Merge pull request #39 from bigbio/dev

major refactoring about ms2rescore and pyarrow

Author: ypriverol

.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: "3.12"
 
     - 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

.gitignore

@@ -162,3 +162,7 @@ cython_debug/
 *_df.csv
 *.tsv
 /tests/test_data/hMICAL1_coiPAnP-N2-200_3Murea-1Mthiourea-200mMtcep_14733.d/
+/tests/test_data/diann2mztab/RD139_Narrow_UPS1_0_1fmol_inj1.mzML
+/tests/test_data/diann2mztab/RD139_Narrow_UPS1_0_1fmol_inj2.mzML
+/tests/test_data/diann2mztab/RD139_Narrow_UPS1_0_25fmol_inj1.mzML
+/tests/test_data/diann2mztab/RD139_Narrow_UPS1_0_25fmol_inj2.mzML

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>=3.2.0
   - 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
+  - pyarrow>=16.1.0
+  - 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 = ">=3.2.0"
 pandas = "*"
-numpy = "*"
-pyarrow = "*"
-psm-utils = "0.8.3"
-deepLC = "2.2.38"
-scipy = "1.13.1"
-pygam = "*"
-protobuf= "3.19.6"
+pyarrow = ">=16.1.0"
+scipy = "*"
 
 [tool.poetry.urls]
 GitHub = "https://github.com/bigbio/quantms-utils"

quantmsutils/__init__.py

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