class OWItemsets(widget.OWWidget):
name = 'Frequent Itemsets'
description = 'Explore sets of items that frequently appear together.'
icon = 'icons/FrequentItemsets.svg'
priority = 10
class Inputs:
data = Input("Data", Table)
class Outputs:
matching_data = Output("Matching Data", Table)
class Error(widget.OWWidget.Error):
need_discrete_data = widget.Msg(
"Need some discrete data to work with.")
no_disc_features = widget.Msg(
"Discrete features required but data has none.")
class Warning(widget.OWWidget.Warning):
cont_attrs = widget.Msg(
"Data has continuous attributes which will be skipped.")
err_reg_expression = widget.Msg("Error in regular expression: {}")
minSupport = settings.Setting(30)
maxItemsets = settings.Setting(10000)
filterSearch = settings.Setting(True)
autoFind = settings.Setting(False)
autoSend = settings.Setting(True)
filterKeywords = settings.Setting('')
filterMinItems = settings.Setting(1)
filterMaxItems = settings.Setting(10000)
UserAdviceMessages = [
widget.Message(
'Itemset are listed in item-sorted order, i.e. '
'an itemset containing A and B is only listed once, as '
'A > B (and not also B > A).', 'itemsets-order',
widget.Message.Warning),
widget.Message(
'To select all the itemsets that are descendants of '
'(include) some item X (i.e. the whole subtree), you '
'can fold the subtree at that item and then select it.',
'itemsets-order', widget.Message.Information)
]
def __init__(self):
self.data = None
self.output = None
self._is_running = False
self.isRegexMatch = lambda x: True
self.tree = QTreeWidget(self.mainArea,
columnCount=2,
allColumnsShowFocus=True,
alternatingRowColors=True,
selectionMode=QTreeWidget.ExtendedSelection,
uniformRowHeights=True)
self.tree.setHeaderLabels(["Itemsets", "Support", "%"])
self.tree.header().setStretchLastSection(True)
self.tree.itemSelectionChanged.connect(self.selectionChanged)
self.mainArea.layout().addWidget(self.tree)
box = gui.widgetBox(self.controlArea, "Info")
self.nItemsets = self.nSelectedExamples = self.nSelectedItemsets = ''
gui.label(box, self, "Number of itemsets: %(nItemsets)s")
gui.label(box, self, "Selected itemsets: %(nSelectedItemsets)s")
gui.label(box, self, "Selected examples: %(nSelectedExamples)s")
hbox = gui.widgetBox(box, orientation='horizontal')
gui.button(hbox, self, "Expand all", callback=self.tree.expandAll)
gui.button(hbox, self, "Collapse all", callback=self.tree.collapseAll)
box = gui.widgetBox(self.controlArea, 'Find itemsets')
gui.valueSlider(box,
self,
'minSupport',
values=[.0001, .0005, .001, .005, .01, .05, .1, .5] +
list(range(1, 101)),
label='Minimal support:',
labelFormat="%g%%",
callback=lambda: self.find_itemsets())
gui.hSlider(box,
self,
'maxItemsets',
minValue=10000,
maxValue=100000,
step=10000,
label='Max. number of itemsets:',
labelFormat="%d",
callback=lambda: self.find_itemsets())
self.button = gui.auto_commit(
box,
self,
'autoFind',
'Find Itemsets',
commit=self.find_itemsets,
callback=lambda: self.autoFind and self.find_itemsets())
box = gui.widgetBox(self.controlArea, 'Filter itemsets')
gui.lineEdit(box,
self,
'filterKeywords',
'Contains:',
callback=self.filter_change,
orientation='horizontal',
tooltip='A comma or space-separated list of regular '
'expressions.')
hbox = gui.widgetBox(box, orientation='horizontal')
gui.spin(hbox,
self,
'filterMinItems',
1,
998,
label='Min. items:',
callback=self.filter_change)
gui.spin(hbox,
self,
'filterMaxItems',
2,
999,
label='Max. items:',
callback=self.filter_change)
gui.checkBox(box,
self,
'filterSearch',
label='Apply these filters in search',
tooltip='If checked, the itemsets are filtered according '
'to these filter conditions already in the search '
'phase. \nIf unchecked, the only filters applied '
'during search are the ones above, '
'and the itemsets are \nfiltered afterwards only for '
'display, i.e. only the matching itemsets are shown.')
gui.rubber(hbox)
gui.rubber(self.controlArea)
gui.auto_commit(self.controlArea, self, 'autoSend', 'Send selection')
self.filter_change()
ITEM_DATA_ROLE = Qt.UserRole + 1
def selectionChanged(self):
X = self.X
mapping = self.onehot_mapping
instances = set()
where = np.where
def whole_subtree(node):
yield node
for i in range(node.childCount()):
yield from whole_subtree(node.child(i))
def itemset(node):
while node:
yield node.data(0, self.ITEM_DATA_ROLE)
node = node.parent()
def selection_ranges(node):
n_children = node.childCount()
if n_children:
yield (self.tree.indexFromItem(node.child(0)),
self.tree.indexFromItem(node.child(n_children - 1)))
for i in range(n_children):
yield from selection_ranges(node.child(i))
nSelectedItemsets = 0
item_selection = QItemSelection()
for node in self.tree.selectedItems():
nodes = (node, ) if node.isExpanded() else whole_subtree(node)
if not node.isExpanded():
for srange in selection_ranges(node):
item_selection.select(*srange)
for node in nodes:
nSelectedItemsets += 1
cols, vals = zip(*(mapping[i] for i in itemset(node)))
if issparse(X):
rows = (len(cols) == np.bincount(
(X[:, cols] != 0).indices,
minlength=X.shape[0])).nonzero()[0]
else:
rows = where((X[:, cols] == vals).all(axis=1))[0]
instances.update(rows)
self.tree.itemSelectionChanged.disconnect(self.selectionChanged)
self.tree.selectionModel().select(
item_selection,
QItemSelectionModel.Select | QItemSelectionModel.Rows)
self.tree.itemSelectionChanged.connect(self.selectionChanged)
self.nSelectedExamples = len(instances)
self.nSelectedItemsets = nSelectedItemsets
self.output = self.data[sorted(instances)] or None
self.commit()
def commit(self):
self.Outputs.matching_data.send(self.output)
def filter_change(self):
self.Warning.err_reg_expression.clear()
try:
isRegexMatch = self.isRegexMatch = re.compile(
'|'.join(
i.strip()
for i in re.split('(,|\s)+', self.filterKeywords.strip())
if i.strip()), re.IGNORECASE).search
except Exception as e:
self.Warning.err_reg_expression(e.args[0])
isRegexMatch = self.isRegexMatch = lambda x: True
def hide(node, depth, has_kw):
if not has_kw:
has_kw = isRegexMatch(node.text(0))
hidden = (
sum(
hide(node.child(i), depth + 1, has_kw)
for i in range(node.childCount())) == node.childCount()
if node.childCount() else
(not has_kw
or not self.filterMinItems <= depth <= self.filterMaxItems))
node.setHidden(hidden)
return hidden
hide(self.tree.invisibleRootItem(), 0, False)
class TreeWidgetItem(QTreeWidgetItem):
def data(self, column, role):
"""Construct lazy tooltips"""
if role != Qt.ToolTipRole:
return super().data(column, role)
tooltip = []
while self:
tooltip.append(self.text(0))
self = self.parent()
return '\n'.join(reversed(tooltip))
def find_itemsets(self):
if self.data is None or not len(self.data):
return
if self._is_running:
self._is_running = False
return
self._is_running = True
self.button.button.setText('Cancel')
data = self.data
self.tree.clear()
self.tree.setUpdatesEnabled(False)
self.tree.blockSignals(True)
class ItemDict(dict):
def __init__(self, item):
self.item = item
top = ItemDict(self.tree.invisibleRootItem())
X, mapping = OneHot.encode(data)
self.Error.need_discrete_data.clear()
if X is None:
self.Error.need_discrete_data()
self.onehot_mapping = mapping
ITEM_FMT = '{}' if issparse(data.X) else '{}={}'
names = {
item: ITEM_FMT.format(var.name, val)
for item, var, val in OneHot.decode(mapping.keys(), data, mapping)
}
nItemsets = 0
filterSearch = self.filterSearch
filterMinItems, filterMaxItems = self.filterMinItems, self.filterMaxItems
isRegexMatch = self.isRegexMatch
# Find itemsets and populate the TreeView
with self.progressBar(self.maxItemsets + 1) as progress:
for itemset, support in frequent_itemsets(X,
self.minSupport / 100):
if filterSearch and not filterMinItems <= len(
itemset) <= filterMaxItems:
continue
parent = top
first_new_item = None
itemset_matches_filter = False
for item in sorted(itemset):
name = names[item]
if filterSearch and not itemset_matches_filter:
itemset_matches_filter = isRegexMatch(name)
child = parent.get(name)
if child is None:
try:
wi = self.TreeWidgetItem(parent.item, [
name,
str(support), '{:.4g}'.format(
100 * support / len(data))
])
except RuntimeError:
# FIXME: When autoFind was in effect and the support
# slider was moved, this line excepted with:
# RuntimeError: wrapped C/C++ object of type
# TreeWidgetItem has been deleted
return
wi.setData(0, self.ITEM_DATA_ROLE, item)
child = parent[name] = ItemDict(wi)
if first_new_item is None:
first_new_item = (parent, name)
parent = child
if filterSearch and not itemset_matches_filter:
parent, name = first_new_item
parent.item.removeChild(parent[name].item)
del parent[name].item
del parent[name]
else:
nItemsets += 1
progress.advance()
if not self._is_running or nItemsets >= self.maxItemsets:
break
qApp.processEvents()
if not filterSearch:
self.filter_change()
self.nItemsets = nItemsets
self.nSelectedItemsets = 0
self.nSelectedExamples = 0
self.tree.expandAll()
for i in range(self.tree.columnCount()):
self.tree.resizeColumnToContents(i)
self.tree.setUpdatesEnabled(True)
self.tree.blockSignals(False)
self._is_running = False
self.button.button.setText('Find Itemsets')
@Inputs.data
def set_data(self, data):
self.data = data
is_error = False
if data is not None:
self.Warning.cont_attrs.clear()
self.Error.no_disc_features.clear()
self.button.setDisabled(False)
self.X = data.X
if issparse(data.X):
self.X = data.X.tocsc()
else:
if not data.domain.has_discrete_attributes():
self.Error.no_disc_features()
is_error = True
self.button.setDisabled(True)
elif data.domain.has_continuous_attributes():
self.Warning.cont_attrs()
else:
self.output = None
self.commit()
if self.autoFind and not is_error:
self.find_itemsets()
class OWKEGGPathwayBrowser(widget.OWWidget):
name = "KEGG Pathways"
description = "Browse KEGG pathways that include an input set of genes."
icon = "../widgets/icons/KEGGPathways.svg"
priority = 2030
inputs = [("Data", Orange.data.Table, "SetData", widget.Default), ("Reference", Orange.data.Table, "SetRefData")]
outputs = [("Selected Data", Orange.data.Table, widget.Default), ("Unselected Data", Orange.data.Table)]
settingsHandler = settings.DomainContextHandler()
organismIndex = settings.ContextSetting(0)
geneAttrIndex = settings.ContextSetting(0)
useAttrNames = settings.ContextSetting(False)
autoCommit = settings.Setting(False)
autoResize = settings.Setting(True)
useReference = settings.Setting(False)
showOrthology = settings.Setting(True)
Ready, Initializing, Running = 0, 1, 2
def __init__(self, parent=None):
super().__init__(parent)
self.organismCodes = []
self._changedFlag = False
self.__invalidated = False
self.__runstate = OWKEGGPathwayBrowser.Initializing
self.__in_setProgress = False
self.controlArea.setMaximumWidth(250)
box = gui.widgetBox(self.controlArea, "Info")
self.infoLabel = gui.widgetLabel(box, "No data on input\n")
# Organism selection.
box = gui.widgetBox(self.controlArea, "Organism")
self.organismComboBox = gui.comboBox(
box,
self,
"organismIndex",
items=[],
callback=self.Update,
addSpace=True,
tooltip="Select the organism of the input genes",
)
# Selection of genes attribute
box = gui.widgetBox(self.controlArea, "Gene attribute")
self.geneAttrCandidates = itemmodels.VariableListModel(parent=self)
self.geneAttrCombo = gui.comboBox(box, self, "geneAttrIndex", callback=self.Update)
self.geneAttrCombo.setModel(self.geneAttrCandidates)
gui.checkBox(
box, self, "useAttrNames", "Use variable names", disables=[(-1, self.geneAttrCombo)], callback=self.Update
)
self.geneAttrCombo.setDisabled(bool(self.useAttrNames))
gui.separator(self.controlArea)
gui.checkBox(self.controlArea, self, "useReference", "From signal", box="Reference", callback=self.Update)
gui.separator(self.controlArea)
gui.checkBox(
self.controlArea,
self,
"showOrthology",
"Show pathways in full orthology",
box="Orthology",
callback=self.UpdateListView,
)
gui.checkBox(
self.controlArea, self, "autoResize", "Resize to fit", box="Image", callback=self.UpdatePathwayViewTransform
)
box = gui.widgetBox(self.controlArea, "Cache Control")
gui.button(
box,
self,
"Clear cache",
callback=self.ClearCache,
tooltip="Clear all locally cached KEGG data.",
default=False,
autoDefault=False,
)
gui.separator(self.controlArea)
gui.auto_commit(self.controlArea, self, "autoCommit", "Commit")
gui.rubber(self.controlArea)
spliter = QSplitter(Qt.Vertical, self.mainArea)
self.pathwayView = PathwayView(self, spliter)
self.pathwayView.scene().selectionChanged.connect(self._onSelectionChanged)
self.mainArea.layout().addWidget(spliter)
self.listView = QTreeWidget(
allColumnsShowFocus=True, selectionMode=QTreeWidget.SingleSelection, sortingEnabled=True, maximumHeight=200
)
spliter.addWidget(self.listView)
self.listView.setColumnCount(4)
self.listView.setHeaderLabels(["Pathway", "P value", "Genes", "Reference"])
self.listView.itemSelectionChanged.connect(self.UpdatePathwayView)
select = QAction("Select All", self, shortcut=QKeySequence.SelectAll)
select.triggered.connect(self.selectAll)
self.addAction(select)
self.data = None
self.refData = None
self._executor = concurrent.ThreadExecutor()
self.setEnabled(False)
self.setBlocking(True)
progress = concurrent.methodinvoke(self, "setProgress", (float,))
def get_genome():
"""Return a KEGGGenome with the common org entries precached."""
genome = kegg.KEGGGenome()
essential = genome.essential_organisms()
common = genome.common_organisms()
# Remove duplicates of essential from common.
# (essential + common list as defined here will be used in the
# GUI.)
common = [c for c in common if c not in essential]
# TODO: Add option to specify additional organisms not
# in the common list.
keys = list(map(genome.org_code_to_entry_key, essential + common))
genome.pre_cache(keys, progress_callback=progress)
return (keys, genome)
self._genomeTask = task = concurrent.Task(function=get_genome)
task.finished.connect(self.__initialize_finish)
self.progressBarInit()
self.infoLabel.setText("Fetching organism definitions\n")
self._executor.submit(task)
def __initialize_finish(self):
if self.__runstate != OWKEGGPathwayBrowser.Initializing:
return
try:
keys, genome = self._genomeTask.result()
except Exception as err:
self.error(0, str(err))
raise
self.progressBarFinished()
self.setEnabled(True)
self.setBlocking(False)
entries = [genome[key] for key in keys]
items = [entry.definition for entry in entries]
codes = [entry.organism_code for entry in entries]
self.organismCodes = codes
self.organismComboBox.clear()
self.organismComboBox.addItems(items)
self.organismComboBox.setCurrentIndex(self.organismIndex)
self.infoLabel.setText("No data on input\n")
def Clear(self):
"""
Clear the widget state.
"""
self.queryGenes = []
self.referenceGenes = []
self.genes = {}
self.uniqueGenesDict = {}
self.revUniqueGenesDict = {}
self.pathways = {}
self.org = None
self.geneAttrCandidates[:] = []
self.infoLabel.setText("No data on input\n")
self.listView.clear()
self.pathwayView.SetPathway(None)
self.send("Selected Data", None)
self.send("Unselected Data", None)
def SetData(self, data=None):
if self.__runstate == OWKEGGPathwayBrowser.Initializing:
self.__initialize_finish()
self.closeContext()
self.data = data
self.warning(0)
self.error(0)
self.information(0)
if data is not None:
vars = data.domain.variables + data.domain.metas
vars = [var for var in vars if isinstance(var, Orange.data.StringVariable)]
self.geneAttrCandidates[:] = vars
# Try to guess the gene name variable
if vars:
names_lower = [v.name.lower() for v in vars]
scores = [(name == "gene", "gene" in name) for name in names_lower]
imax, _ = max(enumerate(scores), key=itemgetter(1))
else:
imax = -1
self.geneAttrIndex = imax
taxid = data_hints.get_hint(data, "taxid", None)
if taxid:
try:
code = kegg.from_taxid(taxid)
self.organismIndex = self.organismCodes.index(code)
except Exception as ex:
print(ex, taxid)
self.useAttrNames = data_hints.get_hint(data, "genesinrows", self.useAttrNames)
self.openContext(data)
if len(self.geneAttrCandidates) == 0:
self.useAttrNames = True
self.geneAttrIndex = -1
else:
self.geneAttrIndex = min(self.geneAttrIndex, len(self.geneAttrCandidates) - 1)
else:
self.Clear()
self.__invalidated = True
def SetRefData(self, data=None):
self.refData = data
self.information(1)
if data is not None and self.useReference:
self.__invalidated = True
def handleNewSignals(self):
if self.__invalidated:
self.Update()
self.__invalidated = False
def UpdateListView(self):
self.bestPValueItem = None
self.listView.clear()
if not self.data:
return
allPathways = self.org.pathways()
allRefPathways = kegg.pathways("map")
items = []
kegg_pathways = kegg.KEGGPathways()
org_code = self.organismCodes[min(self.organismIndex, len(self.organismCodes) - 1)]
if self.showOrthology:
self.koOrthology = kegg.KEGGBrite("ko00001")
self.listView.setRootIsDecorated(True)
path_ids = set([s[-5:] for s in self.pathways.keys()])
def _walkCollect(koEntry):
num = koEntry.title[:5] if koEntry.title else None
if num in path_ids:
return [koEntry] + reduce(
lambda li, c: li + _walkCollect(c), [child for child in koEntry.entries], []
)
else:
c = reduce(lambda li, c: li + _walkCollect(c), [child for child in koEntry.entries], [])
return c + (c and [koEntry] or [])
allClasses = reduce(lambda li1, li2: li1 + li2, [_walkCollect(c) for c in self.koOrthology], [])
def _walkCreate(koEntry, lvItem):
item = QTreeWidgetItem(lvItem)
id = "path:" + org_code + koEntry.title[:5]
if koEntry.title[:5] in path_ids:
p = kegg_pathways.get_entry(id)
if p is None:
# In case the genesets still have obsolete entries
name = koEntry.title
else:
name = p.name
genes, p_value, ref = self.pathways[id]
item.setText(0, name)
item.setText(1, "%.5f" % p_value)
item.setText(2, "%i of %i" % (len(genes), len(self.genes)))
item.setText(3, "%i of %i" % (ref, len(self.referenceGenes)))
item.pathway_id = id if p is not None else None
else:
if id in allPathways:
text = kegg_pathways.get_entry(id).name
else:
text = koEntry.title
item.setText(0, text)
if id in allPathways:
item.pathway_id = id
elif "path:map" + koEntry.title[:5] in allRefPathways:
item.pathway_id = "path:map" + koEntry.title[:5]
else:
item.pathway_id = None
for child in koEntry.entries:
if child in allClasses:
_walkCreate(child, item)
for koEntry in self.koOrthology:
if koEntry in allClasses:
_walkCreate(koEntry, self.listView)
self.listView.update()
else:
self.listView.setRootIsDecorated(False)
pathways = self.pathways.items()
pathways = sorted(pathways, key=lambda item: item[1][1])
for id, (genes, p_value, ref) in pathways:
item = QTreeWidgetItem(self.listView)
item.setText(0, kegg_pathways.get_entry(id).name)
item.setText(1, "%.5f" % p_value)
item.setText(2, "%i of %i" % (len(genes), len(self.genes)))
item.setText(3, "%i of %i" % (ref, len(self.referenceGenes)))
item.pathway_id = id
items.append(item)
self.bestPValueItem = items and items[0] or None
self.listView.expandAll()
for i in range(4):
self.listView.resizeColumnToContents(i)
if self.bestPValueItem:
index = self.listView.indexFromItem(self.bestPValueItem)
self.listView.selectionModel().select(index, QItemSelectionModel.ClearAndSelect)
def UpdatePathwayView(self):
items = self.listView.selectedItems()
if len(items) > 0:
item = items[0]
else:
item = None
self.commit()
item = item or self.bestPValueItem
if not item or not item.pathway_id:
self.pathwayView.SetPathway(None)
return
def get_kgml_and_image(pathway_id):
"""Return an initialized KEGGPathway with pre-cached data"""
p = kegg.KEGGPathway(pathway_id)
p._get_kgml() # makes sure the kgml file is downloaded
p._get_image_filename() # makes sure the image is downloaded
return (pathway_id, p)
self.setEnabled(False)
self._pathwayTask = concurrent.Task(function=lambda: get_kgml_and_image(item.pathway_id))
self._pathwayTask.finished.connect(self._onPathwayTaskFinshed)
self._executor.submit(self._pathwayTask)
def _onPathwayTaskFinshed(self):
self.setEnabled(True)
pathway_id, self.pathway = self._pathwayTask.result()
self.pathwayView.SetPathway(self.pathway, self.pathways.get(pathway_id, [[]])[0])
def UpdatePathwayViewTransform(self):
self.pathwayView.updateTransform()
def Update(self):
"""
Update (recompute enriched pathways) the widget state.
"""
if not self.data:
return
self.error(0)
self.information(0)
# XXX: Check data in setData, do not even alow this to be executed if
# data has no genes
try:
genes = self.GeneNamesFromData(self.data)
except ValueError:
self.error(0, "Cannot extract gene names from input.")
genes = []
if not self.useAttrNames and any("," in gene for gene in genes):
genes = reduce(add, (split_and_strip(gene, ",") for gene in genes), [])
self.information(0, "Separators detected in input gene names. " "Assuming multiple genes per instance.")
self.queryGenes = genes
self.information(1)
reference = None
if self.useReference and self.refData:
reference = self.GeneNamesFromData(self.refData)
if not self.useAttrNames and any("," in gene for gene in reference):
reference = reduce(add, (split_and_strip(gene, ",") for gene in reference), [])
self.information(
1, "Separators detected in reference gene " "names. Assuming multiple genes per " "instance."
)
org_code = self.SelectedOrganismCode()
def run_enrichment(org_code, genes, reference=None, progress=None):
org = kegg.KEGGOrganism(org_code)
if reference is None:
reference = org.get_genes()
# Map 'genes' and 'reference' sets to unique KEGG identifiers
unique_genes, _, _ = org.get_unique_gene_ids(set(genes))
unique_ref_genes, _, _ = org.get_unique_gene_ids(set(reference))
taxid = kegg.to_taxid(org.org_code)
# Map the taxid back to standard 'common' taxids
# (as used by 'geneset') if applicable
r_tax_map = dict((v, k) for k, v in kegg.KEGGGenome.TAXID_MAP.items())
if taxid in r_tax_map:
taxid = r_tax_map[taxid]
# We use the kegg pathway gene sets provided by 'geneset' for
# the enrichment calculation.
# Ensure we are using the latest genesets
# TODO: ?? Is updating the index enough?
serverfiles.update(geneset.sfdomain, "index.pck")
kegg_gs_collections = geneset.collections((("KEGG", "pathways"), taxid))
pathways = pathway_enrichment(
kegg_gs_collections, unique_genes.keys(), unique_ref_genes.keys(), callback=progress
)
# Ensure that pathway entries are pre-cached for later use in the
# list/tree view
kegg_pathways = kegg.KEGGPathways()
kegg_pathways.pre_cache(pathways.keys(), progress_callback=progress)
return pathways, org, unique_genes, unique_ref_genes
self.progressBarInit()
self.setEnabled(False)
self.infoLabel.setText("Retrieving...\n")
progress = concurrent.methodinvoke(self, "setProgress", (float,))
self._enrichTask = concurrent.Task(function=lambda: run_enrichment(org_code, genes, reference, progress))
self._enrichTask.finished.connect(self._onEnrichTaskFinished)
self._executor.submit(self._enrichTask)
def _onEnrichTaskFinished(self):
self.setEnabled(True)
self.setBlocking(False)
try:
pathways, org, unique_genes, unique_ref_genes = self._enrichTask.result()
except Exception:
raise
self.progressBarFinished()
self.org = org
self.genes = unique_genes.keys()
self.uniqueGenesDict = unique_genes
self.revUniqueGenesDict = dict([(val, key) for key, val in self.uniqueGenesDict.items()])
self.referenceGenes = unique_ref_genes.keys()
self.pathways = pathways
if not self.pathways:
self.warning(0, "No enriched pathways found.")
else:
self.warning(0)
count = len(set(self.queryGenes))
self.infoLabel.setText(
"%i unique gene names on input\n"
"%i (%.1f%%) genes names matched"
% (count, len(unique_genes), 100.0 * len(unique_genes) / count if count else 0.0)
)
self.UpdateListView()
@Slot(float)
def setProgress(self, value):
if self.__in_setProgress:
return
self.__in_setProgress = True
self.progressBarSet(value)
self.__in_setProgress = False
def GeneNamesFromData(self, data):
"""
Extract and return gene names from `data`.
"""
if self.useAttrNames:
genes = [str(v.name).strip() for v in data.domain.attributes]
elif self.geneAttrCandidates:
assert 0 <= self.geneAttrIndex < len(self.geneAttrCandidates)
geneAttr = self.geneAttrCandidates[self.geneAttrIndex]
genes = [str(e[geneAttr]) for e in data if not numpy.isnan(e[geneAttr])]
else:
raise ValueError("No gene names in data.")
return genes
def SelectedOrganismCode(self):
"""
Return the selected organism code.
"""
return self.organismCodes[min(self.organismIndex, len(self.organismCodes) - 1)]
def selectAll(self):
"""
Select all items in the pathway view.
"""
changed = False
scene = self.pathwayView.scene()
with disconnected(scene.selectionChanged, self._onSelectionChanged):
for item in scene.items():
if item.flags() & QGraphicsItem.ItemIsSelectable and not item.isSelected():
item.setSelected(True)
changed = True
if changed:
self._onSelectionChanged()
def _onSelectionChanged(self):
# Item selection in the pathwayView/scene has changed
self.commit()
def commit(self):
if self.data:
selectedItems = self.pathwayView.scene().selectedItems()
selectedGenes = reduce(set.union, [item.marked_objects for item in selectedItems], set())
if self.useAttrNames:
selected = [self.data.domain[self.uniqueGenesDict[gene]] for gene in selectedGenes]
# newDomain = Orange.data.Domain(selectedVars, 0)
data = self.data[:, selected]
# data = Orange.data.Table(newDomain, self.data)
self.send("Selected Data", data)
elif self.geneAttrCandidates:
assert 0 <= self.geneAttrIndex < len(self.geneAttrCandidates)
geneAttr = self.geneAttrCandidates[self.geneAttrIndex]
selectedIndices = []
otherIndices = []
for i, ex in enumerate(self.data):
names = [
self.revUniqueGenesDict.get(name, None) for name in split_and_strip(str(ex[geneAttr]), ",")
]
if any(name and name in selectedGenes for name in names):
selectedIndices.append(i)
else:
otherIndices.append(i)
if selectedIndices:
selected = self.data[selectedIndices]
else:
selected = None
if otherIndices:
other = self.data[otherIndices]
else:
other = None
self.send("Selected Data", selected)
self.send("Unselected Data", other)
else:
self.send("Selected Data", None)
self.send("Unselected Data", None)
def ClearCache(self):
kegg.caching.clear_cache()
def onDeleteWidget(self):
"""
Called before the widget is removed from the canvas.
"""
super().onDeleteWidget()
self.org = None
self._executor.shutdown(wait=False)
gc.collect() # Force collection (WHY?)
def sizeHint(self):
return QSize(1024, 720)
class OWKEGGPathwayBrowser(widget.OWWidget):
name = "KEGG Pathways"
description = "Browse KEGG pathways that include an input set of genes."
icon = "../widgets/icons/OWKEGGPathwayBrowser.svg"
priority = 70
inputs = [("Data", Orange.data.Table, "SetData", widget.Default),
("Reference", Orange.data.Table, "SetRefData")]
outputs = [("Selected Data", Orange.data.Table, widget.Default),
("Unselected Data", Orange.data.Table)]
autoCommit = settings.Setting(False)
autoResize = settings.Setting(True)
useReference = settings.Setting(False)
showOrthology = settings.Setting(True)
Ready, Initializing, Running = 0, 1, 2
class Error(widget.OWWidget.Error):
missing_annotation = widget.Msg(ERROR_ON_MISSING_ANNOTATION)
missing_gene_id = widget.Msg(ERROR_ON_MISSING_GENE_ID)
missing_tax_id = widget.Msg(ERROR_ON_MISSING_TAX_ID)
def __init__(self, parent=None):
super().__init__(parent)
self._changedFlag = False
self.__invalidated = False
self.__runstate = OWKEGGPathwayBrowser.Initializing
self.__in_setProgress = False
self.controlArea.setMaximumWidth(250)
box = gui.widgetBox(self.controlArea, "Info")
self.infoLabel = gui.widgetLabel(box, "No data on input\n")
gui.separator(self.controlArea)
gui.checkBox(self.controlArea,
self,
"useReference",
"From signal",
box="Reference",
callback=self.Update)
gui.separator(self.controlArea)
gui.checkBox(
self.controlArea,
self,
"showOrthology",
"Show pathways in full orthology",
box="Orthology",
callback=self.UpdateListView,
)
gui.checkBox(
self.controlArea,
self,
"autoResize",
"Resize to fit",
box="Image",
callback=self.UpdatePathwayViewTransform,
)
box = gui.widgetBox(self.controlArea, "Cache Control")
gui.button(
box,
self,
"Clear cache",
callback=self.ClearCache,
tooltip="Clear all locally cached KEGG data.",
default=False,
autoDefault=False,
)
gui.separator(self.controlArea)
gui.auto_commit(self.controlArea, self, "autoCommit", "Commit")
gui.rubber(self.controlArea)
spliter = QSplitter(Qt.Vertical, self.mainArea)
self.pathwayView = PathwayView(self, spliter)
self.pathwayView.scene().selectionChanged.connect(
self._onSelectionChanged)
self.mainArea.layout().addWidget(spliter)
self.listView = QTreeWidget(allColumnsShowFocus=True,
selectionMode=QTreeWidget.SingleSelection,
sortingEnabled=True,
maximumHeight=200)
spliter.addWidget(self.listView)
self.listView.setColumnCount(4)
self.listView.setHeaderLabels(
["Pathway", "P value", "Genes", "Reference"])
self.listView.itemSelectionChanged.connect(self.UpdatePathwayView)
select = QAction("Select All", self, shortcut=QKeySequence.SelectAll)
select.triggered.connect(self.selectAll)
self.addAction(select)
self.data = None
self.input_genes = []
self.tax_id = None
self.use_attr_names = None
self.gene_id_attribute = None
self.gene_id_column = None
self.ref_data = None
self.ref_genes = []
self.ref_tax_id = None
self.ref_use_attr_names = None
self.ref_gene_id_attribute = None
self.ref_gene_id_column = None
self.pathways = {}
self.ncbi_gene_map = []
self.org = None
self._executor = concurrent.ThreadExecutor()
self.setEnabled(False)
self.setBlocking(True)
progress = concurrent.methodinvoke(self, "setProgress", (float, ))
def get_genome():
"""Return a KEGGGenome with the common org entries precached."""
genome = kegg.KEGGGenome()
essential = genome.essential_organisms()
common = genome.common_organisms()
# Remove duplicates of essential from common.
# (essential + common list as defined here will be used in the
# GUI.)
common = [c for c in common if c not in essential]
# TODO: Add option to specify additional organisms not
# in the common list.
keys = list(map(genome.org_code_to_entry_key, essential + common))
genome.pre_cache(keys, progress_callback=progress)
return (keys, genome)
self._genomeTask = task = concurrent.Task(function=get_genome)
task.finished.connect(self.__initialize_finish)
self.progressBarInit()
self.infoLabel.setText("Fetching organism definitions\n")
self._executor.submit(task)
def __initialize_finish(self):
if self.__runstate != OWKEGGPathwayBrowser.Initializing:
return
try:
keys, genome = self._genomeTask.result()
except Exception as err:
self.error(0, str(err))
raise
self.progressBarFinished()
self.setEnabled(True)
self.setBlocking(False)
self.infoLabel.setText("No data on input\n")
def clear(self):
"""
Clear the widget state.
"""
self.pathways = {}
self.org = None
self.infoLabel.setText("No data on input\n")
self.listView.clear()
self.pathwayView.SetPathway(None)
self.send("Selected Data", None)
self.send("Unselected Data", None)
def SetData(self, data=None):
if self.__runstate == OWKEGGPathwayBrowser.Initializing:
self.__initialize_finish()
self.Error.clear()
if data:
self.data = data
self.tax_id = str(self.data.attributes.get(TAX_ID, None))
self.use_attr_names = self.data.attributes.get(
GENE_AS_ATTRIBUTE_NAME, None)
self.gene_id_attribute = self.data.attributes.get(
GENE_ID_ATTRIBUTE, None)
self.gene_id_column = self.data.attributes.get(
GENE_ID_COLUMN, None)
if not (self.use_attr_names is not None and
((self.gene_id_attribute is None) ^
(self.gene_id_column is None))):
if self.tax_id is None:
self.Error.missing_annotation()
return
self.Error.missing_gene_id()
return
elif self.tax_id is None:
self.Error.missing_tax_id()
return
self.warning(0)
self.error(0)
self.information(0)
self.__invalidated = True
else:
self.clear()
def SetRefData(self, data=None):
self.information(1)
if data is not None and self.useReference:
self.ref_data = data
self.ref_tax_id = str(self.ref_data.attributes.get(TAX_ID, None))
self.ref_use_attr_names = self.ref_data.attributes.get(
GENE_AS_ATTRIBUTE_NAME, None)
self.ref_gene_id_attribute = self.ref_data.attributes.get(
GENE_ID_ATTRIBUTE, None)
self.ref_gene_id_column = self.ref_data.attributes.get(
GENE_ID_COLUMN, None)
if not (self.ref_use_attr_names is not None and
((self.ref_gene_id_attribute is None) ^
(self.ref_gene_id_column is None))):
if self.ref_tax_id is None:
self.Error.missing_annotation()
return
self.Error.missing_gene_id()
return
elif self.ref_tax_id is None:
self.Error.missing_tax_id()
return
self.__invalidated = True
def handleNewSignals(self):
if self.__invalidated:
self.Update()
self.__invalidated = False
def UpdateListView(self):
self.bestPValueItem = None
self.listView.clear()
if not self.data:
return
allPathways = self.org.pathways()
allRefPathways = kegg.pathways("map")
items = []
kegg_pathways = kegg.KEGGPathways()
org_code = self.org.org_code
if self.showOrthology:
self.koOrthology = kegg.KEGGBrite("ko00001")
self.listView.setRootIsDecorated(True)
path_ids = {s[-5:] for s in self.pathways.keys()}
def _walkCollect(koEntry):
num = koEntry.title[:5] if koEntry.title else None
if num in path_ids:
return [koEntry] + reduce(
lambda li, c: li + _walkCollect(c),
[child for child in koEntry.entries], [])
else:
c = reduce(lambda li, c: li + _walkCollect(c),
[child for child in koEntry.entries], [])
return c + (c and [koEntry] or [])
allClasses = reduce(lambda li1, li2: li1 + li2,
[_walkCollect(c) for c in self.koOrthology],
[])
def _walkCreate(koEntry, lvItem):
item = QTreeWidgetItem(lvItem)
id = "path:" + org_code + koEntry.title[:5]
if koEntry.title[:5] in path_ids:
p = kegg_pathways.get_entry(id)
if p is None:
# In case the genesets still have obsolete entries
name = koEntry.title
else:
name = p.name
genes, p_value, ref = self.pathways[id]
item.setText(0, name)
item.setText(1, "%.5f" % p_value)
item.setText(
2, "%i of %i" % (len(genes), len(self.input_genes)))
item.setText(3, "%i of %i" % (ref, len(self.ref_genes)))
item.pathway_id = id if p is not None else None
else:
if id in allPathways:
text = kegg_pathways.get_entry(id).name
else:
text = koEntry.title
item.setText(0, text)
if id in allPathways:
item.pathway_id = id
elif "path:map" + koEntry.title[:5] in allRefPathways:
item.pathway_id = "path:map" + koEntry.title[:5]
else:
item.pathway_id = None
for child in koEntry.entries:
if child in allClasses:
_walkCreate(child, item)
for koEntry in self.koOrthology:
if koEntry in allClasses:
_walkCreate(koEntry, self.listView)
self.listView.update()
else:
self.listView.setRootIsDecorated(False)
pathways = self.pathways.items()
pathways = sorted(pathways, key=lambda item: item[1][1])
for id, (genes, p_value, ref) in pathways:
item = QTreeWidgetItem(self.listView)
item.setText(0, kegg_pathways.get_entry(id).name)
item.setText(1, "%.5f" % p_value)
item.setText(2,
"%i of %i" % (len(genes), len(self.input_genes)))
item.setText(3, "%i of %i" % (ref, len(self.ref_genes)))
item.pathway_id = id
items.append(item)
self.bestPValueItem = items and items[0] or None
self.listView.expandAll()
for i in range(4):
self.listView.resizeColumnToContents(i)
if self.bestPValueItem:
index = self.listView.indexFromItem(self.bestPValueItem)
self.listView.selectionModel().select(
index, QItemSelectionModel.ClearAndSelect)
def UpdatePathwayView(self):
items = self.listView.selectedItems()
if len(items) > 0:
item = items[0]
else:
item = None
self.commit()
item = item or self.bestPValueItem
if not item or not item.pathway_id:
self.pathwayView.SetPathway(None)
return
def get_kgml_and_image(pathway_id):
"""Return an initialized KEGGPathway with pre-cached data"""
p = kegg.KEGGPathway(pathway_id)
p._get_kgml() # makes sure the kgml file is downloaded
p._get_image_filename() # makes sure the image is downloaded
return (pathway_id, p)
self.setEnabled(False)
self._pathwayTask = concurrent.Task(
function=lambda: get_kgml_and_image(item.pathway_id))
self._pathwayTask.finished.connect(self._onPathwayTaskFinshed)
self._executor.submit(self._pathwayTask)
def _onPathwayTaskFinshed(self):
self.setEnabled(True)
pathway_id, self.pathway = self._pathwayTask.result()
objects = self.pathways.get(pathway_id, [[]])[0] # [ncbi_gene_id]
# map ncbi_gene_id to keg_id for display
objects = flatten(relation_map(self.ncbi_gene_map, objects))
self.pathwayView.SetPathway(self.pathway, objects)
def UpdatePathwayViewTransform(self):
self.pathwayView.updateTransform()
def Update(self):
"""
Update (recompute enriched pathways) the widget state.
"""
if not self.data:
return
self.error(0)
self.information(0)
# XXX: Check data in setData, do not even allow this to be executed if
# data has no genes
try:
self.__get_input_genes()
self.input_genes = set(self.input_genes)
except ValueError:
self.error(0, "Cannot extract gene names from input.")
self.information(1)
self.org = kegg.KEGGOrganism(kegg.from_taxid(self.tax_id))
if self.useReference and self.ref_data:
self.__get_ref_genes()
self.ref_genes = set(self.ref_genes)
else:
self.ref_genes = self.org.get_ncbi_ids()
def run_enrichment(org_code, genes, reference, progress=None):
# We use the kegg pathway gene sets provided by 'geneset' for
# the enrichment calculation.
kegg_api = kegg.api.CachedKeggApi()
link_map = kegg_api.link(org_code,
"pathway") # [(pathway_id, kegg_gene_id)]
ncbi_gene_map = kegg_api.conv(
org_code, 'ncbi-geneid') # [(ncbi_gene_id, kegg_gene_id)]
ncbi_gene_map = [(_1.split(":", 1)[1], _2)
for _1, _2 in ncbi_gene_map]
link_map = relation_join(
link_map,
[(_2, _1)
for _1, _2 in ncbi_gene_map]) # [(pathway_id, ncbi_gene_id)]
kegg_sets = relation_list_to_multimap(
link_map) # {pathway_id -> [ncbi_gene_ids]}
# map kegg gene ids to ncbi_gene_ids.
kegg_sets = geneset.GeneSets(sets=[
geneset.GeneSet(gs_id=ddi, genes=set(genes))
for ddi, genes in kegg_sets.items()
])
pathways = pathway_enrichment(kegg_sets,
genes,
reference,
callback=progress)
# Ensure that pathway entries are pre-cached for later use in the
# list/tree view
kegg_pathways = kegg.KEGGPathways()
kegg_pathways.pre_cache(pathways.keys(),
progress_callback=progress)
return pathways, ncbi_gene_map
self.progressBarInit()
self.setEnabled(False)
self.infoLabel.setText("Retrieving...\n")
progress = concurrent.methodinvoke(self, "setProgress", (float, ))
run_func = partial(run_enrichment, self.org.org_code, self.input_genes,
self.ref_genes, progress)
self._enrichTask = concurrent.Task(function=run_func)
self._enrichTask.finished.connect(self._onEnrichTaskFinished)
self._executor.submit(self._enrichTask)
def _onEnrichTaskFinished(self):
self.setEnabled(True)
self.setBlocking(False)
try:
pathways, ncbi_gene_map = self._enrichTask.result()
except Exception:
raise
self.progressBarFinished()
self.pathways = pathways
self.ncbi_gene_map = ncbi_gene_map
if not self.pathways:
self.warning(0, "No enriched pathways found.")
else:
self.warning(0)
self.infoLabel.setText("{} unique gene names on input\n".format(
len(set(self.input_genes))))
self.UpdateListView()
@Slot(float)
def setProgress(self, value):
if self.__in_setProgress:
return
self.__in_setProgress = True
self.progressBarSet(value)
self.__in_setProgress = False
def __get_input_genes(self):
"""
Extract and return gene names from `data`.
"""
self.input_genes = []
if self.use_attr_names:
for variable in self.data.domain.attributes:
self.input_genes.append(
str(variable.attributes.get(self.gene_id_attribute, '?')))
else:
genes, _ = self.data.get_column_view(self.gene_id_column)
self.input_genes = [str(g) for g in genes]
if len(self.input_genes) <= 0:
raise ValueError("No gene names in data.")
def __get_ref_genes(self):
"""
Extract and return gene names from `data`.
"""
self.ref_genes = []
if self.ref_use_attr_names:
for variable in self.ref_data.domain.attributes:
self.ref_genes.append(
str(
variable.attributes.get(self.ref_gene_id_attribute,
'?')))
else:
genes, _ = self.ref_data.get_column_view(self.ref_gene_id_column)
self.ref_genes = [str(g) for g in genes]
def selectAll(self):
"""
Select all items in the pathway view.
"""
changed = False
scene = self.pathwayView.scene()
with disconnected(scene.selectionChanged, self._onSelectionChanged):
for item in scene.items():
if item.flags(
) & QGraphicsItem.ItemIsSelectable and not item.isSelected():
item.setSelected(True)
changed = True
if changed:
self._onSelectionChanged()
def _onSelectionChanged(self):
# Item selection in the pathwayView/scene has changed
self.commit()
def commit(self):
if self.data:
selectedItems = self.pathwayView.scene().selectedItems()
selectedGenes = reduce(
set.union, [item.marked_objects for item in selectedItems],
set())
# map kegg_ids back to ncbi_gene_id
backmap = [(_2, _1) for _1, _2 in self.ncbi_gene_map]
selectedGenes = set(flatten(relation_map(backmap, selectedGenes)))
if self.use_attr_names:
selected = [
column for column in self.data.domain.attributes
if self.gene_id_attribute in column.attributes
and str(column.attributes[
self.gene_id_attribute]) in selectedGenes
]
data = self.data[:, selected]
self.send("Selected Data", data)
else:
selected_indices = []
other_indices = []
for row_index, row in enumerate(self.data):
gene_in_row = str(row[self.gene_id_column])
if gene_in_row in self.input_genes and gene_in_row in selectedGenes:
selected_indices.append(row_index)
else:
other_indices.append(row_index)
if selected_indices:
selected = self.data[selected_indices]
else:
selected = None
if other_indices:
other = self.data[other_indices]
else:
other = None
self.send("Selected Data", selected)
self.send("Unselected Data", other)
else:
self.send("Selected Data", None)
self.send("Unselected Data", None)
def ClearCache(self):
kegg.caching.clear_cache()
def onDeleteWidget(self):
"""
Called before the widget is removed from the canvas.
"""
super().onDeleteWidget()
self.org = None
self._executor.shutdown(wait=False)
gc.collect() # Force collection (WHY?)
def sizeHint(self):
return QSize(1024, 720)
class OWKEGGPathwayBrowser(widget.OWWidget):
name = "KEGG Pathways"
description = "Browse KEGG pathways that include an input set of genes."
icon = "../widgets/icons/OWKEGGPathwayBrowser.svg"
priority = 8
inputs = [("Data", Orange.data.Table, "SetData", widget.Default),
("Reference", Orange.data.Table, "SetRefData")]
outputs = [("Selected Data", Orange.data.Table, widget.Default),
("Unselected Data", Orange.data.Table)]
settingsHandler = settings.DomainContextHandler()
organismIndex = settings.ContextSetting(0)
geneAttrIndex = settings.ContextSetting(0)
useAttrNames = settings.ContextSetting(False)
autoCommit = settings.Setting(False)
autoResize = settings.Setting(True)
useReference = settings.Setting(False)
showOrthology = settings.Setting(True)
Ready, Initializing, Running = 0, 1, 2
def __init__(self, parent=None):
super().__init__(parent)
self.organismCodes = []
self._changedFlag = False
self.__invalidated = False
self.__runstate = OWKEGGPathwayBrowser.Initializing
self.__in_setProgress = False
self.controlArea.setMaximumWidth(250)
box = gui.widgetBox(self.controlArea, "Info")
self.infoLabel = gui.widgetLabel(box, "No data on input\n")
# Organism selection.
box = gui.widgetBox(self.controlArea, "Organism")
self.organismComboBox = gui.comboBox(
box, self, "organismIndex",
items=[],
callback=self.Update,
addSpace=True,
tooltip="Select the organism of the input genes")
# Selection of genes attribute
box = gui.widgetBox(self.controlArea, "Gene attribute")
self.geneAttrCandidates = itemmodels.VariableListModel(parent=self)
self.geneAttrCombo = gui.comboBox(
box, self, "geneAttrIndex", callback=self.Update)
self.geneAttrCombo.setModel(self.geneAttrCandidates)
gui.checkBox(box, self, "useAttrNames",
"Use variable names", disables=[(-1, self.geneAttrCombo)],
callback=self.Update)
self.geneAttrCombo.setDisabled(bool(self.useAttrNames))
gui.separator(self.controlArea)
gui.checkBox(self.controlArea, self, "useReference",
"From signal", box="Reference", callback=self.Update)
gui.separator(self.controlArea)
gui.checkBox(self.controlArea, self, "showOrthology",
"Show pathways in full orthology", box="Orthology",
callback=self.UpdateListView)
gui.checkBox(self.controlArea, self, "autoResize",
"Resize to fit", box="Image",
callback=self.UpdatePathwayViewTransform)
box = gui.widgetBox(self.controlArea, "Cache Control")
gui.button(box, self, "Clear cache",
callback=self.ClearCache,
tooltip="Clear all locally cached KEGG data.",
default=False, autoDefault=False)
gui.separator(self.controlArea)
gui.auto_commit(self.controlArea, self, "autoCommit", "Commit")
gui.rubber(self.controlArea)
spliter = QSplitter(Qt.Vertical, self.mainArea)
self.pathwayView = PathwayView(self, spliter)
self.pathwayView.scene().selectionChanged.connect(
self._onSelectionChanged
)
self.mainArea.layout().addWidget(spliter)
self.listView = QTreeWidget(
allColumnsShowFocus=True,
selectionMode=QTreeWidget.SingleSelection,
sortingEnabled=True,
maximumHeight=200)
spliter.addWidget(self.listView)
self.listView.setColumnCount(4)
self.listView.setHeaderLabels(
["Pathway", "P value", "Genes", "Reference"])
self.listView.itemSelectionChanged.connect(self.UpdatePathwayView)
select = QAction(
"Select All", self,
shortcut=QKeySequence.SelectAll
)
select.triggered.connect(self.selectAll)
self.addAction(select)
self.data = None
self.refData = None
self._executor = concurrent.ThreadExecutor()
self.setEnabled(False)
self.setBlocking(True)
progress = concurrent.methodinvoke(self, "setProgress", (float,))
def get_genome():
"""Return a KEGGGenome with the common org entries precached."""
genome = kegg.KEGGGenome()
essential = genome.essential_organisms()
common = genome.common_organisms()
# Remove duplicates of essential from common.
# (essential + common list as defined here will be used in the
# GUI.)
common = [c for c in common if c not in essential]
# TODO: Add option to specify additional organisms not
# in the common list.
keys = list(map(genome.org_code_to_entry_key, essential + common))
genome.pre_cache(keys, progress_callback=progress)
return (keys, genome)
self._genomeTask = task = concurrent.Task(function=get_genome)
task.finished.connect(self.__initialize_finish)
self.progressBarInit()
self.infoLabel.setText("Fetching organism definitions\n")
self._executor.submit(task)
def __initialize_finish(self):
if self.__runstate != OWKEGGPathwayBrowser.Initializing:
return
try:
keys, genome = self._genomeTask.result()
except Exception as err:
self.error(0, str(err))
raise
self.progressBarFinished()
self.setEnabled(True)
self.setBlocking(False)
entries = [genome[key] for key in keys]
items = [entry.definition for entry in entries]
codes = [entry.organism_code for entry in entries]
self.organismCodes = codes
self.organismComboBox.clear()
self.organismComboBox.addItems(items)
self.organismComboBox.setCurrentIndex(self.organismIndex)
self.infoLabel.setText("No data on input\n")
def Clear(self):
"""
Clear the widget state.
"""
self.queryGenes = []
self.referenceGenes = []
self.genes = {}
self.uniqueGenesDict = {}
self.revUniqueGenesDict = {}
self.pathways = {}
self.org = None
self.geneAttrCandidates[:] = []
self.infoLabel.setText("No data on input\n")
self.listView.clear()
self.pathwayView.SetPathway(None)
self.send("Selected Data", None)
self.send("Unselected Data", None)
def SetData(self, data=None):
if self.__runstate == OWKEGGPathwayBrowser.Initializing:
self.__initialize_finish()
self.data = data
self.warning(0)
self.error(0)
self.information(0)
if data is not None:
vars = data.domain.variables + data.domain.metas
vars = [var for var in vars
if isinstance(var, Orange.data.StringVariable)]
self.geneAttrCandidates[:] = vars
# Try to guess the gene name variable
if vars:
names_lower = [v.name.lower() for v in vars]
scores = [(name == "gene", "gene" in name)
for name in names_lower]
imax, _ = max(enumerate(scores), key=itemgetter(1))
else:
imax = -1
self.geneAttrIndex = imax
taxid = data_hints.get_hint(data, TAX_ID, None)
if taxid:
try:
code = kegg.from_taxid(taxid)
self.organismIndex = self.organismCodes.index(code)
except Exception as ex:
print(ex, taxid)
self.useAttrNames = data_hints.get_hint(data, GENE_NAME, self.useAttrNames)
if len(self.geneAttrCandidates) == 0:
self.useAttrNames = True
self.geneAttrIndex = -1
else:
self.geneAttrIndex = min(self.geneAttrIndex,
len(self.geneAttrCandidates) - 1)
else:
self.Clear()
self.__invalidated = True
def SetRefData(self, data=None):
self.refData = data
self.information(1)
if data is not None and self.useReference:
self.__invalidated = True
def handleNewSignals(self):
if self.__invalidated:
self.Update()
self.__invalidated = False
def UpdateListView(self):
self.bestPValueItem = None
self.listView.clear()
if not self.data:
return
allPathways = self.org.pathways()
allRefPathways = kegg.pathways("map")
items = []
kegg_pathways = kegg.KEGGPathways()
org_code = self.organismCodes[min(self.organismIndex,
len(self.organismCodes) - 1)]
if self.showOrthology:
self.koOrthology = kegg.KEGGBrite("ko00001")
self.listView.setRootIsDecorated(True)
path_ids = set([s[-5:] for s in self.pathways.keys()])
def _walkCollect(koEntry):
num = koEntry.title[:5] if koEntry.title else None
if num in path_ids:
return ([koEntry] +
reduce(lambda li, c: li + _walkCollect(c),
[child for child in koEntry.entries],
[]))
else:
c = reduce(lambda li, c: li + _walkCollect(c),
[child for child in koEntry.entries],
[])
return c + (c and [koEntry] or [])
allClasses = reduce(lambda li1, li2: li1 + li2,
[_walkCollect(c) for c in self.koOrthology],
[])
def _walkCreate(koEntry, lvItem):
item = QTreeWidgetItem(lvItem)
id = "path:" + org_code + koEntry.title[:5]
if koEntry.title[:5] in path_ids:
p = kegg_pathways.get_entry(id)
if p is None:
# In case the genesets still have obsolete entries
name = koEntry.title
else:
name = p.name
genes, p_value, ref = self.pathways[id]
item.setText(0, name)
item.setText(1, "%.5f" % p_value)
item.setText(2, "%i of %i" % (len(genes), len(self.genes)))
item.setText(3, "%i of %i" % (ref, len(self.referenceGenes)))
item.pathway_id = id if p is not None else None
else:
if id in allPathways:
text = kegg_pathways.get_entry(id).name
else:
text = koEntry.title
item.setText(0, text)
if id in allPathways:
item.pathway_id = id
elif "path:map" + koEntry.title[:5] in allRefPathways:
item.pathway_id = "path:map" + koEntry.title[:5]
else:
item.pathway_id = None
for child in koEntry.entries:
if child in allClasses:
_walkCreate(child, item)
for koEntry in self.koOrthology:
if koEntry in allClasses:
_walkCreate(koEntry, self.listView)
self.listView.update()
else:
self.listView.setRootIsDecorated(False)
pathways = self.pathways.items()
pathways = sorted(pathways, key=lambda item: item[1][1])
for id, (genes, p_value, ref) in pathways:
item = QTreeWidgetItem(self.listView)
item.setText(0, kegg_pathways.get_entry(id).name)
item.setText(1, "%.5f" % p_value)
item.setText(2, "%i of %i" % (len(genes), len(self.genes)))
item.setText(3, "%i of %i" % (ref, len(self.referenceGenes)))
item.pathway_id = id
items.append(item)
self.bestPValueItem = items and items[0] or None
self.listView.expandAll()
for i in range(4):
self.listView.resizeColumnToContents(i)
if self.bestPValueItem:
index = self.listView.indexFromItem(self.bestPValueItem)
self.listView.selectionModel().select(
index, QItemSelectionModel.ClearAndSelect
)
def UpdatePathwayView(self):
items = self.listView.selectedItems()
if len(items) > 0:
item = items[0]
else:
item = None
self.commit()
item = item or self.bestPValueItem
if not item or not item.pathway_id:
self.pathwayView.SetPathway(None)
return
def get_kgml_and_image(pathway_id):
"""Return an initialized KEGGPathway with pre-cached data"""
p = kegg.KEGGPathway(pathway_id)
p._get_kgml() # makes sure the kgml file is downloaded
p._get_image_filename() # makes sure the image is downloaded
return (pathway_id, p)
self.setEnabled(False)
self._pathwayTask = concurrent.Task(
function=lambda: get_kgml_and_image(item.pathway_id)
)
self._pathwayTask.finished.connect(self._onPathwayTaskFinshed)
self._executor.submit(self._pathwayTask)
def _onPathwayTaskFinshed(self):
self.setEnabled(True)
pathway_id, self.pathway = self._pathwayTask.result()
self.pathwayView.SetPathway(
self.pathway,
self.pathways.get(pathway_id, [[]])[0]
)
def UpdatePathwayViewTransform(self):
self.pathwayView.updateTransform()
def Update(self):
"""
Update (recompute enriched pathways) the widget state.
"""
if not self.data:
return
self.error(0)
self.information(0)
# XXX: Check data in setData, do not even allow this to be executed if
# data has no genes
try:
genes = self.GeneNamesFromData(self.data)
except ValueError:
self.error(0, "Cannot extract gene names from input.")
genes = []
if not self.useAttrNames and any("," in gene for gene in genes):
genes = reduce(add, (split_and_strip(gene, ",")
for gene in genes),
[])
self.information(0,
"Separators detected in input gene names. "
"Assuming multiple genes per instance.")
self.queryGenes = genes
self.information(1)
reference = None
if self.useReference and self.refData:
reference = self.GeneNamesFromData(self.refData)
if not self.useAttrNames \
and any("," in gene for gene in reference):
reference = reduce(add, (split_and_strip(gene, ",")
for gene in reference),
[])
self.information(1,
"Separators detected in reference gene "
"names. Assuming multiple genes per "
"instance.")
org_code = self.SelectedOrganismCode()
from orangecontrib.bioinformatics.ncbi.gene import GeneMatcher
gm = GeneMatcher(kegg.to_taxid(org_code))
gm.genes = genes
gm.run_matcher()
mapped_genes = {gene: str(ncbi_id) for gene, ncbi_id in gm.map_input_to_ncbi().items()}
def run_enrichment(org_code, genes, reference=None, progress=None):
org = kegg.KEGGOrganism(org_code)
if reference is None:
reference = org.get_ncbi_ids()
# This is here just to keep widget working without any major changes.
# map not needed, geneMatcher will not work on widget level.
unique_genes = genes
unique_ref_genes = dict([(gene, gene) for gene in set(reference)])
taxid = kegg.to_taxid(org.org_code)
# Map the taxid back to standard 'common' taxids
# (as used by 'geneset') if applicable
r_tax_map = dict((v, k) for k, v in
kegg.KEGGGenome.TAXID_MAP.items())
if taxid in r_tax_map:
taxid = r_tax_map[taxid]
# We use the kegg pathway gene sets provided by 'geneset' for
# the enrichment calculation.
kegg_api = kegg.api.CachedKeggApi()
linkmap = kegg_api.link(org.org_code, "pathway")
converted_ids = kegg_api.conv(org.org_code, 'ncbi-geneid')
kegg_sets = relation_list_to_multimap(linkmap, dict((gene.upper(), ncbi.split(':')[-1])
for ncbi, gene in converted_ids))
kegg_sets = geneset.GeneSets(input=kegg_sets)
pathways = pathway_enrichment(
kegg_sets, unique_genes.values(),
unique_ref_genes.keys(),
callback=progress
)
# Ensure that pathway entries are pre-cached for later use in the
# list/tree view
kegg_pathways = kegg.KEGGPathways()
kegg_pathways.pre_cache(
pathways.keys(), progress_callback=progress
)
return pathways, org, unique_genes, unique_ref_genes
self.progressBarInit()
self.setEnabled(False)
self.infoLabel.setText("Retrieving...\n")
progress = concurrent.methodinvoke(self, "setProgress", (float,))
self._enrichTask = concurrent.Task(
function=lambda:
run_enrichment(org_code, mapped_genes, reference, progress)
)
self._enrichTask.finished.connect(self._onEnrichTaskFinished)
self._executor.submit(self._enrichTask)
def _onEnrichTaskFinished(self):
self.setEnabled(True)
self.setBlocking(False)
try:
pathways, org, unique_genes, unique_ref_genes = \
self._enrichTask.result()
except Exception:
raise
self.progressBarFinished()
self.org = org
self.genes = unique_genes.keys()
self.uniqueGenesDict = {ncbi_id: input_name for input_name, ncbi_id in unique_genes.items()}
self.revUniqueGenesDict = dict([(val, key) for key, val in
self.uniqueGenesDict.items()])
self.referenceGenes = unique_ref_genes.keys()
self.pathways = pathways
if not self.pathways:
self.warning(0, "No enriched pathways found.")
else:
self.warning(0)
count = len(set(self.queryGenes))
self.infoLabel.setText(
"%i unique gene names on input\n"
"%i (%.1f%%) genes names matched" %
(count, len(unique_genes),
100.0 * len(unique_genes) / count if count else 0.0)
)
self.UpdateListView()
@Slot(float)
def setProgress(self, value):
if self.__in_setProgress:
return
self.__in_setProgress = True
self.progressBarSet(value)
self.__in_setProgress = False
def GeneNamesFromData(self, data):
"""
Extract and return gene names from `data`.
"""
if self.useAttrNames:
genes = [str(v.name).strip() for v in data.domain.attributes]
elif self.geneAttrCandidates:
assert 0 <= self.geneAttrIndex < len(self.geneAttrCandidates)
geneAttr = self.geneAttrCandidates[self.geneAttrIndex]
genes = [str(e[geneAttr]) for e in data
if not numpy.isnan(e[geneAttr])]
else:
raise ValueError("No gene names in data.")
return genes
def SelectedOrganismCode(self):
"""
Return the selected organism code.
"""
return self.organismCodes[min(self.organismIndex,
len(self.organismCodes) - 1)]
def selectAll(self):
"""
Select all items in the pathway view.
"""
changed = False
scene = self.pathwayView.scene()
with disconnected(scene.selectionChanged, self._onSelectionChanged):
for item in scene.items():
if item.flags() & QGraphicsItem.ItemIsSelectable and \
not item.isSelected():
item.setSelected(True)
changed = True
if changed:
self._onSelectionChanged()
def _onSelectionChanged(self):
# Item selection in the pathwayView/scene has changed
self.commit()
def commit(self):
if self.data:
selectedItems = self.pathwayView.scene().selectedItems()
selectedGenes = reduce(set.union, [item.marked_objects
for item in selectedItems],
set())
if self.useAttrNames:
selected = [self.data.domain[self.uniqueGenesDict[gene]]
for gene in selectedGenes]
# newDomain = Orange.data.Domain(selectedVars, 0)
data = self.data[:, selected]
# data = Orange.data.Table(newDomain, self.data)
self.send("Selected Data", data)
elif self.geneAttrCandidates:
assert 0 <= self.geneAttrIndex < len(self.geneAttrCandidates)
geneAttr = self.geneAttrCandidates[self.geneAttrIndex]
selectedIndices = []
otherIndices = []
for i, ex in enumerate(self.data):
names = [self.revUniqueGenesDict.get(name, None)
for name in split_and_strip(str(ex[geneAttr]), ",")]
if any(name and name in selectedGenes for name in names):
selectedIndices.append(i)
else:
otherIndices.append(i)
if selectedIndices:
selected = self.data[selectedIndices]
else:
selected = None
if otherIndices:
other = self.data[otherIndices]
else:
other = None
self.send("Selected Data", selected)
self.send("Unselected Data", other)
else:
self.send("Selected Data", None)
self.send("Unselected Data", None)
def ClearCache(self):
kegg.caching.clear_cache()
def onDeleteWidget(self):
"""
Called before the widget is removed from the canvas.
"""
super().onDeleteWidget()
self.org = None
self._executor.shutdown(wait=False)
gc.collect() # Force collection (WHY?)
def sizeHint(self):
return QSize(1024, 720)
