Add coverage factor

metagenopolis · Mar 13, 2024 · 1a3a77b · 1a3a77b
1 parent 0b4f252
commit 1a3a77b
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 4 deletions.
diff --git a/meteor/merging.py b/meteor/merging.py
@@ -338,7 +338,7 @@ def execute(self) -> None:
             ]
             if self.remove_sample_with_no_msp:
                 # Filter the DataFrame to keep only columns with a non-zero sum
-                filtered_df = filtered_df.loc[:, (merged_df.sum() != 0)]
+                filtered_df = filtered_df.loc[:, (filtered_df.sum(axis=0) != 0)]
             if my_pattern == "msp":
                 annotation = pd.read_csv(
                     self.meteor.ref_dir

diff --git a/meteor/meteor.py b/meteor/meteor.py
@@ -367,6 +367,13 @@ def get_arguments() -> Namespace:  # pragma: no cover
         default="coverage",
         help="Normalization applied to gene abundance (default coverage).",
     )
+    profiling_parser.add_argument(
+        "-c",
+        dest="coverage_factor",
+        type=float,
+        default=100.0,
+        help="Multiplication factor for coverage normalization (Default 100.0).",
+    )
     profiling_parser.add_argument(
         "--core_size",
         dest="core_size",
@@ -732,6 +739,7 @@ def main() -> None:  # pragma: no cover
             args.core_size,
             args.msp_filter,
             args.completeness,
+            args.coverage_factor,
         )
         profiler.execute()
     # Run merging

diff --git a/meteor/profiler.py b/meteor/profiler.py
@@ -37,6 +37,7 @@ class Profiler(Session):
     core_size: int
     msp_filter: float
     completeness: float
+    coverage_factor: float = 100.0
 
     def __post_init__(self):
         # Get the json file
@@ -199,11 +200,11 @@ def normalize_coverage(self, trim_length: int) -> None:
         ]
 
         choicelist = [
-            (100.0 * self.gene_count["value"])
+            (self.coverage_factor * self.gene_count["value"])
             / (self.gene_count["gene_length"] - trim_length + 1),
-            (100.0 * self.gene_count["value"] * 4 * trim_length)
+            (self.coverage_factor * self.gene_count["value"] * 4 * trim_length)
             / (self.gene_count["gene_length"] * (self.gene_count["gene_length"] + 2)),
-            (100.0 * self.gene_count["value"] * 4 * trim_length)
+            (self.coverage_factor * self.gene_count["value"] * 4 * trim_length)
             / (self.gene_count["gene_length"] + 1) ** 2,
         ]
         self.gene_count["value"] = np.select(condlist, choicelist)