Added some logging to dev version

src/SOPRANO/R/parse_vcf.R

@@ -1,4 +1,5 @@
 library(magrittr)
+library(dplyr)
 
 paste("parse_vcf.R")
 

src/SOPRANO/app.py

@@ -261,6 +261,7 @@ def with_tab_annotator(tab: DeltaGenerator):
         vcf_definition_method_selection = st.radio(
             "Method for defining VCF files to annoatate:",
             options=AnnotatorUIOptions.vcf_definition_method(),
+            index=1
         )
 
         if vcf_definition_method_selection == "File uploader":
@@ -320,7 +321,10 @@ def with_tab_annotator(tab: DeltaGenerator):
                 output_name=name_processed,
                 assembly=assembly_processed,
             )
-            st.text(f"Processed sources @ {vcf_dir_processed}")
+
+            output = Directories.app_annotated_inputs()
+            st.text(f"Completed. Processed sources @ {vcf_dir_processed}")
+            st.write(f"Output annotated file to {output}{name_processed}")            
             anno_cache.clean_up()
 
 

src/SOPRANO/core/objects.py

@@ -282,7 +282,7 @@ def __init__(
 
     def log(self, msg: str) -> None:
         self.logger.info(msg)
-
+        
 
 class GlobalParameters:
     def __init__(
@@ -299,6 +299,7 @@ def __init__(
         genomes: GenomePaths,
         n_samples: int,
     ):
+        print("Global params")
         # Sanitized
         self.job_cache = check_cache_path(job_cache, analysis_name)
         self.seed = GlobalParameters.check_seed(seed)
@@ -389,7 +390,7 @@ def gather(self):
         sample_results_paths = [
             self.get_sample(idx).results_path for idx in range(self.n_samples)
         ]
-
+                
         for expected_results_path in sample_results_paths:
             if not expected_results_path.exists():
                 warnings.warn(
@@ -401,35 +402,37 @@ def gather(self):
                 sample_results_paths.remove(expected_results_path)
 
         if len(sample_results_paths) == 0:
-            raise ValueError(f"No sample results found for {self.job_cache}.")
-
-        joined_df: pd.DataFrame | None = None
-
-        with open(self.samples_meta_path, "w") as f:
-            for path in sample_results_paths:
-                if joined_df is None:
-                    joined_df = pd.read_csv(path, sep="\t")
-                else:
-                    joined_df = pd.concat(
-                        [joined_df, pd.read_csv(path, sep="\t")],
-                        ignore_index=True,
-                    )
-
-                f.write(f"{path.as_posix()}\n")
-
-        # Dropped estimateed statistics... don't mean much in this context
-        joined_df.drop(
-            columns=[
-                "ON_Low_CI",
-                "ON_High_CI",
-                "OFF_Low_CI",
-                "OFF_High_CI",
-                "Pvalue",
-            ]
-        )
+            print("Expected results paths:",sample_results_paths)
+            #raise ValueError(f"No sample results found for {self.job_cache}.")        
+            print(f"No sample results found for {self.job_cache}.")        
+        else:
+            joined_df: pd.DataFrame | None = None
+
+            with open(self.samples_meta_path, "w") as f:
+                for path in sample_results_paths:
+                    if joined_df is None:
+                        joined_df = pd.read_csv(path, sep="\t")
+                    else:
+                        joined_df = pd.concat(
+                            [joined_df, pd.read_csv(path, sep="\t")],
+                            ignore_index=True,
+                        )
+
+                    f.write(f"{path.as_posix()}\n")
+
+            # Dropped estimateed statistics... don't mean much in this context
+            joined_df.drop(
+                columns=[
+                    "ON_Low_CI",
+                    "ON_High_CI",
+                    "OFF_Low_CI",
+                    "OFF_High_CI",
+                    "Pvalue",
+                ]
+            )
 
-        joined_df.to_csv(self.samples_path)
-        self.plot_hist()
+            joined_df.to_csv(self.samples_path)
+            self.plot_hist()
 
     @staticmethod
     def split_joined_df(

src/SOPRANO/pipeline.py

@@ -556,7 +556,8 @@ def _apply(self, params: Parameters):
         tar_and_compress(params)
 
 
-def run_pipeline(params: Parameters):
+def run_pipeline(params: Parameters, tidy=True):
+    print("Running pipeline")
     jobs: List[_PipelineComponent] = [FilterTranscripts()]
 
     if params.use_random_regions:
@@ -594,7 +595,8 @@ def run_pipeline(params: Parameters):
     jobs.append(CheckTargetMutations())
     jobs.append(ComputeIntronRate())
     jobs.append(ComputeStatistics())
-    #jobs.append(TidyUp())
+    if tidy:
+        jobs.append(TidyUp())
 
     for job in jobs:
         job.apply(params)

src/SOPRANO/utils/anno_utils.py

@@ -76,6 +76,12 @@ def annotate_source(
     replace_existing: str = "N",
 ):
     print("------------- Annotating source -------------")
+    print(f"Source path: {source_path}")
+    print(f"Assembly: {assembly}")
+    print(f"Output name: {output_name}")
+    print(f"Cache directory: {cache_directory}")
+    print(f"Skip missing: {skip_missing}")
+    print(f"Replace existing: {replace_existing}")
     vcf_paths = find_vcf_files(source_path)
 
     bskip_missing = skip_missing.upper() == "Y"

src/SOPRANO/utils/app_utils.py

@@ -636,11 +636,11 @@ def pipeline(params: Parameters):
 
         params.cache_dir.mkdir(exist_ok=True)
         output = st.empty()
-        with st_capture(output.code):
+        with st_capture(output.code):            
             t_start = time()
             output = st.empty()
             with st_capture(output.code):
-                run_pipeline(params)
+                run_pipeline(params,tidy=False)
                 print("Tidying files...")
         TidyUp()
         t_end = time()        
@@ -705,7 +705,7 @@ def annotate(
             "Annotation in progress ... please wait until this "
             "process has finished."
         )
-
+                
         output = st.empty()
         with st_capture(output.code):                                                
             all_annotated_paths = anno_utils.annotate_source(
@@ -714,6 +714,7 @@ def annotate(
                 cache_directory=Directories.app_annotated_inputs(),
                 assembly=assembly,
                 skip_missing="Y",
+                replace_existing="Y",
             )
 
             running_msg.empty()

src/SOPRANO/utils/path_utils.py

@@ -4,6 +4,7 @@
 # Repo and source roots
 _SOPRANO_SRC = pathlib.Path(__file__).parent.parent
 _SOPRANO_REPO = _SOPRANO_SRC.parent.parent
+print("SOPRANO repo =",_SOPRANO_SRC)
 
 # Source directories
 _SOPRANO_SCRIPTS = _SOPRANO_SRC / "scripts"