def __init__(self,
organism,
ontology=None,
progress_callback=None,
filename=None):
#: A dictionary mapping a gene (gene_id) to a set of all annotations of that gene.
self.gene_annotations = defaultdict(list)
#: A dictionary mapping a GO term id to a set of annotations that are directly annotated to that term
self.term_anotations = defaultdict(list)
self.all_annotations = defaultdict(list)
self._gene_names = None
self._gene_names_dict = None
#: A list of all :class:`AnnotationRecords` instances.
self.annotations = []
self.header = ''
self.taxid = organism
self._ontology = ontology
if filename is None:
try:
filename = serverfiles.localpath_download(
DOMAIN,
FILENAME_ANNOTATION.format(organism),
progress_callback=progress_callback)
except FileNotFoundError:
raise taxonomy.UnknownSpeciesIdentifier(organism)
self._parse_file(filename)
def __filename(self, domain, organism):
""" Create filename based od domain name and organism.
"""
if domain in self.supported_domains.values(
) and domain == gene_ontology_domain and organism:
return FILENAME_ANNOTATION.format(organism)
elif domain in self.supported_domains.values(
) and domain == gene_sets_domain and organism:
return filename((self.__get_selected_hier()), organism)
def __init__(self, parent=None):
super().__init__(self, parent)
self.input_data = None
self.ref_data = None
self.ontology = None
self.annotations = None
self.loaded_annotation_code = None
self.treeStructRootKey = None
self.probFunctions = [statistics.Binomial(), statistics.Hypergeometric()]
self.selectedTerms = []
self.selectionChanging = 0
self.__state = State.Ready
self.__scheduletimer = QTimer(self, singleShot=True)
self.__scheduletimer.timeout.connect(self.__update)
#############
# GUI
#############
self.tabs = gui.tabWidget(self.controlArea)
# Input tab
self.inputTab = gui.createTabPage(self.tabs, "Input")
box = gui.widgetBox(self.inputTab, "Info")
self.infoLabel = gui.widgetLabel(box, "No data on input\n")
gui.button(box, self, "Ontology/Annotation Info",
callback=self.ShowInfo,
tooltip="Show information on loaded ontology and annotations")
self.referenceRadioBox = gui.radioButtonsInBox(
self.inputTab, self, "useReferenceDataset",
["Entire genome", "Reference set (input)"],
tooltips=["Use entire genome for reference",
"Use genes from Referece Examples input signal as reference"],
box="Reference", callback=self.__invalidate)
self.referenceRadioBox.buttons[1].setDisabled(True)
gui.radioButtonsInBox(
self.inputTab, self, "aspectIndex",
["Biological process", "Cellular component", "Molecular function"],
box="Aspect", callback=self.__invalidate)
# Filter tab
self.filterTab = gui.createTabPage(self.tabs, "Filter")
box = gui.widgetBox(self.filterTab, "Filter GO Term Nodes")
gui.checkBox(box, self, "filterByNumOfInstances", "Genes",
callback=self.FilterAndDisplayGraph,
tooltip="Filter by number of input genes mapped to a term")
ibox = gui.indentedBox(box)
gui.spin(ibox, self, 'minNumOfInstances', 1, 100,
step=1, label='#:', labelWidth=15,
callback=self.FilterAndDisplayGraph,
callbackOnReturn=True,
tooltip="Min. number of input genes mapped to a term")
gui.checkBox(box, self, "filterByPValue_nofdr", "p-value",
callback=self.FilterAndDisplayGraph,
tooltip="Filter by term p-value")
gui.doubleSpin(gui.indentedBox(box), self, 'maxPValue_nofdr', 1e-8, 1,
step=1e-8, label='p:', labelWidth=15,
callback=self.FilterAndDisplayGraph,
callbackOnReturn=True,
tooltip="Max term p-value")
# use filterByPValue for FDR, as it was the default in prior versions
gui.checkBox(box, self, "filterByPValue", "FDR",
callback=self.FilterAndDisplayGraph,
tooltip="Filter by term FDR")
gui.doubleSpin(gui.indentedBox(box), self, 'maxPValue', 1e-8, 1,
step=1e-8, label='p:', labelWidth=15,
callback=self.FilterAndDisplayGraph,
callbackOnReturn=True,
tooltip="Max term p-value")
box = gui.widgetBox(box, "Significance test")
gui.radioButtonsInBox(box, self, "probFunc", ["Binomial", "Hypergeometric"],
tooltips=["Use binomial distribution test",
"Use hypergeometric distribution test"],
callback=self.__invalidate) # TODO: only update the p values
box = gui.widgetBox(self.filterTab, "Evidence codes in annotation",
addSpace=True)
self.evidenceCheckBoxDict = {}
for etype in go.evidenceTypesOrdered:
ecb = QCheckBox(
etype, toolTip=go.evidenceTypes[etype],
checked=self.useEvidenceType[etype])
ecb.toggled.connect(self.__on_evidenceChanged)
box.layout().addWidget(ecb)
self.evidenceCheckBoxDict[etype] = ecb
# Select tab
self.selectTab = gui.createTabPage(self.tabs, "Select")
box = gui.radioButtonsInBox(
self.selectTab, self, "selectionDirectAnnotation",
["Directly or Indirectly", "Directly"],
box="Annotated genes",
callback=self.ExampleSelection)
box = gui.widgetBox(self.selectTab, "Output", addSpace=True)
gui.radioButtonsInBox(
box, self, "selectionDisjoint",
btnLabels=["All selected genes",
"Term-specific genes",
"Common term genes"],
tooltips=["Outputs genes annotated to all selected GO terms",
"Outputs genes that appear in only one of selected GO terms",
"Outputs genes common to all selected GO terms"],
callback=self.ExampleSelection)
# ListView for DAG, and table for significant GOIDs
self.DAGcolumns = ['GO term', 'Cluster', 'Reference', 'p-value',
'FDR', 'Genes', 'Enrichment']
self.splitter = QSplitter(Qt.Vertical, self.mainArea)
self.mainArea.layout().addWidget(self.splitter)
# list view
self.listView = GOTreeWidget(self.splitter)
self.listView.setSelectionMode(QTreeView.ExtendedSelection)
self.listView.setAllColumnsShowFocus(1)
self.listView.setColumnCount(len(self.DAGcolumns))
self.listView.setHeaderLabels(self.DAGcolumns)
self.listView.header().setSectionsClickable(True)
self.listView.header().setSortIndicatorShown(True)
self.listView.header().setSortIndicator(self.DAGcolumns.index('p-value'), Qt.AscendingOrder)
self.listView.setSortingEnabled(True)
self.listView.setItemDelegateForColumn(
6, EnrichmentColumnItemDelegate(self))
self.listView.setRootIsDecorated(True)
self.listView.itemSelectionChanged.connect(self.ViewSelectionChanged)
# table of significant GO terms
self.sigTerms = QTreeWidget(self.splitter)
self.sigTerms.setColumnCount(len(self.DAGcolumns))
self.sigTerms.setHeaderLabels(self.DAGcolumns)
self.sigTerms.setSortingEnabled(True)
self.sigTerms.setSelectionMode(QTreeView.ExtendedSelection)
self.sigTerms.header().setSortIndicator(self.DAGcolumns.index('p-value'), Qt.AscendingOrder)
self.sigTerms.setItemDelegateForColumn(
6, EnrichmentColumnItemDelegate(self))
self.sigTerms.itemSelectionChanged.connect(self.TableSelectionChanged)
self.sigTableTermsSorted = []
self.graph = {}
self.originalGraph = None
self.inputTab.layout().addStretch(1)
self.filterTab.layout().addStretch(1)
self.selectTab.layout().addStretch(1)
class AnnotationSlot(SimpleNamespace):
taxid = ... # type: str
name = ... # type: str
filename = ... # type:str
@staticmethod
def parse_tax_id(f_name):
return f_name.split('.')[1]
try:
remote_files = serverfiles.ServerFiles().listfiles(DOMAIN)
except (ConnectTimeout, RequestException, ConnectionError):
# TODO: Warn user about failed connection to the remote server
remote_files = []
self.available_annotations = [
AnnotationSlot(
taxid=AnnotationSlot.parse_tax_id(annotation_file),
name=taxonomy.common_taxid_to_name(AnnotationSlot.parse_tax_id(annotation_file)),
filename=FILENAME_ANNOTATION.format(AnnotationSlot.parse_tax_id(annotation_file))
)
for _, annotation_file in set(remote_files + serverfiles.listfiles(DOMAIN))
if annotation_file != FILENAME_ONTOLOGY
]
self._executor = ThreadExecutor()
with gzip.open(os.path.join(domain_path, FTP_FILE_ANNOTATIONS), 'rb') as gene2go:
header = gene2go.readline()
for line in gene2go:
split_line = line.decode().split('\t')
if split_line[0] in tax_ids:
store_lines_by_taxid[split_line[0]].append(line)
#else:
#parent = taxonomy.parent(split_line[0])
#if parent in tax_ids:
#store_lines_by_taxid[parent].append(line)
for org, lines in store_lines_by_taxid.items():
filename = FILENAME_ANNOTATION.format(org)
FILE_PATH = os.path.join(domain_path, filename)
TITLE = "GO Annotations for " + common_taxid_to_name(org)
TAGS = ["gene", "annotation", "ontology", "GO", org]
with open(FILE_PATH, 'wb') as f:
f.write(header)
f.writelines(lines)
db_size = os.stat(FILE_PATH).st_size # store uncompressed database size
with bz2.BZ2File(os.path.join(temp_path, filename), mode='w', compresslevel=9) as f_compressed:
shutil.copyfileobj(open(os.path.join(domain_path, filename), 'rb'), f_compressed)
create_info_file(os.path.join(temp_path, filename),
domain=DOMAIN,