def bottom_up():
from reportlab.lib import colors
from reportlab.lib.units import cm
from Bio.Graphics import GenomeDiagram
from Bio import SeqIO
record = SeqIO.read("NC_005816.gb", "genbank")
# Create the feature set and its feature objects,
gd_feature_set = GenomeDiagram.FeatureSet()
for feature in record.features:
if feature.type != "gene":
# Exclude this feature
continue
if len(gd_feature_set) % 2 == 0:
color = colors.blue
else:
color = colors.lightblue
gd_feature_set.add_feature(feature, color=color, label=True)
# (this for loop is the same as in the previous example)
# Create a track, and a diagram
gd_track_for_features = GenomeDiagram.Track(name="Annotated Features")
gd_diagram = GenomeDiagram.Diagram(
"Yersinia pestis biovar Microtus plasmid pPCP1")
# Now have to glue the bits together...
gd_track_for_features.add_set(gd_feature_set)
gd_diagram.add_track(gd_track_for_features, 1)
def drawsvg(clust):
for k in clust:
fs = GenomeDiagram.FeatureSet()
for g in clust[k]['gene']:
fs.add_feature(
clust[k]['gene'][g],
color = colors.lightgreen,
label=True,
label_size=10,
label_angle=90,
sigil="BIGARROW",
arrowshaft_height=0.5,
arrowhead_length=0.25
)
track = GenomeDiagram.Track(name = k)
diag = GenomeDiagram.Diagram()
track.add_set(fs)
diag.add_track(track, 1)
pglen = float(clust[k]['end'] - clust[k]['start']) / float(1000)
diag.draw(
format = "linear",
orientation = "landscape",
pagesize = (pglen*cm, 5*cm),
fragments = 1,
start = clust[k]['start'],
end= clust[k]['end']
)
diag.write('.'.join([pref, k, 'svg']), "SVG")
def main(name):
record = SeqIO.read("Genome.gb", "genbank")
# Create the feature set and its feature objects
gd_feature_set = GenomeDiagram.FeatureSet()
for feature in record.features:
if feature.type != "gene":
continue
if len(gd_feature_set) % 2 == 0:
color = colors.purple
else:
color = colors.lightblue
gd_feature_set.add_feature(feature,
color=color,
label=True,
label_size=14,
label_angle=10)
# Create a track and a diagram
gd_track_for_features = GenomeDiagram.Track(name="Annotated Features")
gd_diagram = GenomeDiagram.Diagram("Curly Tomato Stunt Virus")
gd_track_for_features.add_set(gd_feature_set)
gd_diagram.add_track(gd_track_for_features, 1)
gd_diagram.draw(
format="circular",
circular=True,
pagesize=(20 * cm, 20 * cm),
start=0,
end=len(record),
circle_core=0.7,
)
gd_diagram.write("tomato_curly_stunt_virus.JPG", "JPG")
def make_diagram(genome_record: SeqIO.SeqRecord,
pseudo_record: SeqIO.SeqRecord, outfile: str):
"""Plots the genome with pseudogenes on another track"""
diagram = GenomeDiagram.Diagram()
original_features = GenomeDiagram.FeatureSet(
) # These features will be from the original genbank file
for feature in genome_record.features: # genome_record is the record from the original genbank file
if feature.type != "gene":
# Exclude this feature
continue
if len(original_features) % 2 == 0: # Alternate colours
color = colors.blue
else:
color = colors.lightblue
original_features.add_feature(feature, color=color)
track_for_original_features = GenomeDiagram.Track(
name="Original Features",
scale_largetick_interval=100000,
scale_largeticks=5,
scale_fontangle=180,
scale_fontsize=10)
track_for_original_features.add_set(original_features)
diagram.add_track(track=track_for_original_features, track_level=1)
pseudo_features = GenomeDiagram.FeatureSet(
) # These features will be from the pseudogene annotation
for feature in pseudo_record.features:
if len(pseudo_features) % 2 == 0: # Alternate colours
color = colors.red
else:
color = colors.lightcoral
pseudo_features.add_feature(feature, color=color)
track_for_pseudogenes = GenomeDiagram.Track(name="Pseudogenes",
scale_largetick_labels=0)
track_for_pseudogenes.add_set(pseudo_features)
diagram.add_track(track=track_for_pseudogenes, track_level=2)
diagram.draw(format="circular",
circular=True,
start=0,
end=len(genome_record),
circle_core=0.8)
diagram.write(filename=outfile, output="PDF")
def __init__(self, trackName):
self.trackName = trackName
self.gdTrack = GenomeDiagram.Track(greytrack=True,
name=self.trackName,
greytrack_labels=1,
greytrack_fontsize=33)
self.gdFeature = GenomeDiagram.FeatureSet()
self.size = 0
self.nbFeats = 0
def _create_feature_set(self, track, **feature_options):
"""Create a Track object for the specified track
Args:
track (str): track identifier
**feature_options (mixed): additional options, passed to FeatureSet.add_feature().
Overrides self.feature_options.
Return:
FeatureSet for the track
"""
fs = GenomeDiagram.FeatureSet()
tracknum = self._trackindices[track]
for i, loc in enumerate(self._repeats[tracknum]):
feature = SeqFeature(loc)
options = dict(self.feature_options)
options.update(feature_options)
options.setdefault("color", self.rainbow(i))
#options.setdefault("name",str(i+1))
fs.add_feature(feature, **options)
return fs
def WriteImg(seqRecIn):
#to select different colors from
colorSelection = [colors.darkgreen, colors.darkorange, colors.lightblue]
currColor = 0
#uses GenomeDiagram package to create a featureset object for the diagram to use later
featSet = GenomeDiagram.FeatureSet()
for currFeat in seqRecIn.features:
if currFeat.type == "CDS":
featSet.add_feature(
currFeat,
color=colorSelection[currColor % 3],
label=True,
label_size=20,
sigil="ARROW",
#alternates widths specifically to accomodate the TCSV Sequence: order goes Medium->Thinnest->Thickest->Medium->Thinnest
arrowshaft_height=(0.5 + ((0.2) - (((currColor + 1) % 3) *
(0.2)))),
#turns arrowhead triangle into a thin line
arrowhead_length=0)
currColor += 1
#add features to track(only 1 because it is circular)
track = GenomeDiagram.Track(name="TCSV Sequence Features")
track.add_set(featSet)
#add track to diagram
diagram = GenomeDiagram.Diagram(
name="Tomato Curly Stunt Virus",
format="circular",
pagesize=(1000, 1000),
circular=True,
start=0,
#goes until end of any length sequence
end=len(seqRecIn),
circle_core=0.5)
diagram.add_track(track, 1)
#writes diagram to memory so it can be written into a file
diagram.draw()
#writes to a file using the reportlab functionalities
diagram.write("TCSV_Sequence_Map.jpg", "JPG")
# query feature coordinates
q_feat_start = row[SSTART] - row[QSTART]
q_feat_end = q_feat_start + row[QLEN]
# trim query coordinates to fit inside the subject. Render an arrow on the end which does not fit.
arrowhead_length_qstart = 0
arrowhead_length_qend = 0
if q_feat_start < 0:
q_feat_start = 0
arrowhead_length_qstart = 0.5
if q_feat_end > SUBJ_LEN:
q_feat_end = SUBJ_END
arrowhead_length_qend = 0.5
gd_feature_set = GenomeDiagram.FeatureSet()
gd_track = GenomeDiagram.Track()
# because a feature can only have one arrow, render two features for the query
# add/subtract 200 to not cover the arrow ends
query_feature_start = SeqFeature(FeatureLocation(q_feat_start,
q_feat_end - 200),
strand=-1)
gd_feature_set.add_feature(query_feature_start,
color=colors.lightblue,
sigil="BIGARROW",
arrowshaft_height=1.0,
arrowhead_length=arrowhead_length_qstart)
query_feature_end = SeqFeature(FeatureLocation(q_feat_start + 200,
q_feat_end),
def write_visuals(seq_name, df, seq_length, results_pdf):
gd_diagram = GenomeDiagram.Diagram(seq_name, track_size=1)
new_row = pn.DataFrame({
"Motif": seq_name,
"Start": 1,
"End": 1
},
index=[0])
df = pn.concat([new_row, df]).reset_index(drop=True)
NCCR = GenomeDiagram.FeatureSet()
for index, row in df.iterrows():
(motif_name, start_motif, end_motif) = (row["Motif"], row["Start"],
row["End"])
cols = [motif_name, start_motif, end_motif]
if index is 0:
block = SeqFeature(FeatureLocation(int(cols[1]),
int(cols[2]),
strand=-1),
type="blocks",
id=motif_name)
NCCR.add_feature(block,
color=colors.HexColor("#8DD35F"),
name=motif_name,
label=True,
label_size=8,
label_position="middle",
label_angle=180)
else:
if motif_name.islower():
motif = SeqFeature(FeatureLocation(int(cols[1]),
int(cols[2]),
strand=+1),
type="motifs",
id=motif_name)
NCCR.add_feature(motif,
color=colors.HexColor("#8DD35F"),
name=motif_name,
label=True,
label_size=10,
label_position="left",
label_angle=90)
else:
block = SeqFeature(FeatureLocation(int(cols[1]),
int(cols[2]),
strand=-1),
type="blocks",
id=motif_name)
if motif_name == "O":
NCCR.add_feature(block,
color=colors.HexColor("#ffc69e"),
name=motif_name,
label=True,
label_size=10,
label_position="center",
label_angle=180)
elif motif_name == "P":
NCCR.add_feature(block,
color=colors.HexColor("#fff6d4"),
name=motif_name,
label=True,
label_size=10,
label_position="middle",
label_angle=180)
elif motif_name == "Q":
NCCR.add_feature(block,
color=colors.HexColor("#f6f9eb"),
name=motif_name,
label=True,
label_size=10,
label_position="middle",
label_angle=180)
elif motif_name == "R":
NCCR.add_feature(block,
color=colors.HexColor("#ebf9f6"),
name=motif_name,
label=True,
label_size=10,
label_position="middle",
label_angle=180)
elif motif_name == "S":
NCCR.add_feature(block,
color=colors.HexColor("#f9ebf6"),
name=motif_name,
label=True,
label_size=10,
label_position="middle",
label_angle=180)
else:
NCCR.add_feature(block,
color=colors.HexColor("#C8C4B7"),
name=motif_name,
label=True,
label_size=20,
label_position="right",
label_angle=180)
NCCR_track = GenomeDiagram.Track(name="Annotated Features", height=0.3)
NCCR_track.add_set(NCCR)
gd_diagram.add_track(NCCR_track, 3)
seq_length = int(cols[2])
rows = max(2, int(round(seq_length / 100)))
gd_diagram.draw(format='linear',
tracklines=0,
pagesize='A4',
orientation='landscape',
fragments=4,
start=1,
end=int(seq_length))
pdf_filepath = os.path.join('results', '{}.pdf'.format(seq_name))
gd_diagram.write(pdf_filepath, 'PDF', dpi=300)
results_pdf.append(pdf_filepath)
def write_schemadelica_plot(self, path='./'):
logger.info('Writing plot')
gd_diagram = GenomeDiagram.Diagram("Primer Scheme", track_size=1)
scale_track = GenomeDiagram.Track(name='scale',
scale=True,
scale_fontsize=10,
scale_largetick_interval=1000,
height=0.1)
gd_diagram.add_track(scale_track, 2)
primer_feature_set_1 = GenomeDiagram.FeatureSet()
primer_feature_set_2 = GenomeDiagram.FeatureSet()
for r in self.regions:
cols1 = [
self.primary_reference.id, r.top_pair.left.start,
r.top_pair.left.end, r.top_pair.left.name, r.pool
]
cols2 = [
self.primary_reference.id, r.top_pair.right.end,
r.top_pair.right.start, r.top_pair.right.name, r.pool
]
region = str(r.region_num)
fwd_feature = SeqFeature(
FeatureLocation(int(cols1[1]), int(cols1[2]), strand=0))
rev_feature = SeqFeature(
FeatureLocation(int(cols2[1]), int(cols2[2]), strand=0))
region_feature = SeqFeature(
FeatureLocation(int(cols1[1]), int(cols2[2]), strand=0))
if int(region) % 2 == 0:
primer_feature_set_1.add_feature(region_feature,
color=colors.palevioletred,
name=region,
label=True,
label_size=10,
label_position="middle",
label_angle=0)
primer_feature_set_1.add_feature(fwd_feature,
color=colors.red,
name=region,
label=False)
primer_feature_set_1.add_feature(rev_feature,
color=colors.red,
name=region,
label=False)
else:
primer_feature_set_2.add_feature(region_feature,
color=colors.palevioletred,
name=region,
label=True,
label_size=10,
label_position="middle",
label_angle=0)
primer_feature_set_2.add_feature(fwd_feature,
color=colors.red,
name=region,
label=False)
primer_feature_set_2.add_feature(rev_feature,
color=colors.red,
name=region,
label=False)
primer_track = GenomeDiagram.Track(name="Annotated Features",
height=0.1)
primer_track.add_set(primer_feature_set_1)
gd_diagram.add_track(primer_track, 4)
primer_track = GenomeDiagram.Track(name="Annotated Features",
height=0.1)
primer_track.add_set(primer_feature_set_2)
gd_diagram.add_track(primer_track, 6)
rows = max(2, int(round(len(self.primary_reference) / 10000.0)))
gd_diagram.draw(format='linear',
pagesize=(300 * rows, 200 * rows),
fragments=rows,
start=0,
end=len(self.primary_reference))
png_filepath = os.path.join(path, '{}.png'.format(self.prefix))
pdf_filepath = os.path.join(path, '{}.pdf'.format(self.prefix))
svg_filepath = os.path.join(path, '{}.svg'.format(self.prefix))
gd_diagram.write(png_filepath, 'PNG', dpi=300)
gd_diagram.write(pdf_filepath, 'PDF', dpi=300)
gd_diagram.write(svg_filepath, 'SVG', dpi=300)
def write_schemadelica_plot(self):
"""Write schemadelica plot as SVG and PDF."""
gd_diagram = GenomeDiagram.Diagram("Primer Scheme", track_size=0.15)
primer_feature_set = GenomeDiagram.FeatureSet()
# make the gc track
window = 50
gc_set = GenomeDiagram.GraphSet("GC content")
graphdata1 = self.apply_to_window(self.primary_ref.seq, window,
self.calc_gc)
gc_set.new_graph(
graphdata1,
"GC content",
style="line",
color=colors.violet,
altcolor=colors.purple,
)
gc_track = GenomeDiagram.Track("GC content",
height=1.5,
greytrack=0,
scale_largetick_interval=1e3)
gc_track.add_set(gc_set)
# make the primer track
for r in self.regions:
region = str(r.region_num)
strand = 1 if r.region_num % 2 else -1
fwd_feature = SeqFeature(
FeatureLocation(r.left.start, r.left.end, strand=strand))
rev_feature = SeqFeature(
FeatureLocation(r.right.end, r.right.start, strand=strand))
region_feature = SeqFeature(
FeatureLocation(r.left.start, r.right.start, strand=strand))
primer_color = colors.red
region_color = colors.palevioletred
primer_feature_set.add_feature(
region_feature,
color=region_color,
name=region,
label=True,
label_position="middle",
label_angle=0 if strand == 1 else -180,
)
primer_feature_set.add_feature(fwd_feature,
color=primer_color,
name=region)
primer_feature_set.add_feature(rev_feature,
color=primer_color,
name=region)
primer_track = GenomeDiagram.Track(name="Annotated Features", height=1)
primer_track.add_set(primer_feature_set)
gd_diagram.add_track(primer_track, 2)
gd_diagram.add_track(gc_track, 1)
rows = max(2, int(round(len(self.primary_ref) / 10000.0)))
gd_diagram.draw(
format="linear",
pagesize=(300 * rows, 200 * rows),
fragments=rows,
start=0,
end=len(self.primary_ref),
)
pdf_filepath = self.outpath / f"{self.prefix}.plot.pdf"
svg_filepath = self.outpath / f"{self.prefix}.plot.svg"
logger.info(f"Writing {pdf_filepath}")
logger.info(f"Writing {svg_filepath}")
gd_diagram.write(str(pdf_filepath), "PDF", dpi=300)
gd_diagram.write(str(svg_filepath), "SVG", dpi=300)
from Bio import SeqIO
from Bio import SeqUtils
from Bio.Seq import Seq
col_list = [
colors.coral, colors.blue, colors.crimson, colors.navy, colors.red,
colors.lightskyblue
]
itr = iter(col_list)
itr_copy = iter(col_list)
record = SeqIO.read("Genome.gb", "genbank")
track_list = []
cdsfs = GenomeDiagram.FeatureSet(name='CDS features')
for feature in record.features:
if feature.type == "CDS":
cdsfs.add_feature(feature, sigil="ARROW", color=next(itr_copy))
gdt1 = GenomeDiagram.Track('CDS features', greytrack=1, greytrack_labels=3)
gdt1.add_set(cdsfs)
track_list.append(gdt1)
for feature in record.features:
if feature.type != "gene":
continue
gd_feature_set = GenomeDiagram.FeatureSet()
gd_feature_set.add_feature(feature,
sigil="ARROW",
# -*- coding: utf-8 -*-
"""
Created on Thu Jan 21 16:18:02 2021
@author: sodasim
"""
from reportlab.lib import colors
from reportlab.lib.units import cm
from Bio.Graphics import GenomeDiagram
from Bio import SeqIO
record = SeqIO.read("Genome.gb", "genbank")
gd_first_set = GenomeDiagram.FeatureSet()
gd_second_set = GenomeDiagram.FeatureSet()
gd_total_set = GenomeDiagram.FeatureSet()
for feature in record.features:
firstTrack = True
if feature.type != "gene":
continue
for other_feature in gd_first_set.get_features():
if other_feature.type != "gene":
continue
# Determines if feature should be placed on the second track
if feature.location.start < other_feature.location.end and feature.location.start > other_feature.location.start:
if len(gd_second_set) % 2 == 0:
color = colors.blue
else:
color = colors.lightblue
gd_second_set.add_feature(feature,
def write_schemadelica_plot(self, path='./'):
logger.info('Writing plot')
#print(dir(GenomeDiagram))
gd_diagram = GenomeDiagram.Diagram("Primer Scheme", track_size=0.15)
primer_feature_set = GenomeDiagram.FeatureSet()
#make the gc track
window = 50
gc_set = GenomeDiagram.GraphSet('GC skew')
graphdata1 = self.apply_to_window(self.primary_reference.seq, window,
self.calc_gc_skew)
gc_set.new_graph(graphdata1,
'GC Skew',
style='line',
color=colors.violet,
altcolor=colors.purple)
gc_track = GenomeDiagram.Track('GC Skew',
height=1.5,
greytrack=0,
scale_largetick_interval=1e3)
gc_track.add_set(gc_set)
#make the primer track
for r in self.regions:
region = str(r.region_num)
strand = 1 if r.region_num % 2 else -1
fwd_feature = SeqFeature(
FeatureLocation(r.top_pair.left.start,
r.top_pair.left.end,
strand=strand))
rev_feature = SeqFeature(
FeatureLocation(r.top_pair.right.end,
r.top_pair.right.start,
strand=strand))
region_feature = SeqFeature(
FeatureLocation(r.top_pair.left.start,
r.top_pair.right.start,
strand=strand))
primer_color = colors.red #if strand == 1 else colors.blue
region_color = colors.palevioletred #if strand == 1 else colors.lightblue
primer_feature_set.add_feature(
region_feature,
color=region_color,
name=region,
label=True,
label_position="middle",
label_angle=0 if strand == 1 else -180)
primer_feature_set.add_feature(fwd_feature,
color=primer_color,
name=region)
primer_feature_set.add_feature(rev_feature,
color=primer_color,
name=region)
primer_track = GenomeDiagram.Track(name="Annotated Features", height=1)
primer_track.add_set(primer_feature_set)
gd_diagram.add_track(primer_track, 2)
gd_diagram.add_track(gc_track, 1)
rows = max(2, int(round(len(self.primary_reference) / 10000.0)))
gd_diagram.draw(format='linear',
pagesize=(300 * rows, 200 * rows),
fragments=rows,
start=0,
end=len(self.primary_reference))
pdf_filepath = os.path.join(path, '{}.pdf'.format(self.prefix))
svg_filepath = os.path.join(path, '{}.svg'.format(self.prefix))
gd_diagram.write(pdf_filepath, 'PDF', dpi=300)
gd_diagram.write(svg_filepath, 'SVG', dpi=300)
gd_track_for_features = GenomeDiagram.Track(name="Annotated Features",
scale=0,
scale_largetick_labels=True,
scale_largetick_interval=5000,
height=1)
gd_diagram = GenomeDiagram.Diagram("Zika Brazil", track_size=0.8)
scale_track = GenomeDiagram.Track(name='scale',
scale=1,
scale_largetick_labels=True,
scale_largetick_interval=5000,
height=0.3)
gd_diagram.add_track(scale_track, 1)
primer_feature_set = GenomeDiagram.FeatureSet()
for line in open(sys.argv[2], 'r'):
cols = line.strip().split()
strand = (+1 if cols[0].split('_')[-1] == 'L' else -1)
colour = (colors.red if cols[0].split('_')[-2] == 'in' else colors.blue)
feature = SeqFeature(
FeatureLocation(int(cols[3]), int(cols[4]), strand=strand))
primer_feature_set.add_feature(feature,
color=colour,
name=cols[0],
label=True,
label_size=4,
label_position="start",
label_angle=45)
for col in seq_df.columns:
bases = seq_df[col]
bases.dropna(how='any', inplace=True)
ent = entropy1(bases)
pos_ent = (col, ent)
alignment_entropy.append(pos_ent)
#%%
for feature in ref_polyprot.features:
print(feature)
# Bottom Up Approach
feature_set1 = GenomeDiagram.FeatureSet()
feature_set2 = GenomeDiagram.FeatureSet()
i = 1
for feature in ref_polyprot.features:
if feature.type != "mat_peptide":
#Exclude this feature
continue
if i % 2 == 0:
feature_set1.add_feature(feature,
color='green',
label=True,
label_size=14,
label_angle=90,
label_position='start',
label_strand=1,
