Mercurial > repos > recetox > matchms

comparison matchms_wrapper.py @ 1:4aecfd6b319b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit d110cb008c3703945fe3718465de36278fa34652"
author recetox
date Wed, 17 Mar 2021 11:40:17 +0000
parents 6a736abe431f
children a7c9fc186f8c
comparison
equal deleted inserted replaced
0:6a736abe431f 1:4aecfd6b319b
1 import argparse 1 import argparse
2 import sys 2 import sys
3 3
4 import pandas
5 from matchms import calculate_scores 4 from matchms import calculate_scores
6 from matchms.importing import load_from_msp 5 from matchms.importing import load_from_msp
7 from matchms.similarity import ( 6 from matchms.similarity import (
8 CosineGreedy, 7 CosineGreedy,
9 CosineHungarian, 8 CosineHungarian,
10 FingerprintSimilarity, 9 FingerprintSimilarity,
11 IntersectMz, 10 IntersectMz,
12 ModifiedCosine, 11 ModifiedCosine,
13 ParentMassMatch 12 ParentMassMatch
14 ) 13 )
14 from pandas import DataFrame
15 15
16 16
17 def main(argv): 17 def main(argv):
18 parser = argparse.ArgumentParser(description="Compute MSP similarity scores") 18 parser = argparse.ArgumentParser(description="Compute MSP similarity scores")
19 parser.add_argument( 19 parser.add_argument(
20 "references_filename", type=str, help="Path to reference MSP library." 20 "references_filename", type=str, help="Path to reference MSP library."
21 ) 21 )
22 parser.add_argument("queries_filename", type=str, help="Path to query spectra.") 22 parser.add_argument("queries_filename", type=str, help="Path to query spectra.")
23 parser.add_argument("output_filename", type=str, help="Path where to store the output .csv.")
24 parser.add_argument("similarity_metric", type=str, help='Metric to use for matching.') 23 parser.add_argument("similarity_metric", type=str, help='Metric to use for matching.')
24 parser.add_argument("output_filename_scores", type=str, help="Path where to store the output .csv scores.")
25 parser.add_argument("output_filename_matches", type=str, help="Path where to store the output .csv matches.")
25 26
26 args = parser.parse_args() 27 args = parser.parse_args()
27 28
28 if args.similarity_metric == 'CosineGreedy': 29 if args.similarity_metric == 'CosineGreedy':
29 similarity_metric = CosineGreedy() 30 similarity_metric = CosineGreedy()
49 similarity_function=similarity_metric, 50 similarity_function=similarity_metric,
50 ) 51 )
51 52
52 query_names = [spectra.metadata['name'] for spectra in scores.queries] 53 query_names = [spectra.metadata['name'] for spectra in scores.queries]
53 reference_names = [spectra.metadata['name'] for spectra in scores.references] 54 reference_names = [spectra.metadata['name'] for spectra in scores.references]
54 dataframe = pandas.DataFrame(data=scores.scores, index=reference_names, columns=query_names) 55
55 dataframe.to_csv(args.output_filename, sep=';') 56 # Write scores to dataframe
57 dataframe_scores = DataFrame(data=[entry["score"] for entry in scores.scores], index=reference_names, columns=query_names)
58 dataframe_scores.to_csv(args.output_filename_scores, sep=';')
59
60 # Write number of matches to dataframe
61 dataframe_matches = DataFrame(data=[entry["matches"] for entry in scores.scores], index=reference_names, columns=query_names)
62 dataframe_matches.to_csv(args.output_filename_matches, sep=';')
56 return 0 63 return 0
57 64
58 65
59 if __name__ == "__main__": 66 if __name__ == "__main__":
60 main(argv=sys.argv[1:]) 67 main(argv=sys.argv[1:])