config_enzymes.py

Read in the enzymes file.

#!/usr/bin/python
##############################################################################
# file: config_enzymes.py                                                    #
# 'msparser' toolkit example code                                            #
##############################################################################
# COPYRIGHT NOTICE                                                           #
# Copyright 1998-2010 Matrix Science Limited  All Rights Reserved.           #
#                                                                            #
##############################################################################
#     $Source: parser/examples/test_python/config_enzymes.py $ #
#     $Author: villek@matrixscience.com $                                                      #
#       $Date: 2018-07-30 16:23:53 +0100 $                                         #
#   $Revision: 1b450440f9c97e1e41d0fc6016a27d68951d4532 | MSPARSER_REL_2_8_1-0-gea32989045 $                                                         #
# $NoKeywords::                                                            $ #
##############################################################################

import msparser
import sys

if len(sys.argv) < 2 :  
    print("""
The location of enzymes file has to be specified as a parameter.
The location should either be the full path to the enzymes file
or a URL to a Mascot server - e.g. http://mascot-server/mascot/cgi
""")
    sys.exit(1)

# A sessionID can optionally be passed as the second parameter.
# This will only be required if the 'file' is a URL.
if len(sys.argv) > 2 :
    cs = msparser.ms_connection_settings()
    cs.setSessionID(sys.argv[2])
    file = msparser.ms_enzymefile(sys.argv[1], cs)
else : 
    file = msparser.ms_enzymefile(sys.argv[1])

if not file.isValid() :
    print("There are errors. Cannot continue. The last error description:")
    print(file.getLastErrorString())
    sys.exit(1)


n = file.getNumberOfEnzymes()
print("There are " + str(n) + " enzyme definitions available")

for i in range(n) :
    enzyme = file.getEnzymeByNumber(i)
    defs = []

    for c in range(enzyme.getNumberOfCutters()) :
        if enzyme.getCutterType(c) == msparser.ms_enzyme.NTERM_CUTTER :
            term = "nTerm"
        else :
            term = "cTerm"

        defs.append("%s - %s!%s" % (term, enzyme.getCleave(c), enzyme.getRestrict(c)))

    print("%s: %s" % (enzyme.getTitle(), "; ".join(defs)))


# Now try updating the first one in the list to semi-specific.
enzyme = file.getEnzymeByNumber(0)
enzyme.setSemiSpecific(1)
file.updateEnzymeByNumber(0, enzyme)

# And delete V8-DE.
file.deleteEnzymeByName("V8-DE")

# Finally, save the file under a new name.
file.setFileName(sys.argv[1] + ".new")
file.save_file()

if not file.isValid() :
    print("Failed to save: %s" % file.getLastErrorString())
else :
    print("%s.new now has %d enzyme definitions available" % (sys.argv[1], file.getNumberOfEnzymes()))


""" Running the program as

python config_enzymes.pl /usr/local/mascot/config/enzymes

will give the following output under Mascot Server 2.3


There are 21 enzyme definitions available
Trypsin: cTerm - KR!P
Trypsin/P: cTerm - KR!
Arg-C: cTerm - R!P
Asp-N: nTerm - BD!
Asp-N_ambic: nTerm - DE!
Chymotrypsin: cTerm - FLWY!P
CNBr: cTerm - M!
CNBr+Trypsin: cTerm - M!; cTerm - KR!P
Formic_acid: nTerm - D!; cTerm - D!
Lys-C: cTerm - K!P
Lys-C/P: cTerm - K!
LysC+AspN: nTerm - BD!; cTerm - K!P
Lys-N: nTerm - K!
PepsinA: cTerm - FL!
semiTrypsin: cTerm - KR!P
TrypChymo: cTerm - FKLRWY!P
TrypsinMSIPI: nTerm - J!; cTerm - KR!P; cTerm - J!
TrypsinMSIPI/P: nTerm - J!; cTerm - JKR!
V8-DE: cTerm - BDEZ!P
V8-E: cTerm - EZ!P
None: cTerm - KR!P
/usr/local/mascot/config/enzymes.new now has 20 enzyme definitions available


"""