Merge branch 'main' into feature/gzip

Author: RalfG

.github/workflows/test.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.10", "3.11"]
     steps:
       - uses: actions/checkout@v4
 

README.md

@@ -47,8 +47,7 @@ timsTOF fragmentation and IM2Deep for ion mobility separation. Bruker .d and min
 files are directly supported through the [timsrust](https://github.com/MannLabs/timsrust) library.
 
 Checkout our [preprint](https://doi.org/10.1101/2024.05.29.596400) for more information and the
-[TIMS²Rescore documentation](https://ms2rescore.readthedocs.io/en/stable/userguide/tims2rescore)
-to get started.
+[TIMS²Rescore documentation][tims2rescore] to get started.
 
 ## Citing
 
@@ -99,15 +98,16 @@ make a [pull request][pr]!
 [issues]: https://github.com/compomics/ms2rescore/issues/
 [discussions]: https://github.com/compomics/ms2rescore/discussions/
 [pr]: https://github.com/compomics/ms2rescore/pulls/
-[desktop]: https://ms2rescore.readthedocs.io/gui.html
+[desktop]: https://ms2rescore.readthedocs.io/en/stable/gui/
 [desktop-installer]: https://github.com/compomics/ms2rescore/releases/latest
-[cli]: https://ms2rescore.readthedocs.io/cli/cli.html
-[python-package]: https://ms2rescore.readthedocs.io/api/ms2rescore.html
-[docker]: https://ms2rescore.readthedocs.io/installation.html#docker-container
+[cli]: https://ms2rescore.readthedocs.io/en/stable/cli/
+[python-package]: https://ms2rescore.readthedocs.io/en/stable/api/ms2rescore/
+[docker]: https://ms2rescore.readthedocs.io/en/stable/installation#docker-container
 [publication-branch]: https://github.com/compomics/ms2rescore/tree/pub
 [ms2pip]: https://github.com/compomics/ms2pip
 [deeplc]: https://github.com/compomics/deeplc
 [percolator]: https://github.com/percolator/percolator/
 [mokapot]: https://mokapot.readthedocs.io/
 [psm_utils]: https://github.com/compomics/psm_utils
 [file-formats]: https://psm-utils.readthedocs.io/en/stable/#supported-file-formats
+[tims2rescore]: https://ms2rescore.readthedocs.io/en/stable/userguide/tims2Rescore

docs/source/config_schema.md

@@ -67,6 +67,7 @@
     - **One of**
       - *string*
       - *null*
+  - **`write_flashlfq`** *(boolean)*: Write results to a FlashLFQ-compatible file. Default: `false`.
   - **`write_report`** *(boolean)*: Write an HTML report with various QC metrics and charts. Default: `false`.
   - **`profile`** *(boolean)*: Write a txt report using cProfile for profiling. Default: `false`.
 ## Definitions
@@ -93,7 +94,6 @@
   - **`train_fdr`** *(number)*: FDR threshold for training Mokapot. Minimum: `0`. Maximum: `1`. Default: `0.01`.
   - **`write_weights`** *(boolean)*: Write Mokapot weights to a text file. Default: `false`.
   - **`write_txt`** *(boolean)*: Write Mokapot results to a text file. Default: `false`.
-  - **`write_flashlfq`** *(boolean)*: Write Mokapot results to a FlashLFQ-compatible file. Default: `false`.
 - <a id="definitions/percolator"></a>**`percolator`** *(object)*: Percolator rescoring engine configuration. Can contain additional properties. Refer to *[#/definitions/rescoring_engine](#definitions/rescoring_engine)*.
   - **`init-weights`**: Weights file for scoring function. Default: `false`.
     - **One of**

docs/source/userguide/configuration.rst

@@ -244,13 +244,13 @@ expression pattern that extracts the decoy status from the protein name:
 
   .. code-block:: json
 
-    "decoy_pattern": "DECOY_"
+    "id_decoy_pattern": "DECOY_"
 
 .. tab:: TOML
 
     .. code-block:: toml
 
-      decoy_pattern = "DECOY_"
+      id_decoy_pattern = "DECOY_"
 
 
 Multi-rank rescoring

examples/msgfplus-ms2rescore.json

@@ -7,9 +7,6 @@
         },
         "log_level": "debug",
         "processes": 16,
-        "feature_generators": {
-            "basic": {}
-        },
         "rescoring_engine": {
             "mokapot": {
                 "fasta_file": "examples/proteins/uniprot-proteome-human-contaminants.fasta",

examples/msgfplus-ms2rescore.toml

@@ -5,25 +5,7 @@ psm_reader_kwargs = { "score_column" = "PSMScore" }
 log_level = "debug"
 processes = 16
 
-# [ms2rescore.modification_mapping]
-
-# [ms2rescore.fixed_modifications]
-
-[ms2rescore.feature_generators.basic]
-# No options, but setting heading enables feature generator
-
-# [ms2rescore.feature_generators.ms2pip]
-# model = "HCD"
-# ms2_tolerance = 0.02
-
-# [ms2rescore.feature_generators.deeplc]
-# deeplc_retrain = false
-
-# [ms2rescore.feature_generators.maxquant]
-# No options, but setting heading enables feature generator
-
 [ms2rescore.rescoring_engine.mokapot]
 fasta_file = "examples/proteins/uniprot-proteome-human-contaminants.fasta"
 write_weights = true
 write_txt = true
-# write_flashlfq = true

ms2rescore/__init__.py

@@ -1,6 +1,6 @@
 """MS²Rescore: Sensitive PSM rescoring with predicted MS² peak intensities and RTs."""
 
-__version__ = "3.1.1"
+__version__ = "3.1.2"
 
 from warnings import filterwarnings
 

ms2rescore/core.py

@@ -163,6 +163,16 @@ def rescore(configuration: Dict, psm_list: Optional[PSMList] = None) -> None:
     logger.info(f"Writing output to {output_file_root}.psms.tsv...")
     psm_utils.io.write_file(psm_list, output_file_root + ".psms.tsv", filetype="tsv")
 
+    if config["write_flashlfq"]:
+        logger.info(f"Writing output to {output_file_root}.flashlfq.tsv...")
+        psm_utils.io.write_file(
+            psm_list,
+            output_file_root + ".flashlfq.tsv",
+            filetype="flashlfq",
+            fdr_threshold=0.01,
+            only_target=True,  # TODO: Make FDR threshold configurable
+        )
+
     # Write report
     if config["write_report"]:
         try:

ms2rescore/feature_generators/deeplc.py

@@ -139,7 +139,7 @@ def add_features(self, psm_list: PSMList) -> None:
 
                 # Disable wild logging to stdout by Tensorflow, unless in debug mode
                 with contextlib.redirect_stdout(
-                    open(os.devnull, "w")
+                    open(os.devnull, "w", encoding="utf-8")
                 ) if not self._verbose else contextlib.nullcontext():
                     # Make new PSM list for this run (chain PSMs per spectrum to flat list)
                     psm_list_run = PSMList(psm_list=list(chain.from_iterable(psms.values())))