use the new mass lists

src/depiction_targeted_preproc/example/run.py

@@ -97,15 +97,22 @@ def export_results(
             shutil.copy(work_dir / sample_name / file, output_dir / sample_name / file)
 
 
-def initial_setup(input_imzml: Path, input_mass_list: Path, params_file: Path, dir: Path, force: bool = False) -> None:
+def initial_setup(
+    input_imzml: Path,
+    input_mass_list: Path,
+    params_file: Path,
+    dir: Path,
+    force: bool = False,
+    mass_list_filename: str = "images_default_mass_list.csv",
+) -> None:
     if not force and (dir / "raw.imzML").exists():
         logger.info("Skipping initial setup, directory already exists: {dir}", dir=dir)
     else:
         logger.info("Setting up directory: {dir}", dir=dir)
         dir.mkdir(exist_ok=True, parents=True)
         shutil.copy(input_imzml, dir / "raw.imzML")
         shutil.copy(input_imzml.with_suffix(".ibd"), dir / "raw.ibd")
-        shutil.copy(input_mass_list, dir / "images_default_mass_list.csv")
+        shutil.copy(input_mass_list, dir / mass_list_filename)
         shutil.copy(params_file, dir / "pipeline_params.yml")
 
 

src/depiction_targeted_preproc/example_compare/run_compare.py

@@ -12,7 +12,7 @@ def get_configs() -> dict[str, Path]:
 
 
 def prepare_tasks(input_imzml_path: Path, work_dir: Path) -> list[Path]:
-    input_mass_list = input_imzml_path.parent / "mass_list_vend.csv"
+    input_mass_list = input_imzml_path.parent / "mass_list.raw.csv"
     folders = set_up_work_dir(work_dir, input_imzml_path, input_mass_list)
     requested_files = get_all_output_files(folders)
 
@@ -34,7 +34,7 @@ def main() -> None:
     for imzml in imzmls:
         requested_files += prepare_tasks(data_raw_dir / imzml, work_dir=work_dir)
 
-    SnakemakeInvoke().invoke(work_dir=work_dir, result_files=requested_files, n_cores=1)
+    SnakemakeInvoke().invoke(work_dir=work_dir, result_files=requested_files, n_cores=2)
 
 
 def get_all_output_files(folders: list[Path]) -> list[Path]:
@@ -55,7 +55,13 @@ def set_up_work_dir(work_dir: Path, input_imzml: Path, input_mass_list: Path) ->
     sample_name = input_imzml.stem
     for config_name, config_path in configs.items():
         dir = work_dir / sample_name / config_name
-        initial_setup(input_imzml=input_imzml, input_mass_list=input_mass_list, params_file=config_path, dir=dir)
+        initial_setup(
+            input_imzml=input_imzml,
+            input_mass_list=input_mass_list,
+            params_file=config_path,
+            dir=dir,
+            mass_list_filename="mass_list.raw.csv",
+        )
         folders.append(dir)
     return folders
 

src/depiction_targeted_preproc/workflow/exp/mass_list_preparation.py

@@ -0,0 +1,36 @@
+from pathlib import Path
+from typing import Annotated
+
+import polars as pl
+import typer
+from typer import Option
+
+
+def exp_mass_list_preparation(
+    input_csv_path: Annotated[Path, Option()],
+    out_calibration_csv_path: Annotated[Path, Option()],
+    out_standards_csv_path: Annotated[Path, Option()],
+    out_visualization_csv_path: Annotated[Path, Option()],
+) -> None:
+    input_df = pl.read_csv(input_csv_path)
+
+    # rename cols
+    input_df = input_df.rename({"Marker": "label", "PC-MT (M+H)+": "mass"}).drop("No.")
+
+    # add tol column
+    visualization_df = input_df.with_columns(tol=pl.lit(0.25))
+
+    # for the calibration remove the CHCA peaks, they have names starting with CHCA
+    calibration_df = visualization_df.filter(~pl.col("name").str.starts_with("CHCA"))
+
+    # for the standards csv only keep the "standard" peaks
+    standards_df = visualization_df.filter(pl.col("name").str.to_lowercase().contains("standard"))
+
+    # write the results
+    calibration_df.write_csv(out_calibration_csv_path)
+    standards_df.write_csv(out_standards_csv_path)
+    visualization_df.write_csv(out_visualization_csv_path)
+
+
+if __name__ == "__main__":
+    typer.run(exp_mass_list_preparation)

src/depiction_targeted_preproc/workflow/experimental.smk

@@ -15,4 +15,18 @@ rule exp_compare_cluster_stats:
     shell:
         "python -m depiction_targeted_preproc.workflow.exp.compare_cluster_stats"
         " {input.csv}"
-        " --output-pdf {output}"
+        " --output-pdf {output}"
+
+rule exp_mass_list_preparation:
+    input:
+        csv="{sample}/mass_list.raw.csv"
+    output:
+        calibration_csv="{sample}/mass_list.calibration.csv",
+        standards_csv="{sample}/mass_list.standards.csv",
+        visualization="{sample}/mass_list.visualization.csv"
+    shell:
+        "python -m depiction_targeted_preproc.workflow.exp.mass_list_preparation"
+        " --input-csv-path {input.csv}"
+        " --out-calibration-csv {output.calibration_csv}"
+        " --out-standards-csv {output.standards_csv}"
+        " --out-visualization {output.visualization}"

src/depiction_targeted_preproc/workflow/rules/rules_proc.smk

@@ -27,7 +27,7 @@ rule proc_calibrate_remove_global_shift:
     input:
         imzml=multiext("{sample}/corrected.peaks",".imzML",".ibd"),
         config="{sample}/pipeline_params.yml",
-        mass_list="{sample}/images_default_mass_list.csv",
+        mass_list="{sample}/mass_list.standards.csv",
     output:
         imzml=temp(multiext("{sample}/calibrated.tmp",".imzML",".ibd")),
     shell:
@@ -40,7 +40,7 @@ rule proc_calibrate_actual:
     input:
         imzml=multiext("{sample}/calibrated.tmp",".imzML",".ibd"),
         config="{sample}/pipeline_params.yml",
-        mass_list="{sample}/images_default_mass_list.csv",
+        mass_list="{sample}/mass_list.calibration.csv",
     output:
         imzml=multiext("{sample}/calibrated",".imzML",".ibd"),
         calib_data="{sample}/calib_data.hdf5",

src/depiction_targeted_preproc/workflow/rules/rules_qc.smk

@@ -1,7 +1,7 @@
 rule qc_table_marker_distances_baseline:
     input:
         imzml=multiext("{sample}/corrected.peaks",".imzML",".ibd"),
-        mass_list="{sample}/images_default_mass_list.csv",
+        mass_list="{sample}/mass_list.visualization.csv",
     output:
         table="{sample}/qc/table_marker_distances_baseline.parquet"
     shell:
@@ -12,7 +12,7 @@ rule qc_table_marker_distances_baseline:
 rule qc_table_marker_distances_calib:
     input:
         imzml_peaks="{sample}/calibrated.imzML",
-        mass_list="{sample}/images_default_mass_list.csv",
+        mass_list="{sample}/mass_list.visualization.csv",
     output:
         table="{sample}/qc/table_marker_distances_calib.parquet"
     shell:
@@ -76,7 +76,7 @@ rule qc_plot_peak_density_grouped:
 rule qc_plot_calibration_map:
     input:
         calib_data="{sample}/calib_data.hdf5",
-        mass_list="{sample}/images_default_mass_list.csv",
+        mass_list="{sample}/mass_list.visualization.csv",
     output:
         pdf="{sample}/qc/plot_calibration_map.pdf"
     shell:
@@ -89,7 +89,7 @@ rule qc_plot_sample_spectra_before_after:
     input:
         imzml_baseline="{sample}/peaks.imzML",
         imzml_calib="{sample}/calibrated.imzML",
-        mass_list="{sample}/images_default_mass_list.csv",
+        mass_list="{sample}/mass_list.visualization.csv",
     output:
         pdf="{sample}/qc/plot_sample_spectra_before_after.pdf"
     shell:

src/depiction_targeted_preproc/workflow/rules/rules_vis.smk

@@ -2,9 +2,9 @@ rule vis_images:
     input:
         imzml=multiext("{sample}/calibrated",".imzML",".ibd"),
         config="{sample}/pipeline_params.yml",
-        mass_list="{sample}/images_{label}_mass_list.csv"
+        mass_list="{sample}/mass_list.visualization.csv"
     output:
-        hdf5="{sample}/images_{label}.hdf5"
+        hdf5="{sample}/images_default.hdf5"
     shell:
         "python -m depiction_targeted_preproc.workflow.vis.images "
         " --imzml-path {input.imzml[0]} --mass-list-path {input.mass_list} "