Coverage for PanACoTA/tree_module/fasttree_func.py: 100%

1#!/usr/bin/env python3 

2# coding: utf-8 

3 

4# ############################################################################### 

5# This file is part of PanACOTA. # 

6# # 

7# Authors: Amandine Perrin # 

8# Copyright © 2018-2020 Institut Pasteur (Paris). # 

9# See the COPYRIGHT file for details. # 

10# # 

11# PanACOTA is a software providing tools for large scale bacterial comparative # 

12# genomics. From a set of complete and/or draft genomes, you can: # 

13# - Do a quality control of your strains, to eliminate poor quality # 

14# genomes, which would not give any information for the comparative study # 

15# - Uniformly annotate all genomes # 

16# - Do a Pan-genome # 

17# - Do a Core or Persistent genome # 

18# - Align all Core/Persistent families # 

19# - Infer a phylogenetic tree from the Core/Persistent families # 

20# # 

21# PanACOTA is free software: you can redistribute it and/or modify it under the # 

22# terms of the Affero GNU General Public License as published by the Free # 

23# Software Foundation, either version 3 of the License, or (at your option) # 

24# any later version. # 

25# # 

26# PanACOTA is distributed in the hope that it will be useful, but WITHOUT ANY # 

27# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS # 

28# FOR A PARTICULAR PURPOSE. See the Affero GNU General Public License # 

29# for more details. # 

30# # 

31# You should have received a copy of the Affero GNU General Public License # 

32# along with PanACOTA (COPYING file). # 

33# If not, see <https://www.gnu.org/licenses/>. # 

34# ############################################################################### 

35 

36""" 

37Function to infer a phylogenetic tree from a persistent genome, using FastTree 

38 

39@author gem 

40June 2017 

41""" 

42 

43import os 

44import logging 

45 

46from PanACoTA import utils 

47 

48logger = logging.getLogger("tree.fasttree") 

49 

50def run_tree(alignfile, boot, outdir, quiet, threads, **kwargs): 

51 """ 

52 Run FastTree for the given alignment file and options 

53 

54 Parameters 

55 ---------- 

56 alignfile: str 

57 path to file containing all persistent families aligned, and grouped by genome 

58 boot: int or None 

59 number of bootstraps to calculate, None if no bootstrap asked 

60 outdir: str or None 

61 Path to the tree file that must be created 

62 quiet: bool 

63 True if nothing must be printed to stderr/stdout, False otherwise 

64 threads: int 

65 Maximum number of threads to use 

66 model: str 

67 DNA substitution model chosen by user 

68 kwargs: Object 

69 Used to be compatible with the 'run_tree' function of other softs like fastME and 

70 quicktree, which require more arguments 

71 """ 

72 model = kwargs["model"] 

73 define_nb_threads(threads) 

74 run_fasttree(alignfile, boot, outdir, model, quiet) 

75 

76 

77def define_nb_threads(threads): 

78 """ 

79 With FastTree, number of threads to use must be defined before running the 

80 script, by changing an environment variable. 

81 

82 Parameters 

83 ---------- 

84 threads: int 

85 Maximal number of threads to use 

86 """ 

87 os.environ["OMP_NUM_THREADS"] = str(threads) 

88 

89 

90def run_fasttree(alignfile, boot, outdir, model, quiet): 

91 """ 

92 Run FastTree on given alignment 

93 

94 Parameters 

95 ---------- 

96 alignfile: str 

97 Path to file containing all families aligned, grouped by genome 

98 boot: int or None 

99 Number of bootstraps to calculate (None if no bootstrap asked) 

100 treefile: str or None 

101 Path to the tree file that must be created 

102 model: str 

103 DNA substitution model 

104 quiet: bool 

105 True if nothing must be printed to stderr/stdout, False otherwise 

106 """ 

107 logger.info("Running FasttreeMP...") 

108 if not boot: 

109 bootinfo = "-nosupport" 

110 else: 

111 bootinfo = "-boot {}".format(boot) 

112 align_name = os.path.basename(alignfile) 

113 logfile = os.path.join(outdir, align_name + ".fasttree.log") 

114 treefile = os.path.join(outdir, align_name + ".fasttree_tree.nwk") 

115 cmd = f"FastTreeMP -nt {model} -noml -nocat {bootinfo} -log {logfile} {alignfile}" 

116 logger.details("Fasttree command: " + cmd) 

117 if quiet: 

118 fnull = open(os.devnull, 'w') 

119 else: 

120 fnull = None 

121 stdout = open(treefile, "w") 

122 error = ("Problem while running Fasttree. See log file ({}) for " 

123 "more information.").format(logfile) 

124 utils.run_cmd(cmd, error, stdout=stdout, eof=True, logger=logger, stderr=fnull)