def rMap_full(f_in, f_out):
# Database connection parameters
dbConn = DatabaseConn()
db = dbConn.databaseConnect()
cursor = db.cursor()
gHandler = GeneralHandler(db, cursor)
rHandler = ReagentHandler(db, cursor)
seqHandler = SequenceHandler(db, cursor)
infile = open(f_in, 'r')
outfile = open(f_out, 'w')
for line in infile.readlines():
reagentID = line.strip() # e.g. V123
rID = rHandler.convertReagentToDatabaseID(reagentID)
seqID = rHandler.findDNASequenceKey(rID)
if seqID:
mySeq = seqHandler.findSequenceByID(seqID)
# Construct a Seq object readable by BioPython:
bioSeq = Seq(mySeq)
fSeq = FormattedSeq(bioSeq) # default linear = TRUE
analysis = Analysis(AllEnzymes, fSeq) # linear = true
result = analysis.full()
header = "==============================================\nRestriction analysis for " + reagentID + "\n==============================================\n"
analysis.print_that(title=header+'\n\n')
def rMap_full(f_in, f_out):
# Database connection parameters
dbConn = DatabaseConn()
db = dbConn.databaseConnect()
cursor = db.cursor()
gHandler = GeneralHandler(db, cursor)
rHandler = ReagentHandler(db, cursor)
seqHandler = SequenceHandler(db, cursor)
infile = open(f_in, 'r')
outfile = open(f_out, 'w')
for line in infile.readlines():
reagentID = line.strip() # e.g. V123
rID = rHandler.convertReagentToDatabaseID(reagentID)
seqID = rHandler.findDNASequenceKey(rID)
if seqID:
mySeq = seqHandler.findSequenceByID(seqID)
# Construct a Seq object readable by BioPython:
bioSeq = Seq(mySeq)
fSeq = FormattedSeq(bioSeq) # default linear = TRUE
analysis = Analysis(AllEnzymes, fSeq) # linear = true
result = analysis.full()
header = "==============================================\nRestriction analysis for " + reagentID + "\n==============================================\n"
analysis.print_that(title=header + '\n\n')
def open_dataset() -> dict:
"""
打开脚本文件
:return: dict response 内容
"""
if request.method == "GET":
file_path = request.args.get("path", "")
if not os.path.exists(file_path):
return {"code": 0, "msg": "打开文件失败！", "data": {"msg": "当前路径不存在文件，请检查文件路径！"}}
try:
print(file_path)
with open(file_path, "r", encoding="utf-8") as file:
dataset = [line for line in jsonlines.Reader(file)]
data_handler = SequenceHandler()
data_handler.set_dataset(dataset)
data_handler.file_path = file_path
uid = str(uuid4())
dataset_dict[uid] = data_handler
feedback = {
"code": 1,
"msg": "打开文件成功！",
"data": {
"length": len(dataset),
"uid": uid
}
}
except Exception as error:
feedback = {
"code": 0,
"msg": "打开文件失败！",
"data": {
"msg": str(error)
}
}
else:
feedback = {"code": 0, "msg": "请求方法有误！", "data": {}}
return feedback
def rMap_specific(f_in, f_out, enz_list):
# Database connection parameters
dbConn = DatabaseConn()
db = dbConn.databaseConnect()
cursor = db.cursor()
gHandler = GeneralHandler(db, cursor)
rHandler = ReagentHandler(db, cursor)
seqHandler = SequenceHandler(db, cursor)
infile = open(f_in, 'r')
outfile = open(f_out, 'w')
for line in infile.readlines():
reagentID = line.strip() # e.g. V123
rID = rHandler.convertReagentToDatabaseID(reagentID)
seqID = rHandler.findDNASequenceKey(rID)
if seqID:
mySeq = seqHandler.findSequenceByID(seqID)
# Construct a Seq object readable by BioPython:
bioSeq = Seq(mySeq)
fSeq = FormattedSeq(bioSeq, linear=False) # linear = FALSE, we're dealing w/ VECTORS
analysis = Analysis(enz_list, fSeq, linear=False) # linear = FALSE again for VECTORS
result = analysis.full()
outfile.write(reagentID + ": " + '\n')
# calculate bandwidths
allSites = []
for enz in result.keys():
sites = result[enz]
if len(allSites) == 0:
allSites = sites
else:
# concatenate
for s in sites:
allSites.append(s)
allSites.sort()
if len(allSites) > 0:
# calculate distances between sites
bandSizes = []
i = 1
while i < len(allSites):
tmpLen = allSites[i] - allSites[i-1]
bandSizes.append(tmpLen)
i += 1
# last band
tmpLen = len(mySeq) - allSites[i-1] + allSites[0]
bandSizes.append(tmpLen)
bandSizes.sort()
outfile.write(`bandSizes` + '\n')
outfile.write('\n')
infile.close()
outfile.close()
cursor.close()
db.close()
def rMap_specific(f_in, f_out, enz_list):
# Database connection parameters
dbConn = DatabaseConn()
db = dbConn.databaseConnect()
cursor = db.cursor()
gHandler = GeneralHandler(db, cursor)
rHandler = ReagentHandler(db, cursor)
seqHandler = SequenceHandler(db, cursor)
infile = open(f_in, 'r')
outfile = open(f_out, 'w')
for line in infile.readlines():
reagentID = line.strip() # e.g. V123
rID = rHandler.convertReagentToDatabaseID(reagentID)
seqID = rHandler.findDNASequenceKey(rID)
if seqID:
mySeq = seqHandler.findSequenceByID(seqID)
# Construct a Seq object readable by BioPython:
bioSeq = Seq(mySeq)
fSeq = FormattedSeq(
bioSeq,
linear=False) # linear = FALSE, we're dealing w/ VECTORS
analysis = Analysis(
enz_list, fSeq,
linear=False) # linear = FALSE again for VECTORS
result = analysis.full()
outfile.write(reagentID + ": " + '\n')
# calculate bandwidths
allSites = []
for enz in result.keys():
sites = result[enz]
if len(allSites) == 0:
allSites = sites
else:
# concatenate
for s in sites:
allSites.append(s)
allSites.sort()
if len(allSites) > 0:
# calculate distances between sites
bandSizes = []
i = 1
while i < len(allSites):
tmpLen = allSites[i] - allSites[i - 1]
bandSizes.append(tmpLen)
i += 1
# last band
tmpLen = len(mySeq) - allSites[i - 1] + allSites[0]
bandSizes.append(tmpLen)
bandSizes.sort()
outfile.write( ` bandSizes ` + '\n')
outfile.write('\n')
infile.close()
outfile.close()
cursor.close()
db.close()
