Refactor config

alphadia/cli.py

@@ -134,14 +134,18 @@ def _get_raw_path_list_from_args_and_config(
     arguments, including files from specified directories. It filters the resulting
     list of file paths using a regular expression provided in the arguments.
 
-    Args:
-        args (argparse.Namespace): Command-line arguments containing file and directory
-            paths, as well as a regex pattern for filtering.
-        config (dict): Configuration dictionary that may include a list of raw paths
-            and a directory to search for files.
-
-    Returns:
-        list: A list of file paths that match the specified regex pattern.
+    Parameters
+    ----------
+    args : argparse.Namespace
+        Command-line arguments containing file and directory
+        paths, as well as a regex pattern for filtering.
+    config : dict
+        Configuration dictionary that may include a list of raw paths
+        and a directory to search for files.
+
+    Returns
+    -------
+        list: a list of file paths that match the specified regex pattern.
     """
 
     raw_path_list = config.get("raw_path_list", [])

alphadia/constants/default.yaml

@@ -1,6 +1,11 @@
 # configuration for the extraction plan
 version: 1
 
+library: null
+output_directory: null
+raw_path_list: []
+output: null
+
 general:
   thread_count: 10
   # maximum number of threads or processes to use per raw file
@@ -25,6 +30,7 @@ library_prediction:
   variable_modifications: 'Oxidation@M;Acetyl@Protein_N-term'
   max_var_mod_num: 2
   missed_cleavages: 1
+  # using tuples here as it makes interaction with the GUI easier
   precursor_len:
     - 7
     - 35
@@ -52,6 +58,9 @@ library_prediction:
 
 # define custom alphabase modifications not part of unimod or alphabase
 # also used for decoy channels
+# TODO make this a list
+#  - name: Dimethyl:d12@K
+#    composition: H(-2)2H(8)13C(2)
 custom_modifications:
   # Dimethyl @K channel decoy
   Dimethyl:d12@K:
@@ -190,8 +199,12 @@ library_multiplexing:
   # channels can be either a number or a string
   # for every channel, the library gets copied and the modifications are translated according to the mapping
   # the following example shows how to multiplex mTRAQ to three sample channels and a decoy channel
+  # TODO make this a list
+  #    - channel_name: 0
+  #      channel_modifications:
+  #        mTRAQ@K: mTRAQ@K
+  #        mTRAQ@Any_N-term: mTRAQ@Any_N-term
   multiplex_mapping: {}
-
     #0:
     #  mTRAQ@K: mTRAQ@K
     #  mTRAQ@Any_N-term: mTRAQ@Any_N-term
@@ -372,11 +385,12 @@ transfer_learning:
   # instrument type encoded during training
   instrument: 'Lumos'
 
+
 # configuration for the calibration manager
 # the config has to start with the calibration keyword and consists of a list of calibration groups.
 # each group consists of datapoints which have multiple properties.
 # This can be for example precursors (mz, rt ...), fragments (mz, ...), quadrupole (transfer_efficiency)
-calibration_manager:
+calibration_manager: # TODO move to a separate file or hard-code
   - name: fragment
     estimators:
       - name: mz

alphadia/search_plan.py

@@ -1,6 +1,7 @@
 """Search plan for single- and multistep search."""
 
 import os
+from collections import defaultdict
 from pathlib import Path
 
 import numpy as np
@@ -230,7 +231,7 @@ def _get_optimized_values_config(output_folder: Path) -> dict:
             )
             return {}
 
-        extra_config = {"search": {}}
+        extra_config = defaultdict(dict)
 
         if not np.isnan(target_ms1_tolerance):
             extra_config["search"]["target_ms1_tolerance"] = target_ms1_tolerance
@@ -243,4 +244,4 @@ def _get_optimized_values_config(output_folder: Path) -> dict:
         # - target_mobility_tolerance and target_rt_tolerance should be reoptimized with the lib resulting from transfer learning step
 
         logger.info(f"Extracted extra_config from previous step: {extra_config}")
-        return extra_config
+        return dict(extra_config)

alphadia/search_step.py

@@ -134,7 +134,7 @@ def _init_config(
             extra_config["output"] = output_folder
             config_updates.append(extra_config_update)
 
-        config.update(config_updates, print_modifications=True)
+        config.update(config_updates, do_print=True)
 
         if "output" not in config:
             config["output"] = output_folder