Add disease ontology

scripts/biomedical/diseaseOntology/README.md

@@ -0,0 +1,94 @@
+# Importing the Disease Ontology (DO) data
+
+## Table of Contents
+
+- [Importing the Disease Ontology (DO) data](#importing-the-disease-ontology-do-data)
+  - [Table of Contents](#table-of-contents)
+  - [About the Dataset](#about-the-dataset)
+    - [Download Data](#download-data)
+    - [Overview](#overview)
+    - [Notes and Caveats](#notes-and-caveats)
+    - [License](#license)
+  - [About the import](#about-the-import)
+    - [Artifacts](#artifacts)
+      - [Scripts](#scripts)
+      - [Files](#files)
+  - [Examples](#examples)
+    -[Run Tests](#run-tests)
+    -[Import](#import)
+
+## About the Dataset
+[Disease Ontology](https://disease-ontology.org) (DO) is a standardized ontology for human disease that was developed "with the purpose of providing the biomedical community with consistent, reusable and sustainable descriptions of human disease terms, phenotype characteristics and related medical vocabulary disease concepts through collaborative efforts of biomedical researchers, coordinated by the University of Maryland School of Medicine, Institute for Genome Sciences.
+
+The Disease Ontology semantically integrates disease and medical vocabularies through extensive cross mapping of DO terms to MeSH, ICD, NCI’s thesaurus, SNOMED and OMIM."
+
+### Download Data
+
+The human disease ontology data can be downloaded from their official github repository [here](https://www.vmh.life/#human/all). The data is in `.owl` format and had to be parsed into a `.csv` format (see [Notes and Caveats](#notes-and-caveats) for additional information on formatting).
+
+### Overview
+
+This directory stores the script used to download, clean, and convert the Disease Ontology data into a `.csv` format, which is ready for ingestion into the Data Commons knowledge graph alongside a `.tmcf` file that maps the `.csv` to the defined schema. In this import the data is ingested as [Disease](https://datacommons.org/browser/Disease) entities into the graph.
+
+### Notes and Caveats
+
+The original format of the data was `.owl` and it was converted to a `.csv` file prior to ingestion into Data Commons.
+
+### License
+
+This data is under a Creative Commons Public Domain Dedication [CC0 1.0 Universal license](https://disease-ontology.org/resources/do-resources).
+
+## About the import
+
+### Artifacts
+
+#### Scripts
+
+##### Shell Script
+
+`download.sh`
+
+##### Python Script
+
+`format_disease_ontology.py`
+
+##### Test Script
+
+`format_disease_ontology_test.py`
+
+#### Files
+
+##### Test File
+
+`input_file.txt`
+
+`expected_output_file.txt`
+
+##### tMCF File
+
+`my_tmcf_file.tmcf`
+
+
+### Examples
+
+#### Run Tests
+
+To test format_refseq_chromosome_id_to_dcid.py run:
+
+```
+python format_disease_ontology.py input_file.owl expected_output.csv
+```
+
+#### Import
+
+1. Download data to scratch/.
+
+```
+bash download.sh
+```
+
+2. Clean and convert the downloaded Disease Ontology data into `.csv` format
+
+```
+python format_disease_ontology.py humanDO.owl humanDO.csv
+```

scripts/biomedical/diseaseOntology/disease_ontology.tmcf

@@ -0,0 +1,23 @@
+Node: E:DiseaseOntology->E1
+typeOf: dcs:Disease
+dcid: C:DiseaseOntology->dcid
+name: C:DiseaseOntology->label
+parent: C:DiseaseOntology->subClassOf
+description: C:DiseaseOntology->IAO_0000115
+alternativeDiseaseOntologyID : C:DiseaseOntology->hasAlternativeId 
+diseaseSynonym: C:DiseaseOntology->hasExactSynonym
+internationalClassificationOfDiseaseID: C:DiseaseOntology->ICDO
+medicalSubjectHeadingDescriptorID: C:DiseaseOntology->MESH
+nationalCancerInstituteID: C:DiseaseOntology->NCI
+snowmedCT: C:DiseaseOntology->SNOMEDCTUS20200901
+snowmedCT: C:DiseaseOntology->SNOMEDCTUS20200301
+snowmedCT: C:DiseaseOntology->SNOMEDCTUS20180301
+snowmedCT: C:DiseaseOntology->SNOMEDCTUS20190901
+unifiedMedicalLanguageSystemConceptUniqueIdentifier: C:DiseaseOntology->UMLSCUI
+icd10CMCode: C:DiseaseOntology->ICD10CM
+icd9CMCode: C:DiseaseOntology->ICD9CM
+orphaNumber: C:DiseaseOntology->ORDO
+geneticAndRareDiseasesID: C:DiseaseOntology->GARD
+omimID: C:DiseaseOntology->OMIM
+experimentalFactorOntologyID: C:DiseaseOntology->EFO
+medDraID: C:DiseaseOntology->MEDDRA

scripts/biomedical/diseaseOntology/disease_ontology_test.py

@@ -0,0 +1,39 @@
+# Copyright 2022 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+'''
+Author: Suhana Bedi
+Date: 07/08/2022
+Name: disease_ontology_test.py
+Description: runs unit tests for format_disease_ontology.py
+Run: python3 disease_ontology_test.py
+'''
+
+import unittest
+from pandas.testing import assert_frame_equal 
+from format_disease_ontology import *
+
+class TestParseMesh(unittest.TestCase): 
+    """Test the functions in format_disease_ontology"""
+
+    def test_main(self):
+        """Test in the main function"""
+        # Read in the expected output files into pandas dataframes
+        df1_expected = pd.read_csv('unit-tests/test-output.csv')
+        df_actual = wrapper_fun('unit-tests/test-do.xml')
+        # Run all the functions in format_mesh.py 
+        # Compare expected and actual output files
+        assert_frame_equal(df1_expected.reset_index(drop=True), df_actual.reset_index(drop=True))
+
+if __name__ == '__main__':
+    unittest.main()