def calculate_similar():
"""
calculate rna1 and rna2 similarity and then insert into mongodb
:return:
"""
client = conn_mongo()
db = client.md
for item in db.rna_times.find():
n1 = int(item["rna1-times"])
n2 = int(item["rna2-times"])
c = int(item["common-times"])
# 将decimal再转化为float，否则不能在mongo中存储
similarity = float(similarity_element(n1, n2, c))
items = {
"rna1": item["rna1"],
"rna2": item["rna2"],
"similar_sore": similarity
}
db.similar_score_new.insert(items)
def calculate_similar():
"""
calculate rna1 and rna2 similarity and then insert into mongodb
:return:
"""
client = conn_mongo()
db = client.md
for item in db.rna_times.find():
n1 = int(item["rna1-times"])
n2 = int(item["rna2-times"])
c = int(item["common-times"])
# 将decimal再转化为float，否则不能在mongo中存储
similarity = float(similarity_element(n1, n2, c))
items = {
"rna1": item["rna1"],
"rna2": item["rna2"],
"similar_sore": similarity
}
db.similar_score_new.insert(items)
def calculate_similar_new():
"""
:return:
"""
client = conn_mongo()
db = client.md
list2 = db.target_scan.distinct("item1")
rna = []
rrna = []
for item in db.rnacount_new.find():
rna.append(item['value']['mirna'])
rrna.append(item['value']['mirna'])
# rna与rrna分别为正序列逆序列存储着rna的list
rrna.reverse()
# get the 2th column distinct number
target_sum = len(list2)
for i in range(0, len(rna)):
for j in range(0, len(rrna)-i):
item_find = db.rna_times.find({"rna1": rna[i], "rna2": rrna[j]})
# # if not db.similar_score_new2.find({"rna1": item["rna1"], "rna2": item["rna2"]}).count():
item = item_find[0]
n1 = int(item["rna1-times"])
n2 = int(item["rna2-times"])
c = int(item["common-times"])
# 将decimal再转化为float，否则不能在mongo中存储
similarity = float(similarity_element_new(n1, n2, c, target_sum))
items = {
"rna1": item["rna1"],
"rna2": item["rna2"],
"similar_sore": similarity
}
db.similar_score.insert(items)
def calculate_similar_new():
"""
:return:
"""
client = conn_mongo()
db = client.md
list2 = db.target_scan.distinct("item1")
rna = []
rrna = []
for item in db.rnacount_new.find():
rna.append(item['value']['mirna'])
rrna.append(item['value']['mirna'])
# rna与rrna分别为正序列逆序列存储着rna的list
rrna.reverse()
# get the 2th column distinct number
target_sum = len(list2)
for i in range(0, len(rna)):
for j in range(0, len(rrna) - i):
item_find = db.rna_times.find({"rna1": rna[i], "rna2": rrna[j]})
# # if not db.similar_score_new2.find({"rna1": item["rna1"], "rna2": item["rna2"]}).count():
item = item_find[0]
n1 = int(item["rna1-times"])
n2 = int(item["rna2-times"])
c = int(item["common-times"])
# 将decimal再转化为float，否则不能在mongo中存储
similarity = float(similarity_element_new(n1, n2, c, target_sum))
items = {
"rna1": item["rna1"],
"rna2": item["rna2"],
"similar_sore": similarity
}
db.similar_score.insert(items)
# !/usr/bin/env python
# -*- coding: utf-8 -*-
__author__ = 'wtq'
import traceback
from mdat.db.conn_mongo import conn_mongo
client = conn_mongo()
db = client.md
def generate_matrix(file_path):
"""
generate the similar_score matrix then write it into csv
:return:
"""
files = file(file_path, "w+")
rna1 = db.target_scan_split.distinct("item2")
rna1.sort()
rna2 = rna1
try:
for r1 in rna1:
similar = []
for r2 in rna2:
for i in db.similar_score_new2.find({
"$or": [{
"rna1": r1,
"rna2": r2
}, {
"rna1": r2,
"rna2": r1
# !/usr/bin/env python
# -*- coding: utf-8 -*-
__author__ = 'wtq'
import traceback
from mdat.db.conn_mongo import conn_mongo
client = conn_mongo()
db = client.md
def split_rna():
"""
split rna if it contains "/"
:return:
"""
try:
# db.target_scan_split.ensureIndex({"item1": 1, "item2": 1})
for item in db.target_scan2.find():
rna = item["item2"]
head = ""
if not rna.__contains__("/"):
items = {
"item2": "hsa-"+rna,
"item1": item["item1"]
}
if db.target_scan_split.find(items).count() == 0:
db.target_scan_split.insert(items)
