Skip to content
Snippets Groups Projects
Select Git revision
  • 8aa1b417862df8efbfa3c07362fbe5be23ed8da4
  • master default protected
  • 2.0.5
  • 2.0.4
  • 2.0.3
  • 2.0.2
  • 2.0.1
  • 2.0.0
  • 1.2.4
  • 1.2.2
  • 1.2.1
  • 1.1.0
  • v1.0.9
13 results

RapidPeptidesGenerator.py

Blame
  • RapidPeptidesGenerator.py 16.63 KiB
    # -*- coding: utf-8 -*-
    #!/usr/bin/env python3.6
    
    ########################################################################
    # Rapid Peptide Generator (RPG) is a software dedicated to predict     #
    # cleavage sites of proteases. User can create his own enzyme,         #
    # following a simple grammar.                                          #
    #                                                                      #
    # Author: Nicolas Maillet                                              #
    # Copyright © 2018 Institut Pasteur, Paris.                            #
    # See the COPYRIGHT file for details                                   #
    #                                                                      #
    # RPG is free software: you can redistribute it and/or modify          #
    # it under the terms of the GNU General Public License as published by #
    # the Free Software Foundation, either version 3 of the License, or    #
    # any later version.                                                   #
    #                                                                      #
    # RPG is distributed in the hope that it will be useful,               #
    # but WITHOUT ANY WARRANTY; without even the implied warranty of       #
    # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the        #
    # GNU General Public License for more details.                         #
    #                                                                      #
    # You should have received a copy of the GNU General Public license    #
    # along with RPG (LICENSE file).                                       #
    # If not, see <http://www.gnu.org/licenses/>.                          #
    ########################################################################
    
    """Main file of RPG software, handle input/output and launch
    necessary functions
    """
    
    #DOC : last peptide, cut at pos -1 because no cut
    # Ajouter les enzymes de peptidecutter
    # Faire de la docstring des enzymes pour le manuel -> ne pas oublier que l'exception (R,)(D)(D)
    # si (R,)(D) n'y est pas ca sera (R,)(D) à TRUE ! Ca dans Factor Xa
    # add with same name !!
    # Test_enzyme ligne 50, bug sur le tmpfile
    
    #Started on 22 avr. 2016
    #Digest sequences given restriction enzymes
    #Input format : a fasta/fastq file or a sequence
    #Output format : a fasta/csv/tsv file containing the digested sequences
    #@author: Nicolas Maillet
    #@version: 0.0.9α
    #@note: Pwet
    
    __version_info__ = ('0', '0', '8')
    __version__ = '.'.join(__version_info__)
    __revision_date__ = "2018-02-28"
    __author__ = "Nicolas Maillet"
    
    import argparse
    import os
    import sys
    import uuid
    from pathlib import Path
    import core
    import digest
    import enzyme
    from enzymes_definition import AVAILABLE_ENZYMES
    sys.path.insert(0, str(Path.home())) # Home path
    from rpg_user import AVAILABLE_ENZYMES_USER
    
    ALL_ENZYMES = AVAILABLE_ENZYMES + AVAILABLE_ENZYMES_USER
    """All available enzymes in RPG."""
    
    def restricted_float(mc_val):
        """Restricts input miss-cleavage value to a float between 0 and 100.
    
        :param mc_val: value to test
        :type mc_val: float
    
        :return: the inputed value if correct
        :rtype: float
    
        :raises custom ValueError: if value is not between 0 and 100
        :raises custom TypeError: if value is not a float
        """
        try:
            mc_val = float(mc_val)
            if mc_val < 0 or mc_val > 100:
                core.handle_errors("miss-cleavage value should be between 0 and "\
                                   "100.", 0, "Value ")
            return mc_val
        except ValueError:
            # Throw an error
            core.handle_errors("miss-cleavage value should be a float between 0 "\
                               "and 100.", 0, "Type ")
    
    def restricted_enzyme_id(enz_id):
        """Restrict input enzyme id to an int corresponding to an enzyme.
    
        :param mc_val: value to test
        :type mc_val: int
    
        :return: the inputed enzyme id
        :rtype: int
    
        :raises custom ValueError: if id does not correspond to any enzyme
        :raises custom TypeError: if value is not an int
        """
        try:
            enz_id = int(enz_id)
            ids_available = []
            for i in ALL_ENZYMES:
                ids_available.append(i.id_)
            if enz_id not in ids_available:
                core.handle_errors("id " + str(enz_id) + " does not correspond to"\
                                   " any enzyme. Use -l to get enzyme ids.", 0,
                                   "Input ")
            return enz_id
        except ValueError:
            # Throw an error
            core.handle_errors("Enzyme id should be an integer.", 0, "Type ")
    
    def list_enzyme():
        """Print all available enzymes"""
        for enz in ALL_ENZYMES:
            print("%i: %s" % (enz.id_, enz.name))
    
    def create_enzymes_to_use(enzymes, miss_cleavage):
        """Create the list of chosen :py:class:`~rpg.enzyme.Enzyme` to use.
        Each enzyme can be associated to a miss-cleavage value.
    
        :param enzymes: enzymes ids chosen by user
        :param miss_cleavage: associated miss-cleavage values
        :type enzymes: list(int)
        :type miss_cleavage: list(float)
    
        :return: list of enzyme's id with associated miss-cleavage values
        :rtype: list(int)
        """
    
        # Complete Enzymes to use (return)
        enzymes_to_use = []
        if enzymes:
            # Too much miss-cleavage values
            if len(miss_cleavage) > len(enzymes):
                core.handle_errors("Too much miss-cleavage values. Last values"
                                   " will be ignored.")
                # Get only the first ones
                miss_cleavage = miss_cleavage[:len(enzymes)]
            cur_pos = -1
            # Get all enzymes with a given miss_cleavage
            for i, _ in enumerate(miss_cleavage):
                # In all available enzymes
                for enz in ALL_ENZYMES:
                    # Get the current one
                    if enz.id_ == enzymes[i]:
                        # Change miss_cleavage ratio
                        enz.ratio_miss_cleavage = miss_cleavage[i]
                        # Add it
                        enzymes_to_use.append(enz)
                cur_pos = i
            # Get all enzymes without miss_cleavage value
            for i in enzymes[cur_pos + 1:]:
                # In all available enzymes
                for enz in ALL_ENZYMES:
                    # Get the current one
                    if enz.id_ == i:
                        # Add it
                        enzymes_to_use.append(enz)
        # Return enzymes to use
        return enzymes_to_use
    # Not tested
    def get_enzymes_to_use(mode, id_enz_selected, miss_cleavage):
        """Get the list of chosen :py:class:`~rpg.enzyme.Enzyme` to use.
        Each enzyme (and associated miss-cleavage value) are inputed by
        user. If there is a problem, user is interrogated again.
    
        :param mode: Digestion mode. If 'concurrent', no miss-cleavage values are used
        :param enzymes: enzyme's ids chosen by user
        :param miss_cleavage: associated miss-cleavage values
        :type mode: str
        :type enzymes: list(int)
        :type miss_cleavage: list(float)
    
        :return: list of enzyme's id with associated miss-cleavage values
        :rtype: list(int)
    
        .. warning:: Not tested
        """
    
        # Get the correct Enzymes inputed
        enzymes_to_use = create_enzymes_to_use(id_enz_selected, miss_cleavage)
        # No good Enzymes inputed, let user choose
        if not enzymes_to_use:
            id_enz_inputed = []
            # Print all available enzymes
            list_enzyme()
            # Ask user to give correct enzymes ids
            while not enzymes_to_use:
                id_enz_inp = input("Choose which enzyme(s) to use, separated by"
                                   " comma (example: 1,5,6). (q) to quit:\n")
                # Quit
                if "q" in id_enz_inp:
                    sys.exit(0)
                # Get a list of ids
                for i in id_enz_inp.split(","):
                    try:
                        # Convert it to int
                        i = int(i)
                        id_enz_inputed.append(i)
                    # Not an int?
                    except ValueError:
                        # Throw an error
                        core.handle_errors("'%s' should be an integer value. This"
                                           " values will be ignored." % i)
                mc_enz_inputed = []
                if mode == "sequential":
                    mc_enz_inp = input("Percentage of miss-cleavage per inputed"
                                       " enzyme (default 0), separated by comma"
                                       " (example: 1,5,6):\n")
                    if mc_enz_inp:
                        # Get a list of int
                        for i in mc_enz_inp.split(","):
                            try:
                                # Convert it to int
                                i = float(i)
                                mc_enz_inputed.append(i)
                            # Not an int?
                            except ValueError:
                                # Throw an error
                                core.handle_errors("'%s' should be an floating"
                                                   " value. This values will be"
                                                   " ignored." % i)
                # Get the correct Enzyme if enzymes inputed
                enzymes_to_use = create_enzymes_to_use(id_enz_inputed,
                                                       mc_enz_inputed)
        # Return Enzymes to use
        return enzymes_to_use
    # Not tested
    def main():
        """Launcher of RapidPeptidesGenerator
    
        .. warning:: Not tested
        """
        parser = argparse.ArgumentParser(description="This software takes protein "
                                                     "sequences as input (-i optio"
                                                     "n). All sequences will be cl"
                                                     "eaved according to selected "
                                                     "enzymes (-e option) and give"
                                                     "n miss-cleavage percentage ("
                                                     "-m option). Cleaving can be "
                                                     "sequential or concurrent (-d"
                                                     " option). Resulting peptides"
                                                     " are outputted in a file (-o "
                                                     "option) if fasta, csv or tsv"
                                                     " format (-f option). Classic"
                                                     "al enzymes are included (-l "
                                                     "option to print available en"
                                                     "zymes) but it is possible to"
                                                     " define other enzymes (-a op"
                                                     "tion).")
        group_launch = parser.add_mutually_exclusive_group(required=True)
        group_launch.add_argument("-a", "--addenzyme", action="store_true",
                                  help="Add a new cleaving enzyme. See the manual"
                                  " for more information")
        parser.add_argument("-d", "--digest", metavar="",
                            choices=['s', 'sequential', 'c', 'concurrent'],
                            default="s", help="Digestion mode. Either 's', 'seque"
                            "ntial', 'c' or 'concurrent' (default: s)")
        parser.add_argument("-e", "--enzymes", metavar="", default=[],
                            action='append', type=restricted_enzyme_id,
                            help="Id of enzyme(s) to use (i.e. -e 0 -e 5 -e 10 to"
                            " use enzymes 0, 5 and 10). Use -l first to get "
                            "enzyme ids")
        parser.add_argument("-f", "--fmt", metavar="",
                            choices=['fasta', 'csv', 'tsv'], default="fasta",
                            help="Output file format. Either 'fasta', 'csv', or "
                            "'tsv' (default: fasta)")
        group_launch.add_argument("-i", "--inputdata", metavar="",
                                  help="Input file, in fasta / fastq format or a "
                                  "single protein sequence without commentary")
        group_launch.add_argument("-l", "--list", action="store_true",
                                  help="Display the list of available enzymes")
        parser.add_argument("-m", "--misscleavage", metavar="", default=[],
                            action='append', type=restricted_float,
                            help="Percentage of miss-cleavage, between 0 and 100,"
                            " by enzyme(s). It should be in the same order than "
                            "-enzymes options (i.e. -m 15 -m 5 -m 10). Only for "
                            "sequential digestion (default: 0)")
        parser.add_argument("-n", "--noninteractive", action='store_true',
                            help="Non-interactive mode. No standard output, only "
                            "error(s) (--quiet enable, overwrite -v). If output "
                            "filename already exists, output file will be "
                            "overwritten.")
        group_output = parser.add_mutually_exclusive_group()
        group_output.add_argument("-o", "--outputfile", type=str, metavar="",
                                  default="peptides", help="Result file to "
                                  "output result peptides (default './peptides"
                                  ".xxx' depending of --fmt)")
        group_output.add_argument("-r", "--randomname", action="store_true",
                                  help="Random (not used) output name file")
        group_verbose = parser.add_mutually_exclusive_group()
        group_verbose.add_argument("-q", "--quiet", action="store_true",
                                   help="No standard output, only error(s)")
        group_verbose.add_argument("-v", "--verbose", action="count", default=0,
                                   help="Increase output verbosity")
        parser.add_argument("--version", action="version",
                            version="%(prog)s " + __version__ + " from " +
                            __revision_date__)
        args = parser.parse_args()
    
        # --addenzyme option
        if args.addenzyme:
            enzyme.user_creation_enzyme()
            sys.exit(0)
    
        # --digest option
        mode = "sequential"
        if args.digest == "c" or args.digest == "concurrent":
            mode = "concurrent"
            args.misscleavage = []  # No miss-cleavage on concurrent, infinite time
    
        # --list option
        if args.list:
            list_enzyme()
            sys.exit(0)
    
        # --nointeractive option
        if args.noninteractive:
            args.quiet = 1
            args.verbose = 0
    
        # --outputfile / --randomname options
        if args.randomname:
            # Generate a random file name
            output_file = str(uuid.uuid4().hex) + "." + args.fmt
            # Ensure the name is unique
            while os.path.isfile(output_file):
                # Generate a random file name
                output_file = str(uuid.uuid4().hex) + "." + args.fmt
        # Chosen file name
        else:
            # Given name
            tmpname = str(args.outputfile)
            # No extension?
            if "." not in tmpname:
                # Add default extension for this file format
                output_file = tmpname + "." + args.fmt
            else:
                output_file = tmpname
            # If interactive mode
            if not args.noninteractive:
                # This file already exist?
                while os.path.isfile(output_file):
                    core.handle_errors("File '%s' already exit!" % output_file)
                    # Don't overwrite it
                    if input("Overwrite it? (y/n)\n") != "y":
                        tmpname = input("Output filename?\n")
                        # No extension?
                        if "." not in tmpname:
                            # Add default extension for this file format
                            output_file = tmpname + "." + args.fmt
                        else:
                            output_file = tmpname
                    # Overwrite it
                    else:
                        break
    
        # More miss cleavage than enzyme
        if len(args.misscleavage) > len(args.enzymes):
            core.handle_errors("Too much miss-cleavage values. Last values will "
                               "be ignored.")
            args.misscleavage = args.misscleavage[:len(args.enzymes)]
    
        # Get all enzymes inputed
        enzymes_to_use = get_enzymes_to_use(mode, args.enzymes, args.misscleavage)
    
        # Output options
        if args.verbose:
            print("Input: " + args.inputdata)
            print("Enzyme(s) used: " + str([enz.name for enz in enzymes_to_use]))
            print("Mode: " + mode)
            print("Miss-cleavage ratio: " +
                  str([enz.ratio_miss_cleavage for enz in enzymes_to_use]))
            print("Output file: " + os.path.abspath(output_file))
    
        # Make the actual digestion of input data
        results_digestion = digest.digest_from_input(args.inputdata,
                                                     enzymes_to_use, mode)
    
        # Output results
        core.output_results(output_file, results_digestion, args.fmt, args.quiet,
                            args.verbose)
    
    
    ### Let'z go ###
    if __name__ == '__main__':
        main()
        # The end
        sys.exit(0)