comparison matchms_split.py @ 23:34439ffa6a60 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit da193865f41a3a840ecc4ba0afab1d358554998a
author recetox
date Mon, 05 Feb 2024 10:39:25 +0000
parents 1b09315a3f87
children
comparison
equal deleted inserted replaced
22:f76a397afbe1 23:34439ffa6a60
1 import argparse 1 import argparse
2 import itertools 2 import itertools
3 import os 3 import os
4 from typing import List
5 4
5 import matchms
6 from matchms.exporting import save_as_msp 6 from matchms.exporting import save_as_msp
7 from matchms.importing import load_from_msp 7 from matchms.importing import load_from_msp
8 8
9 9
10 def get_spectra_names(spectra: list) -> List[str]: 10 matchms.Metadata.set_key_replacements({})
11 """Read the keyword 'compound_name' from a spectra.
12
13 Args:
14 spectra (list): List of individual spectra.
15
16 Returns:
17 List[str]: List with 'compoud_name' of individual spectra.
18 """
19 return [x.get("compound_name") for x in spectra]
20 11
21 12
22 def make_outdir(outdir: str): 13 def make_outdir(outdir: str):
23 """Create destination directory. 14 """Create destination directory.
24 15
33 24
34 Args: 25 Args:
35 spectra (List[Spectrum]): Spectra to write to file 26 spectra (List[Spectrum]): Spectra to write to file
36 outdir (str): Path to destination directory. 27 outdir (str): Path to destination directory.
37 """ 28 """
38 names = get_spectra_names(spectra)
39 for i in range(len(spectra)): 29 for i in range(len(spectra)):
40 outpath = assemble_outpath(names[i], outdir) 30 save_as_msp(spectra[i], os.path.join(outdir, f"{i}.msp"))
41 save_as_msp(spectra[i], outpath)
42
43
44 def assemble_outpath(name, outdir):
45 """Filter special chracteres from name.
46
47 Args:
48 name (str): Name to be filetered.
49 outdir (str): Path to destination directory.
50 """
51 filename = ''.join(filter(str.isalnum, name))
52 outfile = str(filename) + ".msp"
53 outpath = os.path.join(outdir, outfile)
54 return outpath
55 31
56 32
57 def split_round_robin(iterable, num_chunks): 33 def split_round_robin(iterable, num_chunks):
58 chunks = [list() for _ in range(num_chunks)] 34 chunks = [list() for _ in range(num_chunks)]
59 index = itertools.cycle(range(num_chunks)) 35 index = itertools.cycle(range(num_chunks))
74 method = args.method 50 method = args.method
75 parameter = args.parameter 51 parameter = args.parameter
76 52
77 53
78 if __name__ == "__main__": 54 if __name__ == "__main__":
79 spectra = load_from_msp(filename, metadata_harmonization=True) 55 spectra = load_from_msp(filename, metadata_harmonization=False)
80 make_outdir(outdir) 56 make_outdir(outdir)
81 57
82 if method == "one-per-file": 58 if method == "one-per-file":
83 write_spectra(list(spectra), outdir) 59 write_spectra(list(spectra), outdir)
84 else: 60 else: