|
64
|
1 #!/usr/bin/env python
|
|
|
2 import argparse
|
|
|
3 import os
|
|
|
4 import shutil
|
|
|
5 import subprocess
|
|
|
6 import sys
|
|
|
7 import tempfile
|
|
|
8
|
|
|
9 BUFF_SIZE = 1048576
|
|
|
10 OUTPUT_DIR = 'phylogenomicsAnalysis_dir'
|
|
|
11
|
|
|
12 parser = argparse.ArgumentParser()
|
|
|
13
|
|
77
|
14 parser.add_argument('--alignments_method', dest='alignments_method', default=None, help='Multiple sequence alignments method')
|
|
|
15 parser.add_argument('--bootstrap_replicates', dest='bootstrap_replicates', type=int, default=None, help='Number of replicates for rapid bootstrap analysis')
|
|
|
16 parser.add_argument('--codon_alignments', dest='codon_alignments', default=None, help="Flag for constructing orthogroup multiple codon alignments")
|
|
|
17 parser.add_argument('--config_dir', dest='config_dir', help='Directory containing default configuration files')
|
|
|
18 parser.add_argument('--gap_trimming', dest='gap_trimming', default=None, type=float, help='Remove sites in alignments with gaps of')
|
|
|
19 parser.add_argument('--max_orthogroup_size', dest='max_orthogroup_size', type=int, default=None, help='Maximum number of sequences in orthogroup alignments')
|
|
64
|
20 parser.add_argument('--method', dest='method', help='Protein clustering method')
|
|
77
|
21 parser.add_argument('--min_orthogroup_size', dest='min_orthogroup_size', type=int, default=None, help='Minimum number of sequences in orthogroup alignments')
|
|
64
|
22 parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of threads to use for execution')
|
|
77
|
23 parser.add_argument('--output_aln', dest='output_aln', default=None, help='Output for orthogroups alignments')
|
|
|
24 parser.add_argument('--output_aln_dir', dest='output_aln_dir', default=None, help='output_aln.files_path')
|
|
|
25 parser.add_argument('--orthogroup_faa', dest='orthogroup_faa', help="Input dataset files_path")
|
|
64
|
26 parser.add_argument('--orthogroup_fna', dest='orthogroup_fna', default=None, help="Flag for coding sequences associated with orthogroups")
|
|
|
27 parser.add_argument('--output_ptortho', dest='output_ptortho', default=None, help='Output for orthogroups')
|
|
|
28 parser.add_argument('--output_ptorthocs', dest='output_ptorthocs', default=None, help='Output for orthogroups with corresponding coding sequences')
|
|
|
29 parser.add_argument('--output_ptorthocs_dir', dest='output_ptorthocs_dir', default=None, help='output_ptorthocs.files_path')
|
|
77
|
30 parser.add_argument('--output_ptortho_dir', dest='output_ptortho_dir', default=None, help='output_ptortho.files_path')
|
|
64
|
31 parser.add_argument('--output_tree', dest='output_tree', default=None, help='Output for phylogenetic trees')
|
|
|
32 parser.add_argument('--output_tree_dir', dest='output_tree_dir', default=None, help='output_tree.files_path')
|
|
77
|
33 parser.add_argument('--pasta_iter_limit', dest='pasta_iter_limit', type=int, default=None, help='"Maximum number of iteration that the PASTA algorithm will execute')
|
|
|
34 parser.add_argument('--pasta_script_path', dest='pasta_script_path', default=None, help='Path to script for executing pasta')
|
|
|
35 parser.add_argument('--remove_sequences', dest='remove_sequences', default=None, type=float, help='Remove sequences with gaps of')
|
|
|
36 parser.add_argument('--rooting_order', dest='rooting_order', default=None, help='Rooting order configuration for rooting trees')
|
|
|
37 parser.add_argument('--scaffold', dest='scaffold', default='mode', help='Orthogroups or gene families proteins scaffold')
|
|
|
38 parser.add_argument('--sequence_type', dest='sequence_type', default=None, help="Sequence type used in the phylogenetic inference")
|
|
|
39 parser.add_argument('--tree_inference', dest='tree_inference', default=None, help='Phylogenetic trees inference method')
|
|
|
40 parser.add_argument('--trim_type', dest='trim_type', default=None, help='Process used for gap trimming')
|
|
64
|
41
|
|
|
42 args = parser.parse_args()
|
|
|
43
|
|
|
44
|
|
|
45 def get_stderr_exception(tmp_err, tmp_stderr, tmp_out, tmp_stdout, include_stdout=False):
|
|
|
46 tmp_stderr.close()
|
|
|
47 # Get stderr, allowing for case where it's very large.
|
|
|
48 tmp_stderr = open(tmp_err, 'rb')
|
|
|
49 stderr_str = ''
|
|
|
50 buffsize = BUFF_SIZE
|
|
|
51 try:
|
|
|
52 while True:
|
|
|
53 stderr_str += tmp_stderr.read(buffsize)
|
|
|
54 if not stderr_str or len(stderr_str) % buffsize != 0:
|
|
|
55 break
|
|
|
56 except OverflowError:
|
|
|
57 pass
|
|
|
58 tmp_stderr.close()
|
|
|
59 if include_stdout:
|
|
|
60 tmp_stdout = open(tmp_out, 'rb')
|
|
|
61 stdout_str = ''
|
|
|
62 buffsize = BUFF_SIZE
|
|
|
63 try:
|
|
|
64 while True:
|
|
|
65 stdout_str += tmp_stdout.read(buffsize)
|
|
|
66 if not stdout_str or len(stdout_str) % buffsize != 0:
|
|
|
67 break
|
|
|
68 except OverflowError:
|
|
|
69 pass
|
|
|
70 tmp_stdout.close()
|
|
|
71 if include_stdout:
|
|
|
72 return 'STDOUT\n%s\n\nSTDERR\n%s\n' % (stdout_str, stderr_str)
|
|
|
73 return stderr_str
|
|
|
74
|
|
|
75
|
|
|
76 def move_directory_files(source_dir, destination_dir):
|
|
|
77 source_directory = os.path.abspath(source_dir)
|
|
|
78 destination_directory = os.path.abspath(destination_dir)
|
|
|
79 if not os.path.isdir(destination_directory):
|
|
|
80 os.makedirs(destination_directory)
|
|
|
81 for dir_entry in os.listdir(source_directory):
|
|
|
82 source_entry = os.path.join(source_directory, dir_entry)
|
|
|
83 shutil.move(source_entry, destination_directory)
|
|
|
84
|
|
|
85
|
|
|
86 def stop_err(msg):
|
|
|
87 sys.stderr.write(msg)
|
|
|
88 sys.exit(1)
|
|
|
89
|
|
|
90
|
|
|
91 def write_html_output(output, title, dir):
|
|
|
92 with open(output, 'w') as fh:
|
|
|
93 fh.write('<html><head><h3>%s</h3></head>\n' % title)
|
|
|
94 fh.write('<body><p/><table cellpadding="2">\n')
|
|
|
95 fh.write('<tr><th>Size</th><th>Name</th></tr>\n')
|
|
|
96 for index, fname in enumerate(sorted(os.listdir(dir))):
|
|
|
97 if index % 2 == 0:
|
|
|
98 bgcolor = '#D8D8D8'
|
|
|
99 else:
|
|
|
100 bgcolor = '#FFFFFF'
|
|
|
101 try:
|
|
|
102 size = str(os.path.getsize(os.path.join(dir, fname)))
|
|
|
103 except:
|
|
|
104 size = 'unknown'
|
|
|
105 link = '<a href="%s" type="text/plain">%s</a>\n' % (fname, fname)
|
|
|
106 fh.write('<tr bgcolor="%s"><td>%s</td><td>%s</td></tr>\n' % (bgcolor, size, link))
|
|
|
107 fh.write('</table></body></html>\n')
|
|
|
108
|
|
|
109
|
|
|
110 # Define command response buffers.
|
|
|
111 tmp_out = tempfile.NamedTemporaryFile().name
|
|
|
112 tmp_stdout = open(tmp_out, 'wb')
|
|
|
113 tmp_err = tempfile.NamedTemporaryFile().name
|
|
|
114 tmp_stderr = open(tmp_err, 'wb')
|
|
|
115 # Build the command line.
|
|
|
116 cmd = 'PhylogenomicsAnalysis'
|
|
|
117 cmd += ' --orthogroup_faa %s' % args.orthogroup_faa
|
|
|
118 cmd += ' --scaffold %s' % args.scaffold
|
|
|
119 cmd += ' --method %s' % args.method
|
|
|
120 cmd += ' --config_dir %s' % args.config_dir
|
|
|
121 cmd += ' --num_threads %d' % args.num_threads
|
|
|
122
|
|
77
|
123 if args.codon_alignments is not None:
|
|
|
124 cmd += ' --codon_alignments'
|
|
64
|
125 if args.orthogroup_fna is not None:
|
|
|
126 cmd += ' --orthogroup_fna'
|
|
|
127 if args.sequence_type is not None:
|
|
|
128 cmd += ' --sequence_type %s' % args.sequence_type
|
|
|
129 if args.alignments_method is not None:
|
|
|
130 if args.alignments_method == 'create_alignments':
|
|
|
131 cmd += ' --create_alignments'
|
|
|
132 elif args.alignments_method == 'add_alignments':
|
|
|
133 cmd += ' --add_alignments'
|
|
|
134 elif args.alignments_method == 'pasta_alignments':
|
|
|
135 cmd += ' --pasta_alignments'
|
|
|
136 cmd += ' --pasta_script_path %s' % args.pasta_script_path
|
|
|
137 cmd += ' --pasta_iter_limit %d' % args.pasta_iter_limit
|
|
|
138 if args.tree_inference is not None:
|
|
|
139 cmd += ' --tree_inference %s' % args.tree_inference
|
|
|
140 if args.tree_inference == 'raxml':
|
|
|
141 if args.rooting_order is not None:
|
|
|
142 cmd += ' --rooting_order %s' % args.rooting_order
|
|
|
143 cmd += ' --bootstrap_replicates %d' % args.bootstrap_replicates
|
|
|
144 if args.max_orthogroup_size is not None:
|
|
|
145 cmd += ' --max_orthogroup_size %d' % args.max_orthogroup_size
|
|
|
146 if args.min_orthogroup_size is not None:
|
|
|
147 cmd += ' --min_orthogroup_size %d' % args.min_orthogroup_size
|
|
|
148 if args.remove_sequences is not None:
|
|
|
149 cmd += ' --remove_sequences %4f' % args.remove_sequences
|
|
|
150 if args.trim_type is not None:
|
|
|
151 if args.trim_type == 'automated_trimming':
|
|
|
152 cmd += ' --automated_trimming'
|
|
|
153 else:
|
|
|
154 cmd += ' --gap_trimming %4f' % args.gap_trimming
|
|
|
155 # Run the command.
|
|
|
156 proc = subprocess.Popen(args=cmd, stderr=tmp_stderr, stdout=tmp_stdout, shell=True)
|
|
|
157 rc = proc.wait()
|
|
|
158 # Handle execution errors.
|
|
|
159 if rc != 0:
|
|
|
160 error_message = get_stderr_exception(tmp_err, tmp_stderr, tmp_out, tmp_stdout)
|
|
|
161 stop_err( error_message )
|
|
|
162 # Handle phylogenies for orthogroups outputs.
|
|
|
163 if args.orthogroup_fna is not None:
|
|
|
164 out_file = args.output_ptorthocs
|
|
|
165 orthogroups_dest_dir = args.output_ptorthocs_dir
|
|
|
166 title = 'Phylogenies files for orthogroups and corresponding coding sequences'
|
|
|
167 else:
|
|
|
168 out_file = args.output_ptortho
|
|
|
169 orthogroups_dest_dir = args.output_ptortho_dir
|
|
|
170 title = 'Phylogenies files for orthogroups'
|
|
|
171 orthogroups_src_dir = os.path.join(OUTPUT_DIR, 'orthogroups_fasta')
|
|
|
172 move_directory_files(orthogroups_src_dir, orthogroups_dest_dir)
|
|
|
173 write_html_output(out_file, title, orthogroups_dest_dir)
|
|
|
174 # Handle multiple sequences alignments for orthogroups outputs.
|
|
|
175 if args.output_aln is not None:
|
|
|
176 alignments_src_dir = os.path.join(OUTPUT_DIR, 'orthogroups_aln')
|
|
|
177 alignments_dest_dir = args.output_aln_dir
|
|
|
178 title = 'Multiple sequence alignments files for orthogroups'
|
|
|
179 move_directory_files(alignments_src_dir, alignments_dest_dir)
|
|
|
180 write_html_output(args.output_aln, title, alignments_dest_dir)
|
|
|
181 # Handle phylogenies for orthogroups outputs.
|
|
|
182 if args.output_tree is not None:
|
|
|
183 trees_src_dir = os.path.join(OUTPUT_DIR, 'orthogroups_tree')
|
|
|
184 trees_dest_dir = args.output_tree_dir
|
|
|
185 title = 'Phylogenetic tree files for orthogroups'
|
|
|
186 move_directory_files(trees_src_dir, trees_dest_dir)
|
|
|
187 write_html_output(args.output_tree, title, trees_dest_dir)
|
