def plot(self, profile, statsResults):
if len(profile.profileDict) <= 0:
self.emptyAxis()
return
# *** Colour of plot elements
axesColour = str(self.preferences['Axes colour'].name())
profile1Colour = str(self.preferences['Sample 1 colour'].name())
profile2Colour = str(self.preferences['Sample 2 colour'].name())
# *** Determine most abundant features
features = []
field1 = []
field2 = []
parentField1 = []
parentField2 = []
if self.bOnlyActiveFeatures:
activeFeatures = set([d[0] for d in statsResults.activeData])
tables = profile.getLabeledTables()
for table in tables:
feature, seq1, seq2, parentSeq1, parentSeq2 = table
if self.bOnlyActiveFeatures and feature not in activeFeatures:
continue
field1.append(seq1)
field2.append(seq2)
parentField1.append(parentSeq1)
parentField2.append(parentSeq2)
features.append(feature)
fields = zip(field1, field2, parentField1, parentField2, features)
fields.sort(reverse = True)
field1, field2, parentField1, parentField2, features = zip(*fields)
if len(field1) > self.numFeaturesToShow:
field1 = list(field1[0:self.numFeaturesToShow])
field2 = list(field2[0:self.numFeaturesToShow])
parentField1 = parentField1[0:self.numFeaturesToShow]
parentField2 = parentField2[0:self.numFeaturesToShow]
features = list(features[0:self.numFeaturesToShow])
else:
field1 = list(field1)
field2 = list(field2)
features = list(features)
# *** Create lists for each quantity of interest and calculate CIs
wilsonCI = WilsonCI()
confInter1 = []
confInter2 = []
if self.fieldToPlot == 'Number of sequences':
for i in xrange(0, len(field1)):
if self.bShowCIs:
lowerCI, upperCI, p = wilsonCI.run(field1[i], parentField1[i], 0.95, 1.96)
confInter1.append(max((p - lowerCI)*parentField1[i], 0))
lowerCI, upperCI, p = wilsonCI.run(field2[i], parentField2[i], 0.95, 1.96)
confInter2.append(max((p - lowerCI)*parentField2[i], 0))
else:
confInter1.append(0)
confInter2.append(0)
elif self.fieldToPlot == 'Proportion of sequences (%)':
for i in xrange(0, len(field1)):
if self.bShowCIs:
lowerCI, upperCI, p = wilsonCI.run(field1[i], parentField1[i], 0.95, 1.96)
confInter1.append(max((p - lowerCI)*100, 0))
lowerCI, upperCI, p = wilsonCI.run(field2[i], parentField2[i], 0.95, 1.96)
confInter2.append(max((p - lowerCI)*100, 0))
else:
confInter1.append(0)
confInter2.append(0)
field1[i] = float(field1[i])*100 / max(parentField1[i],1)
field2[i] = float(field2[i])*100 / max(parentField2[i],1)
# *** Truncate feature labels
highlightedFeatures = list(self.preferences['Highlighted sample features'])
truncatedNames = list(features)
if self.preferences['Truncate feature names']:
length = self.preferences['Length of truncated feature names']
for i in xrange(0, len(truncatedNames)):
if len(truncatedNames[i]) > length+3:
truncatedNames[i] = truncatedNames[i][0:length] + '...'
for i in xrange(0, len(highlightedFeatures)):
if len(highlightedFeatures[i]) > length+3:
highlightedFeatures[i] = highlightedFeatures[i][0:length] + '...'
# *** Find longest label
longestLabelLen = 0
for i in xrange(0, len(truncatedNames)):
if len(truncatedNames[i]) > longestLabelLen:
longestLabelLen = len(truncatedNames[i])
longestLabel = truncatedNames[i]
# *** Set figure size
self.fig.clear()
figWidth = self.figColWidth*len(features)
figHeight = self.figHeight
if figWidth > 256 or figHeight > 256:
QtGui.QApplication.instance().setOverrideCursor(QtGui.QCursor(QtCore.Qt.ArrowCursor))
self.emptyAxis()
QtGui.QMessageBox.question(self, 'Excessively large plot', 'The resulting plot is too large to display.')
QtGui.QApplication.instance().restoreOverrideCursor()
return
self.fig.set_size_inches(figWidth, figHeight)
xLabelBounds, yLabelBounds = self.labelExtents([longestLabel], 8, 90, ['%.0f' % max(max(field1), max(field2))], 8, 0)
yLabelOffset = 0.3
padding = 0.15 # inches
newFigWidth = figWidth + yLabelBounds.width / figWidth + 2*padding + yLabelOffset
self.fig.set_size_inches(newFigWidth, figHeight)
xOffsetFigSpace = yLabelBounds.width + padding/newFigWidth + yLabelOffset / newFigWidth
yOffsetFigSpace = xLabelBounds.height + padding/figHeight
axesBar = self.fig.add_axes([xOffsetFigSpace, yOffsetFigSpace,
1.0 - xOffsetFigSpace - padding/newFigWidth,
1.0 - yOffsetFigSpace - padding/figHeight])
# *** Plot data
colWidth = self.figColWidth
barWidth = (colWidth*(self.barWidth/100.0)) / 2
if self.bShowCIs == True:
rects1 = axesBar.bar(np.arange(len(features))*colWidth, field1, width=barWidth, color=profile1Colour, yerr=confInter1, ecolor='black', capsize=self.endCapSize)
rects2 = axesBar.bar(np.arange(len(features))*colWidth + barWidth, field2, width=barWidth, color=profile2Colour, yerr=confInter2, ecolor='black', capsize=self.endCapSize)
else:
rects1 = axesBar.bar(np.arange(len(features))*colWidth, field1, width=barWidth, color=profile1Colour)
rects2 = axesBar.bar(np.arange(len(features))*colWidth + barWidth, field2, width=barWidth, color=profile2Colour)
axesBar.set_xticks(np.arange(len(features))*colWidth + barWidth)
axesBar.set_xlim([0, (len(features)-1.0)*colWidth + 2*barWidth + 0.1])
axesBar.set_ylim(0, axesBar.get_ylim()[1])
axesBar.set_xticklabels(truncatedNames, size=8)
axesBar.set_ylabel(self.fieldToPlot, fontsize=8)
# *** Mark significant features
if self.bShowPvalue and statsResults.profile != None:
offset = axesBar.get_ylim()[1]*0.02
x = []
y = []
for i in xrange(0, len(features)):
pValue = float(statsResults.getFeatureStatistic(features[i], 'pValuesCorrected'))
if pValue <= self.pValueThreshold:
x.append(i*colWidth + barWidth)
y.append(max(field1[i], field2[i]) + offset)
axesBar.plot(x, y, color='k', linestyle='', marker='*', markeredgecolor='k', ms = 3)
# *** Prettify plot
if self.legendPos != -1:
legend = axesBar.legend([rects1[0], rects2[0]], (profile.sampleNames[0], profile.sampleNames[1]), loc=self.legendPos)
legend.get_frame().set_linewidth(0)
for label in axesBar.get_xticklabels():
label.set_rotation(90)
if label.get_text() in highlightedFeatures:
label.set_color('red')
for a in axesBar.yaxis.majorTicks:
a.tick1On=False
a.tick2On=False
for a in axesBar.xaxis.majorTicks:
a.tick1On=False
a.tick2On=False
for loc, spine in axesBar.spines.iteritems():
if loc in ['right','top']:
spine.set_color('none')
else:
spine.set_color(axesColour)
self.updateGeometry()
self.draw()
def plot(self, profile, statsResults):
if len(profile.profileDict) <= 0:
self.emptyAxis()
return
# *** Colour of plot elements
axesColour = str(self.preferences['Axes colour'].name())
profile1Colour = str(self.preferences['Sample 1 colour'].name())
profile2Colour = str(self.preferences['Sample 2 colour'].name())
# *** Determine most abundant features
features = []
field1 = []
field2 = []
parentField1 = []
parentField2 = []
if self.bOnlyActiveFeatures:
activeFeatures = set([d[0] for d in statsResults.activeData])
tables = profile.getLabeledTables()
for table in tables:
feature, seq1, seq2, parentSeq1, parentSeq2 = table
if self.bOnlyActiveFeatures and feature not in activeFeatures:
continue
field1.append(seq1)
field2.append(seq2)
parentField1.append(parentSeq1)
parentField2.append(parentSeq2)
features.append(feature)
fields = zip(field1, field2, parentField1, parentField2, features)
fields.sort(reverse=True)
field1, field2, parentField1, parentField2, features = zip(*fields)
if len(field1) > self.numFeaturesToShow:
field1 = list(field1[0:self.numFeaturesToShow])
field2 = list(field2[0:self.numFeaturesToShow])
parentField1 = parentField1[0:self.numFeaturesToShow]
parentField2 = parentField2[0:self.numFeaturesToShow]
features = list(features[0:self.numFeaturesToShow])
else:
field1 = list(field1)
field2 = list(field2)
features = list(features)
# *** Create lists for each quantity of interest and calculate CIs
wilsonCI = WilsonCI()
confInter1 = []
confInter2 = []
if self.fieldToPlot == 'Number of sequences':
for i in xrange(0, len(field1)):
if self.bShowCIs:
lowerCI, upperCI, p = wilsonCI.run(field1[i],
parentField1[i], 0.95,
1.96)
confInter1.append(max((p - lowerCI) * parentField1[i], 0))
lowerCI, upperCI, p = wilsonCI.run(field2[i],
parentField2[i], 0.95,
1.96)
confInter2.append(max((p - lowerCI) * parentField2[i], 0))
else:
confInter1.append(0)
confInter2.append(0)
elif self.fieldToPlot == 'Proportion of sequences (%)':
for i in xrange(0, len(field1)):
if self.bShowCIs:
lowerCI, upperCI, p = wilsonCI.run(field1[i],
parentField1[i], 0.95,
1.96)
confInter1.append(max((p - lowerCI) * 100, 0))
lowerCI, upperCI, p = wilsonCI.run(field2[i],
parentField2[i], 0.95,
1.96)
confInter2.append(max((p - lowerCI) * 100, 0))
else:
confInter1.append(0)
confInter2.append(0)
field1[i] = float(field1[i]) * 100 / max(parentField1[i], 1)
field2[i] = float(field2[i]) * 100 / max(parentField2[i], 1)
# *** Truncate feature labels
highlightedFeatures = list(
self.preferences['Highlighted sample features'])
truncatedNames = list(features)
if self.preferences['Truncate feature names']:
length = self.preferences['Length of truncated feature names']
for i in xrange(0, len(truncatedNames)):
if len(truncatedNames[i]) > length + 3:
truncatedNames[i] = truncatedNames[i][0:length] + '...'
for i in xrange(0, len(highlightedFeatures)):
if len(highlightedFeatures[i]) > length + 3:
highlightedFeatures[
i] = highlightedFeatures[i][0:length] + '...'
# *** Find longest label
longestLabelLen = 0
for i in xrange(0, len(truncatedNames)):
if len(truncatedNames[i]) > longestLabelLen:
longestLabelLen = len(truncatedNames[i])
longestLabel = truncatedNames[i]
# *** Set figure size
self.fig.clear()
figWidth = self.figColWidth * len(features)
figHeight = self.figHeight
if figWidth > 256 or figHeight > 256:
QtGui.QApplication.instance().setOverrideCursor(
QtGui.QCursor(QtCore.Qt.ArrowCursor))
self.emptyAxis()
QtGui.QMessageBox.question(
self, 'Excessively large plot',
'The resulting plot is too large to display.')
QtGui.QApplication.instance().restoreOverrideCursor()
return
self.fig.set_size_inches(figWidth, figHeight)
xLabelBounds, yLabelBounds = self.labelExtents(
[longestLabel], 8, 90, ['%.0f' % max(max(field1), max(field2))], 8,
0)
yLabelOffset = 0.3
padding = 0.15 # inches
newFigWidth = figWidth + yLabelBounds.width / figWidth + 2 * padding + yLabelOffset
self.fig.set_size_inches(newFigWidth, figHeight)
xOffsetFigSpace = yLabelBounds.width + padding / newFigWidth + yLabelOffset / newFigWidth
yOffsetFigSpace = xLabelBounds.height + padding / figHeight
axesBar = self.fig.add_axes([
xOffsetFigSpace, yOffsetFigSpace,
1.0 - xOffsetFigSpace - padding / newFigWidth,
1.0 - yOffsetFigSpace - padding / figHeight
])
# *** Plot data
colWidth = self.figColWidth
barWidth = (colWidth * (self.barWidth / 100.0)) / 2
if self.bShowCIs == True:
rects1 = axesBar.bar(np.arange(len(features)) * colWidth,
field1,
width=barWidth,
color=profile1Colour,
yerr=confInter1,
ecolor='black',
capsize=self.endCapSize)
rects2 = axesBar.bar(np.arange(len(features)) * colWidth +
barWidth,
field2,
width=barWidth,
color=profile2Colour,
yerr=confInter2,
ecolor='black',
capsize=self.endCapSize)
else:
rects1 = axesBar.bar(np.arange(len(features)) * colWidth,
field1,
width=barWidth,
color=profile1Colour)
rects2 = axesBar.bar(np.arange(len(features)) * colWidth +
barWidth,
field2,
width=barWidth,
color=profile2Colour)
axesBar.set_xticks(np.arange(len(features)) * colWidth + barWidth)
axesBar.set_xlim(
[0, (len(features) - 1.0) * colWidth + 2 * barWidth + 0.1])
axesBar.set_ylim(0, axesBar.get_ylim()[1])
axesBar.set_xticklabels(truncatedNames, size=8)
axesBar.set_ylabel(self.fieldToPlot, fontsize=8)
# *** Mark significant features
if self.bShowPvalue and statsResults.profile != None:
offset = axesBar.get_ylim()[1] * 0.02
x = []
y = []
for i in xrange(0, len(features)):
pValue = float(
statsResults.getFeatureStatistic(features[i],
'pValuesCorrected'))
if pValue <= self.pValueThreshold:
x.append(i * colWidth + barWidth)
y.append(max(field1[i], field2[i]) + offset)
axesBar.plot(x,
y,
color='k',
linestyle='',
marker='*',
markeredgecolor='k',
ms=3)
# *** Prettify plot
if self.legendPos != -1:
legend = axesBar.legend(
[rects1[0], rects2[0]],
(profile.sampleNames[0], profile.sampleNames[1]),
loc=self.legendPos)
legend.get_frame().set_linewidth(0)
for label in axesBar.get_xticklabels():
label.set_rotation(90)
if label.get_text() in highlightedFeatures:
label.set_color('red')
for a in axesBar.yaxis.majorTicks:
a.tick1On = False
a.tick2On = False
for a in axesBar.xaxis.majorTicks:
a.tick1On = False
a.tick2On = False
for loc, spine in axesBar.spines.iteritems():
if loc in ['right', 'top']:
spine.set_color('none')
else:
spine.set_color(axesColour)
self.updateGeometry()
self.draw()
def plot(self, profile, statsResults):
if len(profile.profileDict) <= 1:
self.emptyAxis()
return
if len(profile.profileDict) > 10000:
QtGui.QApplication.instance().setOverrideCursor(QtGui.QCursor(QtCore.Qt.ArrowCursor))
reply = QtGui.QMessageBox.question(self, 'Continue?', 'Profile contains ' + str(len(profile.profileDict)) + ' features. ' +
'It may take several seconds to generate this plot. Exploring the data at a higher hierarchy level is recommended. ' +
'Do you wish to continue?', QtGui.QMessageBox.Yes, QtGui.QMessageBox.No)
QtGui.QApplication.instance().restoreOverrideCursor()
if reply == QtGui.QMessageBox.No:
self.emptyAxis()
return
# *** Colour of plot elements
axesColour = str(self.preferences['Axes colour'].name())
profile1Colour = str(self.preferences['Sample 1 colour'].name())
profile2Colour = str(self.preferences['Sample 2 colour'].name())
# *** Create lists for each quantity of interest and calculate CIs
tables = profile.getLabeledTables()
features = []
field1 = []
field2 = []
wilsonCI = WilsonCI()
confInter1 = []
confInter2 = []
for table in tables:
feature, seq1, seq2, parentSeq1, parentSeq2 = table
features.append(feature)
field1.append(float(seq1)*100 / max(parentSeq1,1))
field2.append(float(seq2)*100 / max(parentSeq2,1))
if self.bShowCIs:
lowerCI, upperCI, p = wilsonCI.run(seq1, parentSeq1, 0.95, 1.96)
confInter1.append([max(lowerCI*100, 0), min(upperCI*100,100)])
lowerCI, upperCI, p = wilsonCI.run(seq2, parentSeq2, 0.95, 1.96)
confInter2.append([max(lowerCI*100, 0), min(upperCI*100,100)])
# *** Set figure size
self.fig.clear()
self.fig.set_size_inches(self.figWidth, self.figHeight)
if self.bShowHistograms:
histogramSizeX = self.histogramSize /self.figWidth
histogramSizeY = self.histogramSize /self.figHeight
else:
histogramSizeX = 0.0
histogramSizeY = 0.0
padding = 0.1 # inches
xOffsetFigSpace = (0.4 + padding)/self.figWidth
yOffsetFigSpace = (0.3 + padding)/self.figHeight
axesScatter = self.fig.add_axes([xOffsetFigSpace, yOffsetFigSpace,
1.0 - xOffsetFigSpace - histogramSizeX - (2*padding)/self.figWidth, 1.0 - yOffsetFigSpace - histogramSizeY - (2*padding)/self.figHeight])
if self.bShowHistograms:
axesTopHistogram = self.fig.add_axes([xOffsetFigSpace, 1.0 - histogramSizeY - padding/self.figHeight,
1.0 - xOffsetFigSpace - histogramSizeX - (2*padding)/self.figWidth, histogramSizeY])
axesRightHistogram = self.fig.add_axes([1.0 - histogramSizeX - padding/self.figWidth, yOffsetFigSpace,
histogramSizeX, 1.0 - yOffsetFigSpace - histogramSizeY - (2*padding)/self.figHeight])
# *** Handle mouse events
tooltips = []
for i in xrange(0, len(field1)):
tooltip = features[i] + '\n\n'
tooltip += 'Sequences in ' + profile.sampleNames[0] + ': ' + str(tables[i][1]) + '\n'
tooltip += 'Sequences in ' + profile.sampleNames[1] + ': ' + str(tables[i][2]) + '\n\n'
tooltip += (profile.sampleNames[0] + ' percentage: %.3f' % field1[i]) + '\n'
tooltip += (profile.sampleNames[1] + ' percentage: %.3f' % field2[i]) + '\n\n'
tooltip += 'Difference between proportions (%): ' + ('%.3f' % (field1[i] - field2[i])) + '\n'
if field2[i] != 0:
tooltip += 'Ratio of proportions: %.3f' % (field1[i]/field2[i])
else:
tooltip += 'Ratio of proportions: undefined'
if statsResults.profile != None:
pValue = statsResults.getFeatureStatisticAsStr(features[i], 'pValues')
pValueCorrected = statsResults.getFeatureStatisticAsStr(features[i], 'pValuesCorrected')
tooltip += '\n\n'
tooltip += 'p-value: ' + pValue + '\n'
tooltip += 'Corrected p-value: ' + pValueCorrected
tooltips.append(tooltip)
self.plotEventHandler = PlotEventHandler(field1, field2, tooltips)
self.mouseEventCallback(self.plotEventHandler)
# *** Calculate R^2 value
slope, intercept, r_value, p_value, std_err = linregress(field1, field2)
# *** Plot data
# set visual properties of all points
colours = []
highlightedField1 = []
highlightedField2 = []
highlighColours = []
for i in xrange(0, len(field1)):
if field1[i] > field2[i]:
colours.append(profile1Colour)
else:
colours.append(profile2Colour)
if features[i] in self.preferences['Highlighted sample features']:
highlightedField1.append(field1[i])
highlightedField2.append(field2[i])
highlighColours.append(colours[i])
# scatter plot
axesScatter.scatter(field1, field2, c=colours, s=self.markerSize, zorder=5)
if len(highlightedField1) > 0:
axesScatter.scatter(highlightedField1, highlightedField2, c=highlighColours, s=self.markerSize, edgecolors = 'red', linewidth = 2, zorder=10)
# plot CIs
if self.bShowCIs:
xlist = []
ylist = []
for i in xrange(0, len(field1)):
# horizontal CIs
xlist.append(confInter1[i][0])
xlist.append(confInter1[i][1])
xlist.append(None)
ylist.append(field2[i])
ylist.append(field2[i])
ylist.append(None)
# vertical CIs
xlist.append(field1[i])
xlist.append(field1[i])
xlist.append(None)
ylist.append(confInter2[i][0])
ylist.append(confInter2[i][1])
ylist.append(None)
axesScatter.plot(xlist, ylist, '-', color='gray', antialiased=False)
# plot y=x line
maxProportion = max(max(field1),max(field2))*1.05
axesScatter.plot([0,maxProportion],[0,maxProportion], color=axesColour, linestyle='dashed', marker='', zorder = 1)
axesScatter.set_xlabel(profile.sampleNames[0] + ' (%)')
axesScatter.set_ylabel(profile.sampleNames[1] + ' (%)')
if self.bShowR2:
axesScatter.text(0.02, 0.98, r'R$^2$ = ' + ('%0.3f' % r_value**2), horizontalalignment='left', verticalalignment='top', transform=axesScatter.transAxes)
axesScatter.set_xlim(0, maxProportion)
axesScatter.set_ylim(0, maxProportion)
# *** Prettify scatter plot
for line in axesScatter.yaxis.get_ticklines():
line.set_color(axesColour)
for line in axesScatter.xaxis.get_ticklines():
line.set_color(axesColour)
for loc, spine in axesScatter.spines.iteritems():
spine.set_color(axesColour)
# plot histograms
if not self.bShowHistograms:
for a in axesScatter.yaxis.majorTicks:
a.tick1On=True
a.tick2On=False
for a in axesScatter.xaxis.majorTicks:
a.tick1On=True
a.tick2On=False
for line in axesScatter.yaxis.get_ticklines():
line.set_color(axesColour)
for line in axesScatter.xaxis.get_ticklines():
line.set_color(axesColour)
for loc, spine in axesScatter.spines.iteritems():
if loc in ['right','top']:
spine.set_color('none')
else:
spine.set_color(axesColour)
else: # show histograms
# plot top histogram
axesTopHistogram.xaxis.set_major_formatter(NullFormatter())
pdf, bins, patches = axesTopHistogram.hist(field1, bins = self.numBins, facecolor = profile1Colour)
axesTopHistogram.set_xlim(axesScatter.get_xlim())
axesTopHistogram.set_yticks([0, max(pdf)])
axesTopHistogram.set_ylim([0, max(pdf)*1.05])
# plot right histogram
axesRightHistogram.yaxis.set_major_formatter(NullFormatter())
pdf, bins, patches = axesRightHistogram.hist(field2, bins = self.numBins, orientation='horizontal', facecolor = profile2Colour)
axesRightHistogram.set_ylim(axesScatter.get_ylim())
axesRightHistogram.set_xticks([0, max(pdf)])
axesRightHistogram.set_xlim([0, max(pdf)*1.05])
# *** Prettify histogram plot
for a in axesTopHistogram.yaxis.majorTicks:
a.tick1On=True
a.tick2On=False
for a in axesTopHistogram.xaxis.majorTicks:
a.tick1On=True
a.tick2On=False
for line in axesTopHistogram.yaxis.get_ticklines():
line.set_color(axesColour)
for line in axesTopHistogram.xaxis.get_ticklines():
line.set_color(axesColour)
for loc, spine in axesTopHistogram.spines.iteritems():
if loc in ['right','top']:
spine.set_color('none')
else:
spine.set_color(axesColour)
for a in axesRightHistogram.yaxis.majorTicks:
a.tick1On=True
a.tick2On=False
for a in axesRightHistogram.xaxis.majorTicks:
a.tick1On=True
a.tick2On=False
for line in axesRightHistogram.yaxis.get_ticklines():
line.set_color(axesColour)
for line in axesRightHistogram.xaxis.get_ticklines():
line.set_color(axesColour)
for loc, spine in axesRightHistogram.spines.iteritems():
if loc in ['right','top']:
spine.set_color('none')
else:
spine.set_color(axesColour)
self.updateGeometry()
self.draw()
