class ScrapeEnsembl():
'''
'''
def __init__(self, query, hg_version):
self.query = query.replace("chr","")
self.hg_version = ScrapeEnsembl.genome.get(hg_version) # convert to ensembl release
self.hg = EnsemblRelease(self.hg_version) # convert to ensembl release object
genome = {"hg19": 75, "hg38": 83}
def get_gene_info(self):
''' Get the gene information at a given genomic position
'''
# check if the input is a genomic position or genomic range
if re.search(r"[-:]", self.query) and self.query.replace(":","").isdigit():
chrom = int(self.query.split(":")[0])
pos = int(self.query.split(":")[1])
gene_name = self.hg.gene_names_at_locus(contig=chrom, position=pos)
if not gene_name:
msg = " ".join(("No gene found at",self.query,"for genome version",
str(self.hg_version)))
return msg
gene_info = self.hg.genes_by_name(gene_name[0])
# gene_info[0].loaction doesn't work, hence the mess below
gene_location = str(gene_info[0]).split(",")[-1][:-1].split("=")[1]
gene_info = (gene_info[0].name, gene_info[0].id,
gene_info[0].biotype, gene_location)
return(gene_info)
def get_canonical_transcript(self, gene_name):
''' Determine and return the canonical transcript of the given gene
'''
all_transcripts = self.hg.transcript_ids_of_gene_name(gene_name)
all_transcript_details = [self.hg.transcript_by_id(x) for x in all_transcripts]
protein_coding_transcripts = []
for x in all_transcript_details:
split_transcript_info = re.split(r"[=,]",str(x))
transcript = split_transcript_info[1]
transcript_type = split_transcript_info[9]
location = split_transcript_info[-1][:-1]
start = re.split(r"[:-]", location)[1]
stop = re.split(r"[:-]", location)[2]
size = int(stop) - int(start)
if transcript_type == "protein_coding":
protein_coding_transcripts.append((size,transcript,transcript_type))
# sort by size and return the largest protein coding transcript
if protein_coding_transcripts:
canonical_transcript = sorted(protein_coding_transcripts)[-1][1]
return canonical_transcript
def make_the_gene_with_exon_and_map(chr,
gene_name,
ax,
exon_lib,
x,
y,
locus,
frequency,
width=30.0,
height=5.0,
scale=1.0):
genome = EnsemblRelease(75)
genes = genome.genes_by_name(gene_name)
gene = genes[0]
gene_start = gene.start
gene_end = gene.end
gene_length = float(gene_end - gene_start)
# draw the gene
ax.add_patch(
patches.Rectangle(
(x, y - height / 2),
width,
height,
alpha=0.5,
color="dodgerblue",
linewidth=0,
))
# find the exon ids
exon_id = genome.exon_ids_of_gene_name(gene_name)
# plot the gene with exons
for i in exon_id:
position = exon_lib[i]
exon_start = int(position[0])
exon_end = int(position[1])
exon_length = exon_end - exon_start
plot_length = exon_length / gene_length * width
plot_x = (exon_start - gene_start) / gene_length * width
ax.add_patch(
patches.Rectangle(
(x + plot_x, y - height / 2 - 0.5 * scale),
plot_length,
height + 1 * scale,
color="black",
alpha=0.4,
linewidth=0,
))
# map the read to the plot
for i in range(len(locus)):
plot_x = (locus[0] - gene_start) / gene_length * width
if frequency[i] < 0.0001:
bar_length = 1
else:
bar_length = abs(math.log(frequency[i] / 0.01) * 2)
ax.plot(
(x + plot_x, x + plot_x),
(y + height / 2 + scale * 0.5,
y + height / 2 + scale * 0.5 + bar_length),
color="darkblue",
alpha=0.5,
linewidth=2,
)
# gene name at the left
ax.text(x - 0.5,
y,
gene_name + '\n' + chr,
horizontalalignment='right',
verticalalignment='center',
fontsize=25,
fontweight="bold")
# gene start
ax.text(
x,
y - height / 2 - 0.8 * scale,
gene_start,
horizontalalignment='center',
verticalalignment='top',
fontsize=12,
)
# gene end
ax.text(
x + width,
y - height / 2 - 0.8 * scale,
gene_end,
horizontalalignment='center',
verticalalignment='top',
fontsize=12,
)
def plot_the_genes_mapping(lib,
lib_char_y,
ax,
total_read,
length=50.0,
x_default=10.0,
frequency_parameter=0.05):
#parse the data
l_gene = []
for i in lib:
chr = "chr" + i[0]
gene_name = i[1]
if gene_name == "non-coding":
for j in lib[i]:
frequency = [
float(j[1]) * 100 / total_read,
]
position = j[2]
l_gene.append((chr, None, frequency, position))
else:
frequency = [float(x[1]) * 100 / total_read for x in lib[i]]
position = [int(x[2]) for x in lib[i]]
l_gene.append((chr, gene_name, frequency, position))
# draw the genes
for i in l_gene:
gene_name = i[1]
gene_y = lib_char_y[i[0]]
frequency = sum(i[2])
chr_length = chr_relative_size[i[0]] * chr_relative_size["chr1_length"]
#find the x coordinate of the gene in the corresponding chrs
if gene_name != None:
genome = EnsemblRelease(75)
gene = genome.genes_by_name(gene_name)
gene = gene[0]
gene_start = gene.start
gene_end = gene.end
gene_position_in_chr = (gene_start + gene_end) / 2
gene_x = length * chr_relative_size[
i[0]] * gene_position_in_chr / chr_length
else:
gene_x = length * chr_relative_size[i[0]] * i[3] / chr_length
# draw the genes (size of circle stand for the freqency
if frequency < 0.05:
radius = 0.5
else:
radius = abs(math.log(frequency / frequency_parameter))
if gene_name == None:
color = "deeppink"
else:
color = "dodgerblue"
# gene with frequency related radius
ax.add_patch(
patches.Circle(
(gene_x + x_default, gene_y),
radius,
color=color,
alpha=0.5,
linewidth=0,
))
# gene position
ax.add_patch(
patches.Circle(
(gene_x + x_default, gene_y),
0.5,
color=color,
linewidth=0.5,
edgecolor="black",
))
if gene_name != None:
ax.text(
gene_x + x_default,
gene_y - radius - 0.8,
gene_name,
horizontalalignment='center',
verticalalignment='center',
fontsize=18,
fontweight="bold",
)
if frequency < 0.0001:
number = "%.2e" % float(frequency)
else:
number = "%.4f" % float(frequency)
ax.text(
gene_x + x_default,
gene_y + radius + 0.5,
number,
horizontalalignment='center',
verticalalignment='center',
fontsize=12,
)
return l_gene
def genes_by_name(*args, **kwargs):
genome = EnsemblRelease(ENSEMBL_RELEASE_VERSION)
return genome.genes_by_name(*args, **kwargs)
