Multi-species protein group module

proteobench/datapoint/quant_datapoint.py

@@ -61,9 +61,10 @@ def filter_df_numquant_epsilon(
     return None
 
 
-def filter_df_numquant_nr_prec(row: pd.Series, min_quant: int = 3) -> int | None:
+def filter_df_numquant_nr_feature(row: pd.Series, min_quant: int = 3) -> int | None:
     """
-    Extract the 'nr_prec' value from a row (assumed to be a dictionary).
+    Extract the 'nr_feature' value from a row (assumed to be a dictionary).
+    Falls back to 'nr_prec' for backward compatibility with legacy data.
 
     Parameters
     ----------
@@ -75,12 +76,13 @@ def filter_df_numquant_nr_prec(row: pd.Series, min_quant: int = 3) -> int | None
     Returns
     -------
     int, None
-        The 'nr_prec' value if found, otherwise None.
+        The 'nr_feature' or 'nr_prec' value if found, otherwise None.
     """
     if isinstance(list(row.keys())[0], str):
         min_quant = str(min_quant)
     if isinstance(row, dict) and min_quant in row and isinstance(row[min_quant], dict):
-        return row[min_quant].get("nr_prec")
+        # Try nr_feature first (new standard), then nr_prec (legacy)
+        return row[min_quant].get("nr_feature") or row[min_quant].get("nr_prec")
     return None
 
 
@@ -284,7 +286,7 @@ class QuantDatapointHYE(DatapointBase):
         mean_abs_epsilon_precision_global (float): Mean absolute precision epsilon (deviation from empirical center).
         median_abs_epsilon_precision_eq_species (float): Median absolute precision epsilon for equivalently weighted species.
         mean_abs_epsilon_precision_eq_species (float): Mean absolute precision epsilon for equivalently weighted species.
-        nr_prec (int): Number of precursors identified.
+        nr_feature (int): Number of features identified.
         comments (str): Any additional comments.
         proteobench_version (str): Version of the Proteobench tool used.
     """
@@ -315,7 +317,7 @@ class QuantDatapointHYE(DatapointBase):
     mean_abs_epsilon_precision_global: float = 0
     median_abs_epsilon_precision_eq_species: float = 0
     mean_abs_epsilon_precision_eq_species: float = 0
-    nr_prec: int = 0
+    nr_feature: int = 0
     comments: str = ""
     proteobench_version: str = ""
 
@@ -348,7 +350,7 @@ def generate_datapoint(
             The format of the input data (e.g., file format).
         user_input : dict
             User-defined input values for the benchmark.
-        default_cutoff_min_prec : int, optional
+        default_cutoff_min_feature : int, optional
             The default minimum precursor cutoff value. Defaults to 3.
         max_nr_observed : int, optional
             Maximum nr_observed value to calculate metrics for. If None, defaults to 6.
@@ -408,31 +410,31 @@ def generate_datapoint(
             )
         )
         result_datapoint.results = results
-        result_datapoint.median_abs_epsilon_global = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.median_abs_epsilon_global = result_datapoint.results[default_cutoff_min_feature][
             "median_abs_epsilon_global"
         ]
-        result_datapoint.mean_abs_epsilon_global = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.mean_abs_epsilon_global = result_datapoint.results[default_cutoff_min_feature][
             "mean_abs_epsilon_global"
         ]
-        result_datapoint.median_abs_epsilon_eq_species = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.median_abs_epsilon_eq_species = result_datapoint.results[default_cutoff_min_feature][
             "median_abs_epsilon_eq_species"
         ]
-        result_datapoint.mean_abs_epsilon_eq_species = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.mean_abs_epsilon_eq_species = result_datapoint.results[default_cutoff_min_feature][
             "mean_abs_epsilon_eq_species"
         ]
-        result_datapoint.median_abs_epsilon_precision_global = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.median_abs_epsilon_precision_global = result_datapoint.results[default_cutoff_min_feature][
             "median_abs_epsilon_precision_global"
         ]
-        result_datapoint.mean_abs_epsilon_precision_global = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.mean_abs_epsilon_precision_global = result_datapoint.results[default_cutoff_min_feature][
             "mean_abs_epsilon_precision_global"
         ]
-        result_datapoint.median_abs_epsilon_precision_eq_species = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.median_abs_epsilon_precision_eq_species = result_datapoint.results[default_cutoff_min_feature][
             "median_abs_epsilon_precision_eq_species"
         ]
-        result_datapoint.mean_abs_epsilon_precision_eq_species = result_datapoint.results[default_cutoff_min_prec][
+        result_datapoint.mean_abs_epsilon_precision_eq_species = result_datapoint.results[default_cutoff_min_feature][
             "mean_abs_epsilon_precision_eq_species"
         ]
-        result_datapoint.nr_prec = result_datapoint.results[default_cutoff_min_prec]["nr_prec"]
+        result_datapoint.nr_feature = result_datapoint.results[default_cutoff_min_feature]["nr_feature"]
 
         results_series = pd.Series(dataclasses.asdict(result_datapoint))
 

proteobench/github/gh.py

@@ -9,7 +9,15 @@
 
 import pandas as pd
 from git import Repo, exc
-from github import Github
+
+# Make GitHub functionality optional
+try:
+    from github import Github
+
+    GITHUB_AVAILABLE = True
+except ImportError:
+    Github = None
+    GITHUB_AVAILABLE = False
 
 logger = logging.getLogger(__name__)
 
@@ -38,6 +46,11 @@ class GithubProteobotRepo:
     A class to interact with GitHub repositories related to Proteobot and Proteobench,
     allowing cloning, committing, and creating pull requests.
 
+    Note
+    ----
+    Pull request functionality requires PyGithub to be installed.
+    Repository cloning and local Git operations work without PyGithub.
+
     Parameters
     ----------
     token : str | None, optional
@@ -91,6 +104,18 @@ def __init__(
         self.branch = branch
         self.repo = None
 
+    @staticmethod
+    def is_github_available() -> bool:
+        """
+        Check if PyGithub is available for GitHub API operations.
+
+        Returns
+        -------
+        bool
+            True if PyGithub is available, False otherwise.
+        """
+        return GITHUB_AVAILABLE
+
     def get_remote_url_anon(self) -> str:
         """
         Return the remote URL of the repository to be cloned anonymously (public access).
@@ -245,9 +270,9 @@ def read_results_json_repo(self) -> pd.DataFrame:
                     data.append(pd.read_json(f, typ="series"))
         if not data:
             try:
-                self.read_results_json_repo_single_file()
+                return self.read_results_json_repo_single_file()
             except FileNotFoundError:
-                data = []
+                raise FileNotFoundError("No JSON data files found in repository and no results.json fallback available")
 
         return pd.DataFrame(data)
 
@@ -371,7 +396,24 @@ def create_pull_request(self, commit_name: str, commit_message: str, submission_
         -------
         int
             The pull request number assigned by GitHub.
+
+        Raises
+        ------
+        ImportError
+            If PyGithub is not installed.
+        ValueError
+            If no GitHub token is provided.
         """
+        if not GITHUB_AVAILABLE:
+            raise ImportError(
+                "PyGithub is not installed. Please install it with: " "pip install PyGithub or conda install pygithub"
+            )
+
+        if not self.token:
+            raise ValueError(
+                "GitHub token is required for creating pull requests. " "Please provide a valid GitHub token."
+            )
+
         g = Github(self.token)
         repo = g.get_repo(self.proteobot_repo_name)
         base = repo.get_branch("master")

proteobench/io/params/json/Quant/quant_lfq_DIA_proteingroup.json

@@ -0,0 +1,142 @@
+{
+    "software_name": {
+        "type": "text_input",
+        "label": "Software name",
+        "placeholder": "None"
+    },
+    "software_version": {
+        "type": "text_input",
+        "label": "Software tool version",
+        "placeholder": "1.0"
+    },
+    "search_engine": {
+        "type": "text_input",
+        "label": "Search engine name",
+        "placeholder": "None"
+    },
+    "search_engine_version": {
+        "type": "text_input",
+        "label": "Search engine version",
+        "placeholder": "None"
+    },
+    "ident_fdr_psm": {
+        "type": "text_input",
+        "label": "FDR psm",
+        "placeholder": "None"
+    },
+    "ident_fdr_peptide": {
+        "type": "text_input",
+        "label": "FDR peptide",
+        "placeholder": "None"
+    },
+    "ident_fdr_protein": {
+        "type": "text_input",
+        "label": "FDR protein",
+        "placeholder": "None"
+    },
+    "enable_match_between_runs": {
+        "type": "checkbox",
+        "label": "Quantified with MBR",
+        "value": false
+    },
+    "precursor_mass_tolerance": {
+        "type": "text_input",
+        "label": "Precursor mass tolerance (including unit ppm, PPM or Da)",
+        "placeholder": "None"
+    },
+    "fragment_mass_tolerance": {
+        "type": "text_input",
+        "label": "Fragment mass tolerance (including unit ppm, PPM or Da)",
+        "placeholder": "None"
+    },
+    "enzyme": {
+        "type": "text_input",
+        "label": "Proteolytic Enzyme",
+        "placeholder": "None"
+    },
+    "allowed_miscleavages": {
+        "type": "text_input",
+        "label": "Maximum allowed number of missed cleavage",
+        "placeholder": "None"
+    },
+    "min_peptide_length": {
+        "type": "text_input",
+        "label": "Minimum peptide length",
+        "placeholder": "None"
+    },
+    "max_peptide_length": {
+        "type": "text_input",
+        "label": "Maximum peptide length",
+        "placeholder": "None"
+    },
+    "fixed_mods": {
+        "type": "text_input",
+        "label": "Specify the fixed mods that were set",
+        "placeholder": "None"
+    },
+    "variable_mods": {
+        "type": "text_input",
+        "label": "Specify the variable mods that were set (separated by a comma)",
+        "placeholder": "None"
+    },
+    "max_mods": {
+        "type": "text_input",
+        "label": "Maximum number of modifications",
+        "placeholder": "None"
+    },
+    "min_precursor_charge": {
+        "type": "text_input",
+        "label": "Minimum precursor charge allowed",
+        "placeholder": "None"
+    },
+    "max_precursor_charge": {
+        "type": "text_input",
+        "label": "Maximum precursor charge allowed",
+        "placeholder": "None"
+    },
+    "min_precursor_mz": {
+        "type": "text_input",
+        "label": "Minimum precursor m/z",
+        "placeholder": "None"
+    },
+    "max_precursor_mz": {
+        "type": "text_input",
+        "label": "Maximum precursor m/z",
+        "placeholder": "None"
+    },
+    "min_fragment_mz": {
+        "type": "text_input",
+        "label": "Minimum fragment m/z",
+        "placeholder": "None"
+    },
+    "max_fragment_mz": {
+        "type": "text_input",
+        "label": "Maximum fragment m/z",
+        "placeholder": "None"
+    },
+    "quantification_method": {
+        "type": "text_input",
+        "label": "Quantification method",
+        "placeholder": "None"
+    },
+    "protein_inference": {
+        "type": "text_input",
+        "label": "Protein inference method",
+        "placeholder": "None"
+    },
+    "abundance_normalization_ions": {
+        "type": "text_input",
+        "label": "Abundance normalization method",
+        "placeholder": "None"
+    },
+    "predictors_library": {
+        "type": "text_input",
+        "label": "Utilized spectral library",
+        "placeholder": "None"
+    },
+    "scan_window": {
+        "type": "text_input",
+        "label": "Window scanning size",
+        "placeholder": "None"
+    }
+}

proteobench/io/parsing/io_parse_settings/Quant/lfq/DDA/ion/Astral/module_settings.toml

@@ -13,4 +13,5 @@
 
 [general]
 "min_count_multispec" = 1
-"level" = "ion"
+"level" = "precursor ion"
+"y_axis_title" = "Total number of precursor ions quantified in the selected number of raw files"

proteobench/io/parsing/io_parse_settings/Quant/lfq/DDA/ion/QExactive/module_settings.toml

@@ -13,4 +13,5 @@
 
 [general]
 "min_count_multispec" = 1
-"level" = "ion"
+"level" = "precursor ion"
+"y_axis_title" = "Total number of precursor ions quantified in the selected number of raw files"

proteobench/io/parsing/io_parse_settings/Quant/lfq/DDA/peptidoform/module_settings.toml

@@ -14,3 +14,4 @@
 [general]
 "min_count_multispec" = 1
 "level" = "peptidoform"
+"y_axis_title" = "Total number of peptidoforms quantified in the selected number of raw files"

proteobench/io/parsing/io_parse_settings/Quant/lfq/DIA/ion/AIF/module_settings.toml

@@ -13,4 +13,5 @@
 
 [general]
 "min_count_multispec" = 1
-"level" = "ion"
+"level" = "precursor ion"
+"y_axis_title" = "Total number of precursor ions quantified in the selected number of raw files"

proteobench/io/parsing/io_parse_settings/Quant/lfq/DIA/ion/Astral/module_settings.toml

@@ -13,4 +13,5 @@
 
 [general]
 "min_count_multispec" = 1
-"level" = "ion"
+"level" = "precursor ion"
+"y_axis_title" = "Total number of precursor ions quantified in the selected number of raw files"

proteobench/io/parsing/io_parse_settings/Quant/lfq/DIA/ion/ZenoTOF/module_settings.toml

@@ -13,4 +13,5 @@
 
 [general]
 "min_count_multispec" = 1
-"level" = "ion"
+"level" = "precursor ion"
+"y_axis_title" = "Total number of precursor ions quantified in the selected number of raw files"

proteobench/io/parsing/io_parse_settings/Quant/lfq/DIA/ion/diaPASEF/module_settings.toml

@@ -13,4 +13,5 @@
 
 [general]
 "min_count_multispec" = 1
-"level" = "ion"
+"level" = "precursor ion"
+"y_axis_title" = "Total number of precursor ions quantified in the selected number of raw files"

proteobench/io/parsing/io_parse_settings/Quant/lfq/DIA/ion/singlecell/module_settings.toml

@@ -9,4 +9,5 @@
 
 [general]
 "min_count_multispec" = 1
-"level" = "ion"
+"level" = "precursor ion"
+"y_axis_title" = "Total number of precursor ions quantified in the selected number of raw files"