alphadia 1.9.1__tar.gz → 1.9.3.dev2__tar.gz

{alphadia-1.9.1/alphadia.egg-info → alphadia-1.9.3.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: alphadia
-Version: 1.9.1
+Version: 1.9.3.dev2
 Summary: A novel proteomics search engine for DIA data based on end-to-end transfer learning.
 Author-email: Mann Labs <wallmann@biochem.mpg.de>
 License:                                  Apache License
@@ -223,8 +223,9 @@ Requires-Dist: numba
 Requires-Dist: argparse
 Requires-Dist: alpharaw>=0.3.1
 Requires-Dist: alphatims
-Requires-Dist: alphabase>=1.4.0
+Requires-Dist: alphabase<1.5.0,>=1.4.0
 Requires-Dist: peptdeep>=1.3.0
+Requires-Dist: dask==2024.11.2
 Requires-Dist: progressbar
 Requires-Dist: neptune
 Requires-Dist: seaborn
@@ -254,26 +255,32 @@ Requires-Dist: transformers==4.40.2; extra == "stable"
 Requires-Dist: directlfq==0.2.19; extra == "stable"
 Requires-Dist: pythonnet==3.0.3; extra == "stable"
 Requires-Dist: zstandard==0.22.0; extra == "stable"
+Requires-Dist: dask==2024.11.2; extra == "stable"
 Requires-Dist: numpy<2; extra == "stable"
 Requires-Dist: scipy==1.12.0; extra == "stable"
-Provides-Extra: test
-Requires-Dist: coverage; extra == "test"
-Requires-Dist: coverage-badge; extra == "test"
-Requires-Dist: pytest; extra == "test"
+Provides-Extra: tests
+Requires-Dist: coverage; extra == "tests"
+Requires-Dist: coverage-badge; extra == "tests"
+Requires-Dist: pytest; extra == "tests"
+Provides-Extra: docs
+Requires-Dist: autodocsumm; extra == "docs"
+Requires-Dist: sphinx-rtd-theme; extra == "docs"
+Requires-Dist: nbsphinx; extra == "docs"
+Requires-Dist: myst_parser; extra == "docs"
+Requires-Dist: sphinx_design; extra == "docs"
+Requires-Dist: furo; extra == "docs"
+Requires-Dist: pandoc; extra == "docs"
 Provides-Extra: development
 Requires-Dist: jupyter; extra == "development"
 Requires-Dist: jupyter_contrib_nbextensions; extra == "development"
 Requires-Dist: pyinstaller; extra == "development"
 Requires-Dist: twine; extra == "development"
-Requires-Dist: bumpversion; extra == "development"
+Requires-Dist: bump-my-version; extra == "development"
 Requires-Dist: pipdeptree; extra == "development"
 Requires-Dist: ipykernel; extra == "development"
 Requires-Dist: psutil; extra == "development"
 Requires-Dist: pre-commit==3.7.0; extra == "development"
 Requires-Dist: pywin32; sys_platform == "win32" and extra == "development"
-Requires-Dist: coverage; extra == "development"
-Requires-Dist: coverage-badge; extra == "development"
-Requires-Dist: pytest; extra == "development"
 Requires-Dist: autodocsumm; extra == "development"
 Requires-Dist: sphinx-rtd-theme; extra == "development"
 Requires-Dist: nbsphinx; extra == "development"
@@ -361,8 +368,13 @@ AlphaDIA can be installed on Windows, macOS and Linux. Please choose the preferr
 Currently available for **MacOS** and **Windows**.
 You can download the latest release of alphaDIA [here](https://github.com/Mannlabs/alphadia/releases/latest).
 
-* **Windows:** Download the latest `win-x64` build. Save it and double click it to install. If you receive a warning during installation click *Run anyway*.
-* **MacOS:** Download the latest `darwin-arm64` build. Please note that alphaDIA currently requires an ARM based M1/2/3 processor for the one-click installer. Save the installer and open the parent folder in Finder. Right-click and select *open*. If you receive a warning during installation click *Open*. If you want to use `.raw` files on Thermo instruments alphaRaw is required, which depends on Mono. A detailed guide to installing alphaRaw with mono can be found [here](https://github.com/MannLabs/alpharaw#installation).
+* **Windows:** Download the latest `alphadia-X.Y.Z-windows-amd64.exe` build and double click it to install. If you receive a warning during installation click *Run anyway*.
+* **MacOS:** Download the latest build suitable for your chip architecture
+(can be looked up by clicking on the Apple Symbol > *About this Mac* > *Chip* ("M1", "M2", "M3" -> `arm64`, "Intel" -> `x64`),
+`alphadia-X.Y.Z-macos-darwin-arm64.pkg` or `alphadia-X.Y.Z-macos-darwin-x64.pkg`. Open the parent folder of the downloaded file in Finder,
+right-click and select *open*. If you receive a warning during installation click *Open*. If you want to use `.raw` files on Thermo instruments alphaRaw is required, which depends on Mono. A detailed guide to installing alphaRaw with mono can be found [here](https://github.com/MannLabs/alpharaw#installation).
+* **Linux:** Download the latest `alphadia-X.Y.Z-linux-x64.deb` build and install it via `dpkg -i alphadia-X.Y.Z-linux-x64.deb`.
+
 
 As of now, **Linux** users need follow the steps for the
 [developer installation](docs/installation.md#developer-installation) in order to use the GUI.
@@ -406,7 +418,10 @@ Make sure you have installed the GUI using the one-click installer. To verify yo
 
 ### 2. Test data
 
-For the first search we will be using a spectral library to search 60SPD bulk HeLa samples on the Orbitrap Astral. Download the test samples and save them: [HeLa library](https://datashare.biochem.mpg.de/s/Uw2yfNSbApfPpTk), [RAW files].(https://datashare.biochem.mpg.de/s/339jg5HtGrwLwDN)
+For the first search we will be using a spectral library to search 60SPD bulk HeLa samples on the Orbitrap Astral.
+Download the test samples and save them:
+[HeLa library](https://datashare.biochem.mpg.de/s/Uw2yfNSbApfPpTk),
+[RAW files](https://datashare.biochem.mpg.de/s/339jg5HtGrwLwDN)
 
 ### 3. Search settings
 
@@ -437,7 +452,10 @@ In case of issues, check out the following:
 ---
 ## Citations
 
-A manuscript has been submitted to bioRxiv.
+A manuscript has been submitted to bioRxiv:
+> **AlphaDIA enables End-to-End Transfer Learning for Feature-Free Proteomics**
+> Georg Wallmann, Patricia Skowronek, Vincenth Brennsteiner, Mikhail Lebedev, Marvin Thielert, Sophia Steigerwald, Mohamed Kotb, Tim Heymann, Xie-Xuan Zhou, Magnus Schwörer, Maximilian T. Strauss, Constantin Ammar, Sander Willems, Wen-Feng Zeng, Matthias Mann
+> bioRxiv 2024.05.28.596182; doi: https://doi.org/10.1101/2024.05.28.596182
 
 ---
 ## How to contribute

{alphadia-1.9.1 → alphadia-1.9.3.dev2}/README.md

@@ -77,8 +77,13 @@ AlphaDIA can be installed on Windows, macOS and Linux. Please choose the preferr
 Currently available for **MacOS** and **Windows**.
 You can download the latest release of alphaDIA [here](https://github.com/Mannlabs/alphadia/releases/latest).
 
-* **Windows:** Download the latest `win-x64` build. Save it and double click it to install. If you receive a warning during installation click *Run anyway*.
-* **MacOS:** Download the latest `darwin-arm64` build. Please note that alphaDIA currently requires an ARM based M1/2/3 processor for the one-click installer. Save the installer and open the parent folder in Finder. Right-click and select *open*. If you receive a warning during installation click *Open*. If you want to use `.raw` files on Thermo instruments alphaRaw is required, which depends on Mono. A detailed guide to installing alphaRaw with mono can be found [here](https://github.com/MannLabs/alpharaw#installation).
+* **Windows:** Download the latest `alphadia-X.Y.Z-windows-amd64.exe` build and double click it to install. If you receive a warning during installation click *Run anyway*.
+* **MacOS:** Download the latest build suitable for your chip architecture
+(can be looked up by clicking on the Apple Symbol > *About this Mac* > *Chip* ("M1", "M2", "M3" -> `arm64`, "Intel" -> `x64`),
+`alphadia-X.Y.Z-macos-darwin-arm64.pkg` or `alphadia-X.Y.Z-macos-darwin-x64.pkg`. Open the parent folder of the downloaded file in Finder,
+right-click and select *open*. If you receive a warning during installation click *Open*. If you want to use `.raw` files on Thermo instruments alphaRaw is required, which depends on Mono. A detailed guide to installing alphaRaw with mono can be found [here](https://github.com/MannLabs/alpharaw#installation).
+* **Linux:** Download the latest `alphadia-X.Y.Z-linux-x64.deb` build and install it via `dpkg -i alphadia-X.Y.Z-linux-x64.deb`.
+
 
 As of now, **Linux** users need follow the steps for the
 [developer installation](docs/installation.md#developer-installation) in order to use the GUI.
@@ -122,7 +127,10 @@ Make sure you have installed the GUI using the one-click installer. To verify yo
 
 ### 2. Test data
 
-For the first search we will be using a spectral library to search 60SPD bulk HeLa samples on the Orbitrap Astral. Download the test samples and save them: [HeLa library](https://datashare.biochem.mpg.de/s/Uw2yfNSbApfPpTk), [RAW files].(https://datashare.biochem.mpg.de/s/339jg5HtGrwLwDN)
+For the first search we will be using a spectral library to search 60SPD bulk HeLa samples on the Orbitrap Astral.
+Download the test samples and save them:
+[HeLa library](https://datashare.biochem.mpg.de/s/Uw2yfNSbApfPpTk),
+[RAW files](https://datashare.biochem.mpg.de/s/339jg5HtGrwLwDN)
 
 ### 3. Search settings
 
@@ -153,7 +161,10 @@ In case of issues, check out the following:
 ---
 ## Citations
 
-A manuscript has been submitted to bioRxiv.
+A manuscript has been submitted to bioRxiv:
+> **AlphaDIA enables End-to-End Transfer Learning for Feature-Free Proteomics**
+> Georg Wallmann, Patricia Skowronek, Vincenth Brennsteiner, Mikhail Lebedev, Marvin Thielert, Sophia Steigerwald, Mohamed Kotb, Tim Heymann, Xie-Xuan Zhou, Magnus Schwörer, Maximilian T. Strauss, Constantin Ammar, Sander Willems, Wen-Feng Zeng, Matthias Mann
+> bioRxiv 2024.05.28.596182; doi: https://doi.org/10.1101/2024.05.28.596182
 
 ---
 ## How to contribute

alphadia-1.9.3.dev2/alphadia/__init__.py

@@ -0,0 +1,3 @@
+#!python
+
+__version__ = "1.9.3-dev2"

alphadia-1.9.3.dev2/alphadia/cli.py

@@ -0,0 +1,249 @@
+#!python
+"""CLI for alphaDIA.
+
+Ideally the CLI module should have as little logic as possible so that the search behaves the same from the CLI or a jupyter notebook.
+"""
+
+import argparse
+import json
+import logging
+import os
+import re
+import sys
+
+import matplotlib
+import yaml
+
+import alphadia
+from alphadia import utils
+from alphadia.constants.keys import ConfigKeys
+from alphadia.exceptions import CustomError
+from alphadia.search_plan import SearchPlan
+from alphadia.workflow import reporting
+
+logger = logging.getLogger()
+
+epilog = "Parameters passed via CLI will overwrite parameters from config file (except for  '--file': will be merged)."
+
+parser = argparse.ArgumentParser(
+    description="Search DIA experiments with alphaDIA", epilog=epilog
+)
+parser.add_argument(
+    "--version",
+    "-v",
+    action="store_true",
+    help="Print version and exit",
+)
+parser.add_argument(
+    "--output",
+    "--output-directory",
+    "-o",
+    type=str,
+    help="Output directory.",
+    nargs="?",
+    default=None,
+)
+parser.add_argument(
+    "--file",
+    "--raw-path",
+    "-f",
+    type=str,
+    help="Path to raw data input file. Can be passed multiple times.",
+    action="append",
+    default=[],
+)
+parser.add_argument(
+    "--directory",
+    "-d",
+    type=str,
+    help="Directory containing raw data input files.",
+    action="append",
+    default=[],
+)
+parser.add_argument(
+    "--regex",
+    "-r",
+    type=str,
+    help="Regex to match raw files in 'directory'.",
+    nargs="?",
+    default=".*",
+)
+parser.add_argument(
+    "--library",
+    "--library-path",
+    "-l",
+    type=str,
+    help="Path to spectral library file.",
+    nargs="?",
+    default=None,
+)
+parser.add_argument(
+    "--fasta",
+    "--fasta-path",
+    help="Path to fasta file used to generate or annotate the spectral library. Can be passed multiple times.",
+    action="append",
+    default=[],
+)
+parser.add_argument(
+    "--config",
+    "-c",
+    type=str,
+    help="Path to config yaml file which will be used to update the default config.",
+    nargs="?",
+    default=None,
+)
+parser.add_argument(
+    "--config-dict",
+    type=str,
+    help="Python dictionary which will be used to update the default config.",
+    nargs="?",
+    default="{}",
+)
+parser.add_argument(
+    "--quant-dir",  # TODO deprecate
+    "--quant-directory",
+    type=str,
+    help="Directory to save the quantification results (psm & frag parquet files) to be reused in a distributed search.",
+    nargs="?",
+    default=None,
+)
+
+
+def _get_config_from_args(args: argparse.Namespace) -> dict:
+    """Parse config file from `args.config` if given and update with optional JSON string `args.config_dict`."""
+
+    config = {}
+    if args.config is not None:
+        with open(args.config) as f:
+            config = yaml.safe_load(f)
+
+    try:
+        utils.recursive_update(config, json.loads(args.config_dict))
+    except Exception as e:
+        print(f"Could not parse config update: {e}")
+
+    return config
+
+
+def _get_from_args_or_config(
+    args: argparse.Namespace, config: dict, *, args_key: str, config_key: str
+) -> str:
+    """Get a value from command line arguments (key: `args_key`) or config file (key: `config_key`), the former taking precedence."""
+    value_from_args = args.__dict__.get(args_key)
+    return value_from_args if value_from_args is not None else config.get(config_key)
+
+
+def _get_raw_path_list_from_args_and_config(
+    args: argparse.Namespace, config: dict
+) -> list:
+    """
+    Generate a list of raw file paths based on command-line arguments and configuration.
+
+    This function combines file paths specified in the configuration and command-line
+    arguments, including files from specified directories. It filters the resulting
+    list of file paths using a regular expression provided in the arguments.
+
+    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(ConfigKeys.RAW_PATHS, [])
+    raw_path_list += args.file
+
+    if (config_directory := config.get("directory")) is not None:
+        raw_path_list += [
+            os.path.join(config_directory, f) for f in os.listdir(config_directory)
+        ]
+
+    for directory in args.directory:
+        raw_path_list += [os.path.join(directory, f) for f in os.listdir(directory)]
+
+    # filter raw files by regex
+    len_before = len(raw_path_list)
+    raw_path_list = [
+        f
+        for f in raw_path_list
+        if re.search(args.regex, os.path.basename(f)) is not None
+    ]
+    len_after = len(raw_path_list)
+
+    if len_removed := len_before - len_after:
+        print(
+            f"Ignoring {len_removed} / {len_before} file(s) from arguments list due to --regex."
+        )
+
+    return raw_path_list
+
+
+def run(*args, **kwargs):
+    # parse command line arguments
+    args, unknown = parser.parse_known_args()
+
+    if unknown:
+        print(f"Unknown arguments: {unknown}")
+        parser.print_help()
+        return
+
+    if args.version:
+        print(f"{alphadia.__version__}")
+        return
+
+    user_config = _get_config_from_args(args)
+
+    output_directory = _get_from_args_or_config(
+        args, user_config, args_key="output", config_key="output_directory"
+    )
+    if output_directory is None:
+        parser.print_help()
+
+        print("No output directory specified. Please do so via CL-argument or config.")
+        return
+    reporting.init_logging(output_directory)
+
+    # TODO revisit the multiple sources of raw files (cli, config, regex, ...)
+    raw_paths = _get_raw_path_list_from_args_and_config(args, user_config)
+    cli_params_config = {
+        **({ConfigKeys.RAW_PATHS: raw_paths} if raw_paths else {}),
+        **({ConfigKeys.LIBRARY_PATH: args.library} if args.library is not None else {}),
+        **({ConfigKeys.FASTA_PATHS: args.fasta} if args.fasta else {}),
+        **(
+            {ConfigKeys.QUANT_DIRECTORY: args.quant_dir}
+            if args.quant_dir is not None
+            else {}
+        ),
+    }
+
+    # TODO rename all output_directory, output_folder => output_path, quant_dir->quant_path (except cli parameter)
+
+    # important to suppress matplotlib output
+    matplotlib.use("Agg")
+
+    try:
+        SearchPlan(output_directory, user_config, cli_params_config).run_plan()
+
+    except Exception as e:
+        if isinstance(e, CustomError):
+            exit_code = 1
+        else:
+            import traceback
+
+            logger.info(traceback.format_exc())
+            exit_code = 127
+
+        logger.error(e)
+        sys.exit(exit_code)
+
+
+# uncomment for debugging:
+# if __name__ == "__main__":
+#     run()

{alphadia-1.9.1 → alphadia-1.9.3.dev2}/alphadia/constants/default.yaml

@@ -1,6 +1,14 @@
 # configuration for the extraction plan
 version: 1
 
+# These values are typically filled via CLI parameters
+workflow_name: null
+output_directory: null
+library_path: null
+raw_paths: []
+fasta_paths: []
+quant_directory: null
+
 general:
   thread_count: 10
   # maximum number of threads or processes to use per raw file
@@ -8,7 +16,6 @@ general:
   reuse_quant: false
   astral_ms1: false
   log_level: 'INFO'
-  wsl: false
   mmap_detector_events: false
   use_gpu: true
   # whether to save the libraries to the output directory
@@ -26,6 +33,7 @@ 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
@@ -39,8 +47,13 @@ library_prediction:
     - 200
     - 2000
   nce: 25.0
-  # semicolon separated list of fragment types. Supported types are: a, b, c, x, y, z, b_modloss, y_modloss
-  fragment_types: 'b;y'
+
+  # list of fragment types (see alphabase.peptide.fragment.FRAGMENT_TYPES for supported types)
+  # Supported types are: a, b, c, x, y, z, b_modloss, y_modloss, b_H2O, y_H2O, b_NH3, y_NH3, c_lossH, z_addH
+  fragment_types:
+    - 'b'
+    - 'y'
+
   # maximum charge state for predicted fragments
   max_fragment_charge: 2
   instrument: Lumos
@@ -53,33 +66,33 @@ library_prediction:
 
 # define custom alphabase modifications not part of unimod or alphabase
 # also used for decoy channels
-custom_modififcations:
+custom_modifications:
   # Dimethyl @K channel decoy
-  Dimethyl:d12@K:
+  - name: Dimethyl:d12@K
     composition: H(-2)2H(8)13C(2)
 
   # Dimethyl @Any_N-term channel decoy
-  Dimethyl:d12@Any_N-term:
+  - name: Dimethyl:d12@Any_N-term
     composition: H(-2)2H(8)13C(2)
 
   # Dimethyl @Protein_N-term channel decoy
-  Dimethyl:d12@Protein_N-term:
+  - name: Dimethyl:d12@Protein_N-term
     composition: H(-2)2H(8)13C(2)
 
   # mTRAQ @K channel decoy
-  mTRAQ:d12@K:
+  - name: mTRAQ:d12@K
     composition: H(12)C(1)13C(10)15N(2)O(1)
 
   # mTRAQ @Any_N-term channel decoy
-  mTRAQ:d12@Any_N-term:
+  - name: mTRAQ:d12@Any_N-term
     composition: H(12)C(1)13C(14)15N(2)O(1)
 
   # mTRAQ @Protein_N-term channel decoy
-  mTRAQ:d12@Protein_N-term:
+  - name: mTRAQ:d12@Protein_N-term
     composition: H(12)C(1)13C(14)15N(2)O(1)
 
   # SILAC heavy @K channel decoy
-  Label:13C(12)@K:
+  - name: Label:13C(12)@K
     composition: C(12)
 
 search:
@@ -120,9 +133,6 @@ calibration:
   # the maximum number of times an automatic optimizer can be skipped before it is considered to have converged
   max_skips: 1
 
-  # TODO: remove this parameter
-  final_full_calibration: False
-
   # TODO: remove this parameter
   norm_rt_mode: 'linear'
 
@@ -191,23 +201,27 @@ 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
-  multiplex_mapping: {}
+  multiplex_mapping: []
+#    - channel_name: 0
+#      modifications:
+#        mTRAQ@K: mTRAQ@K
+#        mTRAQ@Any_N-term: mTRAQ@Any_N-term
+#
+#    - channel_name: 4
+#      modifications:
+#        mTRAQ@K: mTRAQ:13C(3)15N(1)@K
+#        mTRAQ@Any_N-term: mTRAQ:13C(3)15N(1)@Any_N-term
+#
+#    - channel_name: 8
+#      modifications:
+#        mTRAQ@K: mTRAQ:13C(6)15N(2)@K
+#        mTRAQ@Any_N-term: mTRAQ:13C(6)15N(2)@Any_N-term
+#
+#    - channel_name: 12
+#      modifications:
+#        mTRAQ@K: mTRAQ:d12@K
+#        mTRAQ@Any_N-term: mTRAQ:d12@Any_N-term
 
-    #0:
-    #  mTRAQ@K: mTRAQ@K
-    #  mTRAQ@Any_N-term: mTRAQ@Any_N-term
-
-    #4:
-    #  mTRAQ@K: mTRAQ:13C(3)15N(1)@K
-    #  mTRAQ@Any_N-term: mTRAQ:13C(3)15N(1)@Any_N-term
-
-    #8:
-    #  mTRAQ@K: mTRAQ:13C(6)15N(2)@K
-    #  mTRAQ@Any_N-term: mTRAQ:13C(6)15N(2)@Any_N-term
-
-    #12:
-    #  mTRAQ@K: mTRAQ:d12@K
-    #  mTRAQ@Any_N-term: mTRAQ:d12@Any_N-term
 
 
 
@@ -225,6 +239,13 @@ fdr:
   keep_decoys: false
   channel_wise_fdr: false
   inference_strategy: "heuristic"
+  # (Experimental)
+  # uses a two-step classifier consisting of a logistic regression and a neural network, with a default maximum of 5 iterations per fitting call
+  enable_two_step_classifier: false
+  two_step_classifier_max_iterations: 5
+  # (Experimental)
+  # Optimizes the batch size and learning rate of the neural network
+  enable_nn_hyperparameter_tuning: false
 
 search_output:
   peptide_level_lfq: false
@@ -313,8 +334,9 @@ transfer_library:
   # if true, the library is created for transfer learning
   enabled: False
 
-  # semicolon separated list of fragment types to include in the library. possible values are 'a', 'b', 'c', 'x', 'y', 'z'
-  fragment_types: 'b;y'
+  # list of fragment types (see alphabase.peptide.fragment.FRAGMENT_TYPES for supported types)
+  # Supported types are: a, b, c, x, y, z, b_modloss, y_modloss, b_H2O, y_H2O, b_NH3, y_NH3, c_lossH, z_addH
+  fragment_types: ['b', 'y']
 
   # maximum charge for fragments
   max_charge: 2
@@ -373,54 +395,8 @@ 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:
-  - name: fragment
-    estimators:
-      - name: mz
-        model: LOESSRegression
-        model_args:
-          n_kernels: 2
-        input_columns:
-          - mz_library
-        target_columns:
-          - mz_observed
-        output_columns:
-          - mz_calibrated
-        transform_deviation: 1e6
-  - name: precursor
-    estimators:
-        - name: mz
-          model: LOESSRegression
-          model_args:
-            n_kernels: 2
-          input_columns:
-            - mz_library
-          target_columns:
-            - mz_observed
-          output_columns:
-            - mz_calibrated
-          transform_deviation: 1e6
-        - name: rt
-          model: LOESSRegression
-          model_args:
-            n_kernels: 6
-          input_columns:
-            - rt_library
-          target_columns:
-            - rt_observed
-          output_columns:
-            - rt_calibrated
-        - name: mobility
-          model: LOESSRegression
-          model_args:
-            n_kernels: 2
-          input_columns:
-            - mobility_library
-          target_columns:
-            - mobility_observed
-          output_columns:
-            - mobility_calibrated
+
+# scope of default yaml should be one search step
+multistep_search:
+  transfer_step_enabled: False
+  mbr_step_enabled: False

alphadia-1.9.3.dev2/alphadia/constants/keys.py

@@ -0,0 +1,34 @@
+class ConstantsClass(type):
+    """A metaclass for classes that should only contain string constants."""
+
+    def __setattr__(self, name, value):
+        raise TypeError("Constants class cannot be modified")
+
+    def get_values(cls):
+        """Get all user-defined string values of the class."""
+        return [
+            value
+            for key, value in cls.__dict__.items()
+            if not key.startswith("__") and isinstance(value, str)
+        ]
+
+
+class StatOutputKeys(metaclass=ConstantsClass):
+    """String constants for reading and writing output columns for the `stat` file."""
+
+    # optimization
+    OPTIMIZATION_PREFIX = "optimization."
+    MS1_ERROR = "ms1_error"
+    MS2_ERROR = "ms2_error"
+    RT_ERROR = "rt_error"
+    MOBILITY_ERROR = "mobility_error"
+
+
+class ConfigKeys(metaclass=ConstantsClass):
+    """String constants for accessing the config."""
+
+    OUTPUT_DIRECTORY = "output_directory"
+    LIBRARY_PATH = "library_path"
+    RAW_PATHS = "raw_paths"
+    FASTA_PATHS = "fasta_paths"
+    QUANT_DIRECTORY = "quant_directory"