Added horizontal barplot for depicting percentage of RNA barcodes wit…

…h at least one HTO count

demuxEM/commands/DemuxEM.py

@@ -38,7 +38,7 @@ class DemuxEM(Base):
   output_name.ambient_hashtag.hist.pdf                   Optional output. A histogram plot depicting hashtag distributions of empty droplets and non-empty droplets.
   output_name.background_probabilities.bar.pdf           Optional output. A bar plot visualizing the estimated hashtag background probability distribution.
   output_name.real_content.hist.pdf                      Optional output. A histogram plot depicting hashtag distributions of not-real-cells and real-cells as defined by total number of expressed genes in the RNA assay.
-  output_name.rna_demux.hist.pdf                         Optional output. A histogram plot depicting RNA UMI distribution for singlets, doublets and unknown cells.
+  output_name.rna_demux.hist.pdf                         Optional output. This figure consists of two plots. The first one is a horizontal bar plot depicting the percentage of RNA barcodes with at least one HTO count. The second plot is a histogram plot depicting RNA UMI distribution for singlets, doublets and unknown cells.
   output_name.gene_name.violin.pdf                       Optional outputs. Violin plots depicting gender-specific gene expression across samples. We can have multiple plots if a gene list is provided in '--generate-gender-plot' option.
 
 Examples:

demuxEM/pipeline/pipeline.py

@@ -61,7 +61,7 @@ def run_pipeline(input_rna_file, input_hto_file, output_name, **kwargs):
         plot_hto_hist(
             hashing_data, "rna_type", output_name + ".real_content.hist.pdf", alpha=0.5
         )
-        plot_rna_hist(rna_data, output_name + ".rna_demux.hist.pdf")
+        plot_rna_hist(rna_data, hashing_data, output_name + ".rna_demux.hist.pdf")
         logger.info("Diagnostic plots are generated.")
 
     if len(kwargs["gen_gender_plot"]) > 0:

demuxEM/tools/plot.py

@@ -28,40 +28,56 @@ def plot_hto_hist(hashing_data: UnimodalData, attr: str, out_file: str, alpha: f
 
 
 def plot_rna_hist(
-    rna_data: UnimodalData, out_file: str, plot_attr: str = "n_counts", cat_attr: str = "demux_type", dpi: int = 500, figsize: Tuple[float, float] = None
+    rna_data: UnimodalData, hashing_data: UnimodalData, out_file: str, plot_attr: str = "n_counts", cat_attr: str = "demux_type", dpi: int = 500, figsize: Tuple[float, float] = None
 ) -> None:
+    fig, axes = plt.subplots(2, 1, gridspec_kw={'height_ratios': [1, 9], 'hspace': 0.6}, figsize = figsize, dpi = dpi)
+
+    # Percentage of RNA barcodes having HTO tags
+    nhto = rna_data.obs_names.isin(hashing_data.obs_names).sum()
+    total = rna_data.shape[0]
+
+    ax = axes[0]
+    p1 = nhto * 100.0 / total
+    p2 = (total - nhto) * 100.0 / total
+    labels = ['Has HTO', 'No HTO']
+    ax.barh(y = 0, width = p1, color = 'red', height = 0.5, label = labels[0])
+    ax.barh(y = 0, width = p2, left = p1, color = 'gray', height = 0.5, label = labels[1])
+    ax.set_yticks([])
+    ax.set_ylabel('RNA    \nbarcodes', rotation = 0, ha = 'right', va = 'center')
+    ax.set_xlim(left = 0, right = 100)
+    ax.set_xlabel('Percentage')
+    ax.legend(ncol=2, bbox_to_anchor=(1, 1), loc='lower right', fontsize = 'small')
+
+    # RNA histogram
     bins = np.logspace(
         np.log10(min(rna_data.obs[plot_attr])), np.log10(max(rna_data.obs[plot_attr])), 101
     )
     cat_vec = rna_data.obs[cat_attr]
-    ax = plt.gca()
-    if cat_attr == "demux_type":
-        ax.hist(
-            rna_data.obs.loc[np.isin(cat_vec, "singlet"), plot_attr],
-            bins,
-            alpha=0.5,
-            label="singlet",
-        )
-        ax.hist(
-            rna_data.obs.loc[np.isin(cat_vec, "doublet"), plot_attr],
-            bins,
-            alpha=0.5,
-            label="doublet",
-        )
-        ax.hist(
-            rna_data.obs.loc[np.isin(cat_vec, "unknown"), plot_attr],
-            bins,
-            alpha=0.5,
-            label="unknown",
-        )
+    ax = axes[1]
+    ax.hist(
+        rna_data.obs.loc[np.isin(cat_vec, "singlet"), plot_attr],
+        bins,
+        alpha=0.5,
+        label="singlet",
+    )
+    ax.hist(
+        rna_data.obs.loc[np.isin(cat_vec, "doublet"), plot_attr],
+        bins,
+        alpha=0.5,
+        label="doublet",
+    )
+    ax.hist(
+        rna_data.obs.loc[np.isin(cat_vec, "unknown"), plot_attr],
+        bins,
+        alpha=0.5,
+        label="unknown",
+    )
     ax.legend(loc="upper right")
     ax.set_xscale("log")
     ax.set_xlabel("Number of RNA UMIs (log10 scale)")
     ax.set_ylabel("Number of cellular barcodes")
-    if figsize is not None:
-        plt.gcf().set_size_inches(*figsize)
-    plt.savefig(out_file, dpi=dpi)
-    plt.close()
+
+    fig.savefig(out_file)
 
 
 def plot_bar(heights: List[float], tick_labels: List[str], xlabel: str, ylabel: str, out_file: str, dpi: int = 500, figsize: Tuple[float, float] = None) -> None:

docs/usage.rst

@@ -74,7 +74,7 @@ to see the usage information::
 		Optional output. A histogram plot depicting hashtag distributions of not-real-cells and real-cells as defined by total number of expressed genes in the RNA assay.
 
 	output_name.rna_demux.hist.pdf
-		Optional output. A histogram plot depicting RNA UMI distribution for singlets, doublets and unknown cells.
+		Optional output. This figure consists of two plots. The first one is a horizontal bar plot depicting the percentage of RNA barcodes with at least one HTO count. The second plot is a histogram plot depicting RNA UMI distribution for singlets, doublets and unknown cells.
 
 	output_name.gene_name.violin.pdf
 		Optional outputs. Violin plots depicting gender-specific gene expression across samples. We can have multiple plots if a gene list is provided in '--generate-gender-plot' option.