def visualize_secondary_structure(sse, first_id):
dssp_to_abc = {
"I": "c",
"S": "c",
"H": "a",
"E": "b",
"G": "c",
"B": "b",
"T": "c",
"C": "c"
}
for element in range(0, len(sse)):
sse[element] = dssp_to_abc[sse[element]]
def _add_sec_str(annotation, first, last, str_type):
if str_type == "a":
str_type = "helix"
elif str_type == "b":
str_type = "sheet"
else:
# coil
return
feature = seq.Feature("SecStr", [seq.Location(first, last)],
{"sec_str_type": str_type})
annotation.add_feature(feature)
# Find the intervals for each secondary structure element
# and add to annotation
annotation = seq.Annotation()
curr_sse = None
curr_start = None
for i in range(len(sse)):
if curr_start is None:
curr_start = i
curr_sse = sse[i]
else:
if sse[i] != sse[i - 1]:
_add_sec_str(annotation, curr_start + first_id,
i - 1 + first_id, curr_sse)
curr_start = i
curr_sse = sse[i]
# Add last secondary structure element to annotation
_add_sec_str(annotation, curr_start + first_id, i - 1 + first_id, curr_sse)
fig = plt.figure(figsize=(8.0, 3.0))
ax = fig.add_subplot(111)
graphics.plot_feature_map(
ax,
annotation,
symbols_per_line=150,
loc_range=(first_id, first_id + len(sse)),
show_numbers=True,
show_line_position=True,
feature_plotters=[HelixPlotter(), SheetPlotter()])
fig.tight_layout()
plt.show()
def make_feature_maps(gene):
try:
find_id = entrez.fetch(gene,
gettempdir(),
suffix="gb",
db_name="nuccore",
ret_type="gb")
read_file = gb.GenBankFile.read(find_id)
file_annotation = gb.get_annotation(read_file)
except:
flash('The entered gene could not found. Please try again.', 'error')
return None
key_list = []
for feature in file_annotation:
keys = feature.key
key_list.append(keys)
if feature.key == "source":
# loc_range has exclusive stop
loc = list(feature.locs)[0]
loc_range = (loc.first, loc.last + 1)
Unique_key = np.unique(key_list)
pwd = os.getcwd()
Unique_key = np.unique(key_list)
for j in range(len(Unique_key)):
i = Unique_key[j]
fig, ax = plt.subplots(figsize=(8.0, 2.0))
graphics.plot_feature_map(ax,
seq.Annotation([
feature for feature in file_annotation
if feature.key == i
]),
multi_line=False,
loc_range=loc_range,
show_line_position=True)
plt.title('This plot is for {} features'.format(i))
plt.savefig(pwd + '/app/static/images/{}.png'.format(i), dpi=300)
session['valid_gene'] = True
return None
def visualize_secondary_structure(sse, first_id, linesize=200):
length = sse.shape[0]
def _add_sec_str(annotation, first, last, str_type):
if str_type == "a":
str_type = "helix"
elif str_type == "b":
str_type = "sheet"
else:
# coil
return
feature = seq.Feature("SecStr", [seq.Location(first, last)],
{"sec_str_type": str_type})
annotation.add_feature(feature)
# Find the intervals for each secondary ssqa element
# and add to annotation
annotation = seq.Annotation()
curr_sse = None
curr_start = None
for i in range(len(sse)):
if curr_start is None:
curr_start = i
curr_sse = sse[i]
else:
if sse[i] != sse[i - 1]:
_add_sec_str(annotation, curr_start + first_id,
i - 1 + first_id, curr_sse)
curr_start = i
curr_sse = sse[i]
# Add last secondary ssqa element to annotation
_add_sec_str(annotation, curr_start + first_id, i - 1 + first_id, curr_sse)
fig = plt.figure(figsize=(8.0, 3.0))
ax = fig.add_subplot(111)
graphics.plot_feature_map(
ax,
annotation,
symbols_per_line=linesize,
loc_range=(1, length + 1),
show_numbers=True,
show_line_position=True,
feature_plotters=[HelixPlotter(), SheetPlotter()])
fig.tight_layout()
annotation = gb.get_annotation(gb_file, include_only=["gene"])
# Find the minimum and maximum locations of lac genes
min_loc = seq_length
max_loc = 1
for feature in annotation:
for loc in feature.locs:
# Ignore if feature is only a pseudo-gene (e.g. gene fragment)
# and check if feature is lacA gene (begin of lac operon)
if "gene" in feature.qual \
and "pseudo" not in feature.qual \
and feature.qual["gene"] == "lacA":
if min_loc > loc.first:
min_loc = loc.first
if max_loc < loc.last:
max_loc = loc.last
# Extend the location range by 1000 (arbitrary) in each dirction
min_loc -= 10000
max_loc += 10000
# Visualize the region as feature map
fig = plt.figure(figsize=(8.0, 8.0))
ax = fig.add_subplot(111)
graphics.plot_feature_map(ax,
annotation,
loc_range=(min_loc, max_loc),
symbols_per_line=2000,
show_numbers=True,
show_line_position=True)
fig.tight_layout()
plt.show()
########################################################################
# Similarily to :class:`Alignment` objects, we can visualize an
# Annotation in a *feature map*.
# In order to avoid overlaping features, we draw only the *CDS* feature.
# Get the range of the entire annotation via the *source* feature
for feature in annotation:
if feature.key == "source":
# loc_range has exclusive stop
loc = list(feature.locs)[0]
loc_range = (loc.first, loc.last + 1)
fig, ax = plt.subplots(figsize=(8.0, 1.0))
graphics.plot_feature_map(
ax,
seq.Annotation([feature for feature in annotation
if feature.key == "CDS"]),
multi_line=False,
loc_range=loc_range,
show_line_position=True)
fig.tight_layout()
########################################################################
# :class:`Annotation` objects can be indexed with slices, that represent
# the start and the stop base/residue of the annotation from which the
# subannotation is created.
# All features, that are not in this range, are not included in the
# subannotation.
# In order to demonstrate this indexing method, we create a
# subannotation that includes only features in range of the gene itself
# (without the regulatory stuff).
# feature_plotters=[ssp.HelixPlotter(), ssp.SheetPlotter()]
# )
#%% Used if 3D structure is not available and secondary structure inferred from model
exported_ss_path = os.path.join(dataRootDir, ssFolderDir1,
'SrpR_structure_model',
'SrpR_Jpred_sec_struct.csv')
annotation = ssp.ss_csv_to_annotation(csv_path=exported_ss_path)
graphics.plot_feature_map(
ax[4, 1],
annotation,
multi_line=False,
show_numbers=False,
show_line_position=False,
# 'loc_range' takes exclusive stop -> length+1 is required
# loc_range=(1,194), # BM010
loc_range=(1, 214), # BM011
feature_plotters=[ssp.HelixPlotter(),
ssp.SheetPlotter()])
# ax[4,1].set_xlim(start_aa,end_aa)
# Make room for plot at the bottom
plt.gcf().subplots_adjust(hspace=0.15, wspace=0.1)
# Save Figure
outputDir = os.path.join(dataRootDir, ssFolderDir1, figName)
fig.savefig(outputDir)
color=biotite.colors["orange"],
linewidth=0))
# Test our drawing functions with example annotation
annotation = seq.Annotation([
seq.Feature("SecStr", [seq.Location(10, 40)], {"sec_str_type": "helix"}),
seq.Feature("SecStr", [seq.Location(60, 90)], {"sec_str_type": "sheet"}),
])
fig = plt.figure(figsize=(8.0, 0.8))
ax = fig.add_subplot(111)
graphics.plot_feature_map(
ax,
annotation,
multi_line=False,
loc_range=(1, 100),
# Register our drawing functions
feature_plotters=[HelixPlotter(), SheetPlotter()])
fig.tight_layout()
########################################################################
# Now let us do some serious application.
# We want to visualize the secondary structure of one monomer of the
# homodimeric transketolase (PDB: 1QGD).
# The simplest way to do that, is to fetch the corresponding GenBank
# file, extract an `Annotation` object from the file and draw the
# annotation.
# Fetch GenBank files of the TK's first chain and extract annotatation
file_name = entrez.fetch("1QGD_A", biotite.temp_dir(), "gb", "protein", "gb")
dx,
dy,
self._tail_width * bbox.height,
self._head_width * bbox.height,
# Create head with 90 degrees tip
# -> head width/length ratio = 1/2
head_ratio=0.5,
draw_head=draw_head,
color=biotite.colors["orange"],
linewidth=0))
#%%
fig = plt.figure(figsize=(8.0, 0.8))
ax = fig.add_subplot(111)
graphics.plot_feature_map(
ax,
annotation,
multi_line=False,
loc_range=(1, 194),
# Register our drawing functions
feature_plotters=[HelixPlotter(), SheetPlotter()])
# graphics.plot_feature_map(
# ax[4,1], annotation, multi_line=False,
# show_numbers=False, show_line_position=False,
# # 'loc_range' takes exclusive stop -> length+1 is required
# loc_range=(1,194),
# feature_plotters=[HelixPlotter(), SheetPlotter()]
# )
import biotite.sequence.graphics as graphics
strand = Location.Strand.FORWARD
prom = Feature("regulatory", [Location(10, 50, strand)], {
"regulatory_class": "promoter",
"note": "T7"
})
rbs1 = Feature("regulatory", [Location(60, 75, strand)], {
"regulatory_class": "ribosome_binding_site",
"note": "RBS1"
})
gene1 = Feature("gene", [Location(81, 380, strand)], {"gene": "gene1"})
rbs2 = Feature("regulatory", [Location(400, 415, strand)], {
"regulatory_class": "ribosome_binding_site",
"note": "RBS2"
})
gene2 = Feature("gene", [Location(421, 1020, strand)], {"gene": "gene2"})
term = Feature("regulatory", [Location(1050, 1080, strand)],
{"regulatory_class": "terminator"})
annotation = Annotation([prom, rbs1, gene1, rbs2, gene2, term])
fig = plt.figure(figsize=(8.0, 0.8))
ax = fig.add_subplot(111)
graphics.plot_feature_map(
ax,
annotation,
multi_line=False,
loc_range=(1, 1101),
)
fig.tight_layout()
plt.show()