Merge pull request #22 from bigbio/dev

Minor changes

.gitignore

@@ -158,6 +158,6 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
-*.tsv
 *.csv
 *_df.csv
+*.tsv

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "quantms-utils"
-version = "0.0.2"
+version = "0.0.7"
 description = "Python scripts and helpers for the quantMS workflow"
 authors = ["Yasset Perez-Riverol", "Dai Chengxin"]
 packages = [

quantmsutils/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.6"
+__version__ = "0.0.7"

quantmsutils/diann/diann2mztab.py

@@ -60,7 +60,7 @@ def diann2mztab(
     :param ctx: Click context
     :param folder: DiannConvert specifies the folder where the required file resides. The folder contains
         the DiaNN main report, protein matrix, precursor matrix, experimental design file, protein sequence
-        FASTA file, version file of DiaNN and ms_info TSVs
+        FASTA file, version file of DiaNN and ms_info parquet
     :param exp_design: Experimental design file
     :param dia_params: A list contains DIA parameters
     :type dia_params: list
@@ -342,7 +342,7 @@ def fasta(self) -> os.PathLike:
 
     @property
     def ms_info(self) -> os.PathLike:
-        return self.find_first_file_with_suffix("ms_info.tsv")
+        return self.find_first_file_with_suffix("ms_info.parquet")
 
     @property
     def diann_version(self) -> str:
@@ -1064,7 +1064,7 @@ def mztab_psh(report, folder, database):
     :type report: pandas.core.frame.DataFrame
     :param folder: DiannConvert specifies the folder where the required file resides. The folder contains
         the DiaNN main report, protein matrix, precursor matrix, experimental design file, protein sequence
-        FASTA file, version file of DiaNN and ms_info TSVs
+        FASTA file, version file of DiaNN and ms_info parquet
     :type folder: str
     :param database: Path to fasta file
     :type database: str
@@ -1075,8 +1075,8 @@ def mztab_psh(report, folder, database):
 
     def __find_info(directory, n):
         # This line matches n="220101_myfile", folder="." to
-        # "myfolder/220101_myfile_ms_info.tsv"
-        files = list(Path(directory).rglob(f"{n}_ms_info.tsv"))
+        # "myfolder/220101_myfile_ms_info.parquet"
+        files = list(Path(directory).rglob(f"{n}_ms_info.parquet"))
         # Check that it matches one and only one file
         if not files:
             raise ValueError(f"Could not find {n} info file in {directory}")
@@ -1094,7 +1094,7 @@ def __find_info(directory, n):
             n = n[0]
 
         file = __find_info(folder, n)
-        target = pd.read_csv(file, sep="\t")
+        target = pd.read_parquet(file)
         group.sort_values(by="RT.Start", inplace=True)
         target = target[["Retention_Time", "SpectrumID", "Exp_Mass_To_Charge"]]
         target.columns = [

quantmsutils/rescoring/ms2rescore.py

@@ -294,6 +294,7 @@ def ms2rescore(
 ):
     """
     Rescore PSMs in an idXML file and keep other information unchanged.
+    :param ms2pip_model_dir: Folder for models.
     :param ctx: Click context object
     :param psm_file: PSM file (idXML)
     :param spectrum_path: Spectrum file or dictionary with spectrum files (MGF/mzML)

tests/test_data/diann2mztab/PXD026600.sdrf_openms_design.tsv

@@ -0,0 +1,9 @@
+Fraction_Group	Fraction	Spectra_Filepath	Label	Sample
+1	1	RD139_Narrow_UPS1_0_1fmol_inj1.mzML	1	1
+2	1	RD139_Narrow_UPS1_0_1fmol_inj2.mzML	1	1
+3	1	RD139_Narrow_UPS1_0_25fmol_inj1.mzML	1	2
+4	1	RD139_Narrow_UPS1_0_25fmol_inj2.mzML	1	2
+
+Sample	MSstats_Condition	MSstats_BioReplicate
+1	CT=Mixture;CN=UPS1;QY=0.1 fmol	1
+2	CT=Mixture;CN=UPS1;QY=0.25 fmol	2