minor changes

python/quantmsio/quantms_io/core/ae.py

@@ -6,16 +6,18 @@
 from quantms_io.core.sdrf import SDRFHandler
 from quantms_io.utils.file_utils import delete_files_extension
 import logging
-logging.basicConfig(level = logging.INFO)
+
+logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
+
 def get_ibaq_columns(path):
     with open(path) as f:
         line = f.readline()
         return line.split('\n')[0].split(',')
 
+
 class AbsoluteExpressionHander:
-
     LABEL_MAP = {
         'ProteinName': 'protein',
         'SampleID': 'sample_accession',
@@ -28,17 +30,16 @@ class AbsoluteExpressionHander:
 #INFO=<ID=condition, Number=1, Type=String, Description="Value of the factor value">
 #INFO=<ID=ibaq, Number=1, Type=Float, Description="Intensity based absolute quantification">
 #INFO=<ID=ribaq, Number=1, Type=Float, Description="relative iBAQ">\n"""
-    
+
     ABSOLUTE_EXPRESSION_EXTENSION = ".absolute.tsv"
-    
+
     def __init__(self):
         self.ibaq_df = None
         self.ae_file_path = None
         self.project_manager = None
         self.sdrf_manager = None
         self.sdrf_file_path = None
-
-
+
     def load_project_file(self, project_file: str):
         """
         Load a project file that link the different files in the quamtms.io format
@@ -53,19 +54,18 @@ def load_project_file(self, project_file: str):
 
         self.project_manager = ProjectHandler()
         self.project_manager.load_project_info(project_file)
-
-
-    def load_ibaq_file(self,path):
-        usecols = ['ProteinName','SampleID','Condition','Ibaq','IbaqLog']
+
+    def load_ibaq_file(self, path):
+        usecols = ['ProteinName', 'SampleID', 'Condition', 'Ibaq', 'IbaqLog']
         ibaq_columns = get_ibaq_columns(path)
         for col in usecols:
             if col not in ibaq_columns:
                 raise Exception(f"Not found {col} in ibaq file")
-        ibaqs = pd.read_csv(path,usecols=usecols)
-        ibaqs.rename(columns=AbsoluteExpressionHander.LABEL_MAP,inplace=True)
+        ibaqs = pd.read_csv(path, usecols=usecols)
+        ibaqs.rename(columns=AbsoluteExpressionHander.LABEL_MAP, inplace=True)
         self.ae_file_path = path
         self.ibaq_df = ibaqs
-    
+
     def load_sdrf_file(self, sdrf_file: str):
         self.sdrf_file_path = sdrf_file
 
@@ -75,32 +75,32 @@ def load_sdrf_file(self, sdrf_file: str):
         self.sdrf_manager = SDRFHandler(sdrf_file=sdrf_file)
 
     def convert_ibaq_to_quantms(
-        self,
-        output_folder: str = None,
-        output_file_prefix: str = None,
-        delete_existing: bool = False,
+            self,
+            output_folder: str = None,
+            output_file_prefix: str = None,
+            delete_existing: bool = False,
     ):
         output_lines = ''
         if self.project_manager:
             output_lines += (
-                "#project_accession: "
-                + self.project_manager.project.project_info["project_accession"]
-                + "\n"
+                    "#project_accession: "
+                    + self.project_manager.project.project_info["project_accession"]
+                    + "\n"
             )
             output_lines += (
-                "#project_title: "
-                + self.project_manager.project.project_info["project_title"]
-                + "\n"
+                    "#project_title: "
+                    + self.project_manager.project.project_info["project_title"]
+                    + "\n"
             )
             output_lines += (
-                "#project_description: "
-                + self.project_manager.project.project_info["project_description"]
-                + "\n"
+                    "#project_description: "
+                    + self.project_manager.project.project_info["project_description"]
+                    + "\n"
             )
             output_lines += (
-                "#quantms_version: "
-                + self.project_manager.project.project_info["quantms_version"]
-                + "\n"
+                    "#quantms_version: "
+                    + self.project_manager.project.project_info["quantms_version"]
+                    + "\n"
             )
         factor_value = self.get_factor_value()
         if factor_value is not None:
@@ -109,7 +109,7 @@ def convert_ibaq_to_quantms(
         output_lines += AbsoluteExpressionHander.AE_HEADER + str(
             self.ibaq_df.to_csv(sep="\t", index=False, header=True)
         )
-        output_lines = output_lines.replace('\r','')
+        output_lines = output_lines.replace('\r', '')
         # Create the output file name
         base_name = output_file_prefix
         if output_file_prefix is None:
@@ -133,9 +133,9 @@ def convert_ibaq_to_quantms(
             output_filename_path = f"{output_folder}/{output_filename}"
 
         # Save the combined lines to a TSV file
-        with open(output_filename_path, "w",encoding='utf8') as f:
+        with open(output_filename_path, "w", encoding='utf8') as f:
             f.write(output_lines)
-    
+
         if self.project_manager:
             self.project_manager.add_quantms_file(
                 file_category="absolute_file", file_name=output_filename
@@ -163,4 +163,4 @@ def update_project_file(self, project_file: str = None):
 
         if project_file is not None:
             project_file = self.project_file
-        self.project_manager.save_updated_project_info(output_file_name=project_file)
+        self.project_manager.save_updated_project_info(output_file_name=project_file)

python/quantmsio/quantms_io/core/database.py

@@ -7,6 +7,7 @@
 import duckdb
 import random
 
+
 def get_skip_rows(path):
     skip_rows = 0
     with open(path) as f:
@@ -16,44 +17,43 @@ def get_skip_rows(path):
             line = f.readline()
         return skip_rows
 
+
 class Database:
-    
+
     def __init__(self):
-        
+
         self.feature_db = []
         self.ibaq_db = []
-        
-    def load_db(self,path:str):
-        
+
+    def load_db(self, path: str):
+
         if path.endswith(".parquet"):
             self.feature_db.append(duckdb.read_parquet(path))
-        elif path.endswith(".absolute.tsv") :
+        elif path.endswith(".absolute.tsv"):
             skip_rows = get_skip_rows(path)
-            self.ibaq_db.append(duckdb.read_csv(path,sep='\t',skiprows=skip_rows))
-                
-    def get_unique_peptides(self,n):
-        
+            self.ibaq_db.append(duckdb.read_csv(path, sep='\t', skiprows=skip_rows))
+
+    def get_unique_peptides(self, n):
+
         feature_db = self.feature_db[n]
         unique_peps = duckdb.sql(f"SELECT DISTINCT sequence FROM feature_db").df()
-        
+
         return unique_peps['sequence'].tolist()
 
-    def get_unique_proteins(self,n):
-        
+    def get_unique_proteins(self, n):
+
         ibaq_db = self.ibaq_db[n]
         unique_prts = duckdb.sql(f"SELECT DISTINCT protein FROM ibaq_db").df()
-        
+
         return unique_prts['protein'].tolist()
- 
-    def query_peptide(self,peptide:str,n):
-       
+
+    def query_peptide(self, peptide: str, n):
+
         feature_db = self.feature_db[n]
         return duckdb.sql(f"SELECT * FROM feature_db WHERE sequence ='{peptide}'").df()
-
 
-    def query_protein(self,protein:str,n):
-        
+    def query_protein(self, protein: str, n):
+
         ibaq_db = self.ibaq_db[n]
-        
+
         return duckdb.sql(f"SELECT * FROM ibaq_db WHERE protein ='{protein}'").df()
-

python/quantmsio/quantms_io/core/de.py

@@ -24,7 +24,8 @@
 from quantms_io.utils.file_utils import delete_files_extension
 
 import logging
-logging.basicConfig(level = logging.INFO)
+
+logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 
@@ -109,10 +110,10 @@ def load_project_file(self, project_file: str):
         self.project_manager.load_project_info(project_file)
 
     def convert_msstats_to_quantms(
-        self,
-        output_folder: str = None,
-        output_file_prefix: str = None,
-        delete_existing: bool = False,
+            self,
+            output_folder: str = None,
+            output_file_prefix: str = None,
+            delete_existing: bool = False,
     ):
         """
         Convert a MSstats differential file to quantms.io format
@@ -140,24 +141,24 @@ def convert_msstats_to_quantms(
         output_lines = ''
         if self.project_manager:
             output_lines += (
-                "#project_accession: "
-                + self.project_manager.project.project_info["project_accession"]
-                + "\n"
+                    "#project_accession: "
+                    + self.project_manager.project.project_info["project_accession"]
+                    + "\n"
             )
             output_lines += (
-                "#project_title: "
-                + self.project_manager.project.project_info["project_title"]
-                + "\n"
+                    "#project_title: "
+                    + self.project_manager.project.project_info["project_title"]
+                    + "\n"
             )
             output_lines += (
-                "#project_description: "
-                + self.project_manager.project.project_info["project_description"]
-                + "\n"
+                    "#project_description: "
+                    + self.project_manager.project.project_info["project_description"]
+                    + "\n"
             )
             output_lines += (
-                "#quantms_version: "
-                + self.project_manager.project.project_info["quantms_version"]
-                + "\n"
+                    "#quantms_version: "
+                    + self.project_manager.project.project_info["quantms_version"]
+                    + "\n"
             )
         factor_value = self.get_factor_value()
         if factor_value is not None:
@@ -197,7 +198,7 @@ def convert_msstats_to_quantms(
             output_filename_path = f"{output_folder}/{output_filename}"
 
         # Save the combined lines to a TSV file
-        with open(output_filename_path, "w",encoding='utf8') as f:
+        with open(output_filename_path, "w", encoding='utf8') as f:
             f.write(output_lines)
         if self.project_manager:
             self.project_manager.add_quantms_file(
@@ -228,7 +229,7 @@ def get_contrast_labels(quantms_df: pd.DataFrame):
         """
         unique_labels = []
         for label in quantms_df["label"].unique():
-            for condition in label.split("-",1):
+            for condition in label.split("-", 1):
                 unique_labels.append(condition)
         '''
         if len(unique_label) == 1: