def addFeat(self,feat,colorMax,percent):
labelTab=[]
try :
labelTab=feat.qualifiers['product'][0].split(" ")
except KeyError:
print " NO PRODUCT FOUND FOR "
print feat
labelTab[0]="No name"
labelName=""
if len(labelTab)<= Track.maxLabelWord :
for word in labelTab :
labelName+=word+" "
else :
labelName=labelTab[0]+" "+labelTab[1]+" "+labelTab[2]+" "
labelName=labelName[0:len(labelName)-1]+" \n "+str(feat.location.start)+" - "+str(feat.location.end) #skip the final space and add location
#change location
newStart=feat.location.start-self.diff
newEnd=feat.location.end-self.diff
if newEnd > Track.maxSize :
Track.maxSize=newEnd
newLocation = FeatureLocation(newStart,newEnd,feat.strand)
feat.location=newLocation
if self.nbFeats==0:
self.gdFeature.add_feature(feat,color=Track.backgroundColor,sigil="ARROW",name=labelName,label_position="start",label_angle=Track.angle[self.nbFeats%2],label=True,strand=Track.strand[self.nbFeats%2])
else :
self.gdFeature.add_feature(feat,color=Track.backgroundColor,sigil="ARROW",name=labelName,label_position="middle",label_angle=Track.angle[self.nbFeats%2],label=True,strand=Track.strand[self.nbFeats%2])
if feat.strand==1:
self.gdFeature.add_feature(feat,border=colorMax,color=colors.linearlyInterpolatedColor(white,colorMax,minSimilarityScore,100,percent),sigil="ARROW",name=feat.qualifiers['product'][0][0:11].replace(" ","_")+" \n "+str(feat.location.start)+" - "+str(feat.location.end),label_position="middle",label_angle=0,label=False)
else :
self.gdFeature.add_feature(feat,border=colorMax,color=colors.linearlyInterpolatedColor(white,colorMax,minSimilarityScore,100,percent),sigil="ARROW",label_position="middle",label_angle=180,label=False)
self.nbFeats+=1
self.gdTrack.add_set(self.gdFeature)
def _blast_feature(self, f, c1, c2):
trans = Translator(self._abort_event)
cds = trans.translate(f.extract(c1), 11)
sixframes = trans.translate_six_frames_single(c2, 11)
if not sixframes: return [(None, None, None)]
results = []
for frame in sixframes:
res = BlastCLI.s2s_blast(cds, frame, self.evalue, command='blastp', task='blastp')
if res: results.extend(res)
hsps = BlastCLI.all_hsps(results)
if not hsps: return [(None, None, None)]
f1 = []
f2 = []
col = []
fname = self._feature_name(f, default='CDS')
cds_len = len(cds)
min_len = len(cds) * self.min_length
for hsp in hsps:
if hsp.align_length < min_len: continue
if hsp.identities / float(hsp.align_length) < self.min_identity: continue
color_t = (float(hsp.identities) / hsp.align_length)
print '%s %s: %5.1f%% (%5.1f%%)' % (c1.description, fname, color_t * 100, float(hsp.identities) / cds_len * 100)
col.append(colors.linearlyInterpolatedColor(colors.Color(0, 0, 1, 0.2), colors.Color(0, 1, 0, 0.2),
0.2, 1, color_t))
qstart = (hsp.query_start - 1) * 3
qend = qstart + hsp.align_length * 3
sstart = (hsp.sbjct_start - 1) * 3
send = sstart + hsp.align_length * 3
f1.append(
SeqFeature(FeatureLocation(f.location.start + qstart, f.location.start + qend, strand=hsp.strand[0])))
f2.append(SeqFeature(FeatureLocation(sstart, send, strand=hsp.strand[1])))
return zip(f1, f2, col)
def Add_Anno(self, aList):
fields = aList.split()
name = fields[1]
chrom = fields[2]
strand = fields[3]
txStart = int(fields[4])
self.txStart = txStart
txEnd = int(fields[5])
self.txEnd = txEnd
self.frag = (txEnd - txStart) / 10000
self.end = txEnd - txStart
cdsStart = int(fields[6])
cdsEnd = int(fields[7])
exonCount = int(fields[8])
exonStarts = [int(i) for i in fields[9].split(',')[0:-1]]
exonEnds = [int(i) for i in fields[10].split(',')[0:-1]]
name2 = fields[12]
exonFrames = [int(i) for i in fields[15].split(',')[0:-1]]
for i in range(exonCount):
color = colors.linearlyInterpolatedColor(colors.white,
colors.green, 0,
exonCount, i + 1)
feature = SeqFeature(FeatureLocation(exonStarts[i] - txStart,
exonEnds[i] - txStart),
strand=+1)
self.gds_features.add_feature(feature,
name=str(i + 1),
label=True,
color=color)
def Add_Blast(self, aList):
self.blast_num += 1
fields = aList.split('\t')
gene = fields[0]
query = fields[1]
chrom = fields[2]
q_start = int(fields[7])
q_end = int(fields[8])
s_start = int(fields[9])
s_end = int(fields[10])
evalue = fields[11]
score = fields[12]
color = colors.linearlyInterpolatedColor(colors.blue, colors.firebrick,
0, self.blast_rownum,
self.blast_num)
if s_start <= s_end:
feature = SeqFeature(FeatureLocation(s_start - self.txStart,
s_end - self.txStart),
strand=-1)
if s_start > s_end:
feature = SeqFeature(FeatureLocation(s_end - self.txStart,
s_start - self.txStart),
strand=-1)
self.gds_features.add_feature(feature,
name=str(self.blast_num),
label=True,
color=color)
def _generate_gene_colors(self):
if not self.clusters: return
full_gene_set = set()
for c in self.clusters:
full_gene_set.update(c.genes)
if 'NONE' in full_gene_set:
full_gene_set.remove('NONE')
ngenes = float(len(full_gene_set))-1
middle = ngenes/2.0
self.colors = {}
for i, gene in enumerate(sorted(full_gene_set)):
t = i/ngenes
if i < middle:
c = colors.linearlyInterpolatedColor(colors.Color(1, 0, 0, 1), colors.Color(0, 1, 0, 1), 0, 1, t*2)
else:
c = colors.linearlyInterpolatedColor(colors.Color(0, 0.9, 0.1, 1), colors.Color(0, 0, 1, 1), 0, 1, t*2-1)
self.colors[gene] = c
def draw(self):
# general widget bits
group = Group()
x, y, w, h, c0, c1 = self._flipRectCorners()
numShades = self.numShades
if self.cylinderMode:
if not numShades % 2: numShades = numShades + 1
halfNumShades = (numShades - 1) / 2 + 1
num = float(numShades) # must make it float!
vertical = self.orientation == 'vertical'
if vertical:
if numShades == 1:
V = [x]
else:
V = frange(x, x + w, w / num)
else:
if numShades == 1:
V = [y]
else:
V = frange(y, y + h, h / num)
for v in V:
stripe = vertical and Rect(v, y, w / num, h) or Rect(
x, v, w, h / num)
if self.cylinderMode:
if V.index(v) >= halfNumShades:
col = colors.linearlyInterpolatedColor(
c1, c0, V[halfNumShades], V[-1], v)
else:
col = colors.linearlyInterpolatedColor(
c0, c1, V[0], V[halfNumShades], v)
else:
col = colors.linearlyInterpolatedColor(c0, c1, V[0], V[-1], v)
stripe.fillColor = col
stripe.strokeColor = col
stripe.strokeWidth = 1
group.add(stripe)
if self.strokeColor and self.strokeWidth >= 0:
rect = Rect(x, y, w, h)
rect.strokeColor = self.strokeColor
rect.strokeWidth = self.strokeWidth
rect.fillColor = None
group.add(rect)
return group
def draw(self):
# general widget bits
group = Group()
x, y, w, h, c0, c1 = self._flipRectCorners()
numShades = self.numShades
if self.cylinderMode:
if not numShades % 2: numShades = numShades + 1
halfNumShades = (numShades - 1) / 2 + 1
num = float(numShades) # must make it float!
vertical = self.orientation == 'vertical'
if vertical:
if numShades == 1:
V = [x]
else:
V = frange(x, x + w, w / num)
else:
if numShades == 1:
V = [y]
else:
V = frange(y, y + h, h / num)
for v in V:
stripe = vertical and Rect(v, y, w / num, h) or Rect(
x, v, w, h / num)
if self.cylinderMode:
if V.index(v) >= halfNumShades:
col = colors.linearlyInterpolatedColor(
c1, c0, V[halfNumShades], V[-1], v)
else:
col = colors.linearlyInterpolatedColor(
c0, c1, V[0], V[halfNumShades], v)
else:
col = colors.linearlyInterpolatedColor(c0, c1, V[0], V[-1], v)
stripe.fillColor = col
stripe.strokeColor = col
stripe.strokeWidth = 1
group.add(stripe)
if self.strokeColor and self.strokeWidth >= 0:
rect = Rect(x, y, w, h)
rect.strokeColor = self.strokeColor
rect.strokeWidth = self.strokeWidth
rect.fillColor = None
group.add(rect)
return group
def colorRange(c0, c1, n):
"Return a range of intermediate colors between c0 and c1"
if n==1: return [c0]
C = []
if n>1:
lim = n-1
for i in range(n):
C.append(colors.linearlyInterpolatedColor(c0,c1,0,lim, i))
return C
def colorRange(c0, c1, n):
"Return a range of intermediate colors between c0 and c1"
if n == 1: return [c0]
C = []
if n > 1:
lim = n - 1
for i in range(n):
C.append(colors.linearlyInterpolatedColor(c0, c1, 0, lim, i))
return C
def _getColors(self):
# for calculating intermediate colors...
numShades = self.numberOfBoxes + 1
fillColorStart = self.startColor
fillColorEnd = self.endColor
colorsList = []
for i in range(0, numShades):
colorsList.append(
colors.linearlyInterpolatedColor(fillColorStart, fillColorEnd,
0, numShades - 1, i))
return colorsList
def _blast_feature(self, f, c1, c2, features1, features2, evalue, max_rlen):
results = BlastCLI.s2s_blast(f.extract(c1), c2, evalue, command='blastn', task='blastn')
hsps = BlastCLI.all_hsps(results, max_rlen)
if not hsps: return [(None, None, None)]
f1 = []
f2 = []
col = []
for hsp in hsps:
col.append(colors.linearlyInterpolatedColor(colors.Color(1,1,1,0.2), colors.Color(0,0,0,0.2),
0, 1, float(hsp.identities)/hsp.align_length))
f1.append(SeqFeature(FeatureLocation(f.location.start+hsp.query_start,
f.location.start+hsp.query_start+hsp.align_length, strand=0)))
f2.append(SeqFeature(FeatureLocation(hsp.sbjct_start, hsp.sbjct_start+hsp.align_length, strand=0)))
return zip(f1, f2, col)
def _blast_feature(self, f, c1, c2, features1, features2, evalue,
max_rlen):
trans = Translator(self._abort_event)
cds = trans.translate(f.extract(c1), 11)
sixframes = trans.translate_six_frames_single(c2, 11)
if not sixframes: return [(None, None, None)]
results = []
for frame in sixframes:
res = BlastCLI.s2s_blast(cds,
frame,
evalue,
command='blastp',
task='blastp')
if res: results.extend(res)
hsps = BlastCLI.all_hsps(results, max_rlen)
if not hsps: return [(None, None, None)]
f1 = []
f2 = []
col = []
c1_name = pretty_rec_name(c1)
if 'locus_tag' in f.qualifiers:
fname = f.qualifiers['locus_tag'][0]
else:
fname = 'CDS'
cds_len = len(cds)
for hsp in hsps:
color_t = (float(hsp.identities) / hsp.align_length)
print '%s %s: %5.1f%% (%5.1f%%)' % (c1_name, fname, color_t * 100,
float(hsp.identities) /
cds_len * 100)
col.append(
colors.linearlyInterpolatedColor(colors.Color(0, 0, 1, 0.2),
colors.Color(0, 1, 0, 0.2),
0.2, 1, color_t))
qstart = (hsp.query_start - 1) * 3
qend = qstart + hsp.align_length * 3
sstart = (hsp.sbjct_start - 1) * 3
send = sstart + hsp.align_length * 3
f1.append(
SeqFeature(
FeatureLocation(f.location.start + qstart,
f.location.start + qend,
strand=hsp.strand[0])))
f2.append(
SeqFeature(FeatureLocation(sstart, send,
strand=hsp.strand[1])))
return zip(f1, f2, col)
def draw_heat_graph(self, graph):
""" draw_heat_graph(self, graph) -> [element, element,...]
o graph Graph object
Returns a list of drawable elements for the heat graph
"""
#print '\tdraw_heat_graph'
# At each point contained in the graph data, we draw a box that is the
# full height of the track, extending from the midpoint between the
# previous and current data points to the midpoint between the current
# and next data points
heat_elements = [] # holds drawable elements
# Get graph data
data_quartiles = graph.quartiles()
minval, maxval = data_quartiles[0], data_quartiles[4]
midval = (maxval + minval) / 2. # mid is the value at the X-axis
btm, ctr, top = self.track_radii[self.current_track_level]
trackheight = (top - btm)
newdata = intermediate_points(self.start, self.end,
graph[self.start:self.end])
# Create elements on the graph, indicating a large positive value by
# the graph's poscolor, and a large negative value by the graph's
# negcolor attributes
for pos0, pos1, val in newdata:
pos0angle, pos0cos, pos0sin = self.canvas_angle(pos0)
pos1angle, pos1cos, pos1sin = self.canvas_angle(pos1)
# Calculate the heat color, based on the differential between
# the value and the median value
heat = colors.linearlyInterpolatedColor(graph.poscolor,
graph.negcolor, maxval,
minval, val)
# Draw heat box
heat_elements.append(
self._draw_arc(btm,
top,
pos0angle,
pos1angle,
heat,
border=heat))
return heat_elements
def Add_Blast(self,aList) :
self.blast_num+=1
fields=aList.split('\t')
gene=fields[0]
query=fields[1]
chrom=fields[2]
q_start=int(fields[7])
q_end=int(fields[8])
s_start=int(fields[9])
s_end=int(fields[10])
evalue=fields[11]
score=fields[12]
color = colors.linearlyInterpolatedColor(colors.blue, colors.firebrick, 0,self.blast_rownum,self.blast_num)
if s_start<=s_end:
feature = SeqFeature(FeatureLocation(s_start-self.txStart,s_end-self.txStart), strand=-1)
if s_start>s_end:
feature = SeqFeature(FeatureLocation(s_end-self.txStart,s_start-self.txStart), strand=-1)
self.gds_features.add_feature(feature,name=str(self.blast_num),label=True,color=color)
def draw_heat_graph(self, graph):
""" draw_heat_graph(self, graph) -> [element, element,...]
o graph Graph object
Returns a list of drawable elements for the heat graph
"""
#print '\tdraw_heat_graph'
# At each point contained in the graph data, we draw a box that is the
# full height of the track, extending from the midpoint between the
# previous and current data points to the midpoint between the current
# and next data points
heat_elements = [] # holds drawable elements
# Get graph data
data_quartiles = graph.quartiles()
minval, maxval = data_quartiles[0],data_quartiles[4]
midval = (maxval + minval)/2. # mid is the value at the X-axis
btm, ctr, top = self.track_radii[self.current_track_level]
trackheight = (top-btm)
newdata = intermediate_points(self.start, self.end,
graph[self.start:self.end])
# Create elements on the graph, indicating a large positive value by
# the graph's poscolor, and a large negative value by the graph's
# negcolor attributes
for pos0, pos1, val in newdata:
pos0angle, pos0cos, pos0sin = self.canvas_angle(pos0)
pos1angle, pos1cos, pos1sin = self.canvas_angle(pos1)
# Calculate the heat color, based on the differential between
# the value and the median value
heat = colors.linearlyInterpolatedColor(graph.poscolor,
graph.negcolor,
maxval, minval, val)
# Draw heat box
heat_elements.append(self._draw_arc(btm, top, pos0angle, pos1angle,
heat, border=heat))
return heat_elements
def Add_Anno(self,aList) :
fields=aList.split()
name=fields[1]
chrom=fields[2]
strand=fields[3]
txStart=int(fields[4])
self.txStart=txStart
txEnd=int(fields[5])
self.txEnd=txEnd
self.frag=(txEnd-txStart)/10000
self.end=txEnd-txStart
cdsStart=int(fields[6])
cdsEnd=int(fields[7])
exonCount=int(fields[8])
exonStarts=[int(i) for i in fields[9].split(',')[0:-1]]
exonEnds=[int(i) for i in fields[10].split(',')[0:-1]]
name2=fields[12]
exonFrames=[int(i) for i in fields[15].split(',')[0:-1]]
for i in range(exonCount):
color = colors.linearlyInterpolatedColor(colors.white, colors.green,0,exonCount,i+1 )
feature = SeqFeature(FeatureLocation(exonStarts[i]-txStart,exonEnds[i]-txStart), strand=+1)
self.gds_features.add_feature(feature,name=str(i+1),label=True,color=color)
gdd = GenomeDiagram.Diagram('Diagram')
gdt1_features = gdd.new_track(1, greytrack=False)
gds1_features = gdt1_features.new_set()
gdt2_features = gdd.new_track(1, greytrack=False)
gds2_features = gdt2_features.new_set()
inFile=open('CHC10A.unmapped.sam.mapped.fa.fa.blasted')
NC_len=5894
num=0
startend=[]
for line in inFile :
fields=line.split('\t')
if fields[1]=='NC_003977.1':
num+=1
color = colors.linearlyInterpolatedColor(colors.white, colors.firebrick, 0, 200, num)
line=line.strip()
q_start=int(fields[6])
q_end=int(fields[7])
s_start=int(fields[9])
s_end=int(fields[9])
startend.append(q_start)
startend.append(q_end)
startend.append(s_start)
startend.append(s_end)
feature = SeqFeature(FeatureLocation(q_start,q_end),strand=+1)
#gds1_features.add_feature(feature,name=str(num),label=True,color=color)
feature = SeqFeature(FeatureLocation(s_start,s_end),strand=+1)
name=record.name,
greytrack=True, height=0.5,
start=0, end=len(record))
assert record.name not in feature_sets
feature_sets[record.name] = gd_track_for_features.new_set()
# We add dummy features to the tracks for each cross-link BEFORE we add the
# arrow features for the genes. This ensures the genes appear on top:
for X, Y, X_vs_Y in [("NC_002703", "AF323668", A_vs_B),
("AF323668", "NC_003212", B_vs_C)]:
features_X = records[X].features
features_Y = records[Y].features
set_X = feature_sets[X]
set_Y = feature_sets[Y]
for score, x, y in X_vs_Y:
color = colors.linearlyInterpolatedColor(colors.white, colors.firebrick,
0, 100, score)
border = colors.lightgrey
f_x = get_feature(features_X, x)
F_x = set_X.add_feature(SeqFeature(FeatureLocation(f_x.location.start,
f_x.location.end,
strand=0)),
color=color, border=border)
f_y = get_feature(features_Y, y)
F_y = set_Y.add_feature(SeqFeature(FeatureLocation(f_y.location.start,
f_y.location.end,
strand=0)),
color=color, border=border)
gd_diagram.cross_track_links.append(CrossLink(F_x, F_y, color, border))
for record, gene_colors in zip([A_rec, B_rec, C_rec],
def addFeat(self, feat, colorMax, percent):
labelTab = []
try:
labelTab = feat.qualifiers['product'][0].split(" ")
except KeyError:
print " NO PRODUCT FOUND FOR "
print feat
labelTab[0] = "No name"
labelName = ""
if len(labelTab) <= Track.maxLabelWord:
for word in labelTab:
labelName += word + " "
else:
labelName = labelTab[0] + " " + labelTab[1] + " " + labelTab[
2] + " "
labelName = labelName[0:len(labelName) - 1] + " \n " + str(
feat.location.start) + " - " + str(
feat.location.end) #skip the final space and add location
#change location
newStart = feat.location.start - self.diff
newEnd = feat.location.end - self.diff
if newEnd > Track.maxSize:
Track.maxSize = newEnd
newLocation = FeatureLocation(newStart, newEnd, feat.strand)
feat.location = newLocation
if self.nbFeats == 0:
self.gdFeature.add_feature(feat,
color=Track.backgroundColor,
sigil="ARROW",
name=labelName,
label_position="start",
label_angle=Track.angle[self.nbFeats %
2],
label=True,
strand=Track.strand[self.nbFeats % 2])
else:
self.gdFeature.add_feature(feat,
color=Track.backgroundColor,
sigil="ARROW",
name=labelName,
label_position="middle",
label_angle=Track.angle[self.nbFeats %
2],
label=True,
strand=Track.strand[self.nbFeats % 2])
if feat.strand == 1:
self.gdFeature.add_feature(
feat,
border=colorMax,
color=colors.linearlyInterpolatedColor(white, colorMax,
minSimilarityScore, 100,
percent),
sigil="ARROW",
name=feat.qualifiers['product'][0][0:11].replace(" ", "_") +
" \n " + str(feat.location.start) + " - " +
str(feat.location.end),
label_position="middle",
label_angle=0,
label=False)
else:
self.gdFeature.add_feature(feat,
border=colorMax,
color=colors.linearlyInterpolatedColor(
white, colorMax, minSimilarityScore,
100, percent),
sigil="ARROW",
label_position="middle",
label_angle=180,
label=False)
self.nbFeats += 1
self.gdTrack.add_set(self.gdFeature)
def generateClusterCompGraphic(cluster1,cluster2,pairs,outname):
noPair = tuple(map(lambda x: x/255.,(211,211,211)))
distDict = {}
colorDict = {}
colorPalette = [tuple(float(value) for value in values) for values in _get_colors_Janus(len(pairs))]
cluster1Name = "%s:%i-%i" % (cluster1[0].species,cluster1.location[0],cluster1.location[1])
cluster2Name = "%s:%i-%i" % (cluster2[0].species,cluster2.location[0],cluster2.location[1])
# Generate color dictionary
maxLen = 0
proteinHits = set()
pairs.reverse()
for idx,(dist,prot1,prot2) in enumerate(pairs):
distDict[prot1.hitName] = dist
distDict[prot2.hitName] = dist
colorDict[prot1.hitName] = colorPalette[idx]
colorDict[prot2.hitName] = colorPalette[idx]
proteinHits.update([prot1,prot2])
# Draw the cluster
gd_diagram = GenomeDiagram.Diagram(outname)
featureHandles = {}
for idx,cluster in enumerate([cluster1,cluster2]):
offset = cluster.location[0]
maxLen = max(maxLen,cluster.location[1]-offset)
clusterName = "%s:%i-%i" % (cluster[0].species,cluster.location[0],cluster.location[1])
gd_track_for_features = gd_diagram.new_track(3-2*idx,name = clusterName,
start=0, end=cluster.location[1]-offset,
scale_ticks=0,scale=0)
assert clusterName not in featureHandles
featureHandles[clusterName] = gd_track_for_features.new_set()
for dist,prot1,prot2 in pairs:
color = colors.linearlyInterpolatedColor(colors.firebrick,colors.white, 0, 1, dist)
border = colors.lightgrey
coord1,direction1 = prot1.location
coord2,direction2 = prot2.location
offset1 = cluster1.location[0]
offset2 = cluster2.location[0]
coord1 = (x - offset1 for x in coord1)
coord2 = (x - offset2 for x in coord2)
F_x = featureHandles[cluster1Name].add_feature(SeqFeature(FeatureLocation(*coord1),strand=0),color=color,border=border)
F_y = featureHandles[cluster2Name].add_feature(SeqFeature(FeatureLocation(*coord2),strand=0),color=color,border=border)
gd_diagram.cross_track_links.append(CrossLink(F_x,F_y,color,border))
for name,cluster in zip([cluster1Name,cluster2Name],[cluster1,cluster2]):
offset = cluster.location[0]
for protein in cluster:
coord,direction = protein.location
coord = (x-offset for x in coord)
if direction == '+':
strand = +1
else:
strand = -1
feature = SeqFeature(FeatureLocation(*coord),strand=strand)
featureHandles[name].add_feature(feature,sigil="BIGARROW", color=colorDict.get(protein.hitName,noPair),
name = protein.name,label_position="middle",
label=protein in proteinHits,arrowshaft_height=1,
arrowshaft_length = 0.1,label_strand = 1,
label_size=8, label_angle=45)
tracks = gd_diagram.get_tracks()
for track in tracks:
track.height=1
track.greytrack_fontcolor = colors.black
track.greytrack_labels = 1
track.greytrack = 1
track.greytrack_fontsize=16
track.greytrack_font_rotation = 0
track.axis_labels = 0
gd_diagram.draw(format="linear", pagesize='A4', fragments=1,
start=0, end=maxLen)
gd_diagram.write(outname + ".svg", "SVG")
c = 0
m = 0
for feature in record.features:
if feature.type != "CDS": #Exclude feature that is no CDS
continue
name = feature.qualifiers["protein_id"][
0] #get protein id of feature
if l == 0: #main gene cluster
if name in main_blast: #feature in main that match with other
color_value = m / n_main_blast #rank of feature in main blast hit
#color range [red,orange,yellow,green,cyan,blue,purple,magenta,pink]
if color_value < 0.125:
color = colors.linearlyInterpolatedColor(
colors.red, colors.orange, 0, 0.125, color_value)
elif color_value < 0.25:
color = colors.linearlyInterpolatedColor(
colors.orange, colors.yellow, 0.125, 0.25,
color_value)
elif color_value < 0.375:
color = colors.linearlyInterpolatedColor(
colors.yellow, colors.green, 0.25, 0.375,
color_value)
elif color_value < 0.5:
color = colors.linearlyInterpolatedColor(
colors.green, colors.cyan, 0.375, 0.5, color_value)
elif color_value < 0.625:
color = colors.linearlyInterpolatedColor(
colors.cyan, colors.blue, 0.5, 0.625, color_value)
elif color_value < 0.75:
def crosslinks(fileName, GenBank_1, GenBank_2):
gd_diagram = GenomeDiagram.Diagram(fileName)
max_len = 0
#Open Files and create fasta files to be compared by Ublast
A_rec = SeqIO.read(GenBank_1, 'gb')
GB_file_name = GenBank_1
fasta_file_name_A = GB_file_name[:-3] + ".fasta"
writeFasta(GB_file_name, fasta_file_name_A)
B_rec = SeqIO.read(GenBank_2, 'gb')
GB_file_name = GenBank_2
fasta_file_name_B = GB_file_name[:-3] + ".fasta"
writeFasta(GB_file_name, fasta_file_name_B)
#create the tab file with the Ublast output
blastfile = ublastfeatures(fasta_file_name_A, fasta_file_name_B)
Gname = 'nn' #name of gene to add
#First section gets the crosslinks from the blast files
A_vs_B = getCrossLinks(blastfile)
#print ('(percent, Gene Query, Gene result)')#This prints the list of Blast results for reference
for item in A_vs_B:
print item
# asks user for a gene name to highlight
gene_search = raw_input(
"would you like to highlight a specific gene name?\n \t1) Yes\n \t2) No\n"
)
if gene_search == "1" or gene_search.lower() == "yes":
gene_highlight = raw_input(
"What is the name of the gene you would like to highlight?\n")
print gene_highlight + " will be printed in red on the genome diagram, all other genes will be grey"
C_colors = [yellow] * 1 + [orange] * 1 + [brown] * 1 + [
lightblue
] * 1 + [purple] * 1 + [green] * 1 + [grey] * 1
else:
gene_highlight = "NONE"
C_colors = [yellow] * 1 + [
orange
] * 1 + [brown] * 1 + [lightblue] * 1 + [purple] * 1 + [green] * 1 + [
grey
] * 1 #this creates an array of color for the arrows in the GUI
i = 0 #index of random color to add
geneColor = grey #color of gene. Grey= no name
# Create new features for concatenations
recs = ("A", "B")
for rec in recs:
if rec == "A":
for loc_a in re.finditer('NNNNNCACACACTTAATTAATTAAGTGTGTGNNNNN',
str(A_rec.seq)):
concat_feature = SeqFeature(FeatureLocation(loc_a.start(),
loc_a.start() + 35,
strand=-1),
id="Concat",
type="CDS",
qualifiers={'product': 'Concat'})
A_rec.features.append(concat_feature)
else:
for loc_b in re.finditer('NNNNNCACACACTTAATTAATTAAGTGTGTGNNNNN',
str(B_rec.seq)):
concat_feature = SeqFeature(FeatureLocation(loc_b.start(),
loc_b.start() + 35,
strand=-1),
id="Concat",
type="CDS",
qualifiers={'product': 'Concat'})
B_rec.features.append(concat_feature)
#Read in lists of gene names and types
with open('Backbones_2_Clean.csv', 'r') as hand1:
back_b = csv.reader(hand1)
backbone = list(back_b)
with open('AntibioticResistanceGenesClean.csv', 'r') as hand2:
AnRe = csv.reader(hand2)
An_Re = list(AnRe)
#this loop adds each gene feature to the record with a color and name
for record, gene_colors in zip([A_rec, B_rec], [C_colors, C_colors]):
max_len = max(max_len, len(record))
gd_track_for_features = gd_diagram.new_track(1,
name=record.name,
greytrack=True,
start=0,
end=len(record))
gd_feature_set = gd_track_for_features.new_set()
for feature in record.features:
if feature.type != "CDS":
#Exclude this feature
continue
## Chose Colors of annotations based on gene name
try:
Gname = feature.qualifiers['product'][0]
if Gname == gene_highlight:
geneColor = red
elif gene_highlight == "NONE":
geneColor = gene_colors[i % 6]
# Backbone genes
elif Gname in backbone[0]:
geneColor = blue
#Antibiotic Resistance Genes
elif Gname in An_Re[0]:
geneColor = green
#Transposease & Intergrase
elif Gname == 'Tnp' or Gname == 'Int':
geneColor = orange
else:
geneColor = grey
except KeyError: #if no gene name make it grey
Gname = 'No Name'
geneColor = grey
gd_feature_set.add_feature(
feature,
sigil="BIGARROW", #this adds gene features to gd_feature_set
arrowhead_length=.25,
color=geneColor,
label=True,
name=Gname,
label_position="start",
label_size=6,
label_angle=45)
i += 1 #increment i so that arrows will have a random color
track_X = gd_diagram.tracks[2]
track_Y = gd_diagram.tracks[1]
#this loop adds the cross links so they point to their feature in the diagram
for score, id_X, id_Y in A_vs_B:
try:
feature_X = get_feature(A_rec.features, id_X)
feature_Y = get_feature(B_rec.features, id_Y)
color = colors.linearlyInterpolatedColor(colors.white,
colors.firebrick, 0, 100,
score)
link_xy = CrossLink(
(track_X, feature_X.location.start, feature_X.location.end),
(track_Y, feature_Y.location.start, feature_Y.location.end),
color, colors.lightgrey)
print "Link made "
gd_diagram.cross_track_links.append(link_xy)
except KeyError:
print "Feature qualifier for crosslink not found" # for those pesky nameless genes
gd_diagram.draw(format="linear",
pagesize=(1200, 2400),
fragments=1,
start=0,
end=max_len)
print max_len
gd_diagram.write(fileName + ".pdf", "PDF")
def draw_heat_graph(self, graph):
""" draw_heat_graph(self, graph) -> [element, element,...]
o graph Graph object
Returns a list of drawable elements for the heat graph
"""
#print '\tdraw_heat_graph'
# At each point contained in the graph data, we draw a box that is the
# full height of the track, extending from the midpoint between the
# previous and current data points to the midpoint between the current
# and next data points
heat_elements = [] # Holds drawable elements for the graph
# Get graph data and information
data_quartiles = graph.quartiles()
minval, maxval = data_quartiles[0], data_quartiles[4]
midval = (maxval + minval) / 2. # mid is the value at the X-axis
btm, ctr, top = self.track_offsets[self.current_track_level]
trackheight = (top - btm)
#print self.start, self.end
newdata = intermediate_points(self.start, self.end,
graph[self.start:self.end])
#print newdata
# Create elements on the graph, indicating a large positive value by
# the graph's poscolor, and a large negative value by the graph's
# negcolor attributes
for pos0, pos1, val in newdata:
fragment0, x0 = self.canvas_location(pos0)
fragment1, x1 = self.canvas_location(pos1)
x0, x1 = self.x0 + x0, self.x0 + x1 # account for margin
#print 'x1 before:', x1
# Calculate the heat color, based on the differential between
# the value and the median value
heat = colors.linearlyInterpolatedColor(graph.poscolor,
graph.negcolor, maxval,
minval, val)
# Draw heat box
if fragment0 == fragment1: # Box is contiguous on one fragment
if pos1 >= self.fragment_limits[fragment0][1]:
x1 = self.xlim
ttop = top + self.fragment_lines[fragment0][0]
tbtm = btm + self.fragment_lines[fragment0][0]
#print 'equal', pos0, pos1, val
#print pos0, pos1, fragment0, fragment1
heat_elements.append(
draw_box((x0, tbtm), (x1, ttop), color=heat, border=None))
else: # box is split over two or more fragments
#if pos0 >= self.fragment_limits[fragment0][0]:
# fragment0 += 1
fragment = fragment0
start = x0
while self.fragment_limits[fragment][1] <= pos1:
#print pos0, self.fragment_limits[fragment][1], pos1
ttop = top + self.fragment_lines[fragment][0]
tbtm = btm + self.fragment_lines[fragment][0]
heat_elements.append(
draw_box((start, tbtm), (self.xlim, ttop),
color=heat,
border=None))
fragment += 1
start = self.x0
ttop = top + self.fragment_lines[fragment][0]
tbtm = btm + self.fragment_lines[fragment][0]
# Add the last part of the bar
#print 'x1 after:', x1, '\n'
heat_elements.append(
draw_box((self.x0, tbtm), (x1, ttop),
color=heat,
border=None))
return heat_elements
for index, connection in enumerate(links_handle):
connection = connection.strip()
values = connection.split("\t")
phage1 = values[0]
phage1Full = phageFullNameConvert[phage1]
phage1_gene = int(values[1])
phage2 = values[2]
phage2Full = phageFullNameConvert[phage2]
phage2_gene = int(values[3])
score = float(values[4])
track1 = genomeDiag.tracks[phageTrack[phage1]]
track2 = genomeDiag.tracks[phageTrack[phage2]]
color = colors.linearlyInterpolatedColor(colors.white, colors.lightcoral, 0, 100, score)
borderColor = None
if phage1Full == "OCN008_K139_region.fa" or phage1Full == "RE98_web_2_ep3.fa" or phage1Full == "RE98_web_1_kappa.fa":
link_xy = CrossLink((track1, phageDict[phage1Full][phage1_gene]["start"], phageDict[phage1Full][phage1_gene]["stop"]), (track2, phageDict[phage2Full][phage2_gene]["start"], phageDict[phage2Full][phage2_gene]["stop"]), color=color, flip=True, border=borderColor)
else:
link_xy = CrossLink((track1, phageDict[phage1Full][phage1_gene]["start"], phageDict[phage1Full][phage1_gene]["stop"]), (track2, phageDict[phage2Full][phage2_gene]["start"], phageDict[phage2Full][phage2_gene]["stop"]), color=color, flip=False, border=borderColor)
# add link features to first track
BoxFeatureTrack1 = SeqFeature(FeatureLocation(phageDict[phage1Full][phage1_gene]["start"], phageDict[phage1Full][phage1_gene]["stop"], strand=0))
borderBoxColor = colors.white
genomeSet = track1.new_set()
genomeSet.add_feature(BoxFeatureTrack1, label=False, label_position="start", sigil="BOX", color=color, border=borderBoxColor)
# add crosslink from blast results
blast_results = open(path_to_blast_result)
# parse blast results
for each_line in blast_results:
each_line_split = each_line.split('\t')
query = each_line_split[0]
target = each_line_split[1]
identity = float(each_line_split[2])
query_start = int(each_line_split[6])
query_end = int(each_line_split[7])
target_start = int(each_line_split[8])
target_end = int(each_line_split[9])
# use color to reflect identity
color = colors.linearlyInterpolatedColor(colors.white, colors.red, 50,
100, identity)
# determine which is which (query/target to contig_1/contig_2)
# if query is contig_1
if query == gene1_contig.name:
link = CrossLink(
(contig_1_gene_content_track, query_start, query_end),
(contig_2_gene_content_track, target_start, target_end),
color=color,
border=color,
flip=False)
diagram.cross_track_links.append(link)
# if query is contig_2
elif query == gene2_contig.name:
link = CrossLink(
def GenomeMap(file, GenomeId, grid=10000, cross=True):
# print(GenomeId)
gd_diagram = GenomeDiagram.Diagram('phages')
with open(file, 'r') as f:
reader = csv.reader(f)
data = list(reader)
records = []
ref = {}
for Id in GenomeId:
try:
record = SeqIO.read(Id + ".gb", "genbank")
except FileNotFoundError or IOError or ValueError:
hd = Entrez.efetch(db="nucleotide",
id=Id,
rettype='gb',
retmode="text")
record = SeqIO.read(hd, 'genbank')
fw = open(Id + '.gb', 'w')
SeqIO.write(record, fw, 'genbank')
fw.close()
os.getcwd()
for i in SeqIO.parse(Id + ".gb", "genbank"):
ref[Id] = i.annotations['keywords']
records.append(record)
feature_sets = {}
max_len = 0
for i, record in enumerate(records):
max_len = max(max_len, len(record))
gd_track_for_features = gd_diagram.new_track(
5 - 2 * i,
name=record.description,
greytrack=True,
greytrack_fontsize=16,
greytrack_labels=1,
largetick=True,
smalltick=True,
scale_ticks=True,
scale_largeticks=0.5,
scale_smallticks=0.1,
scale_largetick_interval=grid,
scale_smalltick_interval=grid / 20,
scale_largetick_labels=True,
start=0,
end=len(record),
)
assert record.name not in feature_sets
feature_sets[record.id] = gd_track_for_features.new_set()
for crosslink in data:
if not cross:
break
set_X = feature_sets[crosslink[0].split(' ')[0]]
set_Y = feature_sets[crosslink[1].split(' ')[0]]
# 手动划分连接类型时使用
# score = 100
# try:
# if crosslink[7] == 1 or crosslink[7] == -1:
# score = 100
# except TypeError:
# score = 50
if crosslink[0].split(' ')[0] in CLASS1 and crosslink[1].split(
' ')[0] in CLASS1:
color = colors.linearlyInterpolatedColor(
colors.green, colors.yellow, 0, len(GenomeId),
GenomeId.index(crosslink[1].split(' ')[0]))
elif crosslink[0].split(' ')[0] in CLASS2 and crosslink[1].split(
' ')[0] in CLASS2:
color = colors.linearlyInterpolatedColor(
colors.purple, colors.red, 0, len(GenomeId),
GenomeId.index(crosslink[1].split(' ')[0]))
else:
color = colors.linearlyInterpolatedColor(
colors.blue, colors.cyan, 0, len(GenomeId),
GenomeId.index(crosslink[1].split(' ')[0]))
# color = list(colors.getAllNamedColors().keys())[GenomeId.index(crosslink[1].split(' ')[0]) * 17 + 17 % 163]
F_x = set_X.add_feature(
SeqFeature(
FeatureLocation(int(crosslink[2]), int(crosslink[3]),
strand=0)),
color=color,
border=color,
)
F_y = set_Y.add_feature(
SeqFeature(
FeatureLocation(int(crosslink[4]), int(crosslink[5]),
strand=0)),
color=color,
border=color,
)
link_xy = CrossLink(F_x, F_y, color, color)
gd_diagram.cross_track_links.append(link_xy)
for record in records:
gd_feature_set = feature_sets[record.id]
# 矫正ori
for feature in record.features:
if feature.type == 'rep_origin':
print(record.description + ' 的起始位点在:' +
str(feature.location.start))
record = record[feature.location.
start:] + record[:feature.location.start]
if record.features[0].strand == -1:
print('daole')
record = record.reverse_complement(id=True,
name=True,
description=True,
features=True,
annotations=True,
letter_annotations=True)
break
# 务必绘制反向互补序列时手动开启
# record = record.reverse_complement(id=True, name=True, description=True, features=True,
# annotations=True, letter_annotations=True)
print(record.description + ' 的起始位点已校正')
# 画features
i = 0
if ref[record.id] != ['']:
for feature in record.features:
if feature.type != "gene":
continue
color = list(colors.getAllNamedColors().keys())[len(feature) %
163]
gd_feature_set.add_feature(feature,
color=color,
label=True,
label_size=10,
label_angle=90,
sigil="ARROW",
arrowshaft_height=1.0,
arrowhead_length=0.1)
i += 1
elif ref[record.id] == ['']:
for feature in record.features:
if feature.type != "CDS":
continue
color = list(colors.getAllNamedColors().keys())[len(feature) %
163]
gd_feature_set.add_feature(feature,
color=color,
label=True,
label_size=10,
label_angle=90,
sigil="ARROW",
arrowshaft_height=1.0,
arrowhead_length=0.2)
i += 1
# 用来手动添加重组位点
# for pos in recombinations:
# if pos in record.features:
# gd_feature_set.add_feature(feature, color=color, label=True, label_size=10, label_angle=90,
# sigil="ARROW", arrowshaft_height=1.0, arrowhead_length=0.1)
if not cross:
# 用来绘制单一序列
gd_diagram.draw(format="linear",
pagesize='A4',
fragments=5,
start=0,
end=max_len,
fragment_size=1)
gd_diagram.write("T7.pdf", "PDF")
else:
# 用来绘制比对序列
gd_diagram.draw(format="linear",
pagesize=(10 * len(GenomeId) * cm, 120 * cm),
fragments=1,
start=0,
end=max_len,
fragment_size=1)
gd_diagram.write(output, "PDF")
print("已输出为PDF")
name=record.name,
greytrack=True, height=0.5,
start=0, end=len(record))
assert record.name not in feature_sets
feature_sets[record.name] = gd_track_for_features.new_set()
# We add dummy features to the tracks for each cross-link BEFORE we add the
# arrow features for the genes. This ensures the genes appear on top:
for X, Y, X_vs_Y in [("NC_002703", "AF323668", A_vs_B),
("AF323668", "NC_003212", B_vs_C)]:
features_X = records[X].features
features_Y = records[Y].features
set_X = feature_sets[X]
set_Y = feature_sets[Y]
for score, x, y in X_vs_Y:
color = colors.linearlyInterpolatedColor(colors.white, colors.firebrick,
0, 100, score)
border = colors.lightgrey
f_x = get_feature(features_X, x)
F_x = set_X.add_feature(SeqFeature(FeatureLocation(f_x.location.start,
f_x.location.end,
strand=0)),
color=color, border=border)
f_y = get_feature(features_Y, y)
F_y = set_Y.add_feature(SeqFeature(FeatureLocation(f_y.location.start,
f_y.location.end,
strand=0)),
color=color, border=border)
gd_diagram.cross_track_links.append(CrossLink(F_x, F_y, color, border))
for record, gene_colors in zip([A_rec, B_rec, C_rec],
def draw_alignment(self, _gdd, query_id, query_length, blast_hits):
# draw reference
gdt_features = _gdd.new_track(1,
greytrack=False,
start=1,
end=self.ref_length)
gds_features = gdt_features.new_set()
max_length = 0
for annot in self.annotation:
if annot[-1] == '1':
strand = 1
elif annot[-1] == '-1':
strand = -1
else:
strand = None
start, end = int(annot[0]), int(annot[1])
if end > max_length:
max_length = end
feature = SeqFeature(FeatureLocation(start, end),
strand=strand,
id=annot[2])
gds_features.add_feature(feature,
label=True,
name=annot[2],
sigil='BOX',
label_size=14,
label_angle=0,
arrowhead_length=0.1,
arrowshaft_height=1)
gds_features.add_feature(SeqFeature(
FeatureLocation(self.start, self.start + 1)),
label=True,
name='PCR start',
label_size=14,
color='black')
_gdd.draw(format='linear', fragments=1, start=1, end=max_length)
# draw query sequence
gdt_features = _gdd.new_track(1,
greytrack=True,
start=0,
end=query_length,
name=query_id)
gds_features = gdt_features.new_set()
for r in blast_hits:
feature = SeqFeature(FeatureLocation(r[0], r[1]), strand=r[-1])
gds_features.add_feature(feature, label=False, sigil='BOX')
gdt_features.greytrack_fontcolor = colors.black
gdt_features.greytrack_fontsize = 12
# draw cross link
for r in blast_hits:
alpha = self.scale_color(r[4])
color = colors.linearlyInterpolatedColor(colors.white,
colors.firebrick, 0, 100,
alpha)
feature = SeqFeature(FeatureLocation(r[0], r[1]), strand=r[-1])
gds_features.add_feature(feature, label=False, sigil='BOX')
if max(r[2], r[3]) < self.start:
continue
link_xy = CrossLink((_gdd.tracks[1], r[0], r[1]),
(_gdd.tracks[2], r[2], r[3]), color)
_gdd.cross_track_links.append(link_xy)
_gdd.draw(format='linear', fragments=1)
def draw_heat_graph(self, graph):
""" draw_heat_graph(self, graph) -> [element, element,...]
o graph Graph object
Returns a list of drawable elements for the heat graph
"""
#print '\tdraw_heat_graph'
# At each point contained in the graph data, we draw a box that is the
# full height of the track, extending from the midpoint between the
# previous and current data points to the midpoint between the current
# and next data points
heat_elements = [] # Holds drawable elements for the graph
# Get graph data and information
data_quartiles = graph.quartiles()
minval, maxval = data_quartiles[0],data_quartiles[4]
midval = (maxval + minval)/2. # mid is the value at the X-axis
btm, ctr, top = self.track_offsets[self.current_track_level]
trackheight = (top-btm)
#print self.start, self.end
newdata = intermediate_points(self.start, self.end,
graph[self.start:self.end])
#print newdata
# Create elements on the graph, indicating a large positive value by
# the graph's poscolor, and a large negative value by the graph's
# negcolor attributes
for pos0, pos1, val in newdata:
fragment0, x0 = self.canvas_location(pos0)
fragment1, x1 = self.canvas_location(pos1)
x0, x1 = self.x0 + x0, self.x0 + x1 # account for margin
#print 'x1 before:', x1
# Calculate the heat color, based on the differential between
# the value and the median value
heat = colors.linearlyInterpolatedColor(graph.poscolor,
graph.negcolor,
maxval, minval, val)
# Draw heat box
if fragment0 == fragment1: # Box is contiguous on one fragment
if pos1 >= self.fragment_limits[fragment0][1]:
x1 = self.xlim
ttop = top + self.fragment_lines[fragment0][0]
tbtm = btm + self.fragment_lines[fragment0][0]
#print 'equal', pos0, pos1, val
#print pos0, pos1, fragment0, fragment1
heat_elements.append(draw_box((x0, tbtm), (x1, ttop),
color=heat, border=None))
else: # box is split over two or more fragments
#if pos0 >= self.fragment_limits[fragment0][0]:
# fragment0 += 1
fragment = fragment0
start = x0
while self.fragment_limits[fragment][1] <= pos1:
#print pos0, self.fragment_limits[fragment][1], pos1
ttop = top + self.fragment_lines[fragment][0]
tbtm = btm + self.fragment_lines[fragment][0]
heat_elements.append(draw_box((start, tbtm),
(self.xlim, ttop),
color=heat,
border=None))
fragment += 1
start = self.x0
ttop = top + self.fragment_lines[fragment][0]
tbtm = btm + self.fragment_lines[fragment][0]
# Add the last part of the bar
#print 'x1 after:', x1, '\n'
heat_elements.append(draw_box((self.x0, tbtm), (x1, ttop),
color=heat, border=None))
return heat_elements