Plot specimen summary from geneshot results HDF5

plot_geneshot_specimen_summary.py

# Plot the number of genes detected and the proportion of reads aligned
def plot_specimen_summary(hdf_fp, pdf=None, alpha = 0.85):
    
    specimen_summary = pd.read_hdf(hdf_fp, "/summary/all").set_index("specimen")
    
    specimen_summary = specimen_summary.assign(
        prop_reads = specimen_summary["aligned_reads"] / specimen_summary["n_reads"]
    )
    
    for col_name, axis_title in [
        ("n_genes_assembled", "Number of genes detected by assembly"),
        ("n_genes_aligned", "Number of genes detected by alignment"),
        ("prop_reads", "Proportion of reads aligned"),
    ]:
        g = sns.scatterplot(
            data=specimen_summary,
            x = "n_reads",
            y = col_name,
            linewidth = 0,
            alpha = alpha
        )
        if col_name == "prop_reads":
            plt.ylim(0, 1)
        else:
            plt.ylim(0, )
        plt.xlim(0, )
        plt.ylabel(axis_title)
        plt.xlabel("Number of reads")
        if pdf is not None:
            pdf.savefig(bbox_inches="tight")
        plt.show()
    
plot_specimen_summary(hdf_fp)