1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
|
# #START_LICENSE###########################################################
#
#
# This file is part of the Environment for Tree Exploration program
# (ETE). http://etetoolkit.org
#
# ETE 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
# (at your option) any later version.
#
# ETE 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 ETE. If not, see <http://www.gnu.org/licenses/>.
#
#
# ABOUT THE ETE PACKAGE
# =====================
#
# ETE is distributed under the GPL copyleft license (2008-2015).
#
# If you make use of ETE in published work, please cite:
#
# Jaime Huerta-Cepas, Joaquin Dopazo and Toni Gabaldon.
# ETE: a python Environment for Tree Exploration. Jaime BMC
# Bioinformatics 2010,:24doi:10.1186/1471-2105-11-24
#
# Note that extra references to the specific methods implemented in
# the toolkit may be available in the documentation.
#
# More info at http://etetoolkit.org. Contact: huerta@embl.de
#
#
# #END_LICENSE#############################################################
from __future__ import absolute_import
import os
import re
import logging
import shutil
from six.moves import map
log = logging.getLogger("main")
from ..master_task import ModelTesterTask
from ..master_job import Job
from ..errors import TaskError
from ..utils import basename, PhyloTree, GLOBALS, pjoin
__all__ = ["Prottest"]
class Prottest(ModelTesterTask):
def __init__(self, nodeid, alg_fasta_file, alg_phylip_file,
constrain_tree, seqtype, conf, confname):
GLOBALS["citator"].add('phyml')
self.alg_phylip_file = alg_phylip_file
self.alg_fasta_file = alg_fasta_file
self.confname = confname
self.conf = conf
self.lk_mode = conf[confname]["_lk_mode"]
if self.lk_mode == "raxml":
phyml_optimization = "n"
elif self.lk_mode == "phyml":
phyml_optimization = "lr"
else:
raise ValueError("Choose a valid lk_mode value (raxml or phyml)")
base_args = {
"--datatype": "aa",
"--input": self.alg_phylip_file,
"--bootstrap": "0",
"-o": phyml_optimization,
"--model": None, # I will iterate over this value when
# creating jobs
"--quiet": ""
}
self.models = conf[confname]["_models"]
task_name = "Prottest-[%s]" %','.join(self.models)
ModelTesterTask.__init__(self, nodeid, "mchooser", task_name,
base_args, conf[confname])
if seqtype == "nt":
log.error('Prottest can only be used with amino-acid alignments!')
raise TaskError(self, 'Prottest can only be used with amino-acid alignments!')
self.best_model = None
self.seqtype = "aa"
self.init()
def load_jobs(self):
conf = self.conf
for m in self.models:
args = self.args.copy()
args["--model"] = m
bionj_job = Job(conf["app"]["phyml"], args,
parent_ids=[self.nodeid])
bionj_job.jobname += "-bionj-" + m
bionj_job.jobcat = "bionj"
bionj_job.add_input_file(self.alg_phylip_file, bionj_job.jobdir)
self.jobs.append(bionj_job)
if self.lk_mode == "raxml":
raxml_args = {
"-f": "e",
"-s": pjoin(bionj_job.jobdir, self.alg_phylip_file),
"-m": "PROTGAMMA%s" % m,
"-n": self.alg_phylip_file+"."+m,
"-t": pjoin(bionj_job.jobdir,
self.alg_phylip_file+"_phyml_tree.txt")
}
raxml_job = Job(conf["app"]["raxml"], raxml_args,
parent_ids=[bionj_job.jobid])
raxml_job.jobname += "-lk-optimize"
raxml_job.dependencies.add(bionj_job)
raxml_job.model = m
raxml_job.jobcat = "raxml"
self.jobs.append(raxml_job)
def finish(self):
lks = []
if self.lk_mode == "phyml":
for job in self.jobs:
if job.jobcat != "bionj": continue
phyml_job = job
tree_file = pjoin(phyml_job.jobdir,
self.alg_phylip_file+"_phyml_tree.txt")
stats_file = pjoin(phyml_job.jobdir,
self.alg_phylip_file+"_phyml_stats.txt")
tree = PhyloTree(tree_file)
m = re.search('Log-likelihood:\s+(-?\d+\.\d+)',
open(stats_file).read())
lk = float(m.groups()[0])
tree.add_feature("lk", lk)
tree.add_feature("model", phyml_job.args["--model"])
lks.append([float(tree.lk), tree.model, tree])
elif self.lk_mode == "raxml":
for job in self.jobs:
if job.jobcat != "raxml": continue
raxml_job = job
lk = open(pjoin(raxml_job.jobdir, "RAxML_log.%s"
%raxml_job.args["-n"])).readline().split()[1]
tree = PhyloTree(raxml_job.args["-t"])
tree.add_feature("lk", lk)
tree.add_feature("model", raxml_job.model)
lks.append([float(tree.lk), tree.model, tree])
# sort lks in ASC order
lks.sort()
# choose the model with higher likelihood, the lastone in the list
best_model = lks[-1][1]
best_tree = lks[-1][2]
log.log(22, "%s model selected from the following lk values:\n%s" %(best_model, '\n'.join(map(str, lks))))
ModelTesterTask.store_data(self, best_model, lks)
|
