-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
-
- Loading branch information
Showing
2 changed files
with
80 additions
and
51 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,54 +1,72 @@ | ||
| """Migration pipeline | ||
| """Slurp migration pipeline | ||
| #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING | ||
| #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING | ||
| #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING | ||
| #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING | ||
| TODOs: | ||
| TODO's: | ||
| - add CLI: look to makefile for what to include | ||
| """ | ||
| import oakliblib | ||
| import pandas | ||
|
|
||
| import os | ||
| from argparse import ArgumentParser | ||
| from typing import Dict | ||
|
|
||
| #Inputs: | ||
| source_ontology = '' #e.g. omim | ||
| sssom_map = '' # e.g. mondo.sssom.tsv | ||
| min_id = '' | ||
| termlist_mondo = '' | ||
| import oaklib | ||
| import pandas as pd | ||
|
|
||
|
|
||
| def run(source_ontology = '', sssom_map = '', min_id = '', termlist_mondo = ''): | ||
| """source_ontology = '' #e.g. omim | ||
| sssom_map = '' # e.g. mondo.sssom.tsv | ||
| min_id = '' | ||
| termlist_mondo = ''""" | ||
| #Outputs: | ||
| def run(ontology_path: str, sssom_map_path: str, min_id: int, mondo_terms_path: str, outpath: str): | ||
| # TODO: read files | ||
| source_ontology = ontology_path | ||
| print(os.path.exists(os.path.join(os.getcwd(), sssom_map_path))) | ||
| print(os.path.exists(os.path.join(os.getcwd(), mondo_terms_path))) | ||
| print(os.path.exists(os.path.join(os.getcwd(), ontology_path))) | ||
| sssom_map = pd.read_csv(sssom_map_path, comment='#', sep='\t') | ||
| termlist_mondo = pd.read_csv(mondo_terms_path, comment='#', sep='\t') | ||
| data = [] | ||
| # for t in source_ontology: | ||
| # if t not in sssom_map['object_id']: | ||
| # parents = [] | ||
| # migrate = True | ||
| # for p in oaklib.get_direct_parents(t): | ||
| # if p not in sssom_map['object_id']: | ||
| # migrate = False | ||
| # break | ||
| # elif sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:exactMatch' \ | ||
| # or sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:narrowMatch': | ||
| # # In other words, if the parent is mapped, and the mapping is either exact or narrower | ||
| # parents.append(sssom_map[sssom_map['object_id']==p]['subject_id']) | ||
| # else: | ||
| # # Its fine, just continue looking for other parents in this case | ||
| # if migrate and parents: | ||
| # next_mondo_id = determine_next_available_mondo_id(min_id, termlist_mondo) # satrting from min_id, then counting up and checking if it does not already exist. | ||
| # label = oaklib.get_label(t) | ||
| # definition = oaklib.get_definition(t) | ||
| # data.append({'mondo_id':next_mondo_id, 'xref': t, 'label': label, 'definition': definition}) | ||
| # | ||
| # pd.DataFrame(data).to_csv(fn, sep="\t") | ||
| pass | ||
|
|
||
|
|
||
| for t in source_ontology: | ||
| if t not in sssom_map['object_id']: | ||
| parents = [] | ||
| migrate = True | ||
| for p in oaklib.get_direct_parents(t): | ||
| if p not in sssom_map['object_id']: | ||
| migrate = False | ||
| break | ||
| elif sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:exactMatch' \ | ||
| or sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:narrowMatch': | ||
| # In other words, if the parent is mapped, and the mapping is either exact or narrower | ||
| parents.append(sssom_map[sssom_map['object_id']==p]['subject_id']) | ||
| else: | ||
| # Its fine, just continue looking for other parents in this case | ||
| if migrate and parents: | ||
| next_mondo_id = determine_next_available_mondo_id(min_id, termlist_mondo) # satrting from min_id, then counting up and checking if it does not already exist. | ||
| label = oaklib.get_label(t) | ||
| definition = oaklib.get_definition(t) | ||
| data.append({'mondo_id':next_mondo_id, 'xref': t, 'label': label, 'definition': definition}) | ||
|
|
||
| pandas.DataFrame(data).to_csv(fn, sep="\t") | ||
| def cli() : | ||
| """Command line interface.""" | ||
| package_description = \ | ||
| 'Slurp pipeline: Integrate new terms from other ontologies into Mondo.' | ||
| parser = ArgumentParser(description=package_description) | ||
| parser.add_argument( | ||
| '-o', '--ontology-path', required=True, | ||
| help='xxxxxx') | ||
| parser.add_argument( | ||
| '-m', '--sssom-map-path', required=True, | ||
| help='xxxxxx') | ||
| parser.add_argument( | ||
| '-i', '--min-id', required=True, | ||
| help='xxxxxx') | ||
| parser.add_argument( | ||
| '-t', '--mondo-terms-path', required=True, | ||
| help='xxxxxx') | ||
| parser.add_argument( | ||
| '-O', '--outpath', required=True, | ||
| help='xxxxxx') | ||
| d: Dict = vars(parser.parse_args()) | ||
| return run(**d) | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| run() | ||
| cli() |