Merge branch 'main' into split_json_results

proteobench/datapoint/quant_datapoint.py

@@ -58,12 +58,12 @@ class Datapoint:
     Attributes:
         id (str): Unique identifier for the benchmark run.
         software_name (str): Name of the software used in the benchmark.
-        software_version (int): Version of the software.
+        software_version (str): Version of the software.
         search_engine (str): Name of the search engine used.
-        search_engine_version (int): Version of the search engine.
-        ident_fdr_psm (int): False discovery rate for PSMs.
-        ident_fdr_peptide (int): False discovery rate for peptides.
-        ident_fdr_protein (int): False discovery rate for proteins.
+        search_engine_version (str): Version of the search engine.
+        ident_fdr_psm (float): False discovery rate for PSMs.
+        ident_fdr_peptide (float): False discovery rate for peptides.
+        ident_fdr_protein (float): False discovery rate for proteins.
         enable_match_between_runs (bool): Whether matching between runs is enabled.
         precursor_mass_tolerance (str): Mass tolerance for precursor ions.
         fragment_mass_tolerance (str): Mass tolerance for fragment ions.
@@ -74,7 +74,8 @@ class Datapoint:
         is_temporary (bool): Whether the data is temporary.
         intermediate_hash (str): Hash of the intermediate result.
         results (dict): A dictionary of metrics for the benchmark run.
-        median_abs_epsilon (int): Median absolute epsilon value for the benchmark.
+        median_abs_epsilon (float): Median absolute epsilon value for the benchmark.
+        mean_abs_epsilon (float): Mean absolute epsilon value for the benchmark.
         nr_prec (int): Number of precursors identified.
         comments (str): Any additional comments.
         proteobench_version (str): Version of the Proteobench tool used.
@@ -98,8 +99,8 @@ class Datapoint:
     is_temporary: bool = True
     intermediate_hash: str = ""
     results: dict = None
-    median_abs_epsilon: int = 0
-    mean_abs_epsilon: int = 0
+    median_abs_epsilon: float = 0
+    mean_abs_epsilon: float = 0
     nr_prec: int = 0
     comments: str = ""
     proteobench_version: str = ""
@@ -171,6 +172,7 @@ def generate_datapoint(
         result_datapoint.results = results
         result_datapoint.median_abs_epsilon = result_datapoint.results[default_cutoff_min_prec]["median_abs_epsilon"]
         result_datapoint.mean_abs_epsilon = result_datapoint.results[default_cutoff_min_prec]["mean_abs_epsilon"]
+        result_datapoint.nr_prec = result_datapoint.results[default_cutoff_min_prec]["nr_prec"]
 
         results_series = pd.Series(dataclasses.asdict(result_datapoint))
 

proteobench/github/gh.py

@@ -26,8 +26,8 @@ def __init__(
         token: Optional[str] = None,
         clone_dir: str = None,
         clone_dir_pr: str = None,
-        proteobench_repo_name: str = "Proteobench/Results_Module2_quant_DDA",
-        proteobot_repo_name: str = "Proteobot/Results_Module2_quant_DDA",
+        proteobench_repo_name: str = "Proteobench/Results_quant_ion_DDA",
+        proteobot_repo_name: str = "Proteobot/Results_quant_ion_DDA",
         username: str = "Proteobot",
     ):
         """
@@ -37,8 +37,8 @@ def __init__(
             token (str | None, optional): GitHub access token for authenticated access. Defaults to None.
             clone_dir (str): Directory where the repository will be cloned.
             clone_dir_pr (str): Directory for cloning pull request repositories.
-            proteobench_repo_name (str, optional): Name of the Proteobench repository. Defaults to "Proteobench/Results_Module2_quant_DDA".
-            proteobot_repo_name (str, optional): Name of the Proteobot repository. Defaults to "Proteobot/Results_Module2_quant_DDA".
+            proteobench_repo_name (str, optional): Name of the Proteobench repository. Defaults to "Proteobench/Results_quant_ion_DDA".
+            proteobot_repo_name (str, optional): Name of the Proteobot repository. Defaults to "Proteobot/Results_quant_ion_DDA".
             username (str, optional): GitHub username for authentication. Defaults to "Proteobot".
         """
         self.token = token
@@ -112,7 +112,7 @@ def clone_repo(self) -> Repo:
         Returns:
             Repo: The local repository object.
         """
-        if self.token is None:
+        if self.token is None or self.token == "":
             self.repo = self.clone_repo_anonymous()
         else:
             remote = f"https://{self.username}:{self.token}@github.com/{self.proteobench_repo_name}.git"
@@ -128,7 +128,7 @@ def clone_repo_pr(self) -> Repo:
         Returns:
             Repo: The local repository object for the pull request.
         """
-        if self.token is None:
+        if self.token is None or self.token == "":
             self.repo = self.clone_repo_anonymous()
         else:
             remote = f"https://{self.username}:{self.token}@github.com/{self.proteobot_repo_name}.git"

proteobench/io/params/peaks.py

@@ -117,12 +117,17 @@ def read_peaks_settings(file_path: str) -> ProteoBenchParameters:
     """
     # Try to read the file contents
 
-    try:
-        # Attempt to open and read the file
-        with open(file_path, encoding="utf-8") as f:
-            lines = f.readlines()
-    except Exception as e:
-        raise IOError(f"Failed to open or read the file at {file_path}. Error: {e}")
+    # Check if file_path is an UploadedFile instance
+    if hasattr(file_path, "read"):
+        # Assume it behaves like a file object
+        lines = file_path.read().decode("utf-8").splitlines()
+    else:
+        try:
+            # Attempt to open and read the file
+            with open(file_path, encoding="utf-8") as f:
+                lines = f.readlines()
+        except Exception as e:
+            raise IOError(f"Failed to open or read the file at {file_path}. Error: {e}")
 
     # Remove any trailing newline characters from each line
     lines = [line.strip() for line in lines]

proteobench/modules/quant/lfq/ion/DDA/quant_lfq_ion_DDA.py

@@ -27,8 +27,8 @@ class DDAQuantIonModule(QuantModule):
     def __init__(
         self,
         token: str,
-        proteobench_repo_name: str = "Proteobench/Results_Module2_quant_DDA",
-        proteobot_repo_name: str = "Proteobot/Results_Module2_quant_DDA",
+        proteobench_repo_name: str = "Proteobench/Results_quant_ion_DDA",
+        proteobot_repo_name: str = "Proteobot/Results_quant_ion_DDA",
         # TODO: Figure out how to do nicer relative calls
         parse_settings_dir: str = os.path.abspath(
             os.path.join(

test/test_github_repo.py

@@ -18,10 +18,10 @@ def test_clone_repo_anonymous():
     tmp_dir = TemporaryDirectory()
     temp_dir_name = tmp_dir.name
 
-    github_repo = GithubProteobotRepo("", temp_dir_name, proteobot_repo_name="Proteobench/Results_Module2_quant_DDA")
+    github_repo = GithubProteobotRepo("", temp_dir_name, proteobot_repo_name="Proteobench/Results_quant_ion_DDA")
     url = github_repo.get_remote_url_anon()
-    # assert that url equal 'https://github.com/Proteobench/Results_Module2_quant_DDA.git'
-    # assert url == 'https://github.com/Proteobench/Results_Module2_quant_DDA.git'
+    # assert that url equal 'https://github.com/Proteobench/Results_quant_ion_DDA.git'
+    # assert url == 'https://github.com/Proteobench/Results_quant_ion_DDA.git'
     repo = github_repo.clone_repo_anonymous()
     assert isinstance(repo, Repo)
     jsonfile = github_repo.read_results_json_repo()