minor_change

docs/tools.rst

@@ -269,6 +269,7 @@ Example:
       --modifications "Carbamidomethyl (C)" "null"
       --qvalue_threshold 0.05
       --mzml_info_folder mzml
+      --sdrf_path PXD037682.sdrf.tsv
       --output_folder result
       --output_prefix_file PXD037682
       --threads 60

python/quantmsio/quantms_io/commands/diann_convert_command.py

@@ -42,6 +42,11 @@ def cli():
     help="mzml info tsv file",
     required=True,
 )
+@click.option(
+    "--sdrf_path",
+    help="the SDRF file needed to extract some of the metadata",
+    required=True,
+)
 @click.option(
     "--output_folder",
     help="Folder where the Json file will be generated",
@@ -50,13 +55,14 @@ def cli():
 @click.option("--output_prefix_file", help="Prefix of the Json file needed to generate the file name", required=False)
 @click.option("--threads",help="The number of thread", default=60)
 @click.pass_context
-def diann_convert_to_parquet(ctx,report_path:str,design_file:str,modifications:List,qvalue_threshold: float,mzml_info_folder:str,output_folder:str,output_prefix_file:str,threads:int):
+def diann_convert_to_parquet(ctx,report_path:str,design_file:str,modifications:List,qvalue_threshold: float,mzml_info_folder:str,sdrf_path:str,output_folder:str,output_prefix_file:str,threads:int):
     '''
     report_path: diann report file path
     design_file: the disign file path
     modifications: a list contains fix modifications and variable modifications
     qvalue_threshold: qvalue threshold
     mzml_info_folder: mzml info file folder
+    sdrf_path: sdrf file path
     output_folder: Folder where the Json file will be generated
     output_prefix_file: Prefix of the Json file needed to generate the file name
     threads: The number of thread
@@ -78,6 +84,7 @@ def diann_convert_to_parquet(ctx,report_path:str,design_file:str,modifications:L
                                         folder=mzml_info_folder,
                                         design_file=design_file,
                                         modifications=modifications,
+                                        sdrf_path = sdrf_path,
                                         psm_output_path=psm_output_path,
                                         feature_output_path = feature_output_path,
                                         thread_num = threads

python/quantmsio/quantms_io/core/diann_convert.py

@@ -283,15 +283,15 @@ def intergrate_msg(n):
             report = self.add_additional_msg(report)
             yield report
 
-    def generate_psm_and_feature_file(self,report_path: str, qvalue_threshold: float,folder: str,design_file:str,modifications:list,psm_output_path:str,feature_output_path:str,thread_num:int=60):
+    def generate_psm_and_feature_file(self,report_path: str, qvalue_threshold: float,folder: str,design_file:str,modifications:list,sdrf_path:str,psm_output_path:str,feature_output_path:str,thread_num:int=60):
         psm_pqwriter = None
         feature_pqwriter = None
 
         s_data_frame, f_table = get_exp_design_dfs(design_file)
         self._modifications = get_modifications(modifications[0], modifications[1])
         for report in self.main_report_df(report_path, qvalue_threshold,folder,thread_num):
             psm_pqwriter = self.generate_psm_file(report,psm_pqwriter,psm_output_path)
-            feature_pqwriter = self.generate_feature_file(report,s_data_frame,f_table,feature_pqwriter,feature_output_path)
+            feature_pqwriter = self.generate_feature_file(report,s_data_frame,f_table,sdrf_path,feature_pqwriter,feature_output_path)
         if psm_pqwriter:
             psm_pqwriter.close()
         if feature_pqwriter:
@@ -332,8 +332,9 @@ def generate_psm_file(self,report,psm_pqwriter,psm_output_path):
         psm_pqwriter.write_table(parquet_table)
         return psm_pqwriter
 
-    def generate_feature_file(self,report,s_data_frame,f_table,feature_pqwriter,feature_output_path):
-
+    def generate_feature_file(self,report,s_data_frame,f_table,sdrf_path,feature_pqwriter,feature_output_path):
+
+        sample_name = pd.read_csv(sdrf_path,sep='\t',usecols=['source name'],nrows=1)['source name'].values[0].split('-')[0]
         report = report[report["intensity"] != 0]
         report.loc[:,"fragment_ion"] = "NA"
         report.loc[:,"isotope_label_type"] = "L"
@@ -360,6 +361,7 @@ def generate_feature_file(self,report,s_data_frame,f_table,feature_pqwriter,feat
             peptide_score_name + ":" + report["global_qvalue"].astype(str).values + ","
             + "Best PSM PEP:" + report["posterior_error_probability"].astype(str).values
         )
+        report['sample_accession'] = sample_name + '-Sample-' + report['sample_accession'].astype(str).values 
         schema = FeatureHandler()
         feature = FeatureInMemory('LFQ',schema.schema)
         feature._modifications = self._modifications