Merge pull request #12 from bigbio/dev

Major changes - including all sync from quantms

environment.yml

@@ -6,7 +6,7 @@ channels:
   - conda-forge
 dependencies:
   - click
-  - sdrf-pipelines>=0.0.28
+  - sdrf-pipelines>=0.0.29
   - pyopenms
   - ms2rescore=3.0.2
   - psm-utils=0.8.0

quantmsutils/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.3"
+__version__ = "0.0.3"

quantmsutils/mzml/mzml_statistics.py

@@ -132,7 +132,11 @@ def parse_mzml(file_name: str, file_columns: list, id_only: bool = False):
         if id_only and len(psm_part_info) > 0:
             pd.DataFrame(
                 psm_part_info, columns=["scan", "ms_level", "mz", "intensity"]
-            ).to_parquet(f"{Path(ms_path).stem}_spectrum_df.parquet", index=False, compression="gzip")
+            ).to_parquet(
+                f"{Path(ms_path).stem}_spectrum_df.parquet",
+                index=False,
+                compression="gzip",
+            )
 
         return pd.DataFrame(info, columns=file_columns)
 
@@ -227,5 +231,8 @@ def parse_bruker_d(file_name: str, file_columns: list):
         raise RuntimeError(msg)
 
     ms_df.to_parquet(
-        f"{Path(ms_path).stem}_ms_info.parquet", engine="pyarrow", index=False, compression="gzip"
+        f"{Path(ms_path).stem}_ms_info.parquet",
+        engine="pyarrow",
+        index=False,
+        compression="gzip",
     )

quantmsutils/psm/psm_conversion.py

@@ -56,7 +56,11 @@ def mods_position(peptide):
     "psmconvert", short_help="Convert idXML to parquet file with PSMs information."
 )
 @click.option("--idxml", type=click.Path(exists=True))
-@click.option("--spectra_file", type=click.Path(exists=True), help="Parquet file from mzml_statistics")
+@click.option(
+    "--spectra_file",
+    type=click.Path(exists=True),
+    help="Parquet file from mzml_statistics",
+)
 @click.option("--export_decoy_psm", is_flag=True)
 @click.pass_context
 def convert_psm(ctx, idxml: str, spectra_file: str, export_decoy_psm: bool = False):
@@ -173,4 +177,5 @@ def convert_psm(ctx, idxml: str, spectra_file: str, export_decoy_psm: bool = Fal
             )
 
     pd.DataFrame(parquet_data, columns=_parquet_field).to_parquet(
-        f"{Path(idxml).stem}_psm.csv", index=False, engine="pyarrow", compression="gzip")
+        f"{Path(idxml).stem}_psm.csv", index=False, engine="pyarrow", compression="gzip"
+    )

quantmsutils/quantmsutilsc.py

@@ -13,7 +13,9 @@
 CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
 
 
-@click.version_option(version=__version__, package_name="quantmsutils", message="%(package)s %(version)s")
+@click.version_option(
+    version=__version__, package_name="quantmsutils", message="%(package)s %(version)s"
+)
 @click.group(context_settings=CONTEXT_SETTINGS)
 def cli():
     pass

quantmsutils/rescoring/ms2rescore.py

@@ -225,7 +225,7 @@ def filter_out_artifact_psms(
     "--ms2pip_model_dir",
     help="The path of MS²PIP model (default: `./`)",
     type=str,
-    default="./"
+    default="./",
 )
 @click.option(
     "-ms2tol",

quantmsutils/sdrf/check_samplesheet.py

@@ -30,26 +30,50 @@ def print_error(error, context="Line", context_str=""):
     sys.exit(1)
 
 
-def check_sdrf(check_ms, sdrf, validate_ontologies):
-    df = SdrfDataFrame.parse(sdrf)
-    if validate_ontologies:
-        errors = df.validate(DEFAULT_TEMPLATE)
-        if check_ms:
-            errors = errors + df.validate(MASS_SPECTROMETRY)
-        for error in errors:
-            print(error)
-        if not errors:
-            print("Everying seems to be fine. Well done.")
-        else:
-            print("There were validation errors!")
-    else:
-        errors = False
-        print("No ontology term validation was performed.")
+def check_sdrf(
+    input_sdrf: str,
+    skip_ms_validation: bool = False,
+    skip_factor_validation: bool = False,
+    skip_experimental_design_validation: bool = False,
+    use_ols_cache_only: bool = False,
+    skip_sdrf_validation: bool = False,
+):
+    """
+    Check the SDRF file for errors. If any errors are found, print them and exit with a non-zero status code.
+    @param input_sdrf: Path to the SDRF file to check
+    @param skip_ms_validation: Disable the validation of mass spectrometry fields in SDRF (e.g. posttranslational modifications)
+    @param skip_factor_validation: Disable the validation of factor values in SDRF
+    @param skip_experimental_design_validation: Disable the validation of experimental design
+    @param use_ols_cache_only: Use ols cache for validation of the terms and not OLS internet service
+    @param skip_sdrf_validation: Disable the validation of SDRF
+    """
+    if skip_sdrf_validation:
+        print("No SDRF validation was performed.")
+        sys.exit(0)
+
+    df = SdrfDataFrame.parse(input_sdrf)
+    errors = df.validate(DEFAULT_TEMPLATE, use_ols_cache_only)
+
+    if not skip_ms_validation:
+        errors = errors + df.validate(MASS_SPECTROMETRY, use_ols_cache_only)
+
+    if not skip_factor_validation:
+        errors = errors + df.validate_factor_values()
+
+    if not skip_experimental_design_validation:
+        errors = errors + df.validate_experimental_design()
+
+    for error in errors:
+        print(error)
 
     sys.exit(bool(errors))
 
 
 def check_expdesign(expdesign):
+    """
+    Check the expdesign file for errors. If any errors are found, print them and exit with a non-zero status code.
+    @param expdesign: Path to the expdesign file to check
+    """
     data = pd.read_csv(expdesign, sep="\t", header=0, dtype=str)
     data = data.dropna()
     schema_file = ["Fraction_Group", "Fraction", "Spectra_Filepath", "Label", "Sample"]
@@ -111,34 +135,64 @@ def check_expdesign_logic(f_table, s_table):
         sys.exit(1)
 
 
-@click.command("checksamplesheet", short_help="Check samplesheet")
-@click.option("--is_sdrf", "-s", help="In Sdrf format", is_flag=True, default=False)
+@click.command(
+    "check_samplesheet",
+    short_help="Reformat nf-core/quantms sdrf file and check its contents.",
+)
+@click.option("--exp_design", help="SDRF/Expdesign file to be validated")
+@click.option("--is_sdrf", help="SDRF file or Expdesign file", is_flag=True)
+@click.option(
+    "--skip_sdrf_validation", help="Disable the validation of SDRF", is_flag=True
+)
+@click.option(
+    "--skip_ms_validation",
+    help="Disable the validation of mass spectrometry fields in SDRF (e.g. posttranslational modifications)",
+    is_flag=True,
+)
 @click.option(
-    "--check_ms",
-    "-m",
-    required=False,
+    "--skip_factor_validation",
+    help="Disable the validation of factor values in SDRF",
     is_flag=True,
-    help="Check mass spectrometry fields in sample metadata.",
-    default=False,
 )
 @click.option(
-    "--validate_ontologies", help="Validate the ontologies", is_flag=True, default=False
+    "--skip_experimental_design_validation",
+    help="Disable the validation of experimental design",
+    is_flag=True,
 )
 @click.option(
-    "-in",
-    "--input_file",
-    type=click.Path(exists=True),
-    required=True,
-    help="Input SDRF or Expdesign file",
+    "--use_ols_cache_only",
+    help="Use ols cache for validation of the terms and not OLS internet service",
+    is_flag=True,
 )
-@click.pass_context
 def check_samplesheet(
-    ctx, is_sdrf: bool, check_ms: bool, validate_ontologies: bool, input_file: str
-) -> None:
+    exp_design: str,
+    is_sdrf: bool = False,
+    skip_sdrf_validation: bool = False,
+    skip_ms_validation: bool = False,
+    skip_factor_validation: bool = False,
+    skip_experimental_design_validation: bool = False,
+    use_ols_cache_only: bool = False,
+):
     """
-    Check the samplesheet for errors.
+    Reformat nf-core/quantms sdrf file and check its contents.
+    @param exp_design: SDRF/Expdesign file to be validated
+    @param is_sdrf: SDRF file or Expdesign file
+    @param skip_sdrf_validation: Disable the validation of SDRF
+    @param skip_ms_validation: Disable the validation of mass spectrometry fields in SDRF (e.g. posttranslational modifications)
+    @param skip_factor_validation: Disable the validation of factor values in SDRF
+    @param skip_experimental_design_validation: Disable the validation of experimental design
+    @param use_ols_cache_only: Use ols cache for validation of the terms and not OLS internet service
+
     """
+    # TODO validate expdesign file
     if is_sdrf:
-        check_sdrf(check_ms, input_file, validate_ontologies)
+        check_sdrf(
+            input_sdrf=exp_design,
+            skip_sdrf_validation=skip_sdrf_validation,
+            skip_ms_validation=skip_ms_validation,
+            skip_factor_validation=skip_factor_validation,
+            skip_experimental_design_validation=skip_experimental_design_validation,
+            use_ols_cache_only=use_ols_cache_only,
+        )
     else:
-        check_expdesign(input_file)
+        check_expdesign(exp_design)

requirements.txt

@@ -1,5 +1,5 @@
 click
-sdrf-pipelines==0.0.28
+sdrf-pipelines==0.0.29
 pyopenms
 ms2rescore==3.0.2
 psm-utils==0.8.0

setup.py

@@ -1,6 +1,17 @@
 from setuptools import find_packages, setup
+import os
+import codecs
 
-VERSION = "0.0.3"
+def read(rel_path):
+    here = os.path.abspath(os.path.dirname(__file__))
+    with codecs.open(os.path.join(here, rel_path), "r") as fp:
+        return fp.read()
+def get_version(rel_path):
+    for line in read(rel_path).splitlines():
+        if line.startswith("__version__"):
+            delim = '"' if '"' in line else "'"
+            return line.split(delim)[1]
+    raise RuntimeError("Unable to find version string.")
 
 NAME = "quantms-utils"
 LICENSE = "MIT License"
@@ -30,7 +41,7 @@
 
 INSTALL_REQUIRES = [
     "click",
-    "sdrf-pipelines==0.0.28",
+    "sdrf-pipelines==0.0.29",
     "pyopenms",
     "ms2rescore==3.0.2",
     "psm-utils==0.8.0",
@@ -46,7 +57,7 @@
 
 setup(
     name=NAME,
-    version=VERSION,
+    version=get_version("quantmsutils/__init__.py"),
     license=LICENSE,
     description=DESCRIPTION,
     long_description=LONG_DESCRIPTION,

tests/test_commands.py

@@ -70,7 +70,7 @@ def test_convert_psm_help():
 # test for the check_samplesheet command in cli
 def test_check_samplesheet_help():
     runner = CliRunner()
-    result = runner.invoke(cli, ["checksamplesheet", "--help"])
+    result = runner.invoke(cli, ["check_samplesheet", "--help"])
 
     assert result.exit_code == 0
 
@@ -81,10 +81,9 @@ def test_check_samplesheet_sdrf():
     result = runner.invoke(
         cli,
         [
-            "checksamplesheet",
+            "check_samplesheet",
             "--is_sdrf",
-            "--check_ms",
-            "--input_file",
+            "--exp_design",
             "tests/test_data/PXD000001.sdrf.tsv",
         ],
     )