add dry-run option

Author: msarkis-icr

pages/run_pipeline.py

@@ -84,6 +84,7 @@ def reset_button_state():
     )
 WORK_DIR = st.text_input("Working directory", value=WORK_DIR or SCRATCH)
 OUTPUT_DIR = st.text_input("Output directory", value=OUTPUT_DIR or SCRATCH)
+dry_run = st.checkbox("Dry run (do not execute the job)", value=False)
 
 # passing inputs between tabs
 if OK:
@@ -96,7 +97,8 @@ def reset_button_state():
         work_dir=WORK_DIR,
         output_dir=OUTPUT_DIR,
         custom_sample_list=custom_sample_list,
-        bed_file=BED_FILE
+        bed_file=BED_FILE,
+        dry_run=dry_run
     )
     save_in_ss(
         {

shared/command_helper.py

@@ -28,7 +28,8 @@ def pipe_cmd(
     work_dir="work",
     output_dir="output",
     custom_sample_list=[],
-    bed_file=""
+    bed_file="",
+    dry_run=False
 ):
     def get_pipeline_command():
         """Generate the pipeline execution command based on the sample selection."""
@@ -37,17 +38,19 @@ def get_pipeline_command():
         # not sure if this is the best thing-using job id for filenamne
         log_out = f"{work_dir}/logs/%j.out"
         log_err = f"{work_dir}/logs/%j.err"
-
-        args = []
+        
+        args = [path_to_script]
         base_cmd = f"sbatch -o {log_out} -e {log_err}"
 
         if selected_samples == "demo":
-            args = [path_to_script, work_dir, output_dir]
+            args += [work_dir, output_dir]
 
-        elif selected_samples == "all":
+        elif selected_samples == "all":#I removed this option
             #./your_script.sh --env "/my/custom/env" --work-dir "my_work" --outdir "my_output" --config "my_config" --params "parans.json" --bed file.bed
-            args = [
-                path_to_script,
+            if dry_run:
+                args.append("--dry-run")
+
+            args += [
                 "--work-dir", work_dir,
                 "--outdir", output_dir,
             ]
@@ -57,17 +60,16 @@ def get_pipeline_command():
         elif selected_samples == "customised":
             if not custom_sample_list:
                 raise ValueError("custom_sample_list cannot be empty")
-            args = [
-                path_to_script,
+            if dry_run:
+                args.append("--dry-run")
+            args += [
                 "--work-dir", work_dir,
                 "--outdir", output_dir,
                 "--samples", "\t".join(custom_sample_list),
             ]
             if bed_file:
                 args += ["--bed", bed_file]
-        # elif selected_samples == "test": #this will become dry-run, but I should develop it for all scripts
-        #     cmd_pipeline += f"sbatch  -o {log_out} -e {log_err} /data/scratch/DCO/DIGOPS/SCIENCOM/msarkis/NF-project-configurations/test.sh --work-dir {work_dir} --outdir {output_dir}"
- 
+
         preamble = f"""
         mkdir -p {work_dir}/logs
         cd {work_dir}

tabs/tab_command.py

@@ -15,7 +15,8 @@ def tab(
     work_dir="work",
     output_dir="output",
     custom_sample_list=[],
-    bed_file=""
+    bed_file="",
+    dry_run=False
 ):
     # --- Initialize session state ---
     st.session_state.setdefault("username", username)
@@ -47,7 +48,8 @@ def run_nextflow():
             output_dir=output_dir,
             work_dir=work_dir,
             custom_sample_list=custom_sample_list,
-            bed_file=bed_file
+            bed_file=bed_file,
+            dry_run=dry_run
         )
         st.code(cmd_pipeline)
         result = MY_SSH.run_cmd(cmd_pipeline)