import sys import argparse import operator import pythomics.parsers.fasta as fasta import pythomics.genomics.parsers as gp description = """ This script will incorporate the a given GFF file into a specified fasta file. It can also incorporate variants given in a VCF file while generating this fasta file. """ parser = CustomParser(description = description) parser.add_fasta(help="The fasta file to reference.") parser.add_out(help="The file to write resulting fasta file to.") gff_group = parser.add_argument_group('GFF file related options') gff_group.add_argument('--gff', help="The GFF file to use.", type=argparse.FileType('r'), required=True) gff_group.add_argument('--group-on', help="The key to group entries together by (such as transcript_id)", type=str, default='ID') gff_group.add_argument('--feature', help="The feature to use for fetching coordinates (such as CDS, does not apply with cufflinks flag).", type=str, default='') gff_group.add_argument('--cufflinks', help="If the gff file is in the standard cufflinks output", action='store_true', default=False) vcf_group = parser.add_argument_group('VCF file related options') vcf_group.add_vcf() vcf_group.add_argument('--variants-only', help="Only output transcripts with variants.", action='store_true', default=False) splice_group = parser.add_argument_group('Splice Junction Options (if a variant falls over a exon-exon junction. Default is to ignore.)') splice_group.add_argument('--splice-partial', help="Partially splice variants (only include exonic portions of variant)", action='store_true', default=False) def main(): args = parser.parse_args() snps = not args.no_snps dels = args.dels
import pythomics.proteomics.digest as digest import pythomics.parsers.fasta as fasta from pythomics.utils import ColumnFunctions parser = CustomParser(description = description) parser.add_fasta(help="The fasta file to match peptides against.") parser.add_out(help="The name of the file you wish to create with results appended.") parser.add_argument('--peptide-out', nargs='?', help="The file to write digested products to.", type=argparse.FileType('w'), default=os.devnull) parser.add_argument('--protein-out', nargs='?', help="The file to write grouped products to.", type=argparse.FileType('w'), default=os.devnull) parser.add_argument('--strict', help='For numeric operations, fail if types are incorrect (converting NA to a float for instance).', action='store_true') parser.add_delimited_file(cols=['--peptide-col'], col_default='Peptide') parser.add_argument('-r', '--regex', help="A perl regular expression determining which parts of the header to capture.", type=str) parser.add_argument('--inferred-name', help="The name you want to assign for protein inference (in case you are regexing for gene names or something).", type=str, default='Proteins') parser.add_argument('--no-inference', help="Do not append proteins inferred from sequences.", action='store_true') parser.add_argument('--no-equality', help="Do not consider Leucine and Isoleucine equal for peptide mapping.", action='store_true') ibaq_group = parser.add_argument_group('iBAQ related options') ibaq_group.add_argument('--ibaq', help="Provide to append iBAQ values as well (requires protein inference).", action='store_true') ibaq_group.add_argument('--precursors', help="The column with precursor area (defaults to header lines containing 'Precursor').", type=str) parser.add_column_function('', col_argument='--ibaq-function', group=ibaq_group, col_help="The function to apply to groups of iBAQ values (for multiple peptide matches).", parent=False) ibaq_group.add_argument('--non-redundant', help="Use only non-redundant theoretical tryptic peptides for the iBAQ denominator.", action='store_true') parser.add_enzyme(help="The enzyme used to digest the sample.") ibaq_group.add_argument('--normalize', help="Normalize iBAQ to total intensity of column (useful for comparing multiple samples).", action='store_true') protein_group = parser.add_argument_group('Protein Grouping Options') protein_group.add_argument('--unique-only', help="Only group proteins with unique peptides", action='store_true') protein_group.add_argument('--position', help="Write the position of the peptide matches.", action='store_true') protein_group.add_argument('--case-sensitive', help="Treat peptides as case-sensitive (ie separate modified peptides)", action='store_true') mod_group = parser.add_argument_group('Peptide Modification Options') mod_group.add_argument('--mod-out', nargs='?', help="The file to write a modification-centric summary to.", type=argparse.FileType('w'), default=None) mod_group.add_argument('--modification-site', help="Write the position in the parent protein of the modification (requires case-sensitive and modifications being lower-cased).", action='store_true') parser.add_column_function('--mod-col', help="The column containing modification information.", group=mod_group) motif_group = mod_group.add_argument_group('Motif Options')
__author__ = 'chris' description = """ """ import sys import os import operator import argparse from pythomics.templates import CustomParser parser = CustomParser(description=description) group = parser.add_argument_group('Protein Inference File') group.add_argument( '--inference', help= "The protein inference file (your peptide file with gene/protein annotations). For multiple files, separate by spaces (must be in same order as mods).", nargs='+', type=argparse.FileType('r'), required=True) group.add_argument('--gene', help="The Gene column name", type=str, default='Gene') group.add_argument('--protein', help="The Protein column name", type=str, default='Protein')
__author__ = 'chris' description = """ """ import sys import os import operator import argparse from pythomics.templates import CustomParser parser = CustomParser(description=description) group = parser.add_argument_group('Protein Inference File') group.add_argument('--inference', help="The protein inference file (your peptide file with gene/protein annotations). For multiple files, separate by spaces (must be in same order as mods).", nargs='+', type=argparse.FileType('r'), required=True) group.add_argument('--gene', help="The Gene column name", type=str, default='Gene') group.add_argument('--protein', help="The Protein column name", type=str, default='Protein') group.add_argument('--peptide', help="The Peptide column name", type=str, default='Peptide') group.add_argument('--quant', help="The name of quantification columns (such as Heavy/Light). Separate multiple columns by spaces", nargs='+', default=['Heavy/Light']) mods = parser.add_argument_group('Modification File') mods.add_argument('--mods', help="The modifications file (the file with sites, peptides). For multiple files, separate by spaces (must be in same order as inference).", nargs='+', type=argparse.FileType('r'), required=True) mods.add_argument('--site-protein', help="The mod file protein column name", type=str, default='Protein') parser.add_argument('--no-log2', help='Do not log2 normalize quantification values.', action='store_true') parser.add_argument('--no-median', help='Do not normalize quantification values by the median of the experiment.', action='store_true') parser.add_argument('--wp', help="The whole proteome inference file, if it exists. For multiple replicates, separate by spaces.", nargs='+', type=argparse.FileType('r')) parser.add_argument('--non-mod-norm', help='Normalize the data by the non-modified peptides.', action='store_true') parser.add_argument('--site-file', help='The output path for the file with sumamries at the site level.', default=sys.stdout, type=argparse.FileType('wb'))
"A perl regular expression determining which parts of the header to capture.", type=str) parser.add_argument( '--inferred-name', help= "The name you want to assign for protein inference (in case you are regexing for gene names or something).", type=str, default='Proteins') parser.add_argument('--no-inference', help="Do not append proteins inferred from sequences.", action='store_true') parser.add_argument( '--no-equality', help="Do not consider Leucine and Isoleucine equal for peptide mapping.", action='store_true') ibaq_group = parser.add_argument_group('iBAQ related options') ibaq_group.add_argument( '--ibaq', help="Provide to append iBAQ values as well (requires protein inference).", action='store_true') ibaq_group.add_argument( '--precursors', help= "The column with precursor area (defaults to header lines containing 'Precursor').", type=str) parser.add_column_function( '', col_argument='--ibaq-function', group=ibaq_group, col_help= "The function to apply to groups of iBAQ values (for multiple peptide matches).",
""" import argparse, sys, re, csv, copy, decimal from pythomics.templates import CustomParser import pythomics.proteomics.config as config import pythomics.proteomics.digest as digest import pythomics.parsers.fasta as fasta parser = CustomParser(description = description) parser.add_fasta(help="The fasta file to match peptides against.") parser.add_argument('--peptide_out', nargs='?', help="The file to write digested products to.", type=argparse.FileType('w'), default=sys.stdout) parser.add_argument('--protein_out', nargs='?', help="The file to write grouped products to.", type=argparse.FileType('w'), default=sys.stdout) parser.add_delimited_file() parser.add_argument('-r', '--regex', help="A perl regular expression determining which parts of the header to capture.", type=str) parser.add_argument('--no-inference', help="Do not append proteins inferred from sequences.", action='store_false', default=False) group = parser.add_argument_group('iBAQ related options') group.add_argument('--ibaq', help="Provide to append iBAQ values as well (requires protein inference).", action='store_true', default=False) group.add_argument('--precursors', help="The column with precursor area (defaults to header lines containing 'Precursor').", type=int, default=None) parser.add_enzyme() group.add_argument('--no-normalize', help="Don't normalize iBAQ to total intensity", action='store_false', default=True) group.add_argument('--case-sensitive', help="Treat peptides as case-sensitive (ie separate modified peptides)", action='store_true', default=False) protein_group = parser.add_argument_group('Protein Grouping Options') protein_group.add_argument('--unique-only', help="Only group proteins with unique peptides", action='store_true', default=False) protein_group.add_argument('--position', help="Write the position of the peptide matches.", action='store_true', default=False) def main(): args = parser.parse_args() fasta_file = fasta.FastaIterator(args.fasta) peptide_column = args.col-1 tsv_file = args.tsv header_lines = args.header