Merge ff4b2cd into 1f91110

download.yaml

@@ -140,3 +140,11 @@
 -
   url: http://current.geneontology.org/ontology/extensions/go-plus.json
   local_name: go-plus.json
+
+#
+# GO-CAM
+#
+
+-
+  url: https://github.com/justaddcoffee/go-cam-models-kg-covid-19/raw/master/lifted-go-cams-20200619.xml.gz
+  local_name: lifted-go-cams-20200619.xml.gz

kg_covid_19/transform.py

@@ -5,6 +5,7 @@
 
 from kg_covid_19.transform_utils.chembl.chembl_transform import ChemblTransform
 from kg_covid_19.transform_utils.drug_central.drug_central import DrugCentralTransform
+from kg_covid_19.transform_utils.gocam_transform.gocam_transform import GocamTransform
 from kg_covid_19.transform_utils.intact.intact import IntAct
 from kg_covid_19.transform_utils.ontology import OntologyTransform
 from kg_covid_19.transform_utils.ontology.ontology_transform import ONTOLOGIES
@@ -22,13 +23,14 @@
     'DrugCentralTransform': DrugCentralTransform,
     'TTDTransform': TTDTransform,
     'StringTransform': StringTransform,
-    'ScibiteCordTransform': ScibiteCordTransform,
+    # 'ScibiteCordTransform': ScibiteCordTransform,
     'PharmGKB': PharmGKB,
     'SARSCoV2GeneAnnot': SARSCoV2GeneAnnot,
     'IntAct': IntAct,
     'GoTransform': OntologyTransform,
     'HpTransform': OntologyTransform,
     'MondoTransform': OntologyTransform,
+    'GocamTransform': GocamTransform,
     'ChemblTransform': ChemblTransform
 }
 

kg_covid_19/transform_utils/gocam_transform/__init__.py

@@ -0,0 +1,5 @@
+from .gocam_transform import GocamTransform
+
+__all__ = [
+    "GocamTransform"
+]

kg_covid_19/transform_utils/gocam_transform/gocam_transform.py

@@ -0,0 +1,100 @@
+import gzip
+import os
+import shutil
+from typing import Optional
+
+from kgx import RdfTransformer, PandasTransformer # type: ignore
+
+from kg_covid_19.transform_utils.transform import Transform
+
+
+class GocamTransform(Transform):
+    """
+    GocamTransform parses GO-CAMs that have been subjected to
+    RDF edge project (REP) pattern.
+    """
+    def __init__(self, input_dir: str = None, output_dir: str = None):
+        source_name = "GOCAMs"
+        super().__init__(source_name, input_dir, output_dir)
+
+    def run(self, data_file: Optional[str] = None, **kwargs) -> None:
+        """Method is called and performs needed transformations to process
+        an ontology.
+
+        Args:
+            data_file: data file to parse
+
+        Returns:
+            None.
+
+        """
+        if not data_file:
+            data_file = os.path.join(self.input_base_dir, 'lifted-go-cams-20200619.xml.gz')
+
+        if data_file.endswith('.gz'):
+            print("Decompressing")
+            decompressed_data_file = '.'.join(data_file.split('.')[0:-1])
+            self.decompress_file(data_file, decompressed_data_file)
+        else:
+            decompressed_data_file = data_file
+
+        if 'input_format' in kwargs:
+            input_format = kwargs['input_format']
+            if input_format not in {'nt', 'ttl', 'rdf/xml'}:
+                raise ValueError(f"Unsupported input_format: {input_format}")
+        else:
+            input_format = None
+        self.parse(decompressed_data_file, input_format)
+
+    def parse(self, data_file: str, input_format: str) -> None:
+        """Processes the data_file.
+
+        Args:
+            data_file: data file to parse
+            input_format: format of input file
+
+        Returns:
+             None
+
+        """
+        # define prefix to IRI mappings
+        cmap = {
+            'REACT': 'http://purl.obolibrary.org/obo/go/extensions/reacto.owl#REACTO_',
+            'WB': 'http://identifiers.org/wormbase/',
+            'FB': 'http://identifiers.org/flybase/',
+            'LEGO': 'http://geneontology.org/lego/',
+            'GOCAM': 'http://model.geneontology.org/',
+            'TAIR.LOCUS': 'http://identifiers.org/tair.locus/',
+            'POMBASE': 'http://identifiers.org/PomBase',
+            'DICTYBASE.GENE': 'http://identifiers.org/dictybase.gene/',
+            'XENBASE': 'http://identifiers.org/xenbase/'
+        }
+
+        # define predicates that are to be treated as node properties
+        np = {
+            'http://geneontology.org/lego/evidence',
+            'https://w3id.org/biolink/vocab/subjectActivity',
+            'https://w3id.org/biolink/vocab/objectActivity',
+        }
+
+        print(f"Parsing {data_file}")
+        transformer = RdfTransformer(curie_map=cmap)
+        transformer.parse(data_file, node_property_predicates=np, input_format=input_format)
+        output_transformer = PandasTransformer(transformer.graph)
+        output_transformer.save(os.path.join(self.output_dir, self.source_name), output_format='tsv', mode=None)
+
+    def decompress_file(self, input_file: str, output_file: str):
+        """Decompress a file.
+
+        Args:
+             input_file: Input file
+             output_file: Output file
+
+        Returns:
+            str
+
+        """
+        FH = gzip.open(input_file, 'rb')
+        WH = open(output_file, 'wb')
+        WH.write(FH.read())
+        return output_file

kg_covid_19/transform_utils/ontology/ontology_transform.py

@@ -1,16 +1,18 @@
 import os
-import logging
+
 from typing import Optional
 
 from kg_covid_19.transform_utils.transform import Transform
-from kgx import PandasTransformer, ObographJsonTransformer # type: ignore
+from kgx import PandasTransformer, ObographJsonTransformer  # type: ignore
+
 
 ONTOLOGIES = {
     'HpTransform': 'hp.json',
     'GoTransform': 'go-plus.json',
-    'MondoTransform':  'mondo.json'
+    'MondoTransform':  'mondo.json',
 }
 
+
 class OntologyTransform(Transform):
     """
     OntologyTransform parses an Obograph JSON form of an Ontology into nodes nad edges.
@@ -22,13 +24,10 @@ def __init__(self, input_dir: str = None, output_dir: str = None):
     def run(self, data_file: Optional[str] = None) -> None:
         """Method is called and performs needed transformations to process
         an ontology.
-
         Args:
             data_file: data file to parse
-
         Returns:
             None.
-
         """
         if data_file:
             k = data_file.split('.')[0]
@@ -42,18 +41,15 @@ def run(self, data_file: Optional[str] = None) -> None:
 
     def parse(self, name: str, data_file: str, source: str) -> None:
         """Processes the data_file.
-
         Args:
             name: Name of the ontology
             data_file: data file to parse
             source: Source name
-
         Returns:
              None.
-
         """
-        logging.info(f"Parsing {data_file}")
+        print(f"Parsing {data_file}")
         transformer = ObographJsonTransformer()
         transformer.parse(data_file, provided_by=source)
         output_transformer = PandasTransformer(transformer.graph)
-        output_transformer.save(filename=os.path.join(self.output_dir, f'{name}'), output_format='tsv', mode=None)
+        output_transformer.save(filename=os.path.join(self.output_dir, f'{name}'), output_format='tsv', mode=None)

kg_covid_19/utils/transform_utils.py

@@ -2,7 +2,10 @@
 # -*- coding: utf-8 -*-
 import gzip
 import logging
+import os
 import re
+import shutil
+import tempfile
 import zipfile
 from typing import Any, Dict, List, Union
 from tqdm import tqdm  # type: ignore
@@ -157,6 +160,16 @@ def unzip_to_tempdir(zip_file_name: str, tempdir: str) -> None:
         z.extractall(tempdir)
 
 
+def ungzip_to_tempdir(gzipped_file: str, tempdir: str) -> str:
+    ungzipped_file = os.path.join(tempdir, os.path.basename(gzipped_file))
+    if ungzipped_file.endswith('.gz'):
+        ungzipped_file = os.path.splitext(ungzipped_file)[0]
+
+    with gzip.open(gzipped_file, 'rb') as f_in, open(ungzipped_file, 'wb') as f_out:
+        shutil.copyfileobj(f_in, f_out)
+    return ungzipped_file
+
+
 def guess_bl_category(identifier: str) -> str:
     """Guess category for a given identifier.
 

merge.yaml

@@ -82,6 +82,11 @@ target:
       filename:
          - data/transformed/ontologies/hp_nodes.tsv
          - data/transformed/ontologies/hp_edges.tsv
+   go-cams:
+      type: tsv
+      filename:
+         - data/transformed/GOCAMs/GOCAMs_nodes.tsv
+         - data/transformed/GOCAMs/GOCAMs_edges.tsv
 destination:
    merged-kg-tsv:
       type: tsv