Enable automatic detection of output format

data/fragpipe_example/ReadMe.md

@@ -15,14 +15,13 @@ To run this example, follow these steps:
 
 **Running PickedGroupFDR**
 
-2. Run the following command (for alternative options see `run_picked_group_fdr.sh`):
+2. Run the following command (for alternatives see `run_picked_group_fdr.sh`):
    ```
    python3 -u -m picked_group_fdr \
       --fasta ./iprg2016_with_labels.fasta \
       --fragpipe_psm ./fragpipe/*/psm.tsv \
       --combined_ion ./fragpipe/combined_ion.tsv \
       --protein_groups_out ./results_from_combined_ion/combined_protein.tsv \
-      --output_format fragpipe \
       --do_quant \
       --lfq_min_peptide_ratios 1 \
       --methods fragpipe
@@ -47,13 +46,48 @@ A quantified protein group result in FragPipe format will be available at `resul
    ```
    This sets the FDR to 100% on all levels, which allows PickedGroupFDR to achieve increased sensitivity over the regular FragPipe results.
 
+
+### Option 2a: reuse IonQuant results
+
 **Running PickedGroupFDR**
 
-5. Run the `run_picked_group_fdr.sh` script. This runs the `picked_group_fdr` and `picked_group_fdr.pipeline.update_fragpipe_results` modules.
+5. Run the following command (for alternatives see `run_picked_group_fdr.sh`):
+   ```
+   python3 -u -m picked_group_fdr \
+      --fasta ./iprg2016_with_labels.fasta \
+      --fragpipe_psm ./fragpipe/*/psm.tsv \
+      --combined_ion ./fragpipe/combined_ion.tsv \
+      --protein_groups_out ./results_from_combined_ion/combined_protein.tsv \
+      --do_quant \
+      --lfq_min_peptide_ratios 1 \
+      --methods fragpipe
+   ```
+
+A quantified protein group result in FragPipe format will be available at `results_from_combined_ion/combined_protein.tsv`.
+
+
+### Option 2b: requantify with IonQuant
+
+**Running PickedGroupFDR**
+
+5. Run the following commands:
+   ```
+   python3 -u -m picked_group_fdr \
+      --fasta ./iprg2016_with_labels.fasta \
+      --fragpipe_psm ./fragpipe/*/psm.tsv \
+      --protein_groups_out ./results/proteinGroups.txt \
+      --methods fragpipe
+   
+   python3 -u -m picked_group_fdr.pipeline.update_fragpipe_results \
+      --fasta ./iprg2016_with_labels.fasta \
+      --fragpipe_psm ./fragpipe/*/psm.tsv \
+      --protein_groups ./results/proteinGroups.txt \
+      --output_folder ./results
+   ```
 
 This will produce a protein grouping result similar to MaxQuant's proteinGroups.txt format at `results/proteinGroups.txt`, as well as updated `psm.tsv` and `protein.tsv` file for each experiment in the `results` folder.
 
-**Running IonQuant (optional)**
+**Running IonQuant**
 
 6. Run the `run_ionquant.sh` script with the path to the FragPipe software directory as the first argument:
    ```

data/fragpipe_example/run_picked_group_fdr.sh

@@ -17,7 +17,6 @@ python3 -u -m picked_group_fdr \
     --fragpipe_psm ${fragpipe_psm_files} \
     --combined_ion ./combined_ion.tsv \
     --protein_groups_out ${RESULT_DIR}/combined_protein.tsv \
-    --output_format fragpipe \
     --do_quant \
     --lfq_min_peptide_ratios 1 \
     --methods fragpipe

picked_group_fdr/picked_group_fdr.py

@@ -1,3 +1,4 @@
+from pathlib import Path
 import sys
 import os
 import logging
@@ -110,9 +111,11 @@ def parse_args(argv):
 
     apars.add_argument(
         "--output_format",
-        default="maxquant",
+        default="auto",
         metavar="PG",
-        help="""Protein groups output format. Options are "maxquant" (proteinGroups.txt 
+        help="""Protein groups output format. Options are "auto", "maxquant" and 
+                "fragpipe". "auto": decide based on input file format, will default to 
+                "maxquant" if no suitable format is known; "maxquant" (proteinGroups.txt
                 format) and "fragpipe" (combined_protein.tsv format).""",
     )
 
@@ -226,6 +229,9 @@ def write_protein_groups(
         else:
             label = label.lower().replace(" ", "_")
         protein_groups_out = f"{base}_{label}{ext}"
+
+    Path(protein_groups_out).parent.mkdir(parents=True, exist_ok=True)
+
     protein_groups_writer.write(protein_group_results, protein_groups_out)
     logger.info(f"Protein group results have been written to: {protein_groups_out}")
 
@@ -544,8 +550,13 @@ def do_quantification(
 
     logger.info("Preparing for quantification")
 
+    score_origin = score_type.score_origin.long_description().lower()
+    if args.output_format == "auto" and score_origin in ["maxquant", "fragpipe"]:
+        args.output_format = score_origin
+
     protein_groups_writer = writers.get_protein_groups_output_writer(
         protein_group_results,
+        args.output_format,
         args,
         protein_annotations,
         parse_id,

picked_group_fdr/pipeline/sage_quantification.py

@@ -122,6 +122,7 @@ def main(argv):
 
     protein_groups_writer = writers.get_protein_groups_output_writer(
         protein_group_results,
+        args.output_format,
         args,
         protein_annotations,
         parse_id,

picked_group_fdr/writers/factory.py

@@ -15,6 +15,7 @@
 
 def get_protein_groups_output_writer(
     protein_group_results: results.ProteinGroupResults,
+    output_format: str,
     args: argparse.Namespace,
     protein_annotations: Dict[str, protein_annotation.ProteinAnnotation],
     parse_id: Callable,