Coverage for biobb_analysis/ambertools/cpptraj_rms.py: 83%

1#!/usr/bin/env python3 

2 

3"""Module containing the Cpptraj Rms class and the command line interface.""" 

4import argparse 

5from pathlib import PurePath 

6from biobb_common.generic.biobb_object import BiobbObject 

7from biobb_common.configuration import settings 

8from biobb_common.tools import file_utils as fu 

9from biobb_common.tools.file_utils import launchlogger 

10from biobb_analysis.ambertools.common import get_default_value, check_top_path, check_traj_path, check_out_path, get_binary_path, get_in_parameters, get_negative_mask, copy_instructions_file_to_container, setup_structure, get_mask, get_reference_rms 

11 

12 

13class CpptrajRms(BiobbObject): 

14 """ 

15 | biobb_analysis CpptrajRms 

16 | Wrapper of the Ambertools Cpptraj module for calculating the Root Mean Square deviation (RMSd) of a given cpptraj compatible trajectory. 

17 | Cpptraj (the successor to ptraj) is the main program in Ambertools for processing coordinate trajectories and data files. The parameter names and defaults are the same as the ones in the official `Cpptraj manual <https://amber-md.github.io/cpptraj/CPPTRAJ.xhtml>`_. 

18 

19 Args: 

20 input_top_path (str): Path to the input structure or topology file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/ambertools/cpptraj.parm.top>`_. Accepted formats: top (edam:format_3881), pdb (edam:format_1476), prmtop (edam:format_3881), parmtop (edam:format_3881), zip (edam:format_3987). 

21 input_traj_path (str): Path to the input trajectory to be processed. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/ambertools/cpptraj.traj.dcd>`_. Accepted formats: mdcrd (edam:format_3878), crd (edam:format_3878), cdf (edam:format_3650), netcdf (edam:format_3650), nc (edam:format_3650), restart (edam:format_3886), ncrestart (edam:format_3886), restartnc (edam:format_3886), dcd (edam:format_3878), charmm (edam:format_3887), cor (edam:format_2033), pdb (edam:format_1476), mol2 (edam:format_3816), trr (edam:format_3910), gro (edam:format_2033), binpos (edam:format_3885), xtc (edam:format_3875), cif (edam:format_1477), arc (edam:format_2333), sqm (edam:format_2033), sdf (edam:format_3814), conflib (edam:format_2033). 

22 input_exp_path (str) (Optional): Path to the experimental reference file (required if reference = experimental). File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/ambertools/experimental.1e5t.pdb>`_. Accepted formats: pdb (edam:format_1476). 

23 output_cpptraj_path (str): Path to the output processed analysis. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/ambertools/ref_cpptraj.rms.first.dat>`_. Accepted formats: dat (edam:format_1637), agr (edam:format_2033), xmgr (edam:format_2033), gnu (edam:format_2033). 

24 output_traj_path (str) (Optional): Path to the output processed trajectory. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/ambertools/cpptraj.traj.dcd>`_. Accepted formats: mdcrd (edam:format_3878), crd (edam:format_3878), cdf (edam:format_3650), netcdf (edam:format_3650), nc (edam:format_3650), restart (edam:format_3886), ncrestart (edam:format_3886), restartnc (edam:format_3886), dcd (edam:format_3878), charmm (edam:format_3887), cor (edam:format_2033), pdb (edam:format_1476), mol2 (edam:format_3816), trr (edam:format_3910), gro (edam:format_2033), binpos (edam:format_3885), xtc (edam:format_3875), cif (edam:format_1477), arc (edam:format_2333), sqm (edam:format_2033), sdf (edam:format_3814), conflib (edam:format_2033). 

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

26 * **start** (*int*) - (1) [1~100000|1] Starting frame for slicing 

27 * **end** (*int*) - (-1) [-1~100000|1] Ending frame for slicing 

28 * **steps** (*int*) - (1) [1~100000|1] Step for slicing 

29 * **mask** (*str*) - ("all-atoms") Mask definition. Values: c-alpha (All c-alpha atoms; protein only), backbone (Backbone atoms), all-atoms (All system atoms), heavy-atoms (System heavy atoms; not hydrogen), side-chain (All not backbone atoms), solute (All system atoms except solvent atoms), ions (All ion molecules), solvent (All solvent atoms), AnyAmberFromatMask (Amber atom selection syntax like `@*`). 

30 * **reference** (*str*) - ("first") Reference definition. Values: first (Use the first trajectory frame as reference), average (Use the average of all trajectory frames as reference), experimental (Use the experimental structure as reference). 

31 * **nofit** (*bool*) - (False) Do not perform best-fit RMSD 

32 * **norotate** (*bool*) - (False) Translate but do not rotate coordinates 

33 * **nomod** (*bool*) - (False) Do not modify coordinates 

34 * **binary_path** (*str*) - ("cpptraj") Path to the cpptraj executable binary. 

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

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

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

38 * **container_image** (*str*) - ('afandiadib/ambertools:serial') Container image definition. 

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

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

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

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

43 

44 Examples: 

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

46 

47 from biobb_analysis.ambertools.cpptraj_rms import cpptraj_rms 

48 prop = { 

49 'start': 1, 

50 'end': -1, 

51 'steps': 1, 

52 'mask': 'c-alpha', 

53 'reference': 'first' 

54 } 

55 cpptraj_rms(input_top_path='/path/to/myTopology.top', 

56 input_traj_path='/path/to/myTrajectory.dcd', 

57 output_cpptraj_path='/path/to/newAnalysis.dat', 

58 input_exp_path= '/path/to/myExpStructure.pdb', 

59 output_traj_path='/path/to/newTrajectory.netcdf', 

60 properties=prop) 

61 

62 Info: 

63 * wrapped_software: 

64 * name: Ambertools Cpptraj 

65 * version: >=20.0 

66 * license: GNU 

67 * ontology: 

68 * name: EDAM 

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

70 

71 """ 

72 

73 def __init__(self, input_top_path, input_traj_path, output_cpptraj_path, 

74 input_exp_path=None, output_traj_path=None, properties=None, **kwargs) -> None: 

75 properties = properties or {} 

76 

77 # Call parent class constructor 

78 super().__init__(properties) 

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

80 

81 # Input/Output files 

82 self.io_dict = { 

83 "in": {"input_top_path": input_top_path, "input_traj_path": input_traj_path, "input_exp_path": input_exp_path}, 

84 "out": {"output_cpptraj_path": output_cpptraj_path, "output_traj_path": output_traj_path} 

85 } 

86 

87 # Properties specific for BB 

88 self.instructions_file = get_default_value('instructions_file') 

89 self.start = properties.get('start', 1) 

90 self.end = properties.get('end', -1) 

91 self.steps = properties.get('steps', 1) 

92 self.mask = properties.get('mask', 'all-atoms') 

93 self.reference = properties.get('reference', 'first') 

94 self.nofit = properties.get('nofit', False) 

95 self.norotate = properties.get('norotate', False) 

96 self.nomod = properties.get('nomod', False) 

97 self.properties = properties 

98 self.binary_path = get_binary_path(properties, 'binary_path') 

99 

100 # Check the properties 

101 self.check_properties(properties) 

102 self.check_arguments() 

103 

104 def check_data_params(self, out_log, err_log): 

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

106 self.io_dict["in"]["input_top_path"], self.input_top_path_orig = check_top_path(self.io_dict["in"]["input_top_path"], out_log, self.__class__.__name__) 

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

108 self.io_dict["out"]["output_cpptraj_path"] = check_out_path(self.io_dict["out"]["output_cpptraj_path"], out_log, self.__class__.__name__) 

109 if self.io_dict["out"]["output_traj_path"]: 

110 self.io_dict["out"]["output_traj_path"] = check_out_path(self.io_dict["out"]["output_traj_path"], out_log, self.__class__.__name__) 

111 self.in_parameters = {'start': self.start, 'end': self.end, 'step': self.steps, 'mask': self.mask, 'reference': self.reference} 

112 

113 def create_instructions_file(self, container_io_dict, out_log, err_log): 

114 """Creates an input file using the properties file settings""" 

115 instructions_list = [] 

116 # different path if container execution or not 

117 if self.container_path: 

118 self.instructions_file = str(PurePath(self.container_volume_path).joinpath(self.instructions_file)) 

119 else: 

120 self.instructions_file = str(PurePath(fu.create_unique_dir()).joinpath(self.instructions_file)) 

121 fu.create_name(prefix=self.prefix, step=self.step, name=self.instructions_file) 

122 

123 # parm 

124 instructions_list.append('parm ' + container_io_dict["in"]["input_top_path"]) 

125 

126 # trajin 

127 in_params = get_in_parameters(self.in_parameters, out_log) 

128 instructions_list.append('trajin ' + container_io_dict["in"]["input_traj_path"] + ' ' + in_params) 

129 

130 # Set up 

131 instructions_list += setup_structure(self) 

132 

133 # mask 

134 mask = self.in_parameters.get('mask', '') 

135 ref_mask = '' 

136 if mask: 

137 strip_mask = get_negative_mask(mask, out_log) 

138 ref_mask = get_mask(mask, out_log) 

139 instructions_list.append('strip ' + strip_mask) 

140 

141 # reference 

142 reference = self.in_parameters.get('reference', '') 

143 inp_exp_pth = None 

144 if "input_exp_path" in container_io_dict["in"]: 

145 inp_exp_pth = container_io_dict["in"]["input_exp_path"] 

146 instructions_list += get_reference_rms(reference, container_io_dict["out"]["output_cpptraj_path"], inp_exp_pth, ref_mask, True, 

147 self.__class__.__name__, out_log, self.nofit, self.norotate, self.nomod) 

148 

149 # trajout 

150 if ("output_traj_path" in container_io_dict["out"]): 

151 instructions_list.append('trajout ' + container_io_dict["out"]["output_traj_path"]) 

152 

153 # create .in file 

154 with open(self.instructions_file, 'w') as mdp: 

155 for line in instructions_list: 

156 mdp.write(line.strip() + '\n') 

157 

158 return self.instructions_file 

159 

160 @launchlogger 

161 def launch(self) -> int: 

162 """Execute the :class:`CpptrajRms <ambertools.cpptraj_rms.CpptrajRms>` ambertools.cpptraj_rms.CpptrajRms object.""" 

163 

164 # check input/output paths and parameters 

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

166 

167 # Setup Biobb 

168 if self.check_restart(): 

169 return 0 

170 self.stage_files() 

171 

172 # create instructions file 

173 self.create_instructions_file(self.stage_io_dict, self.out_log, self.err_log) 

174 

175 # if container execution, copy intructions file to container 

176 if self.container_path: 

177 copy_instructions_file_to_container(self.instructions_file, self.stage_io_dict['unique_dir']) 

178 

179 # create cmd and launch execution 

180 self.cmd = [self.binary_path, '-i', self.instructions_file] 

181 

182 # Run Biobb block 

183 self.run_biobb() 

184 

185 # Copy files to host 

186 self.copy_to_host() 

187 

188 # remove temporary folder(s) 

189 self.tmp_files.extend([ 

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

191 PurePath(self.instructions_file).parent 

192 ]) 

193 self.remove_tmp_files() 

194 

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

196 

197 return self.return_code 

198 

199 

200def cpptraj_rms(input_top_path: str, input_traj_path: str, output_cpptraj_path: str, input_exp_path: str = None, output_traj_path: str = None, properties: dict = None, **kwargs) -> int: 

201 """Execute the :class:`CpptrajRms <ambertools.cpptraj_rms.CpptrajRms>` class and 

202 execute the :meth:`launch() <ambertools.cpptraj_rms.CpptrajRms.launch>` method.""" 

203 

204 return CpptrajRms(input_top_path=input_top_path, 

205 input_traj_path=input_traj_path, 

206 output_cpptraj_path=output_cpptraj_path, 

207 input_exp_path=input_exp_path, 

208 output_traj_path=output_traj_path, 

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

210 

211 

212def main(): 

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

214 parser = argparse.ArgumentParser(description="Calculates the Root Mean Square deviation (RMSd) of a given cpptraj compatible trajectory.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999)) 

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

216 

217 # Specific args of each building block 

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

219 required_args.add_argument('--input_top_path', required=True, help='Path to the input structure or topology file. Accepted formats: top, pdb, prmtop, parmtop, zip.') 

220 required_args.add_argument('--input_traj_path', required=True, help='Path to the input trajectory to be processed. Accepted formats: crd, cdf, netcdf, restart, ncrestart, restartnc, dcd, charmm, cor, pdb, mol2, trr, gro, binpos, xtc, cif, arc, sqm, sdf, conflib.') 

221 parser.add_argument('--input_exp_path', required=False, help='Path to the experimental reference file (required if reference = experimental).') 

222 required_args.add_argument('--output_cpptraj_path', required=True, help='Path to the output processed analysis.') 

223 parser.add_argument('--output_traj_path', required=False, help='Path to the output processed trajectory.') 

224 

225 args = parser.parse_args() 

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

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

228 

229 # Specific call of each building block 

230 cpptraj_rms(input_top_path=args.input_top_path, 

231 input_traj_path=args.input_traj_path, 

232 output_cpptraj_path=args.output_cpptraj_path, 

233 input_exp_path=args.input_exp_path, 

234 output_traj_path=args.output_traj_path, 

235 properties=properties) 

236 

237 

238if __name__ == '__main__': 

239 main()