Fix some ruff issues

bicytok/distanceMetricFuncs.py

@@ -14,16 +14,17 @@
 path_here = dirname(dirname(__file__))
 
 
-def KL_EMD_1D(ax, targCell, numFactors, RNA=False, offTargState=0) -> pd.DataFrame:
+def KL_EMD_1D(ax, targCell, numFactors, offTargState=0) -> pd.DataFrame:
     """
     Finds markers which have average greatest difference (EMD and KL) from other cells
     :param ax: Axes to plot on
     :param targCell: Target cell type for analysis
     :param numFactors: Number of top factors to consider
-    :param RNA: Boolean flag indicating RNA data (optional)
-    :param offTargState: State of off-target comparison (0 for all non-memory Tregs, 1 for all non-Tregs, 2 for naive Tregs)
+    :param offTargState: State of off-target comparison (0 for all non-memory Tregs,
+        1 for all non-Tregs, 2 for naive Tregs)
     :return:
-        corrsDF: DataFrame containing marker information and their Wasserstein Distance and KL Divergence values
+        corrsDF: DataFrame containing marker information and their Wasserstein Distance
+            and KL Divergence values
     """
     CITE_DF = importCITE()
     markerDF = pd.DataFrame(columns=["Marker", "Cell Type", "Amount"])
@@ -132,10 +133,12 @@ def EMD_2D(dataset, signal_receptor, target_cells, special_receptor, ax):
     :param dataset: DataFrame containing the dataset
     :param signal_receptor: Name of the signal receptor
     :param target_cells: Target cell type for analysis
-    :param special_receptor: Special receptor to consider (optional, used for just calculating distance for 2 receptors)
+    :param special_receptor: Special receptor to consider
+        (optional, used for just calculating distance for 2 receptors)
     :param ax: Matplotlib Axes object for plotting (optional)
     :return:
-        List of tuples format: (recep1, recep2, OT value) containing optimal transport distances and receptor information
+        List of tuples format: (recep1, recep2, OT value) containing
+            optimal transport distances and receptor information
     """
     CITE_DF = importCITE()
     weightDF = convFactCalc(CITE_DF)
@@ -269,8 +272,8 @@ def EMD_3D(dataset1, target_cells, ax=None):
     :param target_cells: Target cell type for analysis
     :param ax: Matplotlib Axes object for plotting (optional)
     :return:
-    List of tuples (format: (recep1, recep2, recep 3, OT value) containing optimal transport distances and receptor information for 3D analysis
-
+    List of tuples (format: (recep1, recep2, recep 3, OT value) containing
+        optimal transport distances and receptor information for 3D analysis
     """
     CITE_DF = importCITE()
 
@@ -416,7 +419,8 @@ def EMD_3D(dataset1, target_cells, ax=None):
                             receptor3_off_target_counts.astype(float)
                             / average_receptor_counts_3
                         )
-                        # Calculate the EMD between on-target and off-target counts for both receptors # change this so its two [||]
+                        # Calculate the EMD between on-target and off-target counts for
+                        # both receptors # change this so its two [||]
                         on_target_counts = np.concatenate(
                             (
                                 receptor1_on_target_counts[:, np.newaxis],
@@ -495,7 +499,8 @@ def EMD_3D(dataset1, target_cells, ax=None):
 
 def calculate_kl_divergence_2D(targCellMark, offTargCellMark):
     """
-    calculates the Kullback-Leibler (KL) divergence between two probability distributions
+    calculates the Kullback-Leibler (KL) divergence between two
+        probability distributions
     *used in combination with 1D or 2D KL functions
     :param targCellMark: Target cell marker data
     :param offTargCellMark: Off-target cell marker data
@@ -525,7 +530,8 @@ def KL_divergence_2D(dataset, signal_receptor, target_cells, special_receptor, a
     :param dataset: DataFrame containing the dataset
     :param signal_receptor: Name of the signal receptor
     :param target_cells: Target cell type for analysis
-    :param special_receptor: Special receptor to consider (optional, used for just calculating distance for 2 receptors)
+    :param special_receptor: Special receptor to consider
+        (optional, used for just calculating distance for 2 receptors)
     :param ax: Matplotlib Axes object for plotting (optional)
     :return:
     Sorted list of tuples containing KL Divergence values and receptor information

bicytok/figures/common.py

@@ -9,7 +9,6 @@
 
 import matplotlib
 import matplotlib.figure
-import numpy as np
 import seaborn as sns
 from matplotlib import gridspec
 from matplotlib import pyplot as plt

bicytok/figures/figure1.py

@@ -17,13 +17,15 @@
 plt.rcParams["svg.fonttype"] = "none"
 
 
-"""SIGNAL: Receptor that the ligand is delivering signal to; selectivity and target bound are with respect to engagement
-with this receptor
-ALL_TARGETS: List of paired [(target receptor, valency)] combinations for each targeting receptor; to be used for targeting
+"""SIGNAL: Receptor that the ligand is delivering signal to; selectivity and
+    target bound are with respect to engagement with this receptor
+ALL_TARGETS: List of paired [(target receptor, valency)] combinations for each
+    targeting receptor; to be used for targeting
 the target cell, not signaling
 CELLS: Array of cells that will be sampled from and used in calculations
 TARG_CELL: Target cell whose selectivity will be maximized
-STARTING_AFF: Starting affinity to modulate from in order to maximize selectivity for the targCell"""
+STARTING_AFF: Starting affinity to modulate from in order to
+    maximize selectivity for the targCell, affinities are K_a in L/mol"""
 
 SIGNAL = ["CD122", 1]
 ALL_TARGETS = [
@@ -56,9 +58,12 @@
 
 STARTING_AFF = 8.0
 
+
 def makeFigure():
-    """Figure file to generate dose response curves for any combination of multivalent and multispecific ligands.
-    Outputs dose vs. selectivity for the target cell and amount of target cell bound at indicated signal receptor."""
+    """Figure file to generate dose response curves for any combination of
+    multivalent and multispecific ligands.
+    Outputs dose vs. selectivity for the target cell and amount of target cell
+    bound at indicated signal receptor."""
     ax, f = getSetup((6, 3), (1, 2))
 
     offTargCells = CELLS[CELLS != TARG_CELL]

bicytok/figures/figure3.py

@@ -31,8 +31,10 @@
     "NK_CD56bright",
 ]
 
+
 def makeFigure():
-    """Figure file to generate bar plots for amount of signal receptor bound to each given cell type"""
+    """Figure file to generate bar plots for amount of signal receptor
+    bound to each given cell type"""
     ax, f = getSetup((8, 3), (1, 2))
 
     affs = np.array([SECONDARY_AFF, 8.5, 8.5])

bicytok/figures/figure4.py

@@ -15,7 +15,7 @@
 
 SIGNAL = ["CD122", 1]
 ALL_TARGETS = [("CD25", 1), ("CD278", 1), ("CD45RB", 1), ("CD4-2", 1), ("CD81", 1)]
-DOSE = 10e-2 #TODO: ADD UNITS
+DOSE = 10e-2  # In Molarity
 
 CELLS = np.array(
     [
@@ -34,8 +34,10 @@
 )
 targCell = "Treg"
 
+
 def makeFigure():
-    """Figure file to generate bispecific ligand selectivity heatmap of selectivity for each bispecific pairing."""
+    """Figure file to generate bispecific ligand selectivity heatmap of
+    selectivity for each bispecific pairing."""
     ax, f = getSetup((4, 3), (1, 1))
 
     offTCells = CELLS[CELLS != targCell]

bicytok/figures/figure5.py

@@ -18,21 +18,23 @@
 ALL_TARGETS = [["CD25", "CD278"], ["CD25", "CD4-2"], ["CD25", "CD45RB"]]
 DOSE = 10e-2
 CELLS = np.array(
-        [
-            "CD8 Naive",
-            "NK",
-            "CD8 TEM",
-            "CD4 Naive",
-            "CD4 CTL",
-            "CD8 TCM",
-            "CD8 Proliferating",
-            "Treg",
-        ]
-    )
+    [
+        "CD8 Naive",
+        "NK",
+        "CD8 TEM",
+        "CD4 Naive",
+        "CD4 CTL",
+        "CD8 TCM",
+        "CD8 Proliferating",
+        "Treg",
+    ]
+)
 TARG_CELL = "Treg"
 
+
 def makeFigure():
-    """Figure file to generate plots of bispecific ligand selectivity for combinations of different KL divergences, EMDs, and anti-correlations."""
+    """Figure file to generate plots of bispecific ligand selectivity for
+    combinations of different KL divergences, EMDs, and anti-correlations."""
     ax, f = getSetup((9, 3), (1, 3))
 
     CITE_DF = importCITE()

bicytok/figures/figure6.py

@@ -32,8 +32,10 @@
 ]
 CELL_LEVEL = "CellType2"
 
+
 def makeFigure():
-    """Figure file to generate bar plots of 1D KL divergence and EMD values of most unique receptor for each given cell type/subset."""
+    """Figure file to generate bar plots of 1D KL divergence and EMD values
+    of most unique receptor for each given cell type/subset."""
     ax, f = getSetup((12, 4), (1, 2))
 
     CITE_DF = importCITE()
@@ -58,10 +60,12 @@ def makeFigure():
             markAvg = np.mean(CITE_DF[marker].values)
             if markAvg > 0.0001:
                 targCellMark = (
-                    CITE_DF.loc[CITE_DF[CELL_LEVEL] == targCell][marker].values / markAvg
+                    CITE_DF.loc[CITE_DF[CELL_LEVEL] == targCell][marker].values
+                    / markAvg
                 )
                 offTargCellMark = (
-                    CITE_DF.loc[CITE_DF[CELL_LEVEL] != targCell][marker].values / markAvg
+                    CITE_DF.loc[CITE_DF[CELL_LEVEL] != targCell][marker].values
+                    / markAvg
                 )
                 if np.mean(targCellMark) > np.mean(offTargCellMark):
                     kdeTarg = KernelDensity(kernel="gaussian").fit(

bicytok/figures/figure7.py

@@ -8,8 +8,10 @@
 
 TARGET_CELL = "Treg"
 
+
 def makeFigure():
-    """Figure to generate clustermaps of EMD values for receptors + specified cell type"""
+    """Figure to generate clustermaps of EMD values for receptors
+    + specified cell type"""
     ax, f = getSetup((40, 40), (1, 1))
 
     markerDF = importCITE()

bicytok/figures/figure8.py

@@ -8,17 +8,18 @@
 
 TARGET_CELL = "Treg"
 
+
 def makeFigure():
     """clustermaps of KL values for receptors + specified cell type"""
     ax, f = getSetup((40, 40), (1, 1))
-    
+
     markerDF = importCITE()
     new_df = markerDF.head(1000)
     receptors = []
     for column in new_df.columns:
         if column not in ["CellType1", "CellType2", "CellType3", "Cell"]:
             receptors.append(column)
-    
+
     receptors = ["CD25", "CD35"]
     TARGET_CELL = "Treg"
     resultsKL = []

bicytok/imports.py

@@ -61,9 +61,11 @@ def importReceptors():
 # Armaan: lru_cache mutable return value
 @lru_cache(maxsize=None)
 def makeCITEdf():
-    """Makes cite surface epitope csv for given cell type, DON'T USE THIS UNLESS DATA NEEDS RESTRUCTURING"""
+    """Makes cite surface epitope csv for given cell type,
+    DON'T USE THIS UNLESS DATA NEEDS RESTRUCTURING"""
     """
-    matrixDF = pd.read_csv(join(path_here, "bicytok/data/CITEmatrix.gz"), compression='gzip', header=0, sep=' ', quotechar='"', error_bad_lines=False)
+    matrixDF = pd.read_csv(join(path_here, "bicytok/data/CITEmatrix.gz"),
+        compression='gzip', header=0, sep=' ', quotechar='"', error_bad_lines=False)
     matrixDF = matrixDF.iloc[:, 0:-2]
     matrixDF.columns = ["Marker", "Cell", "Number"]
     matrixDF.to_csv(join(path_here, "bicytok/data/CITEmatrix.csv"), index=False)
@@ -152,9 +154,8 @@ def makeTregSC():
         stim_an.obs.index = barcodes["barcode"].values
         stim_an.obs["Condition"] = stim
 
-        if (
-            i == 0
-        ):  # First condition - load features for later labeling (all conditions have same genes)
+        if i == 0:  # First condition - load features for later labeling
+            # (all conditions have same genes)
             Treg_h5ad = stim_an
             features = pd.read_csv(
                 gzip.open(