major refactoring about ms2rescore and pyarrow

.github/workflows/conda-build.yml

@@ -20,7 +20,7 @@ jobs:
         cache-downloads: true
         auto-update-conda: false
         activate-environment: test
-        python-version: "3.10"
+        python-version: "3.9"
 
     - name: Setup conda-build and anaconda-client
       run: |

.github/workflows/python-app.yml

@@ -39,11 +39,4 @@ jobs:
         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
     - name: Test with pytest
       run: |
-        poetry run pytest
-    - name: Download test data
-      run: |
-        wget https://ftp.pride.ebi.ac.uk/pub/databases/pride/resources/proteomes/quantms-ci-github/quantms-utils/TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01.mzML
-        wget https://ftp.pride.ebi.ac.uk/pub/databases/pride/resources/proteomes/quantms-ci-github/quantms-utils/TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01_comet.idXML
-    - name: Test percolator ms2rescore
-      run: |
-        quantmsutilsc ms2rescore --psm_file TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01_comet.idXML --spectrum_path TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01.mzML --processes 2 --ms2pip_model HCD2021 --feature_generators 'ms2pip,deeplc' --id_decoy_pattern ^rev --test_fdr 0.05
+        poetry run pytest

README.md

@@ -27,10 +27,6 @@ The following functionalities are available in the package:
 - `openms2sample` - Extra sample information from OpenMS experimental design file. An example of OpenMS experimental design file is available [here](https://github.com/bigbio/quantms-utils/blob/dev/tests/test_data/BSA_design_urls.tsv).
 - `checksamplesheet` - Check the sample sheet for errors and inconsistencies. The experimental design coult be an OpenMS experimental design file or and SDRF file. 
 
-### ms2rescore scripts
-
-- `ms2rescore` - Rescore MS2 spectra using the MS2PIP model. The output is a mzML file with the rescored MS2 spectra.
-
 ### Features to percolator scripts
 
 - `sage2feature` - The add_sage_feature function enhances an idXML file by appending additional features from a Sage feature table, excluding those generated by 'psm_file'.

environment.yml

@@ -7,13 +7,7 @@ channels:
 dependencies:
   - click
   - sdrf-pipelines>=0.0.31
-  - pyopenms>=2.4.0
+  - pyopenms
   - pandas
-  - numpy
   - pyarrow
-  - ms2rescore=3.0.3
-  - deepLC=2.2.38
-  - psm-utils=0.8.3
-  - scipy=1.13.1
-  - pygam
-  - protobuf=3.19.6
+  - scipy

pyproject.toml

@@ -3,7 +3,7 @@ name = "quantms-utils"
 description = "Python scripts and helpers for the quantMS workflow"
 readme = "README.md"
 license = "MIT"
-version = "0.0.16"
+version = "0.0.17"
 authors = [
     "Yasset Perez-Riverol <[email protected]>",
     "Dai Chengxin <[email protected]>",
@@ -29,19 +29,13 @@ packages = [
 ]
 
 [tool.poetry.dependencies]
-python = ">=3.8,<3.11"
+python = "*"
 click = "*"
 sdrf-pipelines = ">=0.0.31"
-pyopenms = ">=2.4.0"
-ms2rescore = "3.0.3"
+pyopenms = "*"
 pandas = "*"
-numpy = "*"
 pyarrow = "*"
-psm-utils = "0.8.3"
-deepLC = "2.2.38"
-scipy = "1.13.1"
-pygam = "*"
-protobuf= "3.19.6"
+scipy = "*"
 
 [tool.poetry.urls]
 GitHub = "https://github.com/bigbio/quantms-utils"

quantmsutils/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.16"
+__version__ = "0.0.17"

quantmsutils/mzml/mzml_statistics.py

@@ -139,8 +139,8 @@ def _write_batch(self):
                     where=self.output_path, schema=self.parquet_schema, compression="gzip"
                 )
 
-            # Create a RecordBatch directly from the current batch
-            batch = pa.RecordBatch.from_pylist(self.batch_data, schema=self.parquet_schema)
+            # Create a Table directly from the current batch
+            batch = pa.Table.from_pylist(self.batch_data, schema=self.parquet_schema)
 
             # Write the batch directly
             self.parquet_writer.write_batch(batch)
@@ -158,7 +158,7 @@ def _write_batch(self):
                         compression="gzip",
                     )
 
-                id_batch = pa.RecordBatch.from_pylist(
+                id_batch = pa.Table.from_pylist(
                     self.psm_parts, schema=self.id_parquet_schema
                 )
                 self.id_parquet_writer.write_batch(id_batch)

quantmsutils/quantmsutilsc.py

@@ -5,7 +5,6 @@
 from quantmsutils.features.sage_feature import add_sage_feature
 from quantmsutils.mzml.mzml_statistics import mzml_statistics
 from quantmsutils.psm.psm_conversion import convert_psm
-from quantmsutils.rescoring.ms2rescore import ms2rescore
 from quantmsutils.sdrf.check_samplesheet import checksamplesheet
 from quantmsutils.sdrf.extract_sample import extract_sample_from_expdesign
 from quantmsutils.features.snr import spectrum2feature
@@ -28,7 +27,6 @@ def cli():
 cli.add_command(mzml_statistics)
 cli.add_command(extract_sample_from_expdesign)
 cli.add_command(checksamplesheet)
-cli.add_command(ms2rescore)
 cli.add_command(convert_psm)
 cli.add_command(spectrum2feature)