view codon_switch.py @ 0:5397da1ef896 draft

Uploaded
author gianmarco_piccinno
date Tue, 21 May 2019 05:05:15 -0400
parents
children
line wrap: on
line source

#!/usr/bin/env python

__author__= "Gianmarco Piccinno"
__version__ = "1.0.0"

from syngenic import *
from functions import *
from Bio import *
import argparse as ap

if __name__ == '__main__':

    parser = ap.ArgumentParser(description="", formatter_class=ap.RawTextHelpFormatter)

    parser.add_argument(
        '-i', '--input_plasmid', help='Input plasmid', required=True)
    parser.add_argument(
        '-l', '--plasmid_format', help='Format of the plasmid: {fasta, genbank}', required=True)
    parser.add_argument(
        '-p', '--input_patterns', help='Input patterns separated by new_line', required=True)
    parser.add_argument(
        '-g', '--input_genome', help='Input annotated genome', required=True)
    parser.add_argument(
        '-q', '--genome_format', help='Format of the annotated genome: {fasta, gbk}', required=True)
    parser.add_argument(
        '-c', '--codon_table', help='Codon table to be used {Bacterial}', required=True)
    parser.add_argument(
        '-m', '--max_row', help='Max row length when print', required=False)
    parser.add_argument(
        '-d', '--demonstration', help='Use demonstration simplication', required=False)
    parser.add_argument(
        '-f', '--n_plasmids', help='Use demonstration simplication', required=False)
    parser.add_argument(
        '-o', '--output_folder', help='Folder for writing the output file', required=True)
    args = vars(parser.parse_args())

    """

    python codon_switch_v2.py
        -i ./pEPSA5_annotated.gb
        -l genbank
        -p ./patterns.txt
        -g S_aureus_JE2.gbf
        -q gbk -c Bacterial
        -o ./output

        python codon_switch_v2.py -i ./pEPSA5_annotated.gb -l genbank -p ./patterns.txt -g S_aureus_JE2.gbf -q genbank -c Bacterial -o ./output

    """


    pl = SeqIO.read(
        open(args['input_plasmid'], "r"), args['plasmid_format'])

    if args['demonstration'] == "demonstration":
        pl = pl[0:3000]
    pats = read_patterns(args['input_patterns'])


    #############################################################
    #
    #############################################################

    #pl = fake_from_real(path = "./data/pEPSA5_annotated.gb", id_ = "Trial", name = "Fake_plasmid")
    print(type(pl))
    print(pl); print(pl.seq); print(pl.features)

    #for feat in pl.features:
    #    print(str(feat.extract(pl)))
    #    print(str(pl[feat.location.start:feat.location.end]))
    #    print("\n")


    n_pl = plasmid(pl)
    print(n_pl); print(len(n_pl))
    print(n_pl.features)


    patts, n_patts = all_patterns(input_ = pats)


    f_patts = n_pl.findpatterns(n_patts, patts)
    print(f_patts)
    print(pl.seq)
    print(len(pl.seq))


    n_poss = punctuate_targets(f_patts, n_pl)
    print(n_poss)

    print_seq(n_pl.seq)

    synonims_tables = synonims_(table_name=args['codon_table'])

    synonims_tables

    plasmids = generalization(n_poss, n_pl, synonims_tables)

    print(len(plasmids))

    #plasmids

    #if len(plasmids) > 5000000:
        #redo generalization without considering internal bases
        #in target sites that are not in CDS
        #this means considering only the outer bases of the target
    #    plasmids = generalization(n_poss, n_pl, synonims_tables,
    #                              reduced = True)

    #########################################################
    # Read plasmid and compute codon usage
    #########################################################

    genome = annotated_genome(read_annotated_genome(
            data=args['input_genome'], type_=args['genome_format']))

    out_genome = genome.codon_usage(args['codon_table'])
    print(out_genome.keys())
    print(out_genome["Table"])

    print(out_genome["Table"].loc["GCA"]["Proportion"])
    print(type(out_genome["Table"].loc["GCA"]["Proportion"]))


    #########################################################
    # Evaluate the plasmid
    #########################################################

    useful_plasmids = evaluate_plasmids(plasmids = plasmids,
                                        original_plasmid = n_pl,
                                        codon_usage_table = out_genome["Table"],
                                        n_patts = n_patts,
                                        f_patts = patts)

    dat_plasmids = rank_plasmids(original_useful_plasmids = useful_plasmids)

    def_pls = dat_plasmids.index[:int(args['n_plasmids'])]

    for to_save in def_pls:
        #print(to_save)
        #print(useful_plasmids[to_save])
        with open(to_save+".fa", "w") as handle:
            handle.write(">"+to_save+"\n")
            handle.write(useful_plasmids[to_save]["sequence"])



    if args['max_row'] != None:
        tmp_max_row = int(args['max_row'])
    else:
        tmp_max_row = 27

    print_color_seq(original = n_pl,
                    others = def_pls,
                    annotation_information = useful_plasmids,
                    tot = useful_plasmids,
                    ind_range = None,
                    patterns = n_poss,
                    f_patterns = f_patts,
                    patts = patts,
                    max_row = tmp_max_row)


    print_to_pdf(original = n_pl,
                 others = def_pls,
                 annotation_information = useful_plasmids,
                 tot = useful_plasmids,
                 ind_range = None,
                 patterns = n_poss,
                 f_patterns = f_patts,
                 patts = patts,
                 max_row = tmp_max_row)