession'] = col
elif col.startswith('Unit'):
skip_columns.add(col)
last_attr = attributes[-1]
if last_attr.get('unit'):
raise ValueError(
"More than one unit column is supplied for attribute {}"
.format(last_attr['attribute']))
last_attr['_unit'] = col
elif col not in skip_columns:
split_col = col.split("|", 1)
if len(split_col) > 1:
attributes.append({
"attribute": split_col[0],
"attribute_ont_id": split_col[1],
"source": "upload"
})
else:
attributes.append({"attribute": col, "source": "upload"})
# handle the categories for each attribute
for i, attribute in enumerate(attributes):
if '_val_accession' in attribute:
category_df = isa_df[[
attribute['attribute'],
attribute.pop('_val_ont'),
attribute.pop('_val_accession')
]].drop_duplicates()
category_df[
'attribute_ont_id'] = category_df.iloc[:, 1].str.cat(
category_df.iloc[:, 2], ":")
category_df['value'] = category_df[attribute['attribute']]
cats = category_df.set_index(attribute['attribute'])[[
'value', 'attribute_ont_id'
]].to_dict('index')
attribute['categories'] = {
k: self._add_ontology_info(v)
for k, v in cats.items()
}
if '_unit' in attribute:
units = isa_df[attribute.pop('_unit')].unique()
if len(units) > 1:
raise ValueError(
"More than one unit type is supplied for attribute {}: {}"
.format(attribute['attribute'], units))
attribute['unit'] = units[0]
if '_unit_ont' in attribute:
unit_ont = isa_df[attribute.pop('_unit_ont')].str.cat(
isa_df[attribute.pop('_unit_accession')],
":").unique()
if len(units) > 1:
raise ValueError(
"More than one unit ontology is supplied for attribute "
"{}: {}".format(attribute['attribute'], unit_ont))
attribute['unit_ont_id'] = unit_ont[0]
attributes[i] = self._add_ontology_info(attribute)
return attributes, skip_columns
def _search_ontologies(self, term, closest=False):
"""
Match to an existing KBase ontology term
:param term: Test to match
:param closest: if false, term must exactly match an ontology ID
:return: dict(ontology_ref, id)
"""
params = {
"object_types": ["OntologyTerm"],
"match_filter": {
"lookup_in_keys": {
"id": {
"value": term
}
}
},
"access_filter": {
"with_private": 0,
"with_public": 1
},
"pagination": {
"count": 1
},
"post_processing": {
"skip_data": 1
}
}
if closest:
params['match_filter'] = {"full_text_in_all": term}
res = self.kbse.search_objects(params)
if not res['objects']:
return None
term = res['objects'][0]
return {
"ontology_ref": term['guid'].split(":")[1],
"id": term['key_props']['id']
}
def _add_ontology_info(self, attribute):
"""Searches KBASE ontologies for terms matching the user supplied attributes and units.
Add the references if found"""
optionals = {
"unit",
"unit_ont_id",
"unit_ont_ref",
}
attribute = {
k: v
for k, v in attribute.items() if k not in optionals or v != ""
}
ont_info = self._search_ontologies(
attribute.get('attribute_ont_id', "").replace("_", ":"))
if ont_info:
attribute['attribute_ont_ref'] = ont_info['ontology_ref']
attribute['attribute_ont_id'] = ont_info['id']
elif not attribute.get(
'attribute_ont_id') or attribute['attribute_ont_id'] == ":":
attribute.pop('attribute_ont_id', None)
if attribute.get('unit'):
ont_info = self._search_ontologies(
attribute.get('unit_ont_id', '').replace("_", ":"))
if ont_info:
attribute['unit_ont_ref'] = ont_info['ontology_ref']
attribute['unit_ont_id'] = ont_info['id']
elif not attribute.get(
'attribute_ont_id') or attribute['unit_ont_id'] == ":":
attribute.pop('unit_ont_id', None)
return attribute
def to_tsv(self, params):
"""Convert an compound set to TSV file"""
files = {}
_id, df, obj_type = self._ws_obj_to_df(params['input_ref'])
files['file_path'] = os.path.join(params['destination_dir'],
_id + ".tsv")
df.to_csv(files['file_path'], sep="\t", index=False)
return _id, files
def to_excel(self, params):
"""Convert an compound set to Excel file"""
files = {}
_id, df, obj_type = self._ws_obj_to_df(params['input_ref'])
files['file_path'] = os.path.join(params['destination_dir'],
_id + ".xlsx")
writer = pd.ExcelWriter(files['file_path'])
if "KBaseExperiments.AttributeMapping" in obj_type:
df.to_excel(writer, "Attributes", index=False)
elif "KBaseExperiments.ClusterSet" in obj_type:
df.to_excel(writer, "ClusterSet", index=True)
# else is checked in `_ws_obj_to_df`
writer.save()
return _id, files
def export(self, file, name, input_ref):
"""Saves a set of files to SHOCK for export"""
export_package_dir = os.path.join(self.scratch,
name + str(uuid.uuid4()))
os.makedirs(export_package_dir)
shutil.move(file,
os.path.join(export_package_dir, os.path.basename(file)))
# package it up and be done
package_details = self.dfu.package_for_download({
'file_path': export_package_dir,
'ws_refs': [input_ref]
})
return {'shock_id': package_details['shock_id']}
class GenericsAPI:
'''
Module Name:
GenericsAPI
Module Description:
'''
######## WARNING FOR GEVENT USERS ####### noqa
# Since asynchronous IO can lead to methods - even the same method -
# interrupting each other, you must be *very* careful when using global
# state. A method could easily clobber the state set by another while
# the latter method is running.
######################################### noqa
VERSION = "1.0.8"
GIT_URL = "[email protected]:Tianhao-Gu/GenericsAPI.git"
GIT_COMMIT_HASH = "e5a7c9fc2952bf44ebf8ec76d92322f00b606b3e"
#BEGIN_CLASS_HEADER
#END_CLASS_HEADER
# config contains contents of config file in a hash or None if it couldn't
# be found
def __init__(self, config):
#BEGIN_CONSTRUCTOR
self.config = config
self.config['SDK_CALLBACK_URL'] = os.environ['SDK_CALLBACK_URL']
self.config['KB_AUTH_TOKEN'] = os.environ['KB_AUTH_TOKEN']
self.scratch = config['scratch']
self.attr_util = AttributesUtil(self.config)
self.matrix_util = MatrixUtil(self.config)
self.corr_util = CorrelationUtil(self.config)
self.data_util = DataUtil(self.config)
self.network_util = NetworkUtil(self.config)
self.biom_util = BiomUtil(self.config)
self.pca_util = PCAUtil(self.config)
self.data_table_util = DataTableUtil(self.config)
self.template_util = TemplateUtil(self.config)
logging.basicConfig(format='%(created)s %(levelname)s: %(message)s',
level=logging.INFO)
#END_CONSTRUCTOR
pass
def fetch_data(self, ctx, params):
"""
fetch_data: fetch generics data as pandas dataframe for a generics data object
:param params: instance of type "FetchDataParams" (Input of the
fetch_data function obj_ref: generics object reference Optional
arguments: generics_module: the generics data module to be
retrieved from e.g. for an given data type like below: typedef
structure { FloatMatrix2D data; condition_set_ref
condition_set_ref; } SomeGenericsMatrix; generics_module should be
{'data': 'FloatMatrix2D', 'condition_set_ref':
'condition_set_ref'}) -> structure: parameter "obj_ref" of type
"obj_ref" (An X/Y/Z style reference), parameter "generics_module"
of mapping from String to String
:returns: instance of type "FetchDataReturn" (Ouput of the fetch_data
function data_matrix: a pandas dataframe in json format) ->
structure: parameter "data_matrix" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN fetch_data
returnVal = self.data_util.fetch_data(params)
#END fetch_data
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method fetch_data return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def export_matrix(self, ctx, params):
"""
:param params: instance of type "ExportParams" (Input of the
export_matrix function obj_ref: generics object reference Optional
arguments: generics_module: select the generics data to be
retrieved from e.g. for an given data type like below: typedef
structure { FloatMatrix2D data; condition_set_ref
condition_set_ref; } SomeGenericsMatrix; and only 'FloatMatrix2D'
is needed generics_module should be {'data': FloatMatrix2D'}) ->
structure: parameter "obj_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "generics_module" of mapping from String to
String
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN export_matrix
returnVal = self.matrix_util.export_matrix(params)
#END export_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method export_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def validate_data(self, ctx, params):
"""
validate_data: validate data
:param params: instance of type "ValidateParams" (Input of the
validate_data function obj_type: obj type e.g.:
'KBaseMatrices.ExpressionMatrix-1.1' data: data to be validated)
-> structure: parameter "obj_type" of String, parameter "data" of
mapping from String to String
:returns: instance of type "ValidateOutput" -> structure: parameter
"validated" of type "boolean" (A boolean - 0 for false, 1 for
true.), parameter "failed_constraint" of mapping from String to
String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN validate_data
returnVal = self.data_util.validate_data(params)
#END validate_data
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method validate_data return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def import_matrix_from_excel(self, ctx, params):
"""
import_matrix_from_excel: import matrix object from excel
:param params: instance of type "ImportMatrixParams" (Input of the
import_matrix_from_excel function obj_type: a type in
KBaseMatrices input_shock_id: file shock id input_file_path:
absolute file path input_staging_file_path: staging area file path
matrix_name: matrix object name description: optional, a
description of the matrix workspace_name: workspace name matrix
object to be saved to optional: col_attributemapping_ref: column
AttributeMapping reference row_attributemapping_ref: row
AttributeMapping reference genome_ref: genome reference
diff_expr_matrix_ref: DifferentialExpressionMatrix reference
biochemistry_ref: (for ChemicalAbundanceMatrix) reads_set_ref:
(raw data for AmpliconMatrix) sample_set_ref: SampleSet object
reference) -> structure: parameter "obj_type" of String, parameter
"input_shock_id" of String, parameter "input_file_path" of String,
parameter "input_staging_file_path" of String, parameter
"matrix_name" of String, parameter "amplicon_set_name" of String,
parameter "scale" of String, parameter "description" of String,
parameter "workspace_name" of type "workspace_name" (workspace
name of the object), parameter "genome_ref" of type "obj_ref" (An
X/Y/Z style reference), parameter "col_attributemapping_ref" of
type "obj_ref" (An X/Y/Z style reference), parameter
"row_attributemapping_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "diff_expr_matrix_ref" of type "obj_ref" (An
X/Y/Z style reference), parameter "biochemistry_ref" of type
"obj_ref" (An X/Y/Z style reference), parameter "reads_set_ref" of
type "obj_ref" (An X/Y/Z style reference), parameter
"sample_set_ref" of type "obj_ref" (An X/Y/Z style reference),
parameter "unit" of String, parameter "type" of String
:returns: instance of type "ImportMatrixOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "matrix_obj_ref" of type "obj_ref" (An X/Y/Z
style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN import_matrix_from_excel
returnVal = self.matrix_util.import_matrix_from_excel(params)
#END import_matrix_from_excel
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method import_matrix_from_excel return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def import_matrix_from_biom(self, ctx, params):
"""
import_matrix_from_biom: import matrix object from BIOM file format
:param params: instance of type "ImportOTUParams" -> structure:
parameter "obj_type" of String, parameter
"taxonomic_abundance_tsv" of String, parameter "taxonomic_fasta"
of String, parameter "input_local_file" of String, parameter
"matrix_name" of String, parameter "amplicon_set_name" of String,
parameter "scale" of String, parameter "description" of String,
parameter "workspace_name" of type "workspace_name" (workspace
name of the object), parameter "genome_ref" of type "obj_ref" (An
X/Y/Z style reference), parameter "col_attributemapping_ref" of
type "obj_ref" (An X/Y/Z style reference), parameter
"row_attributemapping_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "diff_expr_matrix_ref" of type "obj_ref" (An
X/Y/Z style reference), parameter "biochemistry_ref" of type
"obj_ref" (An X/Y/Z style reference), parameter "reads_set_ref" of
type "obj_ref" (An X/Y/Z style reference), parameter
"sample_set_ref" of type "obj_ref" (An X/Y/Z style reference),
parameter "metadata_keys" of list of String, parameter
"extraction_kit" of String, parameter "amplicon_type" of String,
parameter "target_gene_region" of String, parameter
"forward_primer_sequence" of String, parameter
"reverse_primer_sequence" of String, parameter
"sequencing_platform" of String, parameter "sequencing_run" of
String, parameter "sequencing_kit" of String, parameter
"sequencing_quality_filter_cutoff" of String, parameter
"clustering_cutoff" of Double, parameter "clustering_method" of
String
:returns: instance of type "ImportMatrixOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "matrix_obj_ref" of type "obj_ref" (An X/Y/Z
style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN import_matrix_from_biom
returnVal = self.biom_util.import_matrix_from_biom(params)
#END import_matrix_from_biom
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method import_matrix_from_biom return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def save_object(self, ctx, params):
"""
save_object: validate data constraints and save matrix object
:param params: instance of type "SaveObjectParams" (Input of the
import_matrix_from_excel function obj_type: saving object data
type obj_name: saving object name data: data to be saved
workspace_name: workspace name matrix object to be saved to) ->
structure: parameter "obj_type" of String, parameter "obj_name" of
String, parameter "data" of mapping from String to String,
parameter "workspace_name" of type "workspace_name" (workspace
name of the object)
:returns: instance of type "SaveObjectOutput" -> structure: parameter
"obj_ref" of type "obj_ref" (An X/Y/Z style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN save_object
returnVal = self.data_util.save_object(params)
#END save_object
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method save_object return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def search_matrix(self, ctx, params):
"""
search_matrix: generate a HTML report that allows users to select feature ids
:param params: instance of type "MatrixSelectorParams" (Input of the
search_matrix function matrix_obj_ref: object reference of a
matrix workspace_name: workspace name objects to be saved to) ->
structure: parameter "matrix_obj_ref" of type "obj_ref" (An X/Y/Z
style reference), parameter "workspace_name" of type
"workspace_name" (workspace name of the object)
:returns: instance of type "MatrixSelectorOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN search_matrix
returnVal = self.matrix_util.search_matrix(params)
#END search_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method search_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def filter_matrix(self, ctx, params):
"""
filter_matrix: create sub-matrix based on input filter_ids
:param params: instance of type "MatrixFilterParams" (Input of the
filter_matrix function matrix_obj_ref: object reference of a
matrix workspace_name: workspace name objects to be saved to
filter_ids: string of column or row ids that result matrix
contains filtered_matrix_name: name of newly created filtered
matrix object) -> structure: parameter "matrix_obj_ref" of type
"obj_ref" (An X/Y/Z style reference), parameter "workspace_name"
of type "workspace_name" (workspace name of the object), parameter
"filtered_matrix_name" of String, parameter "remove_ids" of
String, parameter "dimension" of String
:returns: instance of type "MatrixFilterOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "matrix_obj_refs" of list of type "obj_ref" (An
X/Y/Z style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN filter_matrix
returnVal = self.matrix_util.filter_matrix(params)
#END filter_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method filter_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def standardize_matrix(self, ctx, params):
"""
standardize_matrix: standardize a matrix
:param params: instance of type "StandardizeMatrixParams" (Input of
the standardize_matrix function input_matrix_ref: object reference
of a matrix workspace_name: workspace name objects to be saved to
with_mean: center data before scaling with_std: scale data to unit
variance new_matrix_name: name of newly created matrix object) ->
structure: parameter "input_matrix_ref" of type "obj_ref" (An
X/Y/Z style reference), parameter "workspace_name" of type
"workspace_name" (workspace name of the object), parameter
"with_mean" of type "boolean" (A boolean - 0 for false, 1 for
true.), parameter "with_std" of type "boolean" (A boolean - 0 for
false, 1 for true.), parameter "dimension" of String, parameter
"new_matrix_name" of String
:returns: instance of type "StandardizeMatrixOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "new_matrix_obj_ref" of type "obj_ref" (An X/Y/Z
style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN standardize_matrix
returnVal = self.matrix_util.standardize_matrix(params)
#END standardize_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method standardize_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def transform_matrix(self, ctx, params):
"""
:param params: instance of type "TransformMatrixParams" -> structure:
parameter "input_matrix_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "workspace_name" of type "workspace_name"
(workspace name of the object), parameter "workspace_id" of Long,
parameter "new_matrix_name" of String, parameter
"abundance_filtering_params" of mapping from String to String,
parameter "standardization_params" of mapping from String to
String, parameter "ratio_transformation_params" of mapping from
String to String, parameter "perform_relative_abundance" of type
"boolean" (A boolean - 0 for false, 1 for true.)
:returns: instance of type "TransformMatrixOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "new_matrix_obj_ref" of type "obj_ref" (An X/Y/Z
style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN transform_matrix
returnVal = self.matrix_util.transform_matrix(params)
#END transform_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method transform_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def perform_rarefy(self, ctx, params):
"""
:param params: instance of type "RarefyMatrixParams" -> structure:
parameter "input_matrix_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "workspace_id" of Long, parameter
"new_matrix_name" of String, parameter "seed_number" of Long,
parameter "dimension" of String
:returns: instance of type "RarefyMatrixOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "new_matrix_obj_ref" of type "obj_ref" (An X/Y/Z
style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN perform_rarefy
returnVal = self.matrix_util.perform_rarefy(params)
#END perform_rarefy
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method perform_rarefy return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def perform_variable_stats_matrix(self, ctx, params):
"""
:param params: instance of type "VariableStatsParams" -> structure:
parameter "input_matrix_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "attribute_mapping_obj_ref" of type
"obj_ref" (An X/Y/Z style reference), parameter "workspace_id" of
Long, parameter "dist_metric" of String, parameter "dimension" of
String, parameter "grouping" of String, parameter "permutations"
of Long, parameter "perform_anosim" of type "boolean" (A boolean -
0 for false, 1 for true.), parameter "perform_permanova" of type
"boolean" (A boolean - 0 for false, 1 for true.), parameter
"perform_permdisp" of type "boolean" (A boolean - 0 for false, 1
for true.)
:returns: instance of type "VariableStatsOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN perform_variable_stats_matrix
returnVal = self.matrix_util.perform_variable_stats_matrix(params)
#END perform_variable_stats_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError(
'Method perform_variable_stats_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def perform_mantel_test(self, ctx, params):
"""
:param params: instance of type "MantelTestParams" -> structure:
parameter "input_matrix_refs" of list of type "obj_ref" (An X/Y/Z
style reference), parameter "workspace_id" of Long, parameter
"dist_metric" of String, parameter "dimension" of String,
parameter "correlation_method" of String, parameter "permutations"
of Long, parameter "alternative_hypothesis" of String
:returns: instance of type "MantelTestOutput" -> structure: parameter
"report_name" of String, parameter "report_ref" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN perform_mantel_test
returnVal = self.matrix_util.perform_mantel_test(params)
#END perform_mantel_test
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method perform_mantel_test return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def file_to_attribute_mapping(self, ctx, params):
"""
:param params: instance of type "FileToAttributeMappingParams"
(input_shock_id and input_file_path - alternative input params,)
-> structure: parameter "input_shock_id" of String, parameter
"input_file_path" of String, parameter "output_ws_id" of String,
parameter "output_obj_name" of String
:returns: instance of type "FileToAttributeMappingOutput" ->
structure: parameter "attribute_mapping_ref" of type "obj_ref" (An
X/Y/Z style reference)
"""
# ctx is the context object
# return variables are: result
#BEGIN file_to_attribute_mapping
logging.info(
"Starting 'file_to_attribute_mapping' with params:{}".format(
params))
self.attr_util.validate_params(params,
("output_ws_id", "output_obj_name"),
('input_shock_id', 'input_file_path'))
result = self.attr_util.file_to_attribute_mapping(params)
#END file_to_attribute_mapping
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError('Method file_to_attribute_mapping return value ' +
'result is not type dict as required.')
# return the results
return [result]
def file_to_fbamodel_attribute_mapping(self, ctx, params):
"""
:param params: instance of type "FileToAttributeMappingParams"
(input_shock_id and input_file_path - alternative input params,)
-> structure: parameter "input_shock_id" of String, parameter
"input_file_path" of String, parameter "output_ws_id" of String,
parameter "output_obj_name" of String
:returns: instance of type "FileToAttributeMappingOutput" ->
structure: parameter "attribute_mapping_ref" of type "obj_ref" (An
X/Y/Z style reference)
"""
# ctx is the context object
# return variables are: result
#BEGIN file_to_fbamodel_attribute_mapping
logging.info(
"Starting 'file_to_fbamodel_attribute_mapping' with params:{}".
format(params))
self.attr_util.validate_params(params,
("output_ws_id", "output_obj_name"),
('input_shock_id', 'input_file_path'))
params['import_fbamodel_attri_mapping'] = True
result = self.attr_util.file_to_attribute_mapping(params)
#END file_to_fbamodel_attribute_mapping
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError(
'Method file_to_fbamodel_attribute_mapping return value ' +
'result is not type dict as required.')
# return the results
return [result]
def update_matrix_attribute_mapping(self, ctx, params):
"""
:param params: instance of type "UpdateMatrixAMParams" -> structure:
parameter "staging_file_subdir_path" of String, parameter
"dimension" of String, parameter "input_matrix_ref" of type
"obj_ref" (An X/Y/Z style reference), parameter "workspace_name"
of String, parameter "output_am_obj_name" of String, parameter
"output_matrix_obj_name" of String
:returns: instance of type "UpdateMatrixAMOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "new_matrix_obj_ref" of type "obj_ref" (An X/Y/Z
style reference), parameter "new_attribute_mapping_ref" of type
"obj_ref" (An X/Y/Z style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN update_matrix_attribute_mapping
logging.info(
"Starting 'update_matrix_attribute_mapping' with params:{}".format(
params))
self.attr_util.validate_params(
params, ("staging_file_subdir_path", "dimension", "workspace_name",
"output_am_obj_name", "input_matrix_ref",
"output_matrix_obj_name"))
returnVal = self.attr_util.update_matrix_attribute_mapping(params)
#END update_matrix_attribute_mapping
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError(
'Method update_matrix_attribute_mapping return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def attribute_mapping_to_tsv_file(self, ctx, params):
"""
:param params: instance of type "AttributeMappingToTsvFileParams" ->
structure: parameter "input_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "destination_dir" of String
:returns: instance of type "AttributeMappingToTsvFileOutput" ->
structure: parameter "file_path" of String
"""
# ctx is the context object
# return variables are: result
#BEGIN attribute_mapping_to_tsv_file
logging.info(
"Starting 'attribute_mapping_to_tsv_file' with params:{}".format(
params))
self.attr_util.validate_params(params,
("destination_dir", "input_ref"))
am_id, result = self.attr_util.to_tsv(params)
#END attribute_mapping_to_tsv_file
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError(
'Method attribute_mapping_to_tsv_file return value ' +
'result is not type dict as required.')
# return the results
return [result]
def export_attribute_mapping_tsv(self, ctx, params):
"""
:param params: instance of type "ExportObjectParams" -> structure:
parameter "input_ref" of type "obj_ref" (An X/Y/Z style reference)
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: result
#BEGIN export_attribute_mapping_tsv
logging.info(
"Starting 'export_attribute_mapping_tsv' with params:{}".format(
params))
self.attr_util.validate_params(params, ("input_ref", ))
params['destination_dir'] = self.scratch
am_id, files = self.attr_util.to_tsv(params)
result = self.attr_util.export(files['file_path'], am_id,
params['input_ref'])
#END export_attribute_mapping_tsv
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError(
'Method export_attribute_mapping_tsv return value ' +
'result is not type dict as required.')
# return the results
return [result]
def export_attribute_mapping_excel(self, ctx, params):
"""
:param params: instance of type "ExportObjectParams" -> structure:
parameter "input_ref" of type "obj_ref" (An X/Y/Z style reference)
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: result
#BEGIN export_attribute_mapping_excel
logging.info(
"Starting 'export_attribute_mapping_excel' with params:{}".format(
params))
self.attr_util.validate_params(params, ("input_ref", ))
params['destination_dir'] = self.scratch
am_id, files = self.attr_util.to_excel(params)
result = self.attr_util.export(files['file_path'], am_id,
params['input_ref'])
#END export_attribute_mapping_excel
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError(
'Method export_attribute_mapping_excel return value ' +
'result is not type dict as required.')
# return the results
return [result]
def export_cluster_set_excel(self, ctx, params):
"""
:param params: instance of type "ExportObjectParams" -> structure:
parameter "input_ref" of type "obj_ref" (An X/Y/Z style reference)
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: result
#BEGIN export_cluster_set_excel
logging.info(
"Starting 'export_cluster_set_excel' with params:{}".format(
params))
self.attr_util.validate_params(params, ("input_ref", ))
params['destination_dir'] = self.scratch
cs_id, files = self.attr_util.to_excel(params)
result = self.attr_util.export(files['file_path'], cs_id,
params['input_ref'])
#END export_cluster_set_excel
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError('Method export_cluster_set_excel return value ' +
'result is not type dict as required.')
# return the results
return [result]
def export_corr_matrix_excel(self, ctx, params):
"""
:param params: instance of type "ExportObjectParams" -> structure:
parameter "input_ref" of type "obj_ref" (An X/Y/Z style reference)
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: result
#BEGIN export_corr_matrix_excel
logging.info(
"Starting 'export_corr_matrix_excel' with params:{}".format(
params))
result = self.corr_util.export_corr_matrix_excel(params)
#END export_corr_matrix_excel
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError('Method export_corr_matrix_excel return value ' +
'result is not type dict as required.')
# return the results
return [result]
def export_pca_matrix_excel(self, ctx, params):
"""
:param params: instance of type "ExportObjectParams" -> structure:
parameter "input_ref" of type "obj_ref" (An X/Y/Z style reference)
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: result
#BEGIN export_pca_matrix_excel
result = self.pca_util.export_pca_matrix_excel(params)
#END export_pca_matrix_excel
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError('Method export_pca_matrix_excel return value ' +
'result is not type dict as required.')
# return the results
return [result]
def export_amplicon_set_tsv(self, ctx, params):
"""
:param params: instance of type "ExportObjectParams" -> structure:
parameter "input_ref" of type "obj_ref" (An X/Y/Z style reference)
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: result
#BEGIN export_amplicon_set_tsv
result = self.biom_util.export_amplicon_set_tsv(params)
#END export_amplicon_set_tsv
# At some point might do deeper type checking...
if not isinstance(result, dict):
raise ValueError('Method export_amplicon_set_tsv return value ' +
'result is not type dict as required.')
# return the results
return [result]
def compute_correlation_matrix(self, ctx, params):
"""
compute_correlation_matrix: create sub-matrix based on input filter_ids
:param params: instance of type "CompCorrParams" (Input of the
compute_correlation_matrix function input_obj_ref: object
reference of a matrix workspace_name: workspace name objects to be
saved to corr_matrix_name: correlation matrix object name
dimension: compute correlation on column or row, one of ['col',
'row'] method: correlation method, one of ['pearson', 'kendall',
'spearman'] plot_corr_matrix: plot correlation matrix in report,
default False plot_scatter_matrix: plot scatter matrix in report,
default False compute_significance: also compute Significance in
addition to correlation matrix) -> structure: parameter
"input_obj_ref" of type "obj_ref" (An X/Y/Z style reference),
parameter "workspace_name" of type "workspace_name" (workspace
name of the object), parameter "corr_matrix_name" of String,
parameter "dimension" of String, parameter "method" of String,
parameter "plot_corr_matrix" of type "boolean" (A boolean - 0 for
false, 1 for true.), parameter "plot_scatter_matrix" of type
"boolean" (A boolean - 0 for false, 1 for true.), parameter
"compute_significance" of type "boolean" (A boolean - 0 for false,
1 for true.)
:returns: instance of type "CompCorrOutput" -> structure: parameter
"report_name" of String, parameter "report_ref" of String,
parameter "corr_matrix_obj_ref" of type "obj_ref" (An X/Y/Z style
reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN compute_correlation_matrix
returnVal = self.corr_util.compute_correlation_matrix(params)
#END compute_correlation_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError(
'Method compute_correlation_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def compute_correlation_across_matrices(self, ctx, params):
"""
compute_correlation_across_matrices: compute correlation matrix across matrices
:param params: instance of type "CompCorrMetriceParams" (Input of the
compute_correlation_across_matrices function matrix_ref_1: object
reference of a matrix matrix_ref_2: object reference of a matrix
workspace_name: workspace name objects to be saved to
corr_matrix_name: correlation matrix object name dimension:
compute correlation on column or row, one of ['col', 'row']
method: correlation method, one of ['pearson', 'kendall',
'spearman'] plot_corr_matrix: plot correlation matrix in report,
default False compute_significance: also compute Significance in
addition to correlation matrix) -> structure: parameter
"matrix_ref_1" of type "obj_ref" (An X/Y/Z style reference),
parameter "matrix_ref_2" of type "obj_ref" (An X/Y/Z style
reference), parameter "workspace_name" of type "workspace_name"
(workspace name of the object), parameter "corr_matrix_name" of
String, parameter "dimension" of String, parameter "method" of
String, parameter "plot_corr_matrix" of type "boolean" (A boolean
- 0 for false, 1 for true.), parameter "compute_significance" of
type "boolean" (A boolean - 0 for false, 1 for true.), parameter
"corr_threshold" of Double
:returns: instance of type "CompCorrOutput" -> structure: parameter
"report_name" of String, parameter "report_ref" of String,
parameter "corr_matrix_obj_ref" of type "obj_ref" (An X/Y/Z style
reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN compute_correlation_across_matrices
returnVal = self.corr_util.compute_correlation_across_matrices(params)
#END compute_correlation_across_matrices
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError(
'Method compute_correlation_across_matrices return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def build_network(self, ctx, params):
"""
build_network: filter correlation matrix and build network
:param params: instance of type "BuildNetworkParams" (Input of the
build_network function corr_matrix_ref: CorrelationMatrix object
workspace_name: workspace name objects to be saved to
network_obj_name: Network object name filter_on_threshold: Dictory
holder that holds filter on thredshold params params in
filter_on_threshold: coefficient_threshold: correlation
coefficient threshold (select pairs with greater correlation
coefficient)) -> structure: parameter "corr_matrix_ref" of type
"obj_ref" (An X/Y/Z style reference), parameter "workspace_name"
of type "workspace_name" (workspace name of the object), parameter
"network_obj_name" of String, parameter "filter_on_threshold" of
mapping from String to String
:returns: instance of type "BuildNetworkOutput" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "network_obj_ref" of type "obj_ref" (An X/Y/Z
style reference)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN build_network
returnVal = self.network_util.build_network(params)
#END build_network
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method build_network return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def run_pca(self, ctx, params):
"""
run_pca: PCA analysis on matrix
:param params: instance of type "PCAParams" (Input of the run_pca
function input_obj_ref: object reference of a matrix
workspace_name: the name of the workspace pca_matrix_name: name of
PCA (KBaseExperiments.PCAMatrix) object dimension: compute PCA on
column or row, one of ['col', 'row'] n_components - number of
components (default 2) attribute_mapping_obj_ref - associated
attribute_mapping_obj_ref scale_size_by - used for PCA plot to
scale data size color_marker_by - used for PCA plot to group data)
-> structure: parameter "input_obj_ref" of type "obj_ref" (An
X/Y/Z style reference), parameter "workspace_name" of String,
parameter "pca_matrix_name" of String, parameter "dimension" of
String, parameter "n_components" of Long, parameter
"attribute_mapping_obj_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "scale_size_by" of mapping from String to
String, parameter "color_marker_by" of mapping from String to
String
:returns: instance of type "PCAOutput" (Ouput of the run_pca function
pca_ref: PCA object reference (as KBaseExperiments.PCAMatrix data
type) report_name: report name generated by KBaseReport
report_ref: report reference generated by KBaseReport) ->
structure: parameter "pca_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "report_name" of String, parameter
"report_ref" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN run_pca
returnVal = self.pca_util.run_pca(params)
#END run_pca
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method run_pca return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def view_matrix(self, ctx, params):
"""
view_matrix: generate a report for matrix viewer
:param params: instance of type "ViewMatrixParams" -> structure:
parameter "input_matrix_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "workspace_name" of String, parameter
"with_attribute_info" of type "boolean" (A boolean - 0 for false,
1 for true.)
:returns: instance of type "ViewMatrixOutput" -> structure: parameter
"report_name" of String, parameter "report_ref" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN view_matrix
returnVal = self.data_table_util.view_matrix_as_table(params)
#END view_matrix
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method view_matrix return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def build_chemical_abundance_template(self, ctx, params):
"""
:param params: instance of type "ChemAbunTempParams" -> structure:
parameter "workspace_name" of String, parameter "workspace_id" of
Long, parameter "sample_set_ref" of type "obj_ref" (An X/Y/Z style
reference), parameter "chemical_data_included" of mapping from
String to Long, parameter "chemical_ids_included" of mapping from
String to Long
:returns: instance of type "ViewMatrixOutput" -> structure: parameter
"report_name" of String, parameter "report_ref" of String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN build_chemical_abundance_template
returnVal = self.template_util.build_chemical_abundance_template(
params)
#END build_chemical_abundance_template
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError(
'Method build_chemical_abundance_template return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def status(self, ctx):
#BEGIN_STATUS
returnVal = {
'state': "OK",
'message': "",
'version': self.VERSION,
'git_url': self.GIT_URL,
'git_commit_hash': self.GIT_COMMIT_HASH
}
#END_STATUS
return [returnVal]
class BiomUtil:
def _mkdir_p(self, path):
"""
_mkdir_p: make directory for given path
"""
if not path:
return
try:
os.makedirs(path)
except OSError as exc:
if exc.errno == errno.EEXIST and os.path.isdir(path):
pass
else:
raise
def _process_params(self, params):
logging.info('start validating import_matrix_from_biom params')
# check for required parameters
for p in [
'obj_type', 'matrix_name', 'workspace_name', 'scale',
'amplicon_set_name'
]:
if p not in params:
raise ValueError(
'"{}" parameter is required, but missing'.format(p))
obj_type = params.get('obj_type')
if obj_type not in self.matrix_types:
raise ValueError('Unknown matrix object type: {}'.format(obj_type))
scale = params.get('scale')
if scale not in SCALE_TYPES:
raise ValueError('Unknown scale type: {}'.format(scale))
biom_file = None
tsv_file = None
fasta_file = None
metadata_keys = DEFAULT_META_KEYS
if params.get('biom_tsv'):
biom_tsv = params.get('biom_tsv')
biom_file = biom_tsv.get('biom_file_biom_tsv')
tsv_file = biom_tsv.get('tsv_file_biom_tsv')
if not (biom_file and tsv_file):
raise ValueError('missing BIOM or TSV file')
biom_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
biom_file
}).get('copy_file_path')
tsv_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
tsv_file
}).get('copy_file_path')
mode = 'biom_tsv'
elif params.get('biom_fasta'):
biom_fasta = params.get('biom_fasta')
biom_file = biom_fasta.get('biom_file_biom_fasta')
fasta_file = biom_fasta.get('fasta_file_biom_fasta')
if not (biom_file and fasta_file):
raise ValueError('missing BIOM or FASTA file')
biom_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
biom_file
}).get('copy_file_path')
fasta_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
fasta_file
}).get('copy_file_path')
mode = 'biom_fasta'
elif params.get('tsv_fasta'):
tsv_fasta = params.get('tsv_fasta')
tsv_file = tsv_fasta.get('tsv_file_tsv_fasta')
fasta_file = tsv_fasta.get('fasta_file_tsv_fasta')
if not (tsv_file and fasta_file):
raise ValueError('missing TSV or FASTA file')
tsv_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
tsv_file
}).get('copy_file_path')
fasta_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
fasta_file
}).get('copy_file_path')
metadata_keys_str = tsv_fasta.get('metadata_keys_tsv_fasta')
if metadata_keys_str:
metadata_keys += [
x.strip() for x in metadata_keys_str.split(',')
]
mode = 'tsv_fasta'
elif params.get('tsv'):
tsv = params.get('tsv')
tsv_file = tsv.get('tsv_file_tsv')
if not tsv_file:
raise ValueError('missing TSV file')
tsv_file = self.dfu.download_staging_file({
'staging_file_subdir_path':
tsv_file
}).get('copy_file_path')
metadata_keys_str = tsv.get('metadata_keys_tsv')
if metadata_keys_str:
metadata_keys += [
x.strip() for x in metadata_keys_str.split(',')
]
mode = 'tsv'
else:
raise ValueError('missing valide file group type in parameters')
return (biom_file, tsv_file, fasta_file, mode,
list(set(metadata_keys)))
def _retrieve_value(self,
biom_metadata_dict,
tsv_metadata_df,
key,
required=False):
if key in biom_metadata_dict:
return {k.lower(): v
for k, v in biom_metadata_dict.items()}.get(key)
elif key in tsv_metadata_df:
return {k.lower(): v for k, v in tsv_metadata_df.items()}.get(key)
elif required:
raise ValueError('missing necessary [{}] from file'.format(key))
else:
return None
def _search_taxon(self, scientific_name):
"""
logic borrowed from: GFU.GenomeInterface
https://github.com/kbaseapps/GenomeFileUtil/blob/master/lib/GenomeFileUtil/core/GenomeInterface.py#L216
"""
taxon_id = None
search_params = {
"object_types": ["taxon"],
"match_filter": {
"lookup_in_keys": {
"scientific_name": {
"value": scientific_name
}
},
"exclude_subobjects": 1
},
"access_filter": {
"with_private": 0,
"with_public": 1
},
"sorting_rules": [{
"is_object_property": 0,
"property": "timestamp",
"ascending": 0
}]
}
objects = self.kbse.search_objects(search_params)['objects']
if not objects:
search_params['match_filter']['lookup_in_keys'] = {
"aliases": {
"value": scientific_name
}
}
objects = self.kbse.search_objects(search_params)['objects']
if objects:
taxon_id = objects[0].get('object_name')
return taxon_id
def _fetch_taxon_level(self, taxon_char):
taxon_level_mapping = {
'l': 'Life',
'd': 'Domain',
'k': 'Kingdom',
'p': 'Phylum',
'c': 'Class',
'o': 'Order',
'f': 'Family',
'g': 'Genus',
's': 'Species'
}
return taxon_level_mapping.get(taxon_char[0].lower(), 'Unknown')
def _fetch_taxonomy(self, datarow):
lineage = self._retrieve_value([], datarow, 'taxonomy')
if isinstance(lineage, str):
delimiter = csv.Sniffer().sniff(lineage).delimiter
lineage = [x.strip() for x in lineage.split(delimiter)]
taxonomy = {'lineage': lineage}
for key in ['score', 'taxonomy_source', 'species_name']:
val = self._retrieve_value([], datarow, key)
if val:
taxonomy[key] = val
for item in lineage[::-1]:
scientific_name = item.split('_')[-1]
taxon_level_char = item.split('_')[0]
if scientific_name:
taxon_id = self._search_taxon(scientific_name)
if taxon_id:
taxon_ref = f"{self.taxon_wsname}/{taxon_id}"
taxon_level = self._fetch_taxon_level(taxon_level_char)
taxonomy.update({
'taxon_ref': taxon_ref,
'taxon_id': taxon_id,
'scientific_name': scientific_name,
'taxon_level': taxon_level
})
break
return taxonomy
def _retrieve_tsv_amplicon_set_data(self, tsv_file):
amplicons = dict()
try:
logging.info('start parsing TSV file')
reader = pd.read_csv(tsv_file, sep=None, iterator=True)
inferred_sep = reader._engine.data.dialect.delimiter
df = pd.read_csv(tsv_file, sep=inferred_sep, index_col=0)
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide TSV file')
if 'consensus_sequence' not in df.columns.tolist():
raise ValueError('TSV file does not include consensus_sequence')
logging.info('start processing each row in TSV')
for observation_id in df.index:
taxonomy = self._fetch_taxonomy(df.loc[observation_id])
amplicon = {
'consensus_sequence': df.loc[observation_id,
'consensus_sequence'],
'taxonomy': taxonomy
}
amplicons.update({observation_id: amplicon})
logging.info('finished parsing TSV file')
return amplicons
def _retrieve_tsv_fasta_amplicon_set_data(self, tsv_file, fasta_file):
amplicons = dict()
try:
logging.info('start parsing FASTA file')
fastq_dict = SeqIO.index(fasta_file, "fasta")
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide FASTA file')
try:
logging.info('start parsing TSV file')
reader = pd.read_csv(tsv_file, sep=None, iterator=True)
inferred_sep = reader._engine.data.dialect.delimiter
df = pd.read_csv(tsv_file, sep=inferred_sep, index_col=0)
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide TSV file')
logging.info('start processing files')
for observation_id in df.index:
if observation_id not in fastq_dict:
raise ValueError('FASTA file does not have [{}] OTU id'.format(
observation_id))
taxonomy = self._fetch_taxonomy(df.loc[observation_id])
amplicon = {
'consensus_sequence': str(fastq_dict.get(observation_id).seq),
'taxonomy': taxonomy
}
amplicons.update({observation_id: amplicon})
logging.info('finished processing files')
return amplicons
def _retrieve_biom_fasta_amplicon_set_data(self, biom_file, fasta_file):
amplicons = dict()
try:
logging.info('start parsing FASTA file')
fastq_dict = SeqIO.index(fasta_file, "fasta")
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide FASTA file')
logging.info('start parsing BIOM file')
table = biom.load_table(biom_file)
observation_ids = table._observation_ids.tolist()
observation_metadata = table._observation_metadata
logging.info('start processing files')
for index, observation_id in enumerate(observation_ids):
if observation_id not in fastq_dict:
raise ValueError('FASTA file does not have [{}] OTU id'.format(
observation_id))
taxonomy = self._fetch_taxonomy(observation_metadata[index])
amplicon = {
'consensus_sequence': str(fastq_dict.get(observation_id).seq),
'taxonomy': taxonomy
}
amplicons.update({observation_id: amplicon})
logging.info('finished processing files')
return amplicons
def _retrieve_biom_tsv_amplicon_set_data(self, biom_file, tsv_file):
amplicons = dict()
try:
logging.info('start parsing TSV file')
reader = pd.read_csv(tsv_file, sep=None, iterator=True)
inferred_sep = reader._engine.data.dialect.delimiter
df = pd.read_csv(tsv_file, sep=inferred_sep, index_col=0)
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide tsv file')
if 'consensus_sequence' not in df.columns.tolist():
raise ValueError('TSV file does not include consensus_sequence')
logging.info('start parsing BIOM file')
table = biom.load_table(biom_file)
observation_ids = table._observation_ids.tolist()
observation_metadata = table._observation_metadata
logging.info('start processing files')
for index, observation_id in enumerate(observation_ids):
if observation_id not in df.index:
raise ValueError('TSV file does not have [{}] OTU id'.format(
observation_id))
taxonomy = self._fetch_taxonomy(df.loc[observation_id])
amplicon = {
'consensus_sequence': df.loc[observation_id,
'consensus_sequence'],
'taxonomy': taxonomy
}
amplicons.update({observation_id: amplicon})
logging.info('finished processing files')
return amplicons
def _file_to_amplicon_set_data(self, biom_file, tsv_file, fasta_file, mode,
refs, description, matrix_obj_ref):
logging.info('start parsing amplicon_set_data')
amplicon_set_data = dict()
if mode == 'biom_tsv':
amplicons = self._retrieve_biom_tsv_amplicon_set_data(
biom_file, tsv_file)
elif mode == 'biom_fasta':
amplicons = self._retrieve_biom_fasta_amplicon_set_data(
biom_file, fasta_file)
elif mode == 'tsv_fasta':
amplicons = self._retrieve_tsv_fasta_amplicon_set_data(
tsv_file, fasta_file)
elif mode == 'tsv':
amplicons = self._retrieve_tsv_amplicon_set_data(tsv_file)
else:
raise ValueError(
'error parsing _file_to_amplicon_set_data, mode: {}'.format(
mode))
amplicon_set_data.update({'amplicons': amplicons})
if 'reads_set_ref' in refs:
amplicon_set_data['reads_set_ref'] = refs.get('reads_set_ref')
if description:
amplicon_set_data['description'] = description
matrix_obj_ref_array = matrix_obj_ref.split('/')
amplicon_set_data['amplicon_matrix_ref'] = '{}/{}'.format(
matrix_obj_ref_array[0], matrix_obj_ref_array[1])
return amplicon_set_data
def _file_to_amplicon_data(self,
biom_file,
tsv_file,
mode,
refs,
matrix_name,
workspace_id,
scale,
description,
metadata_keys=None):
amplicon_data = refs
if mode.startswith('biom'):
logging.info('start parsing BIOM file for matrix data')
table = biom.load_table(biom_file)
observation_metadata = table._observation_metadata
sample_metadata = table._sample_metadata
matrix_data = {
'row_ids': table._observation_ids.tolist(),
'col_ids': table._sample_ids.tolist(),
'values': table.matrix_data.toarray().tolist()
}
logging.info('start building attribute mapping object')
amplicon_data.update(
self.get_attribute_mapping("row", observation_metadata,
matrix_data, matrix_name, refs,
workspace_id))
amplicon_data.update(
self.get_attribute_mapping("col", sample_metadata, matrix_data,
matrix_name, refs, workspace_id))
amplicon_data['attributes'] = {}
for k in ('create_date', 'generated_by'):
val = getattr(table, k)
if not val:
continue
if isinstance(val, bytes):
amplicon_data['attributes'][k] = val.decode('utf-8')
else:
amplicon_data['attributes'][k] = str(val)
elif mode.startswith('tsv'):
observation_metadata = None
sample_metadata = None
try:
logging.info('start parsing TSV file for matrix data')
reader = pd.read_csv(tsv_file, sep=None, iterator=True)
inferred_sep = reader._engine.data.dialect.delimiter
df = pd.read_csv(tsv_file, sep=inferred_sep, index_col=0)
except Exception:
raise ValueError(
'Cannot parse file. Please provide valide tsv file')
else:
metadata_df = None
if metadata_keys:
shared_metadata_keys = list(
set(metadata_keys) & set(df.columns))
if mode == 'tsv' and 'consensus_sequence' not in shared_metadata_keys:
raise ValueError(
'TSV file does not include consensus_sequence')
if shared_metadata_keys:
metadata_df = df[shared_metadata_keys]
df.drop(columns=shared_metadata_keys, inplace=True)
try:
df = df.astype(float)
except ValueError:
err_msg = 'Found some non-float values. Matrix contains only numeric values\n'
err_msg += 'Please list any non-numeric column names in Metadata Keys field'
raise ValueError(err_msg)
df.fillna(0, inplace=True)
matrix_data = {
'row_ids': df.index.tolist(),
'col_ids': df.columns.tolist(),
'values': df.values.tolist()
}
logging.info('start building attribute mapping object')
amplicon_data.update(
self.get_attribute_mapping("row", observation_metadata,
matrix_data, matrix_name, refs,
workspace_id, metadata_df))
amplicon_data.update(
self.get_attribute_mapping("col", sample_metadata, matrix_data,
matrix_name, refs, workspace_id))
amplicon_data['attributes'] = {}
else:
raise ValueError(
'error parsing _file_to_amplicon_data, mode: {}'.format(mode))
amplicon_data.update({'data': matrix_data})
amplicon_data['search_attributes'] = [
f'{k}|{v}' for k, v in amplicon_data['attributes'].items()
]
amplicon_data['scale'] = scale
if description:
amplicon_data['description'] = description
return amplicon_data
def get_attribute_mapping(self,
axis,
metadata,
matrix_data,
matrix_name,
refs,
workspace_id,
metadata_df=None):
mapping_data = {}
axis_ids = matrix_data[f'{axis}_ids']
if refs.get(f'{axis}_attributemapping_ref'):
am_data = self.dfu.get_objects(
{'object_refs':
[refs[f'{axis}_attributemapping_ref']]})['data'][0]['data']
unmatched_ids = set(axis_ids) - set(am_data['instances'].keys())
if unmatched_ids:
name = "Column" if axis == 'col' else "Row"
raise ValueError(
f"The following {name} IDs from the uploaded matrix do not match "
f"the supplied {name} attribute mapping: {', '.join(unmatched_ids)}"
f"\nPlease verify the input data or upload an excel file with a"
f"{name} mapping tab.")
else:
mapping_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
elif metadata:
name = matrix_name + "_{}_attributes".format(axis)
mapping_data[
f'{axis}_attributemapping_ref'] = self._metadata_to_attribute_mapping(
axis_ids, metadata, name, workspace_id)
# if coming from biom file, metadata and axis IDs are guaranteed to match
mapping_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
elif metadata_df is not None:
name = matrix_name + "_{}_attributes".format(axis)
mapping_data[
f'{axis}_attributemapping_ref'] = self._meta_df_to_attribute_mapping(
axis_ids, metadata_df, name, workspace_id)
mapping_data[f'{axis}_mapping'] = {x: x for x in axis_ids}
return mapping_data
def _meta_df_to_attribute_mapping(self, axis_ids, metadata_df, obj_name,
ws_id):
data = {'ontology_mapping_method': "TSV file", 'instances': {}}
attribute_keys = metadata_df.columns.tolist()
data['attributes'] = [{
'attribute': key,
'source': 'upload'
} for key in attribute_keys]
for axis_id in axis_ids:
data['instances'][axis_id] = metadata_df.loc[axis_id].tolist()
logging.info(
'start saving AttributeMapping object: {}'.format(obj_name))
info = self.dfu.save_objects({
"id":
ws_id,
"objects": [{
"type": "KBaseExperiments.AttributeMapping",
"data": data,
"name": obj_name
}]
})[0]
return f'{info[6]}/{info[0]}/{info[4]}'
def _metadata_to_attribute_mapping(self, instances, metadata, obj_name,
ws_id):
data = {'ontology_mapping_method': "BIOM file", 'instances': {}}
sample_set = metadata[0:min(len(metadata), 25)]
metadata_keys = sorted(
set((k for m_dict in sample_set for k in m_dict)))
data['attributes'] = [{
'attribute': key,
'source': 'upload'
} for key in metadata_keys]
for inst, meta in zip(instances, metadata):
data['instances'][inst] = [
str(meta[attr]) for attr in metadata_keys
]
logging.info(
'start saving AttributeMapping object: {}'.format(obj_name))
info = self.dfu.save_objects({
"id":
ws_id,
"objects": [{
"type": "KBaseExperiments.AttributeMapping",
"data": data,
"name": obj_name
}]
})[0]
return f'{info[6]}/{info[0]}/{info[4]}'
def _generate_report(self, matrix_obj_ref, amplicon_set_obj_ref,
new_row_attr_ref, new_col_attr_ref, workspace_name):
"""
_generate_report: generate summary report
"""
objects_created = [{
'ref': matrix_obj_ref,
'description': 'Imported Amplicon Matrix'
}, {
'ref': amplicon_set_obj_ref,
'description': 'Imported Amplicon Set'
}]
if new_row_attr_ref:
objects_created.append({
'ref':
new_row_attr_ref,
'description':
'Imported Amplicons(Row) Attribute Mapping'
})
if new_col_attr_ref:
objects_created.append({
'ref':
new_col_attr_ref,
'description':
'Imported Samples(Column) Attribute Mapping'
})
report_params = {
'message': '',
'objects_created': objects_created,
'workspace_name': workspace_name,
'report_object_name':
'import_matrix_from_biom_' + str(uuid.uuid4())
}
kbase_report_client = KBaseReport(self.callback_url, token=self.token)
output = kbase_report_client.create_extended_report(report_params)
report_output = {
'report_name': output['name'],
'report_ref': output['ref']
}
return report_output
def _df_to_tsv(self, amplicon_set_df, result_dir, amplicon_set_ref):
logging.info('writting amplicon set data frame to tsv file')
amplicon_set_obj = self.dfu.get_objects(
{'object_refs': [amplicon_set_ref]})['data'][0]
amplicon_set_info = amplicon_set_obj['info']
amplicon_set_name = amplicon_set_info[1]
file_path = os.path.join(result_dir, amplicon_set_name + ".tsv")
amplicon_set_df.to_csv(file_path, sep='\t', index=True, header=True)
return file_path
def _amplicon_set_to_df(self, amplicon_set_ref):
logging.info('converting amplicon set to data frame')
am_set_data = self.dfu.get_objects({'object_refs': [amplicon_set_ref]
})['data'][0]['data']
amplicon_matrix_ref = am_set_data.get('amplicon_matrix_ref')
matrix_data = self.dfu.get_objects(
{'object_refs': [amplicon_matrix_ref]})['data'][0]['data']
matrix_value_data = matrix_data.get('data')
index = matrix_value_data.get('row_ids')
columns = matrix_value_data.get('col_ids')
values = matrix_value_data.get('values')
df = pd.DataFrame(values, index=index, columns=columns)
amplicons = am_set_data.get('amplicons')
meta_index = list()
meta_columns = [
'taxonomy', 'taxon_id', 'taxon_ref', 'taxon_level', 'score',
'taxonomy_source', 'species_name', 'consensus_sequence'
]
meta_values = list()
for otu_id, amplicon in amplicons.items():
meta_index.append(otu_id)
taxonomy_data = amplicon.get('taxonomy')
taxonomy = taxonomy_data.get('lineage')
taxon_id = taxonomy_data.get('taxon_id')
taxon_ref = taxonomy_data.get('taxon_ref')
taxon_level = taxonomy_data.get('taxon_level')
score = taxonomy_data.get('score')
taxonomy_source = taxonomy_data.get('taxonomy_source')
species_name = taxonomy_data.get('species_name')
consensus_sequence = amplicon.get('consensus_sequence')
meta_values.append([
taxonomy, taxon_id, taxon_ref, taxon_level, score,
taxonomy_source, species_name, consensus_sequence
])
meta_df = pd.DataFrame(meta_values,
index=meta_index,
columns=meta_columns)
merged_df = df.merge(meta_df,
left_index=True,
right_index=True,
how='left',
validate='one_to_one')
return merged_df
def __init__(self, config):
self.callback_url = config['SDK_CALLBACK_URL']
self.scratch = config['scratch']
self.token = config['KB_AUTH_TOKEN']
self.dfu = DataFileUtil(self.callback_url)
self.data_util = DataUtil(config)
self.attr_util = AttributesUtil(config)
self.matrix_util = MatrixUtil(config)
self.matrix_types = [
x.split(".")[1].split('-')[0]
for x in self.data_util.list_generic_types()
]
self.taxon_wsname = config['taxon-workspace-name']
self.kbse = KBaseSearchEngine(config['search-url'])
def import_matrix_from_biom(self, params):
"""
arguments:
obj_type: one of ExpressionMatrix, FitnessMatrix, DifferentialExpressionMatrix
matrix_name: matrix object name
workspace_name: workspace name matrix object to be saved to
input_shock_id: file shock id
or
input_file_path: absolute file path
or
input_staging_file_path: staging area file path
optional arguments:
col_attributemapping_ref: column AttributeMapping reference
row_attributemapping_ref: row AttributeMapping reference
genome_ref: genome reference
matrix_obj_ref: Matrix reference
"""
(biom_file, tsv_file, fasta_file, mode,
metadata_keys) = self._process_params(params)
workspace_name = params.get('workspace_name')
matrix_name = params.get('matrix_name')
amplicon_set_name = params.get('amplicon_set_name')
obj_type = params.get('obj_type')
scale = params.get('scale')
description = params.get('description')
refs = {k: v for k, v in params.items() if "_ref" in k}
if not isinstance(workspace_name, int):
workspace_id = self.dfu.ws_name_to_id(workspace_name)
else:
workspace_id = workspace_name
amplicon_data = self._file_to_amplicon_data(biom_file, tsv_file, mode,
refs, matrix_name,
workspace_id, scale,
description, metadata_keys)
new_row_attr_ref = None
if not params.get('row_attributemapping_ref'):
new_row_attr_ref = amplicon_data.get('row_attributemapping_ref')
new_col_attr_ref = None
if not params.get('col_attributemapping_ref'):
new_col_attr_ref = amplicon_data.get('col_attributemapping_ref')
logging.info('start saving Matrix object: {}'.format(matrix_name))
matrix_obj_ref = self.data_util.save_object({
'obj_type':
'KBaseMatrices.{}'.format(obj_type),
'obj_name':
matrix_name,
'data':
amplicon_data,
'workspace_name':
workspace_id
})['obj_ref']
amplicon_set_data = self._file_to_amplicon_set_data(
biom_file, tsv_file, fasta_file, mode, refs, description,
matrix_obj_ref)
logging.info(
'start saving AmpliconSet object: {}'.format(amplicon_set_name))
amplicon_set_obj_ref = self.data_util.save_object({
'obj_type':
'KBaseExperiments.AmpliconSet',
'obj_name':
amplicon_set_name,
'data':
amplicon_set_data,
'workspace_name':
workspace_id
})['obj_ref']
logging.info(
'start resaving Matrix object with amplicon set: {}'.format(
matrix_name))
amplicon_data['amplicon_set_ref'] = '{}/{}'.format(
workspace_id, amplicon_set_name)
matrix_obj_ref = self.data_util.save_object({
'obj_type':
'KBaseMatrices.{}'.format(obj_type),
'obj_name':
matrix_name,
'data':
amplicon_data,
'workspace_name':
workspace_id
})['obj_ref']
returnVal = {
'matrix_obj_ref': matrix_obj_ref,
'amplicon_set_obj_ref': amplicon_set_obj_ref
}
report_output = self._generate_report(matrix_obj_ref,
amplicon_set_obj_ref,
new_row_attr_ref,
new_col_attr_ref, workspace_name)
returnVal.update(report_output)
return returnVal
def export_amplicon_set_tsv(self, params):
"""
export AmpliconSet as TSV
"""
logging.info('start exporting amplicon set object')
amplicon_set_ref = params.get('input_ref')
amplicon_set_df = self._amplicon_set_to_df(amplicon_set_ref)
result_dir = os.path.join(self.scratch, str(uuid.uuid4()))
self._mkdir_p(result_dir)
self._df_to_tsv(amplicon_set_df, result_dir, amplicon_set_ref)
package_details = self.dfu.package_for_download({
'file_path':
result_dir,
'ws_refs': [amplicon_set_ref]
})
return {'shock_id': package_details['shock_id']}
