Dom update chemicals (#140)

* fixed #136 
* fixed #138

Author: terazus

.gitignore

@@ -19,4 +19,5 @@ credentials.json
 .env
 .env.prod
 envv/*
-ptmd.db
+ptmd.db
+scripts/

ptmd/boot/file_parsers/parse_chemicals.py

@@ -2,7 +2,7 @@
 """
 from __future__ import annotations
 
-from pandas import read_excel, DataFrame
+from pandas import read_csv, DataFrame
 
 from ptmd.const import CHEMICALS_FILEPATH, BASE_IDENTIFIER
 
@@ -13,14 +13,12 @@ def parse_chemicals() -> list[dict]:
     :return: A list of chemicals.
     """
     chemicals: list[dict] = []
-    chemicals_dataframe: DataFrame = read_excel(CHEMICALS_FILEPATH,
-                                                engine='openpyxl',
-                                                sheet_name="SUMMARY table of CHEMICALS")
+    chemicals_dataframe: DataFrame = read_csv(CHEMICALS_FILEPATH, sep=",", encoding='utf-8')
     for compound in chemicals_dataframe.itertuples():
         chemicals.append({
-            'common_name': compound.Compound.replace('"', ''),
-            'ptx_code': int(compound._2.replace('"', '').replace(BASE_IDENTIFIER, '')),
-            'formula': compound.Formula.replace('"', ''),
-            'cas': compound._5.replace('"', '').split('\n')[0]
+            'common_name': compound.compound_name_user.replace('\xa0', ''),
+            'ptx_code': int(compound.ptx_code.replace(BASE_IDENTIFIER, '')),
+            'formula': compound.formula,
+            'cas': compound.cas_neutral
         })
     return chemicals

ptmd/const/directories.py

@@ -13,7 +13,7 @@
 SCHEMAS_PATH: str = path.join(DATA_PATH, 'schemas')
 EXPOSURE_INFORMATION_SCHEMA_FILEPATH: str = path.join(SCHEMAS_PATH, 'exposure_information_sheet_schema.json')
 PARTNERS_LONGNAME_PATH: str = path.join(DATA_PATH, 'data', 'partners.json')
-CHEMICALS_FILEPATH: str = path.join(DATA_PATH, 'data', 'chemicals.xlsx')
+CHEMICALS_FILEPATH: str = path.join(DATA_PATH, 'data', 'ptx_chem_database_chemicals.csv')
 ORGANISMS_FILEPATH: str = path.join(DATA_PATH, 'data', 'organisms.json')
 DOWNLOAD_DIRECTORY_PATH: str = path.join(DATA_PATH, 'downloads')
 

ptmd/lib/isa/core.py

@@ -29,7 +29,7 @@
 
 
 class Batch2ISA:
-    """ Class for converting a batch of PTMD data to ISA-Tab format.
+    """ Class for converting a batch of PTMD data to ISA-json format.
 
     :param file: The file to convert.
     """
@@ -53,7 +53,7 @@ def convert(self) -> list[dict]:
         :return: A list of dictionaries containing the ISA investigations.
         """
         study: Study = Study(
-            filename=self.filename,
+            filename=f's_{self.filename.replace(".xlsx", ".txt")}',
             sources=[self.blank_source],
             characteristic_categories=[ORGANISM_OA, SEX_OA, REPLICATE_OA, BOX_OA, POSITION_OA],
             units=[HOURS_OA]
@@ -235,7 +235,7 @@ def create_source(self, sample_identifier: str) -> Source:
         :param sample_identifier: The identifier of the sample.
         :return: A source.
         """
-        source_name: str = f"Source of sample {sample_identifier}"
+        source_name: str = f"{sample_identifier}_source"
 
         if 'Drosophila_melanogaster' not in self.organism_name:
             return Source(name=source_name, characteristics=[

ptmd/resources/data/chemicals.xlsx

@@ -7,5 +7,6 @@
   "NIH": "National Institutes of Health",
   "CLU": "Clemson University Research Foundation",
   "LEITAT": "Acondicionatment tarrasense Associacion",
-  "UOB": "University of Birmingham"
+  "UOB": "University of Birmingham",
+  "MGI": "MGI Tech Co., Ltd."
 }

ptmd/resources/data/partners.json

@@ -12,3 +12,4 @@ def test_parse_chemical(self):
             for key in keys:
                 self.assertIn(key, chemical.keys())
             self.assertEqual(type(chemical), dict)
+            self.assertIsInstance(chemical['ptx_code'], int)