Merge 432804f into ce9ebe8

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: go-cams.rdf.gz

kg_covid_19/transform.py

@@ -29,6 +29,7 @@
     'GoTransform': OntologyTransform,
     'HpTransform': OntologyTransform,
     'MondoTransform': OntologyTransform,
+    'GoCam': OntologyTransform,
     'ChemblTransform': ChemblTransform
 }
 

kg_covid_19/transform_utils/ontology/ontology_transform.py

@@ -1,16 +1,21 @@
 import os
 import logging
+import tempfile
 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, RdfTransformer  # type: ignore
+
+from kg_covid_19.utils.transform_utils import ungzip_to_tempdir
 
 ONTOLOGIES = {
     'HpTransform': 'hp.json',
     'GoTransform': 'go-plus.json',
-    'MondoTransform':  'mondo.json'
+    'MondoTransform':  'mondo.json',
+    'GoCam': 'go-cams.rdf.gz'
 }
 
+
 class OntologyTransform(Transform):
     """
     OntologyTransform parses an Obograph JSON form of an Ontology into nodes nad edges.
@@ -19,7 +24,7 @@ def __init__(self, input_dir: str = None, output_dir: str = None):
         source_name = "ontologies"
         super().__init__(source_name, input_dir, output_dir)
 
-    def run(self, data_file: Optional[str] = None) -> None:
+    def run(self, data_file: Optional[str] = None, input_format = 'json') -> None:
         """Method is called and performs needed transformations to process
         an ontology.
 
@@ -32,28 +37,50 @@ def run(self, data_file: Optional[str] = None) -> None:
         """
         if data_file:
             k = data_file.split('.')[0]
+
+            if data_file.endswith('.gz'):
+                input_format = 'rdf/xml'
+                xml_tempdir = tempfile.mkdtemp()
+                data_file = ungzip_to_tempdir(os.path.join(
+                    self.input_base_dir, data_file), xml_tempdir)
+
             data_file = os.path.join(self.input_base_dir, data_file)
-            self.parse(k, data_file, k)
+            self.parse(k, data_file, k,  input_format=input_format)
         else:
             # load all ontologies
             for k in ONTOLOGIES.keys():
+
                 data_file = os.path.join(self.input_base_dir, ONTOLOGIES[k])
-                self.parse(k, data_file, k)
 
-    def parse(self, name: str, data_file: str, source: str) -> None:
+                if data_file.endswith('.gz'):
+                    input_format = 'rdf/xml'
+                    xml_tempdir = tempfile.mkdtemp()
+                    data_file = ungzip_to_tempdir(os.path.join(
+                        self.input_base_dir, data_file), xml_tempdir)
+
+                self.parse(k, data_file, k, input_format=input_format)
+
+    def parse(self, name: str, data_file: str, source: str,
+              input_format: str = 'json') -> None:
         """Processes the data_file.
 
         Args:
             name: Name of the ontology
             data_file: data file to parse
-            source: Source name
+            source: source name
+            input_format: format of input file
 
         Returns:
              None.
 
         """
         logging.info(f"Parsing {data_file}")
-        transformer = ObographJsonTransformer()
+        if input_format == 'json':
+            transformer = ObographJsonTransformer()
+        elif input_format == 'rdf/xml':
+            transformer = RdfTransformer()
+        else:
+            raise ValueError("No way to parse format %s" % format)
         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)

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.