|
1
|
|
|
"""Functions to read text or tsv files containing GO IDs and sections of GO IDs.""" |
|
2
|
|
|
|
|
3
|
|
|
from __future__ import print_function |
|
4
|
|
|
|
|
5
|
|
|
import os |
|
6
|
|
|
import sys |
|
7
|
|
|
import re |
|
8
|
|
|
from goatools.gosubdag.go_tasks import chk_goids |
|
9
|
|
|
from goatools.grouper.hdrgos import HdrgosSections |
|
10
|
|
|
from goatools.grouper.grprobj import Grouper |
|
11
|
|
|
from goatools.grouper.tasks import SummarySec2dHdrGos |
|
12
|
|
|
|
|
13
|
|
|
__copyright__ = "Copyright (C) 2016-2018, DV Klopfenstein, All rights reserved." |
|
14
|
|
|
__author__ = "DV Klopfenstein" |
|
15
|
|
|
|
|
16
|
|
|
|
|
17
|
|
|
def read_sections(sections_file, exclude_ungrouped=False, prt=sys.stdout): |
|
18
|
|
|
"""Get sections and GO grouping hdrgos from file, if sections exist.""" |
|
19
|
|
|
if sections_file is None: |
|
20
|
|
|
return None |
|
21
|
|
|
if os.path.exists(sections_file): |
|
22
|
|
|
file_contents = read_goids(sections_file, False, exclude_ungrouped) |
|
23
|
|
|
return file_contents.get('sections', None) |
|
24
|
|
|
if prt: |
|
25
|
|
|
prt.write("CANNOT READ: {SEC}\n".format(SEC=sections_file)) |
|
26
|
|
|
|
|
27
|
|
|
def read_goids(fin_txt, get_goids_only=False, exclude_ungrouped=False, prt=sys.stdout): |
|
28
|
|
|
"""Get user list of GO IDs either from a list or from GO IDs on the command-line""" |
|
29
|
|
|
return ReadGoids().read_txt(fin_txt, get_goids_only, exclude_ungrouped, prt) |
|
30
|
|
|
|
|
31
|
|
|
|
|
32
|
|
|
class ReadGoids(object): |
|
33
|
|
|
"""Get user list of GO IDs either from a list or from GO IDs on the command-line""" |
|
34
|
|
|
|
|
35
|
|
|
srch_section = re.compile(r'^#?\s*SECTION:\s*(\S.*\S)\s*$', flags=re.IGNORECASE) |
|
36
|
|
|
|
|
37
|
|
|
def __init__(self): |
|
38
|
|
|
self.goids_fin = [] |
|
39
|
|
|
self.sections_seen = [] |
|
40
|
|
|
self.section2goids = {} |
|
41
|
|
|
|
|
42
|
|
|
def read_txt(self, fin_txt, get_goids_only, exclude_ungrouped, prt=sys.stdout): |
|
43
|
|
|
"""Get user list of GO IDs either from a list or from GO IDs on the command-line""" |
|
44
|
|
|
goids_fin = self._read_txt(fin_txt, get_goids_only, exclude_ungrouped) |
|
45
|
|
|
# Report unused sections, if any |
|
46
|
|
|
if len(self.section2goids) != len(self.sections_seen): |
|
47
|
|
|
self._rpt_unused_sections(prt) |
|
48
|
|
|
# If there are no sections, then goids_fin holds all GO IDs in file |
|
49
|
|
|
if not self.sections_seen: |
|
50
|
|
|
self.goids_fin = goids_fin |
|
51
|
|
|
# Print summary of GO IDs read |
|
52
|
|
|
if prt is not None: |
|
53
|
|
|
self._prt_read_msg(prt, fin_txt, exclude_ungrouped) |
|
54
|
|
|
|
|
55
|
|
|
if goids_fin: |
|
56
|
|
|
return self.internal_get_goids_or_sections() |
|
57
|
|
|
else: |
|
58
|
|
|
sys.stdout.write( |
|
59
|
|
|
"\n**WARNING: GO IDs MUST BE THE FIRST 10 CHARACTERS OF EACH LINE\n\n") |
|
60
|
|
|
|
|
61
|
|
|
def _read_txt(self, fin_txt, get_goids_only, exclude_ungrouped): |
|
62
|
|
|
"""Read GO file. Store results in: section2goids sections_seen. Return goids_fin.""" |
|
63
|
|
|
goids_sec = [] |
|
64
|
|
|
with open(fin_txt) as istrm: |
|
65
|
|
|
# Lines starting with a GO ID will have that GO ID read and stored. |
|
66
|
|
|
# * Lines that do not start with a GO ID will be ignored. |
|
67
|
|
|
# * Text after the 10 characters in a GO ID will be ignored. |
|
68
|
|
|
section_name = None |
|
69
|
|
|
for line in istrm: |
|
70
|
|
|
if line[:3] == "GO:": |
|
71
|
|
|
goids_sec.append(line[:10]) |
|
72
|
|
|
elif not get_goids_only and ":" in line: |
|
73
|
|
|
mtch = self.srch_section.match(line) |
|
74
|
|
|
if mtch: |
|
75
|
|
|
secstr = mtch.group(1) |
|
76
|
|
|
if section_name is not None and goids_sec: |
|
77
|
|
|
self.section2goids[section_name] = goids_sec |
|
78
|
|
|
if not exclude_ungrouped or secstr != HdrgosSections.secdflt: |
|
79
|
|
|
section_name = secstr |
|
80
|
|
|
self.sections_seen.append(section_name) |
|
81
|
|
|
else: |
|
82
|
|
|
section_name = None |
|
83
|
|
|
goids_sec = [] |
|
84
|
|
|
if section_name is not None and goids_sec: |
|
85
|
|
|
self.section2goids[section_name] = goids_sec |
|
86
|
|
|
return goids_sec |
|
87
|
|
|
|
|
88
|
|
|
def _rpt_unused_sections(self, prt): |
|
89
|
|
|
"""Report unused sections.""" |
|
90
|
|
|
sections_unused = set(self.sections_seen).difference(self.section2goids.keys()) |
|
91
|
|
|
for sec in sections_unused: |
|
92
|
|
|
prt.write(" UNUSED SECTION: {SEC}\n".format(SEC=sec)) |
|
93
|
|
|
|
|
94
|
|
|
def internal_get_goids_or_sections(self): |
|
95
|
|
|
"""Return GO IDs, Sections/GOs, or None.""" |
|
96
|
|
|
if self.goids_fin: |
|
97
|
|
|
chk_goids(self.goids_fin, "read_goids") |
|
98
|
|
|
return {'goids' : self.goids_fin} |
|
99
|
|
|
else: |
|
100
|
|
|
# Convert dict into 2D list retaining original section order |
|
101
|
|
|
sections_2d = [] |
|
102
|
|
|
for section_name in self.sections_seen: |
|
103
|
|
|
if section_name in self.section2goids: |
|
104
|
|
|
goids = self.section2goids.get(section_name) |
|
105
|
|
|
chk_goids(goids, "GO IDs IN SECTION({S})".format(S=section_name)) |
|
106
|
|
|
sections_2d.append((section_name, goids)) |
|
107
|
|
|
return {'sections' : sections_2d} |
|
108
|
|
|
|
|
109
|
|
|
def _prt_read_msg(self, prt, fin_txt, exclude_ungrouped): |
|
110
|
|
|
"""Print which file was read and the number of GO IDs found.""" |
|
111
|
|
|
if self.sections_seen or exclude_ungrouped: |
|
112
|
|
|
# dat = Grouper.get_summary_data(self.section2goids.items(), HdrgosSections.secdflt) |
|
113
|
|
|
dat = SummarySec2dHdrGos().summarize_sec2hdrgos(self.section2goids.items()) |
|
114
|
|
|
sys.stdout.write(Grouper.fmtsum.format( |
|
115
|
|
|
GO_DESC='hdr', SECs=len(dat['S']), GOs=len(dat['G']), |
|
116
|
|
|
UNGRP="N/A", undesc="unused", ACTION="READ: ", FILE=fin_txt)) |
|
117
|
|
|
elif self.goids_fin: |
|
118
|
|
|
prt.write(" {G} GO IDs READ: {FIN}\n".format(G=len(self.goids_fin), FIN=fin_txt)) |
|
119
|
|
|
|
|
120
|
|
|
|
|
121
|
|
|
# Copyright (C) 2016-2018, DV Klopfenstein, All rights reserved. |
|
122
|
|
|
|
tanghaibao /
goatools
