Updating Docs for commit 39471b1 made on 2024-08-15T19:45:31+00:00 fr…

…om refs/heads/latest by meson800

README.md

@@ -0,0 +1,9 @@
+# GitHub Pages Cache
+
+Nothing to see here. The contents of this branch are essentially a cache that's not intended to be viewed on github.com.
+
+The actual documentation lives on the latest branch (e.g. the default branch for the repository).
+
+This build is based on Sphinx, and uses a custom Python build script plus includes some of
+Michael Altfield's work on building multi-branch documentation:
+ * https://tech.michaelaltfield.net/2020/07/18/sphinx-rtd-github-pages-1

en/Mary-test/.buildinfo

@@ -0,0 +1,4 @@
+# Sphinx build info version 1
+# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: cabd5fe9be86a8092a8632e59f67c08b
+tags: 645f666f9bcd5a90fca523b33c5a78b7

en/Mary-test/_downloads/0df861a356ef76f2df87e00194cbc164/histograms-1.py

@@ -0,0 +1,89 @@
+# ----- PLOTTING FUNCTION -------
+
+def plot_hists(df,              # DataFrame with data
+               x,               # variable (str, column header of df) or list of variables to plot
+               sample_list,     # list of samples (values of column 'ConditionLabel') to plot in order
+               name,            # short name (str) for saving the figure
+               plot_title=None, # Super-title for plot (optional str)
+               xlim=(1e1,1e6),  # tuple or list of tuples (optional) for x-axis range on subplot(s)
+               gates=None       # list (optional) of x-values at which to draw vertical lines, i.e. gates
+              ):
+
+    # Specify additional parameters
+    lin = set(['FSC-A','FSC-H','FSC-W','SSC-A','SSC-H','SSC-W']) # list of variables to plot on linear scale (size-related params)
+    condition_palette = pd.read_pickle('data/histogram/exp42_palette.pkl') # custom color palette (dict mapping Condition values to colors)
+    sns.set_context('talk',rc={'font.family': 'sans-serif', 'font.sans-serif':['Helvetica Neue']})
+
+    sz = len(x) # number of subplots
+    fig, axs = plt.subplots(1,sz,figsize=(sz*7,5))
+
+    # Create each subplot
+    for i in range(sz):
+        g = sns.kdeplot(data=df, x=x[i], ax=axs[i],
+                        hue='ConditionLabel', hue_order=sample_list,    # samples are specified by the 'ConditionLabel' column in df
+                        palette=condition_palette,
+                        fill=True, alpha = 0.1,                         # shade under the curve, but faintly
+                        log_scale=(x[i] not in lin),                    # default to log scale unless variable is in the linear list
+                        legend=(i==sz-1),                               # add a legend only to the last subplot
+                        common_norm=True)                               # supposed to normalize area under the curve (?)
+
+        # Formatting
+        sns.despine(ax=g)      # remove top and right plot border
+        g.minorticks_off()
+
+        # Set the x-axis range based on provided list or value
+        if isinstance(xlim,list): g.set_xlim(xlim[i])
+        else: g.set_xlim(xlim)
+
+        # Add a vertical line (gate) if specified
+        if gates is not None: g.axvline(gates[i], c='gray', ls='--', alpha=0.5)
+
+    # Adjust the legend to the right of the last subplot
+    sns.move_legend(axs[-1], title='Condition', loc='upper left', bbox_to_anchor=(1,1), frameon=False)
+
+    # Add a super-title to the plot, if specified
+    fig.suptitle(plot_title)
+    fig.tight_layout()
+
+    # [NOT APPLICABLE HERE] Save the figure as an image to the path specified by output_path (not defined here)
+    #   uses rushd outfile function to save metadata associated with the figure
+    # fig.savefig(rd.outfile(output_path/('hist-'+name+'.svg')),bbox_inches='tight')
+
+    return fig
+# ----- END PLOTTING FUNCTION -------
+
+# ----- Load data -----
+labeler = pd.read_pickle('data/histogram/exp42_labeler.pkl') # dict mapping short Condition name to long ConditionLabel
+data = pd.read_csv('data/histogram/exp42_data-small.csv') # stored DataFrame of data with metadata
+
+# ----- Call the plotting function in a loop to generate plots with subsets of samples -----
+
+# Specify variables -> this will generate two subplots
+x = ['mGL-A', 'mCherry-A']
+
+# Filter data
+df = data.loc[(data[x[0]]>0) & (data[x[1]]>0)] # remove cells with log-unfriendly values
+# Normalize number of cells in each sample (Condition) by downsampling to smallest sample size
+num_cells = df.groupby(['Condition','Replicate'])[x[0]].count().min()
+df = df.groupby(['Condition']).sample(n=num_cells, random_state=1)
+
+# Dictionary of plots (separate figures) to generate
+#  keys = short name that plots are saved under
+#  values = list of samples (values in 'Condition' column) to include in the plot
+plot_list = {
+    'tandem': ['260_False','260_True','261_False','261_True','262_False','262_True'],
+    'divergent+dox': ['263_True','264_True','265_True'],
+    'hPGK': ['260_False','260_True','263_False','263_True'],
+}
+
+# Loop to create each plot/figure
+for name, sample_list in plot_list.items():
+
+    # Convert short sample names above (Condition) to long names (ConditionLabel) -> this is particular to my df organization
+    sample_list = [labeler[s] for s in sample_list]
+    # Identify the subset of the data to plot
+    dd = df.loc[df['ConditionLabel'].isin(sample_list)]
+
+    plot_hists(dd, x, sample_list, name,
+               xlim=[(1e0,1e6),(2e0,1e7)],  # specify a different x-axis range for each variable
+               gates=[3e2,0])               # draw a gate on the first subplot but not the second

en/Mary-test/_downloads/1771e2288148197083ef6cf90992e536/sci_ATAC_seq-4.py

@@ -0,0 +1,14 @@
+mapping = {
+   **{f"A{x}": "sciAD1.3" for x in range(1,13)},
+   **{f"B{x}": "sciAD1.4" for x in range(1,13)},
+   **{f"C{x}": "sciAD1.5" for x in range(1,13)},
+   **{f"D{x}": "sciAD1.6" for x in range(1,13)},
+   **{f"E{x}": "sciAD1.7" for x in range(1,13)},
+   **{f"F{x}": "sciAD1.9" for x in range(1,13)},
+   **{f"G{x}": "sciAD1.10" for x in range(1,13)},
+   **{f"H{x}": "sciAD1.11" for x in range(1,13)},
+}
+mapping = {**mapping, **{(k[0] + '0' + k[1]): v for k,v in mapping.items() if len(k) == 2}}
+fig = plt.figure()
+rd.plot.plot_mapping(mapping, style='category', fig=fig)
+plt.title("Transposition sciAD1 layout", fontsize=15)

en/Mary-test/_downloads/1f16eaae4cd8d1384b6510d3e6940671/sci_ATAC_seq-3.py

@@ -0,0 +1,28 @@
+mapping = {
+   "A3": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "A4": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "A5": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "A6": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "A7": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "A8": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "A9": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "A10": "sciAD1.{3,4,5,6,7,9,10,11}",
+   "B1": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B2": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B3": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B4": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B5": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B6": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B7": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B8": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B9": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B10": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B11": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+   "B12": "sciAD2.{1,3,4,6,7,8,11,12,13,14,15,17}",
+}
+mapping = {**mapping, **{(k[0] + '0' + k[1]): v for k,v in mapping.items() if len(k) == 2}}
+fig = plt.figure()
+rd.plot.plot_mapping(mapping, style='category', fig=fig)
+sns.move_legend(fig.get_axes()[0], 'lower center', bbox_to_anchor=(0.5,-0.31))
+fig.tight_layout()
+plt.title("Transposition primer plate", fontsize=15)

en/Mary-test/_downloads/2b66478282dbaaa25621b06ce88b746a/sci_ATAC_seq-5.py

@@ -0,0 +1,18 @@
+mapping = {
+   **{f"{x}1": "sciAD2.1" for x in "ABCDEFGH"},
+   **{f"{x}2": "sciAD2.3" for x in "ABCDEFGH"},
+   **{f"{x}3": "sciAD2.4" for x in "ABCDEFGH"},
+   **{f"{x}4": "sciAD2.6" for x in "ABCDEFGH"},
+   **{f"{x}5": "sciAD2.7" for x in "ABCDEFGH"},
+   **{f"{x}6": "sciAD2.8" for x in "ABCDEFGH"},
+   **{f"{x}7": "sciAD2.11" for x in "ABCDEFGH"},
+   **{f"{x}8": "sciAD2.12" for x in "ABCDEFGH"},
+   **{f"{x}9": "sciAD2.13" for x in "ABCDEFGH"},
+   **{f"{x}10": "sciAD2.14" for x in "ABCDEFGH"},
+   **{f"{x}11": "sciAD2.15" for x in "ABCDEFGH"},
+   **{f"{x}12": "sciAD2.17" for x in "ABCDEFGH"},
+}
+mapping = {**mapping, **{(k[0] + '0' + k[1]): v for k,v in mapping.items() if len(k) == 2}}
+fig = plt.figure()
+rd.plot.plot_mapping(mapping, style='category', fig=fig)
+plt.title("Transposition sciAD2 layout", fontsize=15)

en/Mary-test/_downloads/2ec64224349c36c39ba6631cfc61635c/mixed_distribution_mean_plots-1.py

@@ -0,0 +1,36 @@
+# Read in data
+data = pd.read_csv('data/data_mGL_WPRE/data_mGL_WPRE.csv')
+
+# Plot mGL-H
+x = 'mGL-H'
+hue = 'cond'
+cond_list = ['mGL', 'mGL-WPRE']
+colormap = {'mGL': 'lightgrey',
+            'mGL-WPRE': 'limegreen'}
+
+# Plot
+fig, ax = plt.subplots(1, 1, figsize=(6, 4))
+sns.kdeplot(ax=ax, data=data, x=x, hue=hue, hue_order=cond_list,
+            log_scale=(True, False), common_norm=False,
+            shade=True, palette=colormap)
+
+# Plot neg ctrl
+sns.kdeplot(ax=ax, data=data.loc[data['cond'] == 'Neg'], x=x,
+            log_scale=(True, False), common_norm=False,
+            shade=False, color='black', alpha=0.5, linestyle='--')
+ax.annotate('Neg', (0.08, 0.25),
+            xycoords='axes fraction', alpha=0.5, ha='center')
+
+# Add threshold for mGL+ gating
+mGL_H_thresh = 2*10**2
+ax.axvline(mGL_H_thresh, 0, 1, color='black')
+
+# Title
+plt.suptitle('4 dpi')
+# Adjust limits
+mGL_lim = (10, 10**6)
+ax.set_xlim(mGL_lim)
+
+# Misc plotting stuff
+fig.tight_layout()  # Helps improve white spacing
+plt.show()

en/Mary-test/_downloads/4495ece29809f8b231686789355fea39/test-1.py

@@ -0,0 +1,4 @@
+df = pd.read_csv('data/test_data.csv')
+sns.scatterplot(data=df, x='x', y='y')
+sns.despine()
+plt.show()

en/Mary-test/_downloads/8816ba9b8a60d3f0534141d709587e9c/flow_with_adjunct_hist-1.py

@@ -0,0 +1,66 @@
+# Read in data
+data = pd.read_csv('data/data_flow_with_adjunct_hist/data_flow_with_adjunct_hist.csv')
+
+# Randomly sample 10^4 samples from each condition to make representative flow diagram
+numSamples = 10**4
+small_data = data.groupby(['cond']).sample(n=numSamples, random_state=1)
+
+# General plotting params
+x = 'CFSE-A'
+y = 'sulfo-Cyanine5-A'
+hue = 'cond'
+cond_list = ['Ctrl', 'NIL', 'NILDD', 'NILDDRR']
+colormap = {'Ctrl': 'grey', 'NIL': 'crimson',
+            'NILDD': 'purple', 'NILDDRR': 'dodgerblue'}
+
+# definitions for the axes
+left, width = 0.1, 0.65
+bottom, height = 0.1, 0.65
+spacing = 0.005
+
+rect_scatter = [left, bottom, width, height]
+rect_histx = [left, bottom + height + spacing, width, 0.2]
+rect_histy = [left + width + spacing, bottom, 0.2, height]
+
+# Set up figure
+fig = plt.figure(figsize=(6, 6))
+ax_scatter = plt.axes(rect_scatter)
+ax_scatter.tick_params(direction='in', top=True, right=True)
+ax_histx = plt.axes(rect_histx)
+ax_histx.set_axis_off()
+ax_histy = plt.axes(rect_histy)
+ax_histy.set_axis_off()
+
+# Set limits
+xlim = (10, 1*10**5)
+ylim = (5*10**1, 1*10**5)
+ax_scatter.set_xlim(xlim)
+ax_scatter.set_ylim(ylim)
+ax_histx.set_xlim(xlim)
+ax_histy.set_ylim(ylim)
+
+# Make density plots
+sns.kdeplot(ax=ax_scatter, data=small_data, x=x, y=y, hue=hue, hue_order=cond_list,
+            log_scale=True, common_norm=False,
+            palette=colormap, alpha=0.7, fill=False, legend=True)
+
+# Plot histograms
+sns.kdeplot(ax=ax_histx, data=small_data, x=x, hue=hue, hue_order=cond_list,
+            log_scale=True, common_norm=False,
+            palette=colormap, alpha=0.1, fill=True, legend=False)
+sns.kdeplot(ax=ax_histy, data=small_data, y=y, hue=hue, hue_order=cond_list,
+            log_scale=True, common_norm=False,
+            palette=colormap, alpha=0.1, fill=True, legend=False)
+
+# Add in CFSE and EU lines
+CFSE_low_thresh = np.percentile(data[(data['cond'] == 'Ctrl')]['CFSE-A'],  20)
+EU_thresh = np.percentile(
+    data[(data['cond'] == 'NIL') & (data['CFSE_cat'] == 'CFSE-low')]['sulfo-Cyanine5-A'], 50)
+ax_scatter.axvline(CFSE_low_thresh, 0, 1, color='black')
+ax_scatter.axhline(EU_thresh, 0, 1, color='black')
+
+# Title
+fig.suptitle('14 dpi')
+# Misc plotting stuff
+fig.tight_layout()  # Helps improve white spacing
+plt.show()

en/Mary-test/_downloads/b2101dd4d808c5515eb2ee61fa80e946/sci_ATAC_seq-1.py

@@ -0,0 +1,12 @@
+mapping = {
+   **{f"C{i}": "sciP1.{1-12}" for i in range(1,13)},
+   **{f"D{i}": "sciP1.{13-24}" for i in range(1,13)},
+   **{f"E{i}": "sciP1.{25-36}" for i in range(1,13)},
+}
+mapping = {**mapping, **{(k[0] + '0' + k[1]): v for k,v in mapping.items() if len(k) == 2}}
+fig = plt.figure()
+rd.plot.plot_mapping(mapping, style='category', fig=fig)
+ax = fig.get_axes()[0]
+sns.move_legend(ax, 'lower center', bbox_to_anchor=(0.5,-0.42))
+ax.set_title("sciP1 PCR primer plate", fontsize=15)
+fig.clip_box = ax.get_tightbbox()

en/Mary-test/_downloads/b5cb02dfb06a2a298c48c503973bd697/sci_ATAC_seq-2.py

@@ -0,0 +1,12 @@
+mapping = {
+   **{f"{x}5": "sciP2.{1-8}" for x in 'ABCDEFGH'},
+   **{f"{x}6": "sciP2.{9-16}" for x in 'ABCDEFGH'},
+   **{f"{x}7": "sciP2.{17-24}" for x in 'ABCDEFGH'},
+}
+mapping = {**mapping, **{(k[0] + '0' + k[1]): v for k,v in mapping.items() if len(k) == 2}}
+fig = plt.figure()
+rd.plot.plot_mapping(mapping, style='category', fig=fig)
+ax = fig.get_axes()[0]
+sns.move_legend(ax, 'lower center', bbox_to_anchor=(0.5,-0.42))
+ax.set_title("sciP2 PCR primer plate", fontsize=15)
+fig.clip_box = ax.get_tightbbox()

en/Mary-test/_downloads/bd364e1cecbce0bdf8ebc92ea6da15d2/mixed_distribution_mean_plots-2.py

@@ -0,0 +1,54 @@
+# Categorize if mGL+
+mGL_cat = list()
+for mGL_val in data['mGL-H']:
+    if mGL_val > mGL_H_thresh:
+        mGL_cat.append('mGL+')
+    else:
+        mGL_cat.append('mGL-')
+data['mGL_cat'] = mGL_cat
+
+# Get total counts and percent of mGL+ and mGL-
+well_group = ['cond', 'replicate', 'sampleNum'] # specifies we're splitting by cond >> bio rep >> tech rep >> etc...
+count_df = data.groupby([*well_group, 'mGL_cat'])['mGL-H'   # Doesn't have to be mGL-H, any column would work
+    ].count().unstack(fill_value=0).stack().rename('count') # unstack()/stack() puts 0 if no mGL-H+ rather than dropping row
+percent_df = (count_df*100/count_df.groupby(well_group).transform('sum')
+    ).reset_index(name='percent')
+
+# Extract just the mGL+ cells
+data_mGL = data.loc[data['mGL_cat'] == 'mGL+']
+percent_df_mGL = percent_df.loc[(percent_df['mGL_cat'] == 'mGL+')]
+
+# Calculate geom mean of mGL+ cells
+well_mGL_gmean_df = data_mGL.groupby(well_group)[
+    'mGL-H'].apply(scipy.stats.gmean).reset_index(name='mGL-H (gmean)')
+
+# Plotting parameters
+x = 'cond'
+y = 'mGL-H'
+order = ['mGL', 'mGL-WPRE']
+pairs = [('mGL', 'mGL-WPRE')]
+colormap = {'mGL': 'lightgrey',
+            'mGL-WPRE': 'limegreen'}
+
+# Plot
+fig, ax = plt.subplots(1, 1, figsize=(3, 3))
+sns.boxplot(
+    ax=ax, data=data_mGL,
+    x=x, y=y, order=order,
+    boxprops={'facecolor': 'None'}, showfliers=False) # Gets rid of boxplot colors and outliers
+sns.stripplot(
+    ax=ax, data=well_mGL_gmean_df,
+    x=x, y=y+' (gmean)', order=order,
+    dodge=True, palette=colormap, size=5)
+
+# Add in stats
+annot = Annotator(ax=ax, data=well_mGL_gmean_df, x=x, y=y+' (gmean)', pairs=pairs, order=order)
+annot.configure(test='t-test_ind', text_format='star', loc='inside', verbose=2)
+annot.apply_and_annotate()
+
+# Adjust labels
+plt.ticklabel_format(axis='y',style='sci',scilimits=(0,0))
+plt.ylabel(y)
+plt.title('4 dpi, HG')
+fig.tight_layout()  # Helps improve white spacing
+plt.show()