def setUpClass(cls):
# logging.basicConfig(level=logging.info)
token = environ.get('KB_AUTH_TOKEN', None)
# WARNING: don't call any logging methods on the context object,
# it'll result in a NoneType error
cls.ctx = MethodContext(None)
cls.ctx.update({
'token':
token,
'provenance': [{
'service': 'GenomeFileUtil',
'method': 'please_never_use_it_in_production',
'method_params': []
}],
'authenticated':
1
})
config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
cls.cfg = {}
config = ConfigParser()
config.read(config_file)
for nameval in config.items('GenomeFileUtil'):
cls.cfg[nameval[0]] = nameval[1]
cls.wsURL = cls.cfg['workspace-url']
cls.ws = workspaceService(cls.wsURL, token=token)
cls.serviceImpl = GenomeFileUtil(cls.cfg)
gi_config = SDKConfig(cls.cfg)
cls.genome_interface = GenomeInterface(gi_config)
def __init__(self, config):
self.cfg = config
self.au = AssemblyUtil(config.callbackURL)
self.dfu = DataFileUtil(self.cfg.callbackURL)
self.gi = GenomeInterface(self.cfg)
self.taxon_wsname = self.cfg.raw['taxon-workspace-name']
self.time_string = str(
datetime.datetime.fromtimestamp(
time.time()).strftime('%Y_%m_%d_%H_%M_%S'))
yml_text = open('/kb/module/kbase.yml').read()
self.version = re.search("module-version:\n\W+(.+)\n",
yml_text).group(1)
self.ont_mappings = load_ontology_mappings('/kb/module/data')
self.code_table = 11
self.skip_types = ('exon', 'five_prime_UTR', 'three_prime_UTR',
'start_codon', 'stop_codon', 'region', 'chromosome',
'scaffold')
self.spoof_gene_count = 0
self.is_phytozome = False
self.strict = True
self.generate_genes = False
self.warnings = []
self.feature_dict = collections.OrderedDict()
self.cdss = set()
self.ontologies_present = collections.defaultdict(dict)
self.ontology_events = list()
self.skiped_features = collections.Counter()
self.feature_counts = collections.Counter()
def __init__(self, config):
self.cfg = config
self.gi = GenomeInterface(config)
self.dfu = DataFileUtil(config.callbackURL)
self.aUtil = AssemblyUtil(config.callbackURL)
self.ws = Workspace(config.workspaceURL)
self._messages = []
self.time_string = str(
datetime.datetime.fromtimestamp(
time.time()).strftime('%Y_%m_%d_%H_%M_%S'))
yml_text = open('/kb/module/kbase.yml').read()
self.version = re.search("module-version:\n\W+(.+)\n",
yml_text).group(1)
self.generate_parents = False
self.generate_ids = False
self.genes = OrderedDict()
self.mrnas = OrderedDict()
self.cdss = OrderedDict()
self.noncoding = []
self.ontologies_present = defaultdict(dict)
self.ontology_events = list()
self.skiped_features = Counter()
self.feature_counts = Counter()
self.orphan_types = Counter()
self.contig_seq = {}
self.circ_contigs = set()
self.features_spaning_zero = set()
self.genome_warnings = []
self.genome_suspect = False
self.defects = Counter()
self.spoofed_genes = 0
self.excluded_features = ('source', 'exon', 'fasta_record')
self.ont_mappings = load_ontology_mappings('/kb/module/data')
self.code_table = 11
self.re_api_url = config.re_api_url
# dict with feature 'id's that have been used more than once.
self.used_twice_identifiers = {}
self.default_params = {
'source':
'Genbank',
'taxon_wsname':
self.cfg.raw['taxon-workspace-name'],
'taxon_lookup_obj_name':
self.cfg.raw['taxon-lookup-object-name'],
'ontology_wsname':
self.cfg.raw['ontology-workspace-name'],
'ontology_GO_obj_name':
self.cfg.raw['ontology-gene-ontology-obj-name'],
'ontology_PO_obj_name':
self.cfg.raw['ontology-plant-ontology-obj-name'],
'release':
None,
'genetic_code':
11,
'generate_ids_if_needed':
0,
'metadata': {}
}
def setUpClass(cls):
token = environ.get('KB_AUTH_TOKEN', None)
# WARNING: don't call any logging methods on the context object,
# it'll result in a NoneType error
cls.ctx = MethodContext(None)
cls.ctx.update({'token': token,
'provenance': [
{'service': 'GenomeFileUtil',
'method': 'please_never_use_it_in_production',
'method_params': []
}],
'authenticated': 1})
config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
cls.cfg = {}
config = ConfigParser()
config.read(config_file)
for nameval in config.items('GenomeFileUtil'):
cls.cfg[nameval[0]] = nameval[1]
cls.wsURL = cls.cfg['workspace-url']
cls.ws = workspaceService(cls.wsURL, token=token)
cls.serviceImpl = GenomeFileUtil(cls.cfg)
gi_config = SDKConfig(cls.cfg)
cls.genome_interface = GenomeInterface(gi_config)
# create one WS for all tests
suffix = int(time.time() * 1000)
wsName = "test_GenomeAnnotationAPI_" + str(suffix)
cls.ws.create_workspace({'workspace': wsName})
cls.wsName = wsName
# save new genome
assembly_file_path = os.path.join(cls.cfg['scratch'],
'Rhodo_SPAdes_assembly.fa')
shutil.copy('data/Rhodo_SPAdes_assembly.fa', assembly_file_path)
au = AssemblyUtil(os.environ['SDK_CALLBACK_URL'])
cls.assembly_ref = au.save_assembly_from_fasta({
'workspace_name': cls.wsName,
'assembly_name': 'ecoli.assembly',
'file': {'path': assembly_file_path}
})
rhodobacter_contigs = json.load(open('data/rhodobacter_contigs.json'))
save_info = {
'workspace': cls.wsName,
'objects': [{
'type': 'KBaseGenomes.ContigSet',
'data': rhodobacter_contigs,
'name': 'rhodobacter_contigs'
}]
}
cls.contigset_ref = cls.ws.save_objects(save_info)
def __init__(self, sdk_config):
self.cfg = sdk_config
self.dfu = DataFileUtil(self.cfg.callbackURL)
self.gi = GenomeInterface(sdk_config)
self.default_params = {
'genome_ref': None,
'feature_lists': ['features'],
'filter_ids': [],
'include_functions': True,
'include_aliases': True,
}
self.valid_feature_lists = {
'features', 'mrnas', 'cdss', 'non_coding_features'
}
def setUpClass(cls):
cls.token = environ.get('KB_AUTH_TOKEN', None)
config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
cls.cfg = {}
config = ConfigParser()
config.read(config_file)
for nameval in config.items('GenomeFileUtil'):
cls.cfg[nameval[0]] = nameval[1]
# Getting username from Auth profile for token
authServiceUrl = cls.cfg['auth-service-url']
auth_client = _KBaseAuth(authServiceUrl)
cls.user_id = auth_client.get_user(cls.token)
# WARNING: don't call any logging methods on the context object,
# it'll result in a NoneType error
cls.ctx = MethodContext(None)
cls.ctx.update({'token': cls.token,
'user_id': cls.user_id,
'provenance': [
{'service': 'kb_ke_util',
'method': 'please_never_use_it_in_production',
'method_params': []
}],
'authenticated': 1})
cls.shockURL = cls.cfg['shock-url']
cls.wsURL = cls.cfg['workspace-url']
cls.wsClient = workspaceService(cls.wsURL)
cls.serviceImpl = GenomeFileUtil(cls.cfg)
cls.scratch = cls.cfg['scratch']
cls.callback_url = os.environ['SDK_CALLBACK_URL']
cls.dfu = DataFileUtil(cls.callback_url)
cls.cfg['KB_AUTH_TOKEN'] = cls.token
# build genome interface instance
gi_config = SDKConfig(cls.cfg)
cls.genome_interface = GenomeInterface(gi_config)
# second user
test_cfg_file = '/kb/module/work/test.cfg'
test_cfg_text = "[test]\n"
with open(test_cfg_file, "r") as f:
test_cfg_text += f.read()
config = ConfigParser()
config.readfp(io.StringIO(test_cfg_text))
test_cfg_dict = dict(config.items("test"))
if ('test_token2' not in test_cfg_dict):
raise ValueError("Configuration in <module>/test_local/test.cfg file should " +
"include second user credentials ('test_token2')")
token2 = test_cfg_dict['test_token2']
user2 = auth_client.get_user(token2)
cls.ctx2 = MethodContext(None)
cls.ctx2.update({'token': token2,
'user_id': user2,
'provenance': [
{'service': 'NarrativeService',
'method': 'please_never_use_it_in_production',
'method_params': []
}],
'authenticated': 1})
suffix = int(time.time() * 1000)
cls.wsName = "test_SaveGenomeTest_" + str(suffix)
cls.wsClient.create_workspace({'workspace': cls.wsName})
cls.nodes_to_delete = []
cls.prepare_data()
def __init__(self, sdk_config):
self.cfg = sdk_config
self.dfu = DataFileUtil(self.cfg.callbackURL)
self.gi = GenomeInterface(sdk_config)
self.child_dict = {}
self.transcript_counter = defaultdict(int)
def save_one_genome(self, ctx, params):
"""
:param params: instance of type "SaveOneGenomeParams" -> structure:
parameter "workspace" of String, parameter "name" of String,
parameter "data" of type "Genome" (Genome object holds much of the
data relevant for a genome in KBase Genome publications should be
papers about the genome, not papers about certain features of the
genome (which go into the Feature object) Should the Genome object
have a list of feature ids? (in addition to having a list of
feature_refs) Should the Genome object contain a list of
contig_ids too? @optional assembly_ref quality close_genomes
analysis_events features source_id source contigs contig_ids
publications md5 taxonomy gc_content complete dna_size num_contigs
contig_lengths contigset_ref @metadata ws gc_content as GC content
@metadata ws taxonomy as Taxonomy @metadata ws md5 as MD5
@metadata ws dna_size as Size @metadata ws genetic_code as Genetic
code @metadata ws domain as Domain @metadata ws source_id as
Source ID @metadata ws source as Source @metadata ws
scientific_name as Name @metadata ws length(close_genomes) as
Close genomes @metadata ws length(features) as Number features
@metadata ws num_contigs as Number contigs) -> structure:
parameter "id" of type "Genome_id" (KBase genome ID @id kb),
parameter "scientific_name" of String, parameter "domain" of
String, parameter "genetic_code" of Long, parameter "dna_size" of
Long, parameter "num_contigs" of Long, parameter "contigs" of list
of type "Contig" (Type spec for a "Contig" subobject in the
"ContigSet" object Contig_id id - ID of contig in contigset string
md5 - unique hash of contig sequence string sequence - sequence of
the contig string description - Description of the contig (e.g.
everything after the ID in a FASTA file) @optional length md5
genetic_code cell_compartment replicon_geometry replicon_type name
description complete) -> structure: parameter "id" of type
"Contig_id" (ContigSet contig ID @id external), parameter "length"
of Long, parameter "md5" of String, parameter "sequence" of
String, parameter "genetic_code" of Long, parameter
"cell_compartment" of String, parameter "replicon_type" of String,
parameter "replicon_geometry" of String, parameter "name" of
String, parameter "description" of String, parameter "complete" of
type "Bool", parameter "contig_lengths" of list of Long, parameter
"contig_ids" of list of type "Contig_id" (ContigSet contig ID @id
external), parameter "source" of String, parameter "source_id" of
type "source_id" (Reference to a source_id @id external),
parameter "md5" of String, parameter "taxonomy" of String,
parameter "gc_content" of Double, parameter "complete" of Long,
parameter "publications" of list of type "publication" (Structure
for a publication (from ER API) also want to capture authors,
journal name (not in ER)) -> tuple of size 7: parameter "id" of
Long, parameter "source_db" of String, parameter "article_title"
of String, parameter "link" of String, parameter "pubdate" of
String, parameter "authors" of String, parameter "journal_name" of
String, parameter "features" of list of type "Feature" (Structure
for a single feature of a genome Should genome_id contain the
genome_id in the Genome object, the workspace id of the Genome
object, a genomeref, something else? Should sequence be in
separate objects too? We may want to add additional fields for
other CDM functions (e.g., atomic regulons, coexpressed fids,
co_occurring fids,...) @optional orthologs quality
feature_creation_event md5 location function ontology_terms
protein_translation protein_families subsystems publications
subsystem_data aliases annotations regulon_data atomic_regulons
coexpressed_fids co_occurring_fids dna_sequence
protein_translation_length dna_sequence_length) -> structure:
parameter "id" of type "Feature_id" (KBase Feature ID @id
external), parameter "location" of list of tuple of size 4: type
"Contig_id" (ContigSet contig ID @id external), Long, String,
Long, parameter "type" of String, parameter "function" of String,
parameter "ontology_terms" of mapping from String to mapping from
String to type "OntologyData" -> structure: parameter "id" of
String, parameter "ontology_ref" of String, parameter
"term_lineage" of list of String, parameter "term_name" of String,
parameter "evidence" of list of type "OntologyEvidence" (@optional
translation_provenance alignment_evidence) -> structure: parameter
"method" of String, parameter "method_version" of String,
parameter "timestamp" of String, parameter
"translation_provenance" of tuple of size 3: parameter
"ontologytranslation_ref" of String, parameter "namespace" of
String, parameter "source_term" of String, parameter
"alignment_evidence" of list of tuple of size 4: parameter "start"
of Long, parameter "stop" of Long, parameter "align_length" of
Long, parameter "identify" of Double, parameter "md5" of String,
parameter "protein_translation" of String, parameter
"dna_sequence" of String, parameter "protein_translation_length"
of Long, parameter "dna_sequence_length" of Long, parameter
"publications" of list of type "publication" (Structure for a
publication (from ER API) also want to capture authors, journal
name (not in ER)) -> tuple of size 7: parameter "id" of Long,
parameter "source_db" of String, parameter "article_title" of
String, parameter "link" of String, parameter "pubdate" of String,
parameter "authors" of String, parameter "journal_name" of String,
parameter "subsystems" of list of String, parameter
"protein_families" of list of type "ProteinFamily" (Structure for
a protein family @optional query_begin query_end subject_begin
subject_end score evalue subject_description release_version) ->
structure: parameter "id" of String, parameter "subject_db" of
String, parameter "release_version" of String, parameter
"subject_description" of String, parameter "query_begin" of Long,
parameter "query_end" of Long, parameter "subject_begin" of Long,
parameter "subject_end" of Long, parameter "score" of Double,
parameter "evalue" of Double, parameter "aliases" of list of
String, parameter "orthologs" of list of tuple of size 2: String,
Double, parameter "annotations" of list of type "annotation" (a
notation by a curator of the genome object) -> tuple of size 3:
parameter "comment" of String, parameter "annotator" of String,
parameter "annotation_time" of Double, parameter "subsystem_data"
of list of type "subsystem_data" (Structure for subsystem data
(from CDMI API)) -> tuple of size 3: parameter "subsystem" of
String, parameter "variant" of String, parameter "role" of String,
parameter "regulon_data" of list of type "regulon_data" (Structure
for regulon data (from CDMI API)) -> tuple of size 3: parameter
"regulon_id" of String, parameter "regulon_set" of list of type
"Feature_id" (KBase Feature ID @id external), parameter "tfs" of
list of type "Feature_id" (KBase Feature ID @id external),
parameter "atomic_regulons" of list of type "atomic_regulon"
(Structure for an atomic regulon (from CDMI API)) -> tuple of size
2: parameter "atomic_regulon_id" of String, parameter
"atomic_regulon_size" of Long, parameter "coexpressed_fids" of
list of type "coexpressed_fid" (Structure for coexpressed fids
(from CDMI API)) -> tuple of size 2: parameter "scored_fid" of
type "Feature_id" (KBase Feature ID @id external), parameter
"score" of Double, parameter "co_occurring_fids" of list of type
"co_occurring_fid" (Structure for co-occurring fids (from CDMI
API)) -> tuple of size 2: parameter "scored_fid" of type
"Feature_id" (KBase Feature ID @id external), parameter "score" of
Double, parameter "quality" of type "Feature_quality_measure"
(@optional weighted_hit_count hit_count existence_priority
overlap_rules pyrrolysylprotein truncated_begin truncated_end
existence_confidence frameshifted selenoprotein) -> structure:
parameter "truncated_begin" of type "Bool", parameter
"truncated_end" of type "Bool", parameter "existence_confidence"
of Double, parameter "frameshifted" of type "Bool", parameter
"selenoprotein" of type "Bool", parameter "pyrrolysylprotein" of
type "Bool", parameter "overlap_rules" of list of String,
parameter "existence_priority" of Double, parameter "hit_count" of
Double, parameter "weighted_hit_count" of Double, parameter
"feature_creation_event" of type "Analysis_event" (@optional
tool_name execution_time parameters hostname) -> structure:
parameter "id" of type "Analysis_event_id", parameter "tool_name"
of String, parameter "execution_time" of Double, parameter
"parameters" of list of String, parameter "hostname" of String,
parameter "contigset_ref" of type "ContigSet_ref" (Reference to a
ContigSet object containing the contigs for this genome in the
workspace @id ws KBaseGenomes.ContigSet), parameter "assembly_ref"
of type "Assembly_ref" (Reference to an Assembly object in the
workspace @id ws KBaseGenomeAnnotations.Assembly), parameter
"quality" of type "Genome_quality_measure" (@optional
frameshift_error_rate sequence_error_rate) -> structure: parameter
"frameshift_error_rate" of Double, parameter "sequence_error_rate"
of Double, parameter "close_genomes" of list of type
"Close_genome" (@optional genome closeness_measure) -> structure:
parameter "genome" of type "Genome_id" (KBase genome ID @id kb),
parameter "closeness_measure" of Double, parameter
"analysis_events" of list of type "Analysis_event" (@optional
tool_name execution_time parameters hostname) -> structure:
parameter "id" of type "Analysis_event_id", parameter "tool_name"
of String, parameter "execution_time" of Double, parameter
"parameters" of list of String, parameter "hostname" of String,
parameter "hidden" of type "boolean" (A boolean - 0 for false, 1
for true. @range (0, 1))
:returns: instance of type "SaveGenomeResult" -> structure: parameter
"info" of type "object_info" (Information about an object,
including user provided metadata. obj_id objid - the numerical id
of the object. obj_name name - the name of the object. type_string
type - the type of the object. timestamp save_date - the save date
of the object. obj_ver ver - the version of the object. username
saved_by - the user that saved or copied the object. ws_id wsid -
the workspace containing the object. ws_name workspace - the
workspace containing the object. string chsum - the md5 checksum
of the object. int size - the size of the object in bytes.
usermeta meta - arbitrary user-supplied metadata about the
object.) -> tuple of size 11: parameter "objid" of type "obj_id"
(The unique, permanent numerical ID of an object.), parameter
"name" of type "obj_name" (A string used as a name for an object.
Any string consisting of alphanumeric characters and the
characters |._- that is not an integer is acceptable.), parameter
"type" of type "type_string" (A type string. Specifies the type
and its version in a single string in the format
[module].[typename]-[major].[minor]: module - a string. The module
name of the typespec containing the type. typename - a string. The
name of the type as assigned by the typedef statement. major - an
integer. The major version of the type. A change in the major
version implies the type has changed in a non-backwards compatible
way. minor - an integer. The minor version of the type. A change
in the minor version implies that the type has changed in a way
that is backwards compatible with previous type definitions. In
many cases, the major and minor versions are optional, and if not
provided the most recent version will be used. Example:
MyModule.MyType-3.1), parameter "save_date" of type "timestamp" (A
time in the format YYYY-MM-DDThh:mm:ssZ, where Z is either the
character Z (representing the UTC timezone) or the difference in
time to UTC in the format +/-HHMM, eg: 2012-12-17T23:24:06-0500
(EST time) 2013-04-03T08:56:32+0000 (UTC time)
2013-04-03T08:56:32Z (UTC time)), parameter "version" of Long,
parameter "saved_by" of type "username" (Login name of a KBase
user account.), parameter "wsid" of type "ws_id" (The unique,
permanent numerical ID of a workspace.), parameter "workspace" of
type "ws_name" (A string used as a name for a workspace. Any
string consisting of alphanumeric characters and "_", ".", or "-"
that is not an integer is acceptable. The name may optionally be
prefixed with the workspace owner's user name and a colon, e.g.
kbasetest:my_workspace.), parameter "chsum" of String, parameter
"size" of Long, parameter "meta" of type "usermeta" (User provided
metadata about an object. Arbitrary key-value pairs provided by
the user.) -> mapping from String to String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN save_one_genome
genome_interface = GenomeInterface(self.cfg)
returnVal = genome_interface.save_one_genome(params)
#END save_one_genome
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method save_one_genome return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def save_one_genome(self, ctx, params):
"""
:param params: instance of type "SaveOneGenomeParams" -> structure:
parameter "workspace" of String, parameter "name" of String,
parameter "data" of type "Genome" (Genome object holds much of the
data relevant for a genome in KBase Genome publications should be
papers about the genome Should the Genome object contain a list of
contig_ids too? Source: allowed entries RefSeq, Ensembl,
Phytozome, RAST, Prokka, User_upload #allowed entries RefSeq,
Ensembl, Phytozome, RAST, Prokka, User_upload controlled
vocabulary managed by API Domain is a controlled vocabulary
Warnings : mostly controlled vocab but also allow for unstructured
Genome_tiers : controlled vocabulary (based on ap input and API
checked) Allowed values: #Representative, Reference, ExternalDB,
User Examples Tiers: All phytozome - Representative and ExternalDB
Phytozome flagship genomes - Reference, Representative and
ExternalDB Ensembl - Representative and ExternalDB RefSeq
Reference - Reference, Representative and ExternalDB RefSeq
Representative - Representative and ExternalDB RefSeq Latest or
All Assemblies folder - ExternalDB User Data - User tagged Example
Sources: RefSeq, Ensembl, Phytozome, Microcosm, User, RAST,
Prokka, (other annotators) @optional warnings contig_lengths
contig_ids source_id taxonomy publications @optional
ontology_events ontologies_present non_coding_features mrnas
@optional genbank_handle_ref gff_handle_ref
external_source_origination_date @optional release
original_source_file_name notes quality_scores suspect
assembly_ref @metadata ws gc_content as GC content @metadata ws
taxonomy as Taxonomy @metadata ws md5 as MD5 @metadata ws dna_size
as Size @metadata ws genetic_code as Genetic code @metadata ws
domain as Domain @metadata ws source_id as Source ID @metadata ws
source as Source @metadata ws scientific_name as Name @metadata ws
length(features) as Number of Protein Encoding Genes @metadata ws
length(cdss) as Number of CDS @metadata ws assembly_ref as
Assembly Object @metadata ws num_contigs as Number contigs
@metadata ws length(warnings) as Number of Genome Level Warnings
@metadata ws suspect as Suspect Genome) -> structure: parameter
"id" of type "Genome_id" (KBase genome ID @id kb), parameter
"scientific_name" of String, parameter "domain" of String,
parameter "warnings" of list of String, parameter "genome_tiers"
of list of String, parameter "feature_counts" of mapping from
String to Long, parameter "genetic_code" of Long, parameter
"dna_size" of Long, parameter "num_contigs" of Long, parameter
"molecule_type" of String, parameter "contig_lengths" of list of
Long, parameter "contig_ids" of list of String, parameter "source"
of String, parameter "source_id" of type "source_id" (Reference to
a source_id @id external), parameter "md5" of String, parameter
"taxonomy" of String, parameter "gc_content" of Double, parameter
"publications" of list of type "publication" (Structure for a
publication (float pubmedid string source (ex. Pubmed) string
title string web address string publication year string authors
string journal)) -> tuple of size 7: parameter "pubmedid" of
Double, parameter "source" of String, parameter "title" of String,
parameter "url" of String, parameter "year" of String, parameter
"authors" of String, parameter "journal" of String, parameter
"ontology_events" of list of type "Ontology_event" (@optional
ontology_ref method_version eco) -> structure: parameter "id" of
String, parameter "ontology_ref" of type "Ontology_ref" (Reference
to a ontology object @id ws KBaseOntology.OntologyDictionary),
parameter "method" of String, parameter "method_version" of
String, parameter "timestamp" of String, parameter "eco" of
String, parameter "ontologies_present" of mapping from String to
mapping from String to String, parameter "features" of list of
type "Feature" (Structure for a single CDS encoding ???gene??? of
a genome ONLY PUT GENES THAT HAVE A CORRESPONDING CDS IN THIS
ARRAY NOTE: Sequence is optional. Ideally we can keep it in here,
but Recognize due to space constraints another solution may be
needed. We may want to add additional fields for other CDM
functions (e.g., atomic regulons, coexpressed fids, co_occurring
fids,...) protein_translation_length and protein_translation are
for longest coded protein (representative protein for splice
variants) NOTE: New Aliases field definitely breaks compatibility.
As Does Function. flags are flag fields in GenBank format. This
will be a controlled vocabulary. Initially Acceptable values are
pseudo, ribosomal_slippage, and trans_splicing Md5 is the md5 of
dna_sequence. @optional functions ontology_terms note
protein_translation mrnas flags warnings @optional inference_data
dna_sequence aliases db_xrefs children functional_descriptions) ->
structure: parameter "id" of type "Feature_id" (KBase Feature ID
@id external), parameter "location" of list of tuple of size 4:
type "Contig_id" (ContigSet contig ID @id external), Long, String,
Long, parameter "functions" of list of String, parameter
"functional_descriptions" of list of String, parameter
"ontology_terms" of mapping from String to mapping from String to
list of Long, parameter "note" of String, parameter "md5" of
String, parameter "protein_translation" of String, parameter
"protein_translation_length" of Long, parameter "cdss" of list of
String, parameter "mrnas" of list of String, parameter "children"
of list of String, parameter "flags" of list of String, parameter
"warnings" of list of String, parameter "inference_data" of list
of type "InferenceInfo" (category;#Maybe a controlled vocabulary
type;#Maybe a controlled vocabulary) -> structure: parameter
"category" of String, parameter "type" of String, parameter
"evidence" of String, parameter "dna_sequence" of String,
parameter "dna_sequence_length" of Long, parameter "aliases" of
list of tuple of size 2: parameter "fieldname" of String,
parameter "alias" of String, parameter "db_xrefs" of list of tuple
of size 2: parameter "db_source" of String, parameter
"db_identifier" of String, parameter "non_coding_features" of list
of type "NonCodingFeature" (Structure for a single feature that is
NOT one of the following: Protein encoding gene (gene that has a
corresponding CDS) mRNA CDS Note pseudo-genes and Non protein
encoding genes are put into this flags are flag fields in GenBank
format. This will be a controlled vocabulary. Initially Acceptable
values are pseudo, ribosomal_slippage, and trans_splicing Md5 is
the md5 of dna_sequence. @optional functions ontology_terms note
flags warnings functional_descriptions @optional inference_data
dna_sequence aliases db_xrefs children parent_gene) -> structure:
parameter "id" of type "Feature_id" (KBase Feature ID @id
external), parameter "location" of list of tuple of size 4: type
"Contig_id" (ContigSet contig ID @id external), Long, String,
Long, parameter "type" of String, parameter "functions" of list of
String, parameter "functional_descriptions" of list of String,
parameter "ontology_terms" of mapping from String to mapping from
String to list of Long, parameter "note" of String, parameter
"md5" of String, parameter "parent_gene" of String, parameter
"children" of list of String, parameter "flags" of list of String,
parameter "warnings" of list of String, parameter "inference_data"
of list of type "InferenceInfo" (category;#Maybe a controlled
vocabulary type;#Maybe a controlled vocabulary) -> structure:
parameter "category" of String, parameter "type" of String,
parameter "evidence" of String, parameter "dna_sequence" of
String, parameter "dna_sequence_length" of Long, parameter
"aliases" of list of tuple of size 2: parameter "fieldname" of
String, parameter "alias" of String, parameter "db_xrefs" of list
of tuple of size 2: parameter "db_source" of String, parameter
"db_identifier" of String, parameter "cdss" of list of type "CDS"
(Structure for a single feature CDS flags are flag fields in
GenBank format. This will be a controlled vocabulary. Initially
Acceptable values are pseudo, ribosomal_slippage, and
trans_splicing Md5 is the md5 of dna_sequence. @optional
parent_gene parent_mrna functions ontology_terms note flags
warnings @optional inference_data dna_sequence aliases db_xrefs
functional_descriptions) -> structure: parameter "id" of type
"cds_id" (KBase CDS ID @id external), parameter "location" of list
of tuple of size 4: type "Contig_id" (ContigSet contig ID @id
external), Long, String, Long, parameter "md5" of String,
parameter "protein_md5" of String, parameter "parent_gene" of type
"Feature_id" (KBase Feature ID @id external), parameter
"parent_mrna" of type "mrna_id" (KBase mRNA ID @id external),
parameter "note" of String, parameter "functions" of list of
String, parameter "functional_descriptions" of list of String,
parameter "ontology_terms" of mapping from String to mapping from
String to list of Long, parameter "flags" of list of String,
parameter "warnings" of list of String, parameter "inference_data"
of list of type "InferenceInfo" (category;#Maybe a controlled
vocabulary type;#Maybe a controlled vocabulary) -> structure:
parameter "category" of String, parameter "type" of String,
parameter "evidence" of String, parameter "protein_translation" of
String, parameter "protein_translation_length" of Long, parameter
"aliases" of list of tuple of size 2: parameter "fieldname" of
String, parameter "alias" of String, parameter "db_xrefs" of list
of tuple of size 2: parameter "db_source" of String, parameter
"db_identifier" of String, parameter "dna_sequence" of String,
parameter "dna_sequence_length" of Long, parameter "mrnas" of list
of type "mRNA" (Structure for a single feature mRNA flags are flag
fields in GenBank format. This will be a controlled vocabulary.
Initially Acceptable values are pseudo, ribosomal_slippage, and
trans_splicing Md5 is the md5 of dna_sequence. @optional
parent_gene cds functions ontology_terms note flags warnings
@optional inference_data dna_sequence aliases db_xrefs
functional_descriptions) -> structure: parameter "id" of type
"mrna_id" (KBase mRNA ID @id external), parameter "location" of
list of tuple of size 4: type "Contig_id" (ContigSet contig ID @id
external), Long, String, Long, parameter "md5" of String,
parameter "parent_gene" of type "Feature_id" (KBase Feature ID @id
external), parameter "cds" of type "cds_id" (KBase CDS ID @id
external), parameter "dna_sequence" of String, parameter
"dna_sequence_length" of Long, parameter "note" of String,
parameter "functions" of list of String, parameter
"functional_descriptions" of list of String, parameter
"ontology_terms" of mapping from String to mapping from String to
list of Long, parameter "flags" of list of String, parameter
"warnings" of list of String, parameter "inference_data" of list
of type "InferenceInfo" (category;#Maybe a controlled vocabulary
type;#Maybe a controlled vocabulary) -> structure: parameter
"category" of String, parameter "type" of String, parameter
"evidence" of String, parameter "aliases" of list of tuple of size
2: parameter "fieldname" of String, parameter "alias" of String,
parameter "db_xrefs" of list of tuple of size 2: parameter
"db_source" of String, parameter "db_identifier" of String,
parameter "assembly_ref" of type "Assembly_ref" (Reference to an
Assembly object in the workspace @id ws
KBaseGenomeAnnotations.Assembly), parameter "taxon_ref" of type
"Taxon_ref" (Reference to a taxon object @id ws
KBaseGenomeAnnotations.Taxon), parameter "genbank_handle_ref" of
type "genbank_handle_ref" (Reference to a handle to the Genbank
file on shock @id handle), parameter "gff_handle_ref" of type
"gff_handle_ref" (Reference to a handle to the GFF file on shock
@id handle), parameter "external_source_origination_date" of
String, parameter "release" of String, parameter
"original_source_file_name" of String, parameter "notes" of
String, parameter "quality_scores" of list of type
"GenomeQualityScore" (Score_interpretation : fraction_complete -
controlled vocabulary managed by API @optional method_report_ref
method_version) -> structure: parameter "method" of String,
parameter "method_report_ref" of type "Method_report_ref"
(Reference to a report object @id ws KBaseReport.Report),
parameter "method_version" of String, parameter "score" of String,
parameter "score_interpretation" of String, parameter "timestamp"
of String, parameter "suspect" of type "Bool", parameter "hidden"
of type "boolean" (A boolean - 0 for false, 1 for true. @range (0,
1)), parameter "upgrade" of type "boolean" (A boolean - 0 for
false, 1 for true. @range (0, 1))
:returns: instance of type "SaveGenomeResult" -> structure: parameter
"info" of type "object_info" (Information about an object,
including user provided metadata. obj_id objid - the numerical id
of the object. obj_name name - the name of the object. type_string
type - the type of the object. timestamp save_date - the save date
of the object. obj_ver ver - the version of the object. username
saved_by - the user that saved or copied the object. ws_id wsid -
the workspace containing the object. ws_name workspace - the
workspace containing the object. string chsum - the md5 checksum
of the object. int size - the size of the object in bytes.
usermeta meta - arbitrary user-supplied metadata about the
object.) -> tuple of size 11: parameter "objid" of type "obj_id"
(The unique, permanent numerical ID of an object.), parameter
"name" of type "obj_name" (A string used as a name for an object.
Any string consisting of alphanumeric characters and the
characters |._- that is not an integer is acceptable.), parameter
"type" of type "type_string" (A type string. Specifies the type
and its version in a single string in the format
[module].[typename]-[major].[minor]: module - a string. The module
name of the typespec containing the type. typename - a string. The
name of the type as assigned by the typedef statement. major - an
integer. The major version of the type. A change in the major
version implies the type has changed in a non-backwards compatible
way. minor - an integer. The minor version of the type. A change
in the minor version implies that the type has changed in a way
that is backwards compatible with previous type definitions. In
many cases, the major and minor versions are optional, and if not
provided the most recent version will be used. Example:
MyModule.MyType-3.1), parameter "save_date" of type "timestamp" (A
time in the format YYYY-MM-DDThh:mm:ssZ, where Z is either the
character Z (representing the UTC timezone) or the difference in
time to UTC in the format +/-HHMM, eg: 2012-12-17T23:24:06-0500
(EST time) 2013-04-03T08:56:32+0000 (UTC time)
2013-04-03T08:56:32Z (UTC time)), parameter "version" of Long,
parameter "saved_by" of type "username" (Login name of a KBase
user account.), parameter "wsid" of type "ws_id" (The unique,
permanent numerical ID of a workspace.), parameter "workspace" of
type "ws_name" (A string used as a name for a workspace. Any
string consisting of alphanumeric characters and "_", ".", or "-"
that is not an integer is acceptable. The name may optionally be
prefixed with the workspace owner's user name and a colon, e.g.
kbasetest:my_workspace.), parameter "chsum" of String, parameter
"size" of Long, parameter "meta" of type "usermeta" (User provided
metadata about an object. Arbitrary key-value pairs provided by
the user.) -> mapping from String to String
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN save_one_genome
genome_interface = GenomeInterface(self.cfg)
returnVal = genome_interface.save_one_genome(params)
#END save_one_genome
# At some point might do deeper type checking...
if not isinstance(returnVal, dict):
raise ValueError('Method save_one_genome return value ' +
'returnVal is not type dict as required.')
# return the results
return [returnVal]
def __init__(self, sdk_config):
self.cfg = sdk_config
self.dfu = DataFileUtil(self.cfg.callbackURL)
self.gi = GenomeInterface(sdk_config)