def getProteinExpressData():
dbc = DBConnection()
query_filed = {"entrez_id": 1, "symbol": 1, "_id": 0, 'gene_expression': 1}
# name = "51146"
name = "85358"
if name.isalnum():
if name.isdigit():
query_res = dbc.col.find({"entrez_id": name}, query_filed)[0]
else:
query_res = dbc.col.find({"symbol": name}, query_filed)[0]
if query_res.get('gene_expression'):
if query_res['gene_expression'].get('protein_express'):
gtex_gene_express_pic = query_res['gene_expression'][
'protein_express']
print(gtex_gene_express_pic)
return gtex_gene_express_pic
def main():
dbc = DBConnection()
query_filed = {"entrez_id": 1, "symbol": 1, "_id": 0, 'gene_expression': 1}
name = "SHANK3"
if name.isalnum():
if name.isdigit():
query_res = dbc.col.find({"entrez_id": name}, query_filed)[0]
else:
query_res = dbc.col.find({"symbol": name}, query_filed)[0]
# pprint(query_res)
if query_res.get('gene_expression'):
if query_res['gene_expression'].get(
'brainseq_gene_expression_rpkm'):
gtex_gene_express_pic = BrainSeqExpressPlot.plot(
query_res['gene_expression']
['brainseq_gene_expression_rpkm'])
print(query_res['gene_expression']
['brainseq_gene_expression_rpkm'])
def getHumanEPCExpressData():
dbc = DBConnection()
query_filed = {"entrez_id": 1, "symbol": 1, "_id": 0, 'gene_expression': 1}
# name = "234"
name = "85358"
if name.isalnum():
if name.isdigit():
query_res = dbc.col.find({"entrez_id": name}, query_filed)[0]
else:
query_res = dbc.col.find({"symbol": name}, query_filed)[0]
if query_res.get('gene_expression'):
if query_res['gene_expression'].get('human_epc_tpm'):
human_epc_exp_data = query_res['gene_expression'][
'human_epc_tpm']
pprint.pprint(human_epc_exp_data)
if isinstance(human_epc_exp_data, list):
expData = human_epc_exp_data[0].get('express_data')
return expData
def getGexGeneExpressData():
dbc = DBConnection()
query_filed = {"entrez_id": 1, "symbol": 1, "_id": 0, 'gene_expression': 1}
name = "NSD2"
if name.isalnum():
if name.isdigit():
query_res = dbc.col.find({"entrez_id": name}, query_filed)[0]
else:
query_res = dbc.col.find({"symbol": name}, query_filed)[0]
# pprint(query_res)
if query_res.get('gene_expression'):
if query_res['gene_expression'].get('gtex_v7_gene_tpm'):
gtex_brain_data = query_res['gene_expression'][
'gtex_v7_gene_tpm']
if isinstance(gtex_brain_data, list):
gtex_brain_data_dict = gtex_brain_data[0]
print(gtex_brain_data_dict)
return gtex_brain_data_dict
def getMouseBrainExpressData():
# mainer = MouseBrainExpressPlots('29072')
# mainer.run()
dbc = DBConnection()
query_filed = {"entrez_id": 1, "symbol": 1, "_id": 0, 'gene_expression': 1}
# name = "10344"
name = "85358"
if name.isalnum():
if name.isdigit():
query_res = dbc.col.find({"entrez_id": name}, query_filed)[0]
else:
query_res = dbc.col.find({"symbol": name}, query_filed)[0]
# pprint(query_res)
if query_res.get('gene_expression'):
if query_res['gene_expression'].get('mouse_brain_tpm'):
if isinstance(query_res['gene_expression']['mouse_brain_tpm'],
list):
expData = query_res['gene_expression']['mouse_brain_tpm'][
0].get('expree_data')
print(expData)
return expData
def plot(gene_term):
if gene_term.isalnum():
dbc = DBConnection()
if gene_term.isdigit():
gene_data = \
dbc.col.find({"entrez_id": gene_term}, {"entrez_id": 1, "transcripts": 1, "dnms": 1, "_id": 0})[0]
else:
gene_data = \
dbc.col.find({"symbol": gene_term}, {"entrez_id": 1, "transcripts": 1, "dnms": 1, "_id": 0})[0]
dnms_on_trans_plot = DNMsOnTranscriptsPlot()
pprint(gene_data)
if gene_data:
transcript_data = gene_data.get('transcripts')
dnms_data = gene_data.get('dnms')
transcript_list = []
trans_count = 0
dnm_list = []
if transcript_data:
for trans_item in transcript_data:
transcript_id = trans_item.get('transcript_id')
transcript_structure = trans_item.get('structure')
region_list = []
for item_region in [
'coding_exon_region', 'utr3_exon_region',
'utr5_exon_region'
]:
if transcript_structure.get(item_region):
# print(transcript_structure[item_region])
region_list.append(
transcript_structure[item_region])
else:
region_list.append([])
transcript_list.append([
transcript_id, region_list[0], region_list[1],
region_list[2]
])
transcript_list = sorted(
transcript_list, key=lambda x: x[0],
reverse=True) # 最先添加（排在最前面的）plotly画图的时候会放在越靠近x轴
trans_count = len(transcript_list)
if dnms_data:
for dnm_item in dnms_data:
if dnm_item.get("Func_refGene") == 'exonic':
if dnm_item.get('ExonicFunc_refGene'):
s = '%s,%s,%s' % (
dnm_item['start'], dnm_item['variant'],
dnm_item['ExonicFunc_refGene'])
else:
s = '%s,%s' % (dnm_item['start'],
dnm_item['variant'])
else:
if dnm_item.get('Func_refGene'):
s = '%s,%s,%s' % (dnm_item['start'],
dnm_item['variant'],
dnm_item['Func_refGene'])
else:
s = '%s,%s' % (dnm_item['start'],
dnm_item['variant'])
dnm_list.append([dnm_item['start'], s])
else:
dnm_list.append([])
count_exon_xy, count_utr_xy, fin_DNM_xy = dnms_on_trans_plot.generate_xy(
transcript_list, dnm_list)
if trans_count:
return [
count_exon_xy, count_utr_xy, fin_DNM_xy, trans_count
]
else:
return '<div>There is no corresponding data published yet, we will update it when such data available. </div>'
else:
return '<div>There is no corresponding data published yet, we will update it when such data available. </div>'
else:
return '<div>There is no corresponding data published yet, we will update it when such data available. </div>'
def plot(gene_term):
dnms_on_re_plot = DNMsOnRegulatoryPlot()
if gene_term.isalnum():
dbc = DBConnection()
if gene_term.isdigit():
gene_data = dbc.col.find({"entrez_id": gene_term}, {
"entrez_id": 1,
"_id": 0,
"dnms": 1,
"transcripts": 1,
"promoter": 1,
"enhancer": 1,
"symbol": 1
})[0]
else:
gene_data = dbc.col.find({"symbol": gene_term}, {
"entrez_id": 1,
"_id": 0,
"dnms": 1,
"transcripts": 1,
"promoter": 1,
"enhancer": 1,
"symbol": 1
})[0]
transcript_list = []
if gene_data:
if gene_data.get("transcripts"):
for index, item in enumerate(gene_data["transcripts"]):
if item.get('structure'):
transcript_list.append(
dnms_on_re_plot.get_trans_data(
item['structure'],
item.get('transcript_id'),
item.get("strand")))
transcript_list = sorted(
transcript_list, key=lambda x: x[0],
reverse=True) # 最先添加（排在最前面的）plotly画图的时候会放在越靠近x轴
trans_count = len(transcript_list)
re_data = dnms_on_re_plot.get_promoter_and_enhancer_data(
gene_data.get('promoter'), gene_data.get('enhancer'),
gene_data.get('dnms'))
dnms_list = dnms_on_re_plot.get_dnms_data(
gene_data.get("dnms"))
all_region = dnms_on_re_plot.get_all_region(
transcript_list, re_data)
all_region = dnms_on_re_plot.drop_duplicate(all_region)
all_region = dnms_on_re_plot.sort_list(all_region)
dnm_data = dnms_on_re_plot.DNM_sort_by_site(dnms_list)
all_frag = dnms_on_re_plot.cut_fragment(all_region)
scale_frag = dnms_on_re_plot.scale_fragment(
all_frag, dnm_data, re_data)
exton_count, exton_count1 = dnms_on_re_plot.count_exton_region_in_fragment(
all_frag, scale_frag, transcript_list)
exton_plot_data = dnms_on_re_plot.convert_trans_to_xy(
exton_count, exton_count1, transcript_list)
utr_count, utr_count1 = dnms_on_re_plot.count_utr_region_in_fragment(
all_frag, scale_frag, transcript_list)
utr_plot_data = dnms_on_re_plot.convert_utr_to_xy(
utr_count, utr_count1, transcript_list)
if re_data[0] != []:
promoter_count, promoter_count1 = dnms_on_re_plot.count_promoter_region_in_fragment(
all_frag, scale_frag, re_data)
promoter_plot_data = dnms_on_re_plot.convert_regulatory_elements_to_xy(
promoter_count, 'Promoter', re_data)
else:
promoter_plot_data = None
if re_data[1] != []:
enhancer_count, enhancer_count1 = dnms_on_re_plot.count_enhancer_region_in_fragment(
all_frag, scale_frag, re_data)
enhancer_plot_data = dnms_on_re_plot.convert_regulatory_elements_to_xy(
enhancer_count, 'Enhancer', re_data)
else:
enhancer_plot_data = None
final_dnm = dnms_on_re_plot.mapping_mutation_to_frag(
all_frag, scale_frag, dnm_data)
dnm_plot_data = dnms_on_re_plot.convert_dnms_to_xy(final_dnm)
l = [
exton_plot_data, utr_plot_data, promoter_plot_data,
enhancer_plot_data, dnm_plot_data, trans_count
]
return l
else:
return '<div>There is no corresponding data published yet, we will update it when such data available. </div>'