def export_assembly_as_fasta(self, ctx, params):
"""
A method designed especially for download, this calls 'get_assembly_as_fasta' to do
the work, but then packages the output with WS provenance and object info into
a zip file and saves to shock.
:param params: instance of type "ExportParams" -> structure:
parameter "input_ref" of String
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: output
#BEGIN export_assembly_as_fasta
atf = AssemblyToFasta(self.callback_url, self.sharedFolder)
output = atf.export_as_fasta(ctx, params)
#END export_assembly_as_fasta
# At some point might do deeper type checking...
if not isinstance(output, dict):
raise ValueError('Method export_assembly_as_fasta return value ' +
'output is not type dict as required.')
# return the results
return [output]
def get_assembly_as_fasta(self, ctx, params):
"""
Given a reference to an Assembly (or legacy ContigSet data object), along with a set of options,
construct a local Fasta file with the sequence data. If filename is set, attempt to save to the
specified filename. Otherwise, a random name will be generated.
:param params: instance of type "GetAssemblyParams" (@optional
filename) -> structure: parameter "ref" of String, parameter
"filename" of String
:returns: instance of type "FastaAssemblyFile" -> structure:
parameter "path" of String, parameter "assembly_name" of String
"""
# ctx is the context object
# return variables are: file
#BEGIN get_assembly_as_fasta
atf = AssemblyToFasta(self.callback_url, self.sharedFolder)
file = atf.assembly_as_fasta(ctx, params)
#END get_assembly_as_fasta
# At some point might do deeper type checking...
if not isinstance(file, dict):
raise ValueError('Method get_assembly_as_fasta return value ' +
'file is not type dict as required.')
# return the results
return [file]
def genome_obj_to_fasta(self, ref, obj_type):
# Initiate needed objects
atf = AssemblyToFasta(self.callback_url, self.scratch)
upas = []
if 'KBaseSets.GenomeSet' in obj_type:
obj_data = self.ws.get_objects2({'objects': [{"ref": ref}]})['data'][0]
upas = [gsi['ref'] for gsi in obj_data['data']['items']]
elif 'KBaseSearch.GenomeSet' in obj_type:
obj_data = self.ws.get_objects2({'objects': [{"ref": ref}]})['data'][0]
upas = [gse['ref'] for gse in obj_data['data']['elements'].values()]
elif "KBaseGenomes.Genome" in obj_type:
upas = [ref]
if upas:
for genome_upa in upas:
# Get genome object assembly_ref or contigset_ref through subsetting object
genome_data = self.ws.get_objects2({'objects': \
[{"ref": genome_upa, 'included' : ['/assembly_ref/','/contigset_ref/']}]}) \
['data'][0]['data']
# If genome object contains an assembly_ref or contigset_ref it will return a dictionary, genome_data.
# If not an empty dictionary will be returned
if genome_data:
# Get assembly_upa and fasta
assembly_upa = genome_upa + ';' + \
str(genome_data.get('assembly_ref') or genome_data.get('contigset_ref'))
faf = atf.assembly_as_fasta({'ref': assembly_upa})
# Input data into object dict
self.add_to_dict(assembly_upa, {'paths' : [faf['path']], 'type': obj_type, 'parent_refs': [ref]})
else:
raise TypeError("KBase object type %s does not contain an assembly reference or contig reference." % obj_type)
def export_assembly_as_fasta(self, ctx, params):
"""
A method designed especially for download, this calls 'get_assembly_as_fasta' to do
the work, but then packages the output with WS provenance and object info into
a zip file and saves to shock.
:param params: instance of type "ExportParams" -> structure:
parameter "input_ref" of String
:returns: instance of type "ExportOutput" -> structure: parameter
"shock_id" of String
"""
# ctx is the context object
# return variables are: output
#BEGIN export_assembly_as_fasta
atf = AssemblyToFasta(self.callback_url, self.sharedFolder)
output = atf.export_as_fasta(ctx, params)
#END export_assembly_as_fasta
# At some point might do deeper type checking...
if not isinstance(output, dict):
raise ValueError('Method export_assembly_as_fasta return value ' +
'output is not type dict as required.')
# return the results
return [output]
def get_assembly_as_fasta(self, ctx, params):
"""
Given a reference to an Assembly (or legacy ContigSet data object), along with a set of options,
construct a local Fasta file with the sequence data. If filename is set, attempt to save to the
specified filename. Otherwise, a random name will be generated.
:param params: instance of type "GetAssemblyParams" (@optional
filename) -> structure: parameter "ref" of String, parameter
"filename" of String
:returns: instance of type "FastaAssemblyFile" -> structure:
parameter "path" of String, parameter "assembly_name" of String
"""
# ctx is the context object
# return variables are: file
#BEGIN get_assembly_as_fasta
atf = AssemblyToFasta(self.callback_url, self.sharedFolder)
file = atf.assembly_as_fasta(ctx, params)
#END get_assembly_as_fasta
# At some point might do deeper type checking...
if not isinstance(file, dict):
raise ValueError('Method get_assembly_as_fasta return value ' +
'file is not type dict as required.')
# return the results
return [file]
def assembly_obj_to_fasta(self, ref, obj_type):
# Initiate needed objects
atf = AssemblyToFasta(self.callback_url, self.scratch)
obj = {"ref": ref}
if "KBaseGenomes.ContigSet" in obj_type or "KBaseGenomeAnnotations.Assembly" in obj_type:
# Get fasta
faf = atf.assembly_as_fasta(obj)
self.add_to_dict(ref, {'paths': [faf['path']], 'type': obj_type, 'parent_refs': [ref]})
elif "KBaseSets.AssemblySet" in obj_type:
# Get assembly set object
obj_data = self.ws.get_objects2({'objects': [obj]})['data'][0]
for item_upa in obj_data['data']['items']:
# Get fasta
faf = atf.assembly_as_fasta({"ref": item_upa['ref']})
# Input data into object dict
self.add_to_dict(item_upa['ref'], {'paths' : [faf['path']], 'type' : obj_type, 'parent_refs': [ref]})
def type_to_fasta(self, ctx, ref_lst):
fasta_dict = dict()
fasta_array = []
atf = AssemblyToFasta(self.callback_url, self.scratch)
# Get type info for each ref in ref_lst
for idx, ref in enumerate(ref_lst):
upas = []
obj = {"ref": ref}
obj_info = self.ws_url.get_object_info3({"objects": [obj]})
obj_type = obj_info["infos"][0][2]
# From type info get object
if 'KBaseSets.GenomeSet' in obj_type:
obj_data = self.dfu.get_objects({"object_refs": [ref]})['data'][0]
upas = [gsi['ref'] for gsi in obj_data['data']['items']]
elif 'KBaseSearch.GenomeSet' in obj_type:
obj_data = self.dfu.get_objects({"object_refs": [ref]})['data'][0]
upas = [gse['ref'] for gse in obj_data['data']['elements'].values()]
elif "KBaseGenomes.Genome" in obj_type:
upas = [ref]
elif "KBaseGenomes.ContigSet" in obj_type or "KBaseGenomeAnnotations.Assembly" in obj_type:
faf = [atf.assembly_as_fasta(ctx, obj)]
fasta_array.extend([faf[0]['path'], ref])
elif "KBaseSets.AssemblySet" in obj_type:
fasta_paths = []
obj_data = self.dfu.get_objects({"object_refs": [ref]})['data'][0]
for item_upa in obj_data['data']['items']:
faf = [atf.assembly_as_fasta(ctx, {"ref": item_upa['ref']})]
fasta_paths.extend([faf[0]['path'], item_upa['ref']])
fasta_array = fasta_paths
elif 'KBaseMetagenomes.BinnedContigs' in obj_type:
fasta_paths = []
bin_file_dir = self.mgu.binned_contigs_to_file({'input_ref': ref, 'save_to_shock': 0})['bin_file_directory']
for (dirpath, dirnames, filenames) in os.walk(bin_file_dir):
for fasta_file in filenames:
fasta_path = os.path.join(self.scratch, fasta_file)
copyfile(os.path.join(bin_file_dir, fasta_file), fasta_path)
fasta_paths.extend([fasta_path, ref])
break
fasta_array = fasta_paths
if upas:
for genome_upa in upas:
genome_data = self.ws_url.get_objects2({'objects': [{"ref": genome_upa}]})['data'][0]['data']
assembly_upa = genome_upa + ';' + str(genome_data.get('contigset_ref') or genome_data.get('assembly_ref'))
faf = [atf.assembly_as_fasta(ctx, {'ref': assembly_upa})]
fasta_array.extend([faf[0]['path'], assembly_upa])
# return dictionary of FASTA
fasta_dict["FASTA"] = fasta_array
return fasta_dict