Mercurial > repos > galaxyp > hirieftools

comparison pi_database_splitter.py @ 1:8a30d6e5b97d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit ddcc42d2a767f7c14eb710b8ac264745c25444d3
author galaxyp
date Mon, 24 Jul 2017 05:25:22 -0400
parents 34c5c95740a1
children
comparison
equal deleted inserted replaced
0:34c5c95740a1 1:8a30d6e5b97d
1 #!/usr/bin/env python 1 #!/usr/bin/env python
2 import sys 2 import sys
3 import argparse 3 import argparse
4 from numpy import median 4 from numpy import median
5 from contextlib import ExitStack 5 from contextlib import ExitStack
6
7 from peptide_pi_annotator import get_col_by_pattern
6 8
7 9
8 def main(): 10 def main():
9 if sys.argv[1:] == []: 11 if sys.argv[1:] == []:
10 sys.argv.append('-h') 12 sys.argv.append('-h')
12 locfun = {False: locatefraction, 14 locfun = {False: locatefraction,
13 True: reverse_locatefraction}[args.reverse] 15 True: reverse_locatefraction}[args.reverse]
14 # Column nrs should start from 0 16 # Column nrs should start from 0
15 # If negative, -1 is last item in list, etc 17 # If negative, -1 is last item in list, etc
16 if args.fdrcol > 0: 18 if args.fdrcol > 0:
17 args.fdrcol -= 1 19 fdrcol = args.fdrcol - 1
20 elif args.fdrcol:
21 fdrcol = args.fdrcol
22 elif args.fdrcolpattern:
23 fdrcol = get_col_by_pattern(args.train_peptable, args.fdrcolpattern)
24 else:
25 fdrcol = False
18 if args.deltapicol > 0: 26 if args.deltapicol > 0:
19 args.deltapicol -= 1 27 deltapicol = args.deltapicol - 1
20 pishift = get_pishift(args.train_peptable, args.fdrcol, args.deltapicol, 28 elif args.deltapicol:
29 deltapicol = args.deltapicol
30 elif args.deltapicolpattern:
31 deltapicol = get_col_by_pattern(args.train_peptable,
32 args.deltapicolpattern)
33 else:
34 deltapicol = False
35 pishift = get_pishift(args.train_peptable, fdrcol, deltapicol,
21 args.fdrcutoff, args.picutoff) 36 args.fdrcutoff, args.picutoff)
22 binarray = get_bin_array(args.fr_amount, args.fr_width, args.intercept, 37 binarray = get_bin_array(args.fr_amount, args.fr_width, args.intercept,
23 args.tolerance, pishift) 38 args.tolerance, pishift)
24 write_fractions(args.pipeps, args.fr_amount, args.prefix, 39 write_fractions(args.pipeps, args.fr_amount, args.prefix,
25 binarray, locfun, args.minlen, args.maxlen) 40 binarray, locfun, args.minlen, args.maxlen)
58 'Tab separated file.') 73 'Tab separated file.')
59 parser.add_argument('--deltacol', dest='deltapicol', help='Delta pI column' 74 parser.add_argument('--deltacol', dest='deltapicol', help='Delta pI column'
60 ' number in peptide table. First column is nr. 1. ' 75 ' number in peptide table. First column is nr. 1. '
61 'Negative number for counting from last col ' 76 'Negative number for counting from last col '
62 '(-1 is last).', default=False, type=int) 77 '(-1 is last).', default=False, type=int)
78 parser.add_argument('--deltacolpattern', dest='deltapicolpattern',
79 help='Delta pI column header pattern in peptide '
80 'table.', default=False, type=str)
63 parser.add_argument('--picutoff', dest='picutoff', 81 parser.add_argument('--picutoff', dest='picutoff',
64 help='delta pI value to filter experimental peptides' 82 help='delta pI value to filter experimental peptides'
65 ' when calculating pi shift.', default=0.2, type=float) 83 ' when calculating pi shift.', default=0.2, type=float)
84 parser.add_argument('--fdrcolpattern', dest='fdrcolpattern',
85 help='FDR column header pattern in peptide table.',
86 default=False, type=str)
66 parser.add_argument('--fdrcol', dest='fdrcol', help='FDR column number in ' 87 parser.add_argument('--fdrcol', dest='fdrcol', help='FDR column number in '
67 'peptide table. First column is nr. 1. Empty includes ' 88 'peptide table. First column is nr. 1. Empty includes '
68 'all peptides', default=False, type=int) 89 'all peptides', default=False, type=int)
69 parser.add_argument('--fdrcutoff', dest='fdrcutoff', 90 parser.add_argument('--fdrcutoff', dest='fdrcutoff',
70 help='FDR cutoff value to filter experimental peptides' 91 help='FDR cutoff value to filter experimental peptides'
82 action='store_const', const=True, default=False) 103 action='store_const', const=True, default=False)
83 parser.add_argument('--intercept', dest='intercept', 104 parser.add_argument('--intercept', dest='intercept',
84 help='pI Intercept of strip', type=float) 105 help='pI Intercept of strip', type=float)
85 parser.add_argument('--width', dest='fr_width', 106 parser.add_argument('--width', dest='fr_width',
86 help='Strip fraction width in pI', type=float) 107 help='Strip fraction width in pI', type=float)
87 parser.add_argument('--minlen', dest='minlen', help='Minimal peptide length', 108 parser.add_argument('--minlen', dest='minlen', help='Minimal peptide length',
88 type=int) 109 type=int)
89 parser.add_argument('--maxlen', dest='maxlen', help='Maximal peptide length', 110 parser.add_argument('--maxlen', dest='maxlen', help='Maximal peptide length',
90 type=int, default=False) 111 type=int, default=False)
91 return parser.parse_args(sys.argv[1:]) 112 return parser.parse_args(sys.argv[1:])
92 113
144 pepcount = 0 165 pepcount = 0
145 for line in input_fp: 166 for line in input_fp:
146 accs, pep, pi = line.strip().split("\t") 167 accs, pep, pi = line.strip().split("\t")
147 pi = float(pi) 168 pi = float(pi)
148 if maxlen and len(pep) > maxlen: 169 if maxlen and len(pep) > maxlen:
149 continue 170 continue
150 elif len(pep) >= minlen: 171 elif len(pep) >= minlen:
151 pepcount += 1 172 pepcount += 1
152 if pep[-1] in {'K', 'R'}: 173 if pep[-1] in {'K', 'R'}:
153 rev_pep = pep[::-1][1:] + pep[-1] 174 rev_pep = pep[::-1][1:] + pep[-1]
154 else: 175 else: