Merge pull request #403 from MannLabs/rename_plan

renaming Plan -> SearchStep

Author: mschwoer

alphadia/outputtransform.py

@@ -1103,7 +1103,7 @@ def _build_run_internal_df(
     ----------
 
     folder_path: str
-        Path (from the base directory of the output_folder attribute of the Plan class) to the directory containing the raw file and the managers
+        Path (from the base directory of the output_folder attribute of the SearchStep class) to the directory containing the raw file and the managers
 
 
     Returns

alphadia/search_plan.py

@@ -11,8 +11,8 @@
 from alphadia.outputtransform import (
     SearchPlanOutput,
 )
-from alphadia.planning import (
-    Plan,
+from alphadia.search_step import (
+    SearchStep,
     logger,
 )
 from alphadia.utilities.logging import print_environment, print_logo
@@ -41,7 +41,7 @@ def __init__(
     ):
         """Initialize search plan.
 
-        In case of a single step search, this can be considered as a slim wrapper around the Plan class.
+        In case of a single step search, this can be considered as a slim wrapper around the SearchStep class.
         In case of a multistep search, this class orchestrates the different steps, their data paths,
          and passes information from one step to the next.
 
@@ -199,7 +199,7 @@ def run_step(
         quant_dir: Path | None = None,
     ) -> None:
         """Run a single step of the search plan."""
-        step = Plan(
+        step = SearchStep(
             output_folder=str(output_directory),
             raw_path_list=self._raw_path_list,
             library_path=None if library_path is None else str(library_path),

alphadia/planning.py renamed to alphadia/search_step.py

@@ -19,7 +19,7 @@
 logger = logging.getLogger()
 
 
-class Plan:  # TODO rename -> SearchStep, planning.py -> search_step.py
+class SearchStep:
     def __init__(
         self,
         output_folder: str,
@@ -31,7 +31,8 @@ def __init__(
         extra_config: dict | None = None,
         quant_path: str | None = None,
     ) -> None:
-        """Highest level class to plan a DIA Search.
+        """Highest level class to plan a DIA search step.
+
         Owns the input file list, speclib and the config.
         Performs required manipulation of the spectral library like transforming RT scales and adding columns.
 

docs/alphadia/planning.rst

@@ -1,9 +1,9 @@
-planning
+search_step
 ========
 
-The planning module organizes the search schedule for searching multiple files.
+The search_step module organizes the search schedule for searching multiple files.
 
-.. automodule:: alphadia.planning
+.. automodule:: alphadia.search_step
    :members:
    :undoc-members:
    :show-inheritance:

docs/modules.rst

@@ -12,7 +12,7 @@ Modules
     alphadia/grouping
     alphadia/libtransform
     alphadia/outputtransform
-    alphadia/planning
+    alphadia/search_step
     alphadia/plexscoring
     alphadia/quadrupole
     alphadia/utils

nbs/debug/debug_lvl1.ipynb

@@ -10,10 +10,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 1,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
     "%reload_ext autoreload\n",
     "%autoreload 2\n",
@@ -24,7 +24,7 @@
     "import seaborn as sns\n",
     "import os\n",
     "\n",
-    "from alphadia import planning\n",
+    "from alphadia import search_step\n",
     "from alphadia.workflow import peptidecentric\n",
     "\n",
     "os.environ[\"NUMBA_BOUNDSCHECK\"] = \"1\"\n",
@@ -33,10 +33,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
     "import tempfile\n",
     "\n",
@@ -70,10 +70,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
     "config = {\n",
     "    \"general\": {\n",
@@ -88,28 +88,28 @@
     "        \"target_rt_tolerance\": 200,\n",
     "    }\n",
     "}\n",
-    "plan = planning.Plan(test_folder, raw_data_path_list, library_path, config=config)"
+    "step = search_step.SearchStep(test_folder, raw_data_path_list, library_path, config=config)"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
-    "for raw_name, dia_path, speclib in plan.get_run_data():\n",
+    "for raw_name, dia_path, speclib in step.get_run_data():\n",
     "    pass"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
     "workflow = peptidecentric.PeptideCentricWorkflow(\n",
     "    raw_name,\n",
-    "    plan.config,\n",
+    "    step.config,\n",
     ")\n",
     "workflow.load(dia_path, speclib)\n",
     "workflow.search_parameter_optimization()"

nbs/search/library_search.ipynb

@@ -11,7 +11,7 @@
     "\n",
     "import os\n",
     "\n",
-    "from alphadia import planning"
+    "from alphadia import search_step"
    ]
   },
   {
@@ -71,9 +71,9 @@
     "        \"target_rt_tolerance\": 150,\n",
     "    },\n",
     "}\n",
-    "plan = planning.Plan(output_location, raw_files, speclib, config_update=config_update)\n",
+    "step = search_step.SearchStep(output_location, raw_files, speclib, config_update=config_update)\n",
     "\n",
-    "plan.run()"
+    "step.run()"
    ]
   }
  ],

tests/e2e_tests/e2e_test_cases.yaml

@@ -35,21 +35,24 @@ test_cases:
       - BasicStats
 
   - name: multistep
+    # see also transfer-dimethyl.md
     config:
-      search_initial:
-        initial_num_candidates: 1
-        initial_rt_tolerance: 300
       search:
-        target_num_candidates: 1
+#        target_num_candidates: # mbr: 3
         target_ms1_tolerance: 4
         target_ms2_tolerance: 7
-        target_rt_tolerance: 100
-      calibration:
-        batch_size: 1000
+        target_rt_tolerance: 0.5 # mbr: 0
       transfer_learning:
-        epochs: 5  # this is to speed the test up a little
+        epochs: 5  # this is reduced to speed the test up a little
       library_prediction:
         predict: True
+        precursor_mz:
+          - 380
+          - 980
+        fixed_modifications: 'Dimethyl@Any_N-term;Dimethyl@K'
+        variable_modifications: 'Oxidation@M;Acetyl@Protein_N-term'
+        max_var_mod_num: 1 # mbr: 2
+        missed_cleavages: 0  # mbr: 1
       multistep_search:
         transfer_step_enabled: True
         mbr_step_enabled: True

tests/unit_tests/test_search_plan.py

@@ -34,7 +34,7 @@ def get_search_plan(config):
 
 
 @patch("alphadia.search_plan.reporting.init_logging")
-@patch("alphadia.search_plan.Plan")
+@patch("alphadia.search_plan.SearchStep")
 def test_runs_plan_without_transfer_and_mbr_steps(mock_plan, mock_init_logging):
     """Test that the SearchPlan object runs the plan correctly without transfer and mbr steps."""
     search_plan = get_search_plan(BASE_USER_CONFIG)
@@ -59,7 +59,7 @@ def test_runs_plan_without_transfer_and_mbr_steps(mock_plan, mock_init_logging):
 
 
 @patch("alphadia.search_plan.reporting.init_logging")
-@patch("alphadia.search_plan.Plan")
+@patch("alphadia.search_plan.SearchStep")
 def test_runs_plan_without_transfer_and_mbr_steps_none_dirs(
     mock_plan, mock_init_logging
 ):
@@ -94,7 +94,7 @@ def test_runs_plan_without_transfer_and_mbr_steps_none_dirs(
 
 
 @patch("alphadia.search_plan.reporting.init_logging")
-@patch("alphadia.search_plan.Plan")
+@patch("alphadia.search_plan.SearchStep")
 @patch("alphadia.search_plan.SearchPlan._get_optimized_values_config")
 def test_runs_plan_with_transfer_step(
     mock_get_dyn_config, mock_plan, mock_init_logging
@@ -153,7 +153,7 @@ def test_runs_plan_with_transfer_step(
 
 
 @patch("alphadia.search_plan.reporting.init_logging")
-@patch("alphadia.search_plan.Plan")
+@patch("alphadia.search_plan.SearchStep")
 @patch("alphadia.search_plan.SearchPlan._get_optimized_values_config")
 def test_runs_plan_with_mbr_step(mock_get_dyn_config, mock_plan, mock_init_logging):
     """Test that the SearchPlan object runs the plan correctly with the mbr step enabled."""
@@ -203,7 +203,7 @@ def test_runs_plan_with_mbr_step(mock_get_dyn_config, mock_plan, mock_init_loggi
 
 
 @patch("alphadia.search_plan.reporting.init_logging")
-@patch("alphadia.search_plan.Plan")
+@patch("alphadia.search_plan.SearchStep")
 @patch("alphadia.search_plan.SearchPlan._get_optimized_values_config")
 def test_runs_plan_with_transfer_and_mbr_steps(
     mock_get_dyn_config, mock_plan, mock_init_logging

tests/unit_tests/test_planning.py renamed to tests/unit_tests/test_search_step.py

@@ -5,7 +5,7 @@
 from alphabase.constants import _const
 from alphabase.constants.modification import MOD_DF
 
-from alphadia import planning
+from alphadia import search_step
 from alphadia.test_data_downloader import DataShareDownloader
 
 
@@ -14,35 +14,35 @@ def test_fasta_digest():
     # digest & predict new library
     common_contaminants = os.path.join(_const.CONST_FILE_FOLDER, "contaminants.fasta")
     tempdir = tempfile.gettempdir()
-    plan = planning.Plan(
+    step = search_step.SearchStep(
         tempdir,
         fasta_path_list=[common_contaminants],
         config={"library_prediction": {"predict": True}},
     )
 
-    assert len(plan.spectral_library.precursor_df) > 0
-    assert len(plan.spectral_library.fragment_df) > 0
+    assert len(step.spectral_library.precursor_df) > 0
+    assert len(step.spectral_library.fragment_df) > 0
 
     speclib_path = os.path.join(tempdir, "speclib.hdf")
     assert os.path.exists(speclib_path)
 
     # predict existing library
-    plan = planning.Plan(
+    step = search_step.SearchStep(
         tempdir,
         library_path=speclib_path,
         config={"library_prediction": {"predict": True}},
     )
-    assert len(plan.spectral_library.precursor_df) > 0
-    assert len(plan.spectral_library.fragment_df) > 0
+    assert len(step.spectral_library.precursor_df) > 0
+    assert len(step.spectral_library.fragment_df) > 0
 
     # load existing library without predict
-    plan = planning.Plan(
+    step = search_step.SearchStep(
         tempdir,
         library_path=speclib_path,
         config={"library_prediction": {"predict": False}},
     )
-    assert len(plan.spectral_library.precursor_df) > 0
-    assert len(plan.spectral_library.fragment_df) > 0
+    assert len(step.spectral_library.precursor_df) > 0
+    assert len(step.spectral_library.fragment_df) > 0
 
 
 @pytest.mark.slow()
@@ -70,9 +70,9 @@ def test_library_loading():
         test_data_location = DataShareDownloader(
             test_dict["url"], temp_directory
         ).download()
-        plan = planning.Plan(temp_directory, library_path=test_data_location)
-        assert len(plan.spectral_library.precursor_df) > 0
-        assert len(plan.spectral_library.fragment_df) > 0
+        step = search_step.SearchStep(temp_directory, library_path=test_data_location)
+        assert len(step.spectral_library.precursor_df) > 0
+        assert len(step.spectral_library.fragment_df) > 0
 
 
 def test_custom_modifications():
@@ -86,5 +86,5 @@ def test_custom_modifications():
         }
     }
 
-    plan = planning.Plan(temp_directory, [], config=config)  # noqa F841
+    step = search_step.SearchStep(temp_directory, [], config=config)  # noqa F841
     assert "ThisModDoesNotExists@K" in MOD_DF["mod_name"].values