Python脚本：将mol2分子库文件拆分为单个mol2文件

用法：

python split_multimol2.py multi-mol2.mol2 out_dir

注释：python 脚本文件 mol2分子库 输出目录

split_multimol2.py：

1. #Python2 or Python3
2. #AspirinCode 2018
3. #Script that splits a multi-mol2 file into individual mol2 files.
4. #python split_multimol2.py multi-mol2.mol2 out_dir
6. import sys
7. import os
9. def split_multimol2(multimol2):
10. """
11. Splits a multi-mol2 file.
13. Parameters
14. ----------
15. multimol2 : str
16. Path to the multi-mol2 file.
18. Returns
19. ----------
20. A generator object for lists for every extracted mol2-file. Lists contain
21. the molecule ID and the mol2 file contents.
22. e.g., ['ID1234', '@<TRIPOS>MOLECULE...'
24. """
25. with open(multimol2, 'r') as mol2file:
26. line = mol2file.readline()
28. while not mol2file.tell() == os.fstat(mol2file.fileno()).st_size:
29. if line.startswith("@<TRIPOS>MOLECULE"):
30. mol2cont = []
31. mol2cont.append(line)
32. line = mol2file.readline()
33. molecule_id = line.strip()
35. while not line.startswith("@<TRIPOS>MOLECULE"):
36. mol2cont.append(line)
37. line = mol2file.readline()
38. if mol2file.tell() == os.fstat(mol2file.fileno()).st_size:
39. mol2cont.append(line)
40. break
41. mol2cont[-1] = mol2cont[-1].rstrip() # removes blank line at file end
42. yield [molecule_id, "".join(mol2cont)]
45. def write_multimol2(multimol2, out_dir):
46. """
47. Splits a multi-mol2 file into smaller multi-mol2 files.
49. Parameters
50. -----------
51. multimol2 : str
52. Path to the multi-mol2 file.
54. out_dir : str:
55. Output directory. New files will be named
56. <molecule_name_1>.mol2, ... <molecule_name_n>.mol2
58. Returns
59. -----------
60. chunks : int
61. Number of files written.
63. """
64. if not out_dir:
65. os.mkdir(out_dir)
67. single_mol2s = split_multimol2(args.MOL2_FILE)
68. for mol2 in single_mol2s:
69. out_mol2 = os.path.join(args.OUT_DIR, mol2[0]) + '.mol2'
70. with open(out_mol2, 'w') as out_file:
71. for line in mol2[1]:
72. out_file.write(line)
73. out_file.write('\n')
76. def write_multimol2_chunks(multimol2, chunk_size, out_dir):
77. """
78. Splits a multi-mol2 file into smaller multi-mol2 files.
80. Parameters
81. -----------
82. multimol2 : str
83. Path to the multi-mol2 file.
85. chunksize : int
86. Number of mol2 files per chunk.
88. out_dir : str:
89. Output directory. New files will be named
90. <multimol2>_1.mol2, ... <multimol2>_n.mol2
92. Returns
93. -----------
94. chunks : int
95. Number of files written.
97. """
98. if not os.path.exists(out_dir):
99. os.mkdir(out_dir)
101. out_path_stem = os.path.dirname(multimol2)
102. out_file_stem = os.path.basename(multimol2).split('.mol2')[0]
104. cnt = 0
105. chunks = 1
106. out_file = open(os.path.join(out_dir, out_file_stem)+'_%d.mol2' % chunks, 'w')
107. for mol2 in split_multimol2(multimol2):
108. cnt += 1
109. if cnt == chunk_size:
110. cnt = 0
111. chunks += 1
112. out_file.close()
113. out_file = open(os.path.join(out_dir, out_file_stem)+'_%d.mol2' % chunks, 'w')
114. out_file.write(mol2[1] + '\n')
115. out_file.close()
116. return chunks
119. if __name__ == '__main__':
121. import argparse
123. parser = argparse.ArgumentParser(
124. description='Splits a multi-mol2 file into individual mol2 files',
125. formatter_class=argparse.RawTextHelpFormatter
126. )
128. parser.add_argument('MOL2_FILE')
129. parser.add_argument('OUT_DIR')
130. parser.add_argument('-c', '--chunksize', help='Number of MOL2 structures per file (1 by default)', type=int)
131. parser.add_argument('-v', '--version', action='version', version='split_multimol2 v. 1.1')
133. args = parser.parse_args()
136. if args.chunksize:
137. write_multimol2_chunks(multimol2=args.MOL2_FILE, chunk_size=args.chunksize, out_dir=args.OUT_DIR)
139. else:
140. write_multimol2(multimol2=args.MOL2_FILE, out_dir=args.OUT_DIR)