Merge branch 'main' into develop

# Conflicts:
#	main/como/rnaseq.py

Author: JoshLoecker

main/como/create_context_specific_model.py

@@ -550,6 +550,7 @@ def _collect_boundary_reactions(path: Path) -> _BoundaryReactions:
     df = _create_df(path)
     for column in df.columns:
         if column not in [
+            "boundary",
             "reaction",
             "abbreviation",
             "compartment",
@@ -561,31 +562,25 @@ def _collect_boundary_reactions(path: Path) -> _BoundaryReactions:
                 f"'Minimum Reaction Rate', and 'Maximum Reaction Rate'. Found: {column}"
             )
 
-    reactions: list[str] = []
+    reactions: list[str] = [""] * len(df)
     boundary_type: list[str] = df["reaction"].tolist()
     reaction_abbreviation: list[str] = df["abbreviation"].tolist()
     reaction_compartment: list[str] = df["compartment"].tolist()
-    lower_bounds = df["minimum reaction rate"].tolist()
-    upper_bounds = df["maximum reaction rate"].tolist()
+    lower_bound = df["minimum reaction rate"].tolist()
+    upper_bound = df["maximum reaction rate"].tolist()
+    boundary_map = {"exchange": "EX", "demand": "DM", "sink": "SK"}
     for i in range(len(boundary_type)):
-        current_type: str = boundary_type[i]
-        temp_reaction: str = ""
-
-        match current_type.lower():
-            case "exchange":
-                temp_reaction += "EX_"
-            case "demand":
-                temp_reaction += "DM_"
-            case "sink":
-                temp_reaction += "SK_"
+        boundary: str = boundary_type[i].lower()
+        if boundary not in boundary_map:
+            raise ValueError(f"Boundary reaction type must be 'Exchange', 'Demand', or 'Sink'. Found: {boundary[i]}")
 
         shorthand_compartment = Compartments.get(reaction_compartment[i])
-        temp_reaction += f"{reaction_abbreviation[i]}[{shorthand_compartment}]"
-        reactions.append(temp_reaction)
+        reactions[i] = f"{boundary_map.get(boundary)}_{reaction_abbreviation[i]}[{shorthand_compartment}]"
+
     return _BoundaryReactions(
         reactions=reactions,
-        lower_bounds=lower_bounds,
-        upper_bounds=upper_bounds,
+        lower_bounds=lower_bound,
+        upper_bounds=upper_bound,
     )
 
 

main/como/rnaseq_gen.py

@@ -3,6 +3,7 @@
 import argparse
 import asyncio
 from dataclasses import dataclass
+from pathlib import Path
 
 import pandas as pd
 from fast_bioservices import Taxon
@@ -24,6 +25,7 @@ class _Arguments:
     minimum_cutoff: int | str
     library_prep: RNAPrepMethod
     taxon: Taxon
+    write_zfpkm_png_filepath: Path
 
     def __post_init__(self):
         self.library_prep = RNAPrepMethod.from_string(str(self.library_prep))
@@ -48,6 +50,7 @@ async def _handle_context_batch(
     cut_off: int | float | str,
     prep: RNAPrepMethod,
     taxon: Taxon,
+    write_zfpkm_png_filepath: Path,
 ) -> None:
     """Iterate through each context type and create rnaseq expression file.
 
@@ -110,6 +113,7 @@ async def _handle_context_batch(
             technique=technique,
             cut_off=cut_off,
             taxon_id=taxon,
+            write_zfpkm_png_filepath=write_zfpkm_png_filepath,
         )
         logger.success(f"Results saved at '{rnaseq_output_filepath}'")
 
@@ -119,6 +123,7 @@ async def rnaseq_gen(
     config_filename: str,
     prep: RNAPrepMethod,
     taxon_id: int | str | Taxon,
+    write_zfpkm_png_filepath: Path,
     replicate_ratio: float = 0.5,
     high_replicate_ratio: float = 1.0,
     batch_ratio: float = 0.5,
@@ -180,6 +185,7 @@ async def rnaseq_gen(
         cut_off=cut_off,
         prep=prep,
         taxon=taxon_id,
+        write_zfpkm_png_filepath=write_zfpkm_png_filepath,
     )
 
 
@@ -287,6 +293,12 @@ def _parse_args() -> _Arguments:
         "Will separate samples into groups to only compare similarly prepared libraries. "
         "For example, mRNA, total-rna, scRNA, etc",
     )
+    parser.add_argument(
+        "--write-zfpkm-png-filepath",
+        required=False,
+        type=Path,
+        help="If using zFPKM, the location to write graphs",
+    )
     args = parser.parse_args()
     args.filtering_technique = args.filtering_technique.lower()
     args.taxon = Taxon.from_int(int(args.taxon)) if str(args.taxon).isdigit() else Taxon.from_string(str(args.taxon))  # type: ignore
@@ -306,5 +318,6 @@ def _parse_args() -> _Arguments:
             cut_off=args.minimum_cutoff,
             prep=args.library_prep,
             taxon_id=args.taxon,
+            write_zfpkm_png_filepath=args.write_zfpkm_png_filepath,
         )
     )

main/data/boundary_rxns/naiveB_boundary_rxns.csv

@@ -1,4 +1,4 @@
-Reaction,Abbreviation,Compartment,Minimum Reaction Rate,Maximum Reaction Rate
+Boundary,Abbreviation,Compartment,Minimum Reaction Rate,Maximum Reaction Rate
 Exchange,glc_D,Extracellular,-100,1000
 Exchange,fe2,Extracellular,-1000,1000
 Exchange,gal,Extracellular,0,1000

main/data/boundary_rxns/smB_boundary_rxns.csv

@@ -1,4 +1,4 @@
-Reaction,Abbreviation,Compartment,Minimum Reaction Rate,Maximum Reaction Rate
+Boundary,Abbreviation,Compartment,Minimum Reaction Rate,Maximum Reaction Rate
 Exchange,glc_D,Extracellular,-100,1000
 Exchange,fe2,Extracellular,-1000,1000
 Exchange,gal,Extracellular,0,1000
@@ -67,4 +67,4 @@ Exchange,orn,Extracellular,-1,1000
 Exchange,orn_D,Extracellular,-1,1000
 Exchange,so4,Extracellular,-1000,1000
 Exchange,ribflv,Extracellular,-1,1000
-Exchange,Lcystin,Extracellular,-1,1000
+Exchange,Lcystin,Extracellular,-1,1000