Revert mistaken merge (#209)

* feat: include optional dependencies

Signed-off-by: Josh Loecker <joshloecker@icloud.com>

* fix: include taxon id and input format

Signed-off-by: Josh Loecker <joshloecker@icloud.com>

* fix: update requirements based on CC

Signed-off-by: Josh Loecker <joshloecker@icloud.com>

---------

Signed-off-by: Josh Loecker <joshloecker@icloud.com>

Author: JoshLoecker

main/COMO.ipynb

@@ -340,11 +340,11 @@ def _build_with_imat(
 def _build_with_tinit(cobra_model: cobra.Model, s_matrix, lb, ub, expr_vector, solver, idx_force) -> Model:
     properties = tINITProperties(
         reactions_scores=expr_vector,
-        solver=solver,
         essential_reactions=idx_force,
         production_weight=0.0,
         allow_excretion=False,
         no_reverse_loops=True,
+        solver=solver,
     )
     algorithm = tINIT(s_matrix, lb, ub, properties)
     algorithm.preprocessing()
@@ -565,7 +565,6 @@ def _collect_boundary_reactions(path: Path) -> _BoundaryReactions:
     for column in df.columns:
         if column not in [
             "boundary",
-            "reaction",
             "abbreviation",
             "compartment",
             "minimum reaction rate",
@@ -577,7 +576,7 @@ def _collect_boundary_reactions(path: Path) -> _BoundaryReactions:
             )
 
     reactions: list[str] = [""] * len(df)
-    boundary_type: list[str] = df["reaction"].tolist()
+    boundary_type: list[str] = df["boundary"].tolist()
     reaction_abbreviation: list[str] = df["abbreviation"].tolist()
     reaction_compartment: list[str] = df["compartment"].tolist()
     lower_bound = df["minimum reaction rate"].tolist()

main/como/create_context_specific_model.py

@@ -297,8 +297,8 @@ def calculate_tpm(metrics: NamedMetrics) -> NamedMetrics:
 
 def calculate_fpkm(metrics: NamedMetrics) -> NamedMetrics:
     """Calculate the Fragments Per Kilobase of transcript per Million mapped reads (FPKM) for each sample in the metrics dictionary."""  # noqa: E501
-    matrix_values = []
     for study in metrics:
+        matrix_values = []
         for sample in range(metrics[study].num_samples):
             layout = metrics[study].layout[sample]
             count_matrix: npt.NDArray = metrics[study].count_matrix.iloc[:, sample].values
@@ -311,7 +311,7 @@ def calculate_fpkm(metrics: NamedMetrics) -> NamedMetrics:
                 case LayoutMethod.paired_end:  # FPKM
                     mean_fragment_lengths = metrics[study].fragment_lengths[sample]
                     # Ensure non-negative value
-                    effective_length = [max(0, size - (mean_fragment_lengths + 1)) for size in gene_size]
+                    effective_length = [max(1e-9, size - (mean_fragment_lengths + 1)) for size in gene_size]
                     n = count_matrix.sum()
                     fpkm = ((count_matrix + 1) * 1e9) / (np.array(effective_length) * n)
                     matrix_values.append(fpkm)
@@ -326,7 +326,6 @@ def calculate_fpkm(metrics: NamedMetrics) -> NamedMetrics:
         fpkm_matrix = pd.DataFrame(matrix_values).T  # Transpose is needed because values were appended as rows
         fpkm_matrix = fpkm_matrix[~pd.isna(fpkm_matrix)]
         metrics[study].normalization_matrix = fpkm_matrix
-
         metrics[study].normalization_matrix.columns = metrics[study].count_matrix.columns
 
     return metrics

main/como/rnaseq.py

@@ -99,6 +99,10 @@ async def _handle_context_batch(
         )
         rnaseq_output_filepath.parent.mkdir(parents=True, exist_ok=True)
 
+        write_zfpkm_png_filepath = write_zfpkm_png_filepath or Path(
+            f"data/results/{context_name}/zfpkm_{prep.value}_{context_name}.png"
+        )
+
         await save_rnaseq_tests(
             context_name=context_name,
             counts_matrix_filepath=rnaseq_input_filepath,

main/como/rnaseq_gen.py

@@ -351,7 +351,7 @@ async def _create_config_df(context_name: str) -> pd.DataFrame:  # noqa: C901
                 f"this should be defined by user if using zFPKM or rnaseq_gen.py will not run"
             )
         elif len(layout_files) == 1:
-            with layout_files[0].open("w") as file:
+            with layout_files[0].open("r") as file:
                 layout = file.read().strip()
         elif len(layout_files) > 1:
             raise ValueError(
@@ -367,7 +367,7 @@ async def _create_config_df(context_name: str) -> pd.DataFrame:  # noqa: C901
                 f"infer the strandedness when writing the counts matrix"
             )
         elif len(strand_files) == 1:
-            with strand_files[0].open("w") as file:
+            with strand_files[0].open("r") as file:
                 strand = file.read().strip()
         elif len(strand_files) > 1:
             raise ValueError(
@@ -379,7 +379,7 @@ async def _create_config_df(context_name: str) -> pd.DataFrame:  # noqa: C901
         if len(prep_files) == 0:
             logger.warning(f"No prep file found for {label}, assuming 'total' as in Total RNA library preparation")
         elif len(prep_files) == 1:
-            with prep_files[0].open("w") as file:
+            with prep_files[0].open("r") as file:
                 prep = file.read().strip().lower()
                 if prep not in ["total", "mrna"]:
                     raise ValueError(f"Prep method must be either 'total' or 'mrna' for {label}")

main/como/rnaseq_preprocess.py

@@ -1,11 +1,14 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
 [project]
 name = "COMO"
 dynamic = ["version"]
 requires-python = ">=3.10,<3.13"
 dependencies = [
     "cobra>=0.28.0",
     "fast-bioservices>=0.3.9",
-    "gurobipy>=11.0",
     "kaleido==0.2.1",
     "loguru>=0.7.2",
     "pandas>=1.3.5",
@@ -21,9 +24,20 @@ dependencies = [
     "cobamp@git+https://github.com/JoshLoecker/cobamp@master",
 ]
 
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
+[project.optional-dependencies]
+gurobi = [ "gurobipy>=10.0.0" ]
+interactive = [
+    "jupyterlab>=4.0.0",
+    "ipython>=7.0.0"
+]
+dev = [
+    "commitlint>=1.3.0",
+    "pytest-asyncio>=0.24.0",
+    "pytest>=8.0.0",
+    "ruff>=0.8.0",
+    "hypothesis>=6.122.1",
+    "pytest-cov>=6.0.0",
+]
 
 [tool.hatch.version]
 path = "main/como/__init__.py"
@@ -35,14 +49,4 @@ packages = ["main/como"]
 allow-direct-references = true
 
 [tool.pytest.ini_options]
-pythonpath = [ "main/src" ]
-
-[tool.uv]
-dev-dependencies = [
-    "commitlint>=1.3.0",
-    "pytest-asyncio>=0.24.0",
-    "pytest>=8.3.3",
-    "ruff>=0.8.0",
-    "hypothesis>=6.122.1",
-    "pytest-cov>=6.0.0",
-]
+pythonpath = [ "main/src" ]