Coverage for biobb_flexserv / pcasuite / pcz_lindemann.py: 94%

1#!/usr/bin/env python3 

2 

3"""Module containing the PCZlindemann class and the command line interface.""" 

4from typing import Optional 

5import shutil 

6import json 

7from pathlib import PurePath 

8from biobb_common.tools import file_utils as fu 

9from biobb_common.generic.biobb_object import BiobbObject 

10from biobb_common.tools.file_utils import launchlogger 

11 

12 

13class PCZlindemann(BiobbObject): 

14 """ 

15 | biobb_flexserv PCZlindemann 

16 | Extract Lindemann coefficient (an estimate of the solid-liquid behaviour of a protein) from a compressed PCZ file. 

17 | Wrapper of the pczdump tool from the PCAsuite FlexServ module. 

18 

19 Args: 

20 input_pcz_path (str): Input compressed trajectory file. File type: input. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/data/pcasuite/pcazip.pcz>`_. Accepted formats: pcz (edam:format_3874). 

21 output_json_path (str): Output json file with PCA Eigen Vectors. File type: output. `Sample file <https://github.com/bioexcel/biobb_flexserv/raw/master/biobb_flexserv/test/reference/pcasuite/pcz_lindemann.json>`_. Accepted formats: json (edam:format_3464). 

22 properties (dict - Python dictionary object containing the tool parameters, not input/output files): 

23 * **binary_path** (*str*) - ("pczdump") pczdump binary path to be used. 

24 * **mask** (*str*) - ("all atoms") Residue mask, in the format ":resnum1, resnum2, resnum3" (e.g. ":10,21,33"). See https://mmb.irbbarcelona.org/software/pcasuite/ for the complete format specification. 

25 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files. 

26 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist. 

27 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory. 

28 

29 Examples: 

30 This is a use example of how to use the building block from Python:: 

31 

32 from biobb_flexserv.pcasuite.pcz_lindemann import pcz_lindemann 

33 prop = { 

34 'mask': ':10,12,15' 

35 } 

36 pcz_lindemann( input_pcz_path='/path/to/pcazip_input.pcz', 

37 output_json_path='/path/to/lindemann_report.json', 

38 properties=prop) 

39 

40 Info: 

41 * wrapped_software: 

42 * name: FlexServ PCAsuite 

43 * version: >=1.0 

44 * license: Apache-2.0 

45 * ontology: 

46 * name: EDAM 

47 * schema: http://edamontology.org/EDAM.owl 

48 

49 """ 

50 

51 def __init__(self, input_pcz_path: str, 

52 output_json_path: str, properties: Optional[dict] = None, **kwargs) -> None: 

53 

54 properties = properties or {} 

55 

56 # Call parent class constructor 

57 super().__init__(properties) 

58 self.locals_var_dict = locals().copy() 

59 

60 # Input/Output files 

61 self.io_dict = { 

62 'in': {'input_pcz_path': input_pcz_path}, 

63 'out': {'output_json_path': output_json_path} 

64 } 

65 

66 # Properties specific for BB 

67 self.properties = properties 

68 self.binary_path = properties.get('binary_path', 'pczdump') 

69 self.mask = properties.get('mask', '') 

70 

71 # Check the properties 

72 self.check_properties(properties) 

73 self.check_arguments() 

74 

75 @launchlogger 

76 def launch(self): 

77 """Launches the execution of the FlexServ pcz_lindemann module.""" 

78 

79 # Setup Biobb 

80 if self.check_restart(): 

81 return 0 

82 # self.stage_files() 

83 

84 # Internal file paths 

85 # try: 

86 # # Using rel paths to shorten the amount of characters due to fortran path length limitations 

87 # input_pcz = str(Path(self.stage_io_dict["in"]["input_pcz_path"]).relative_to(Path.cwd())) 

88 # output_json = str(Path(self.stage_io_dict["out"]["output_json_path"]).relative_to(Path.cwd())) 

89 # except ValueError: 

90 # # Container or remote case 

91 # input_pcz = self.stage_io_dict["in"]["input_pcz_path"] 

92 # output_json = self.stage_io_dict["out"]["output_json_path"] 

93 

94 # Manually creating a Sandbox to avoid issues with input parameters buffer overflow: 

95 # Long strings defining a file path makes Fortran or C compiled programs crash if the string 

96 # declared is shorter than the input parameter path (string) length. 

97 # Generating a temporary folder and working inside this folder (sandbox) fixes this problem. 

98 # The problem was found in Galaxy executions, launching Singularity containers (May 2023). 

99 

100 # Creating temporary folder 

101 tmp_folder = fu.create_unique_dir() 

102 fu.log('Creating %s temporary folder' % tmp_folder, self.out_log) 

103 

104 shutil.copy2(self.io_dict["in"]["input_pcz_path"], tmp_folder) 

105 

106 # Temporary output 

107 # temp_out = str(Path(self.stage_io_dict.get("unique_dir", "")).joinpath("output.dat")) 

108 temp_out = "output.dat" 

109 temp_json = "output.json" 

110 

111 # Command line 

112 # pczdump -i structure.ca.std.pcz --lindemann -M ":2-86" -o lindemann_report.txt 

113 # self.cmd = [self.binary_path, 

114 # "-i", input_pcz, 

115 # "-o", temp_out, 

116 # "--lindemann" 

117 # ] 

118 

119 self.cmd = ['cd', tmp_folder, ';', 

120 self.binary_path, 

121 "-i", PurePath(self.io_dict["in"]["input_pcz_path"]).name, 

122 "-o", temp_out, 

123 "--lindemann" 

124 ] 

125 

126 if self.mask: 

127 self.cmd.append("-M {}".format(self.mask)) 

128 

129 # Run Biobb block 

130 self.run_biobb() 

131 

132 # Parse output Lindemann 

133 # 0.132891 

134 info_dict = {} 

135 with open(PurePath(tmp_folder).joinpath(temp_out), 'r') as file: 

136 for line in file: 

137 info = float(line.strip()) 

138 info_dict['lindemann'] = info 

139 

140 with open(PurePath(tmp_folder).joinpath(temp_json), 'w') as out_file: 

141 out_file.write(json.dumps(info_dict, indent=4)) 

142 

143 # Copy outputs from temporary folder to output path 

144 shutil.copy2(PurePath(tmp_folder).joinpath(temp_json), PurePath(self.io_dict["out"]["output_json_path"])) 

145 

146 # Copy files to host 

147 # self.copy_to_host() 

148 

149 # Remove temporary folder(s) 

150 self.tmp_files.append(tmp_folder) 

151 self.remove_tmp_files() 

152 

153 self.check_arguments(output_files_created=True, raise_exception=False) 

154 

155 return self.return_code 

156 

157 

158def pcz_lindemann(input_pcz_path: str, output_json_path: str, 

159 properties: Optional[dict] = None, **kwargs) -> int: 

160 """Create :class:`PCZlindemann <flexserv.pcasuite.pcz_lindemann>`flexserv.pcasuite.PCZlindemann class and 

161 execute :meth:`launch() <flexserv.pcasuite.pcz_lindemann.launch>` method""" 

162 return PCZlindemann(**dict(locals())).launch() 

163 

164 

165pcz_lindemann.__doc__ = PCZlindemann.__doc__ 

166main = PCZlindemann.get_main(pcz_lindemann, "Extract Lindemann coefficients from a compressed PCZ file.") 

167 

168if __name__ == '__main__': 

169 main()