Coverage for biobb_analysis/gromacs/gmx_trjconv_trj.py: 72%

1#!/usr/bin/env python3 

2 

3"""Module containing the GMX TrjConvStr class and the command line interface.""" 

4import argparse 

5from biobb_common.generic.biobb_object import BiobbObject 

6from biobb_common.configuration import settings 

7from biobb_common.tools.file_utils import launchlogger 

8import biobb_common.tools.file_utils as fu 

9import biobb_analysis.gromacs.common as gro_common 

10 

11 

12class GMXTrjConvTrj(BiobbObject): 

13 """ 

14 | biobb_analysis GMXTrjConvTrj 

15 | Wrapper of the GROMACS trjconv module for converting between GROMACS compatible trajectory file formats and/or extracts a selection of atoms. 

16 | GROMACS trjconv module can convert trajectory files in many ways. See the `GROMACS trjconv <http://manual.gromacs.org/documentation/2018/onlinehelp/gmx-trjconv.html>`_ official documentation for further information. 

17 

18 Args: 

19 input_traj_path (str): Path to the GROMACS trajectory file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/trajectory.trr>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876). 

20 input_top_path (str) (Optional): Path to the GROMACS input topology file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/topology.tpr>`_. Accepted formats: tpr (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), brk (edam:format_2033), ent (edam:format_1476). 

21 input_index_path (str) (Optional): Path to the GROMACS index file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/index.ndx>`_. Accepted formats: ndx (edam:format_2033). 

22 output_traj_path (str): Path to the output file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gromacs/ref_trjconv.trj.xtc>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876). 

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

24 * **selection** (*str*) - ("System") Group where the trjconv will be performed. If **input_index_path** provided, check the file for the accepted values. Values: System (all atoms in the system), Protein (all protein atoms), Protein-H (protein atoms excluding hydrogens), C-alpha (C-alpha atoms), Backbone (protein backbone atoms: N; C-alpha and C), MainChain (protein main chain atoms: N; C-alpha; C and O; including oxygens in C-terminus), MainChain+Cb (protein main chain atoms including C-beta), MainChain+H (protein main chain atoms including backbone amide hydrogens and hydrogens on the N-terminus), SideChain (protein side chain atoms: that is all atoms except N; C-alpha; C; O; backbone amide hydrogens and oxygens in C-terminus and hydrogens on the N-terminus), SideChain-H (protein side chain atoms excluding all hydrogens), Prot-Masses (protein atoms excluding dummy masses), non-Protein (all non-protein atoms), Water (water molecules), SOL (water molecules), non-Water (anything not covered by the Water group), Ion (any name matching an Ion entry in residuetypes.dat), NA (all NA atoms), CL (all CL atoms), Water_and_ions (combination of the Water and Ions groups), DNA (all DNA atoms), RNA (all RNA atoms), Protein_DNA (all Protein-DNA complex atoms), Protein_RNA (all Protein-RNA complex atoms), Protein_DNA_RNA (all Protein-DNA-RNA complex atoms), DNA_RNA (all DNA-RNA complex atoms). 

25 * **start** (*int*) - (0) [0~10000|1] Time of first frame to read from trajectory (default unit ps). 

26 * **end** (*int*) - (0) [0~10000|1] Time of last frame to read from trajectory (default unit ps). 

27 * **dt** (*int*) - (0) [0~10000|1] Only write frame when t MOD dt = first time (ps). 

28 * **binary_path** (*str*) - ("gmx") Path to the GROMACS executable binary. 

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

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

31 * **container_path** (*str*) - (None) Container path definition. 

32 * **container_image** (*str*) - ('gromacs/gromacs:2022.2') Container image definition. 

33 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition. 

34 * **container_working_dir** (*str*) - (None) Container working directory definition. 

35 * **container_user_id** (*str*) - (None) Container user_id definition. 

36 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container. 

37 

38 Examples: 

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

40 

41 from biobb_analysis.gromacs.gmx_trjconv_trj import gmx_trjconv_trj 

42 prop = { 

43 'selection': 'System', 

44 'start': 0, 

45 'end': 0 

46 } 

47 gmx_trjconv_trj(input_traj_path='/path/to/myStructure.trr', 

48 output_traj_path='/path/to/newTrajectory.xtc', 

49 input_index_path='/path/to/myIndex.ndx', 

50 properties=prop) 

51 

52 Info: 

53 * wrapped_software: 

54 * name: GROMACS trjconv 

55 * version: >=2019.1 

56 * license: LGPL 2.1 

57 * ontology: 

58 * name: EDAM 

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

60 

61 """ 

62 

63 def __init__(self, input_traj_path, 

64 output_traj_path, input_index_path=None, input_top_path=None, properties=None, **kwargs) -> None: 

65 properties = properties or {} 

66 

67 # Call parent class constructor 

68 super().__init__(properties) 

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

70 

71 # Input/Output files 

72 self.io_dict = { 

73 "in": {"input_traj_path": input_traj_path, "input_index_path": input_index_path, "input_top_path": input_top_path}, 

74 "out": {"output_traj_path": output_traj_path} 

75 } 

76 

77 # Properties specific for BB 

78 if not self.io_dict["in"]["input_index_path"] and not self.io_dict["in"]["input_top_path"]: 

79 self.selection = properties.get('selection', "") 

80 else: 

81 self.selection = properties.get('selection', "System") 

82 self.start = properties.get('start', 0) 

83 self.end = properties.get('end', 0) 

84 self.dt = properties.get('dt', 0) 

85 self.properties = properties 

86 

87 # Properties common in all GROMACS BB 

88 self.binary_path = gro_common.get_binary_path(properties, 'binary_path') 

89 

90 # Check the properties 

91 self.check_properties(properties) 

92 self.check_arguments() 

93 

94 def check_data_params(self, out_log, err_log): 

95 """ Checks all the input/output paths and parameters """ 

96 self.io_dict["in"]["input_traj_path"] = gro_common.check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__) 

97 self.io_dict["in"]["input_index_path"] = gro_common.check_index_path(self.io_dict["in"]["input_index_path"], out_log, self.__class__.__name__) 

98 if self.io_dict["in"]["input_top_path"]: 

99 self.io_dict["in"]["input_top_path"] = gro_common.check_input_path(self.io_dict["in"]["input_top_path"], out_log, self.__class__.__name__) 

100 self.io_dict["out"]["output_traj_path"] = gro_common.check_out_traj_path(self.io_dict["out"]["output_traj_path"], out_log, self.__class__.__name__) 

101 '''if not self.io_dict["in"]["input_index_path"]: 

102 self.selection = get_selection(self.properties, out_log, self.__class__.__name__) 

103 else: 

104 self.selection = get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'selection', out_log, self.__class__.__name__)''' 

105 if self.io_dict["in"]["input_top_path"] and not self.io_dict["in"]["input_index_path"]: 

106 self.selection = gro_common.get_selection(self.properties, out_log, self.__class__.__name__) 

107 elif self.io_dict["in"]["input_index_path"]: 

108 self.selection = gro_common.get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'selection', out_log, self.__class__.__name__) 

109 elif not self.io_dict["in"]["input_top_path"] and not self.io_dict["in"]["input_index_path"]: 

110 self.selection = "" 

111 else: 

112 return True 

113 self.start = gro_common.get_start(self.properties, out_log, self.__class__.__name__) 

114 self.end = gro_common.get_end(self.properties, out_log, self.__class__.__name__) 

115 self.dt = gro_common.get_dt(self.properties, out_log, self.__class__.__name__) 

116 

117 @launchlogger 

118 def launch(self) -> int: 

119 """Execute the :class:`GMXTrjConvTrj <gromacs.gmx_trjconv_trj.GMXTrjConvTrj>` gromacs.gmx_trjconv_trj.GMXTrjConvTrj object.""" 

120 

121 # check input/output paths and parameters 

122 self.check_data_params(self.out_log, self.err_log) 

123 

124 # if not input_index_path and not input_top_path provided, selection must be empty, otherwise exit 

125 if not self.io_dict["in"]["input_index_path"] and not self.io_dict["in"]["input_top_path"] and self.selection != '': 

126 fu.log(self.__class__.__name__ + ': If not input_index_path and not input_top_path provided, selection must be empty', self.out_log) 

127 raise SystemExit(self.__class__.__name__ + ': If not input_index_path and not input_top_path provided, selection must be empty') 

128 

129 # Setup Biobb 

130 if self.check_restart(): 

131 return 0 

132 

133 # standard input 

134 self.io_dict['in']['stdin_file_path'] = fu.create_stdin_file(f'{self.selection}') 

135 self.stage_files() 

136 

137 self.cmd = [self.binary_path, 'trjconv', 

138 '-f', self.stage_io_dict["in"]["input_traj_path"], 

139 '-b', self.start, 

140 '-e', self.end, 

141 '-dt', self.dt, 

142 '-o', self.stage_io_dict["out"]["output_traj_path"]] 

143 

144 if "input_index_path" in self.stage_io_dict["in"]: 

145 self.cmd.extend(['-n', self.stage_io_dict["in"]["input_index_path"]]) 

146 

147 if "input_top_path" in self.stage_io_dict["in"]: 

148 self.cmd.extend(['-s', self.stage_io_dict["in"]["input_top_path"]]) 

149 

150 # Add stdin input file 

151 self.cmd.append('<') 

152 self.cmd.append(self.stage_io_dict["in"]["stdin_file_path"]) 

153 

154 # Run Biobb block 

155 self.run_biobb() 

156 

157 # Copy files to host 

158 self.copy_to_host() 

159 

160 self.tmp_files.extend([ 

161 self.stage_io_dict.get("unique_dir"), 

162 self.io_dict['in'].get("stdin_file_path") 

163 ]) 

164 self.remove_tmp_files() 

165 

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

167 

168 return self.return_code 

169 

170 

171def gmx_trjconv_trj(input_traj_path: str, output_traj_path: str, input_index_path: str = None, input_top_path: str = None, properties: dict = None, **kwargs) -> int: 

172 """Execute the :class:`GMXTrjConvTrj <gromacs.gmx_trjconv_trj.GMXTrjConvTrj>` class and 

173 execute the :meth:`launch() <gromacs.gmx_trjconv_trj.GMXTrjConvTrj.launch>` method.""" 

174 

175 return GMXTrjConvTrj(input_traj_path=input_traj_path, 

176 output_traj_path=output_traj_path, 

177 input_index_path=input_index_path, 

178 input_top_path=input_top_path, 

179 properties=properties, **kwargs).launch() 

180 

181 

182def main(): 

183 """Command line execution of this building block. Please check the command line documentation.""" 

184 parser = argparse.ArgumentParser(description="Converts between GROMACS compatible trajectory file formats and/or extracts a selection of atoms.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999)) 

185 parser.add_argument('--config', required=False, help='Configuration file') 

186 

187 # Specific args of each building block 

188 required_args = parser.add_argument_group('required arguments') 

189 required_args.add_argument('--input_traj_path', required=True, help='Path to the GROMACS trajectory file. Accepted formats: xtc, trr, cpt, gro, g96, pdb, tng.') 

190 parser.add_argument('--input_index_path', required=False, help="Path to the GROMACS index file. Accepted formats: ndx.") 

191 parser.add_argument('--input_top_path', required=False, help='Path to the GROMACS input topology file. Accepted formats: tpr, gro, g96, pdb, brk, ent.') 

192 required_args.add_argument('--output_traj_path', required=True, help='Path to the output file. Accepted formats: xtc, trr, gro, g96, pdb, tng.') 

193 

194 args = parser.parse_args() 

195 args.config = args.config or "{}" 

196 properties = settings.ConfReader(config=args.config).get_prop_dic() 

197 

198 # Specific call of each building block 

199 gmx_trjconv_trj(input_traj_path=args.input_traj_path, 

200 output_traj_path=args.output_traj_path, 

201 input_index_path=args.input_index_path, 

202 input_top_path=args.input_top_path, 

203 properties=properties) 

204 

205 

206if __name__ == '__main__': 

207 main()