plot more components in PCA

build/lib/libcodonusage/__init__.py

+__copyright__ = "Copyright (C) 2022-2023 Blaise Li"
+__licence__ = "GNU GPLv3"
+__version__ = "0.28.1"
+from .libcodonusage import (
+    aa2colour,
+    aa_usage,
+    by_aa_codon_usage,
+    centroid_usage,
+    codon2aa,
+    codon_usage_pca,
+    columns_by_aa,
+    compare_clusterings,
+    compute_rscu,
+    detect_fishy_genes,
+    exclude_all_nan_cols,
+    extract_top_genes_from_cluster,
+    filter_on_idx_levels,
+    find_most_biased_genes,
+    find_valley,
+    format_codon_labels,
+    gene_wide_codon_usage,
+    load_bias_table,
+    load_counts_table,
+    load_table_with_info_index,
+    make_aa_codon_columns,
+    make_cluster_table,
+    make_centroids_cluster_finder,
+    make_counts_only,
+    plot_codon_usage_for_gene_list,
+    render_md,
+    save_counts_table,
+    sort_counts_by_aa,
+    split_info_index,
+    star2stop,
+    to_long_form,
+    violin_usage,
+    violin_usage_vertical,
+    violin_usage_by_clusters,
+    violin_usage_by_clusters_splitby,
+    violin_with_thresh,
+    write_cluster_lists,
+    )

libcodonusage/libcodonusage.py

@@ -14,10 +14,12 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """Functions used in Jupyter notebooks."""
+from http.cookies import Morsel
 from itertools import combinations
 import json
 from operator import attrgetter, itemgetter
 from pathlib import Path
+from unittest import mock
 # python3 -m pip install cytoolz
 from cytoolz import concat, groupby, unique, valmap
 # To render mardown in a Jupyter notebook on gitlab
@@ -139,6 +141,7 @@ def load_counts_table(
     display(codon_counts.head(3))
     return codon_counts
 
+#def filter_codon_counts_table(codon_counts, )
 
 def compute_criteria(codon_counts):
     """
@@ -828,7 +831,7 @@ methionine (M) and tryptophan (W).
 
 def codon_influence_in_components(
         components, colnames,
-        figs_dir=None, formats=None):
+        figs_dir=None, more_components=False, formats=None):
     """
     Plot the influence of the columns in the first 4 principal axes of a PCA.
 
@@ -854,8 +857,11 @@ def codon_influence_in_components(
     be saved, such as "svg" or "png".
     """
     render_md(
-        "Vizualizing the influence of codons in the first 4 components\n")
+        "Vizualizing the influence of codons in the first components\n")
     # TODO: *figsize* could be adapted depending on the number of columns
+    if more_components:
+        (fig, axes) = plt.subplots(12, 1, figsize=(16, 60))
+    else:
         (fig, axes) = plt.subplots(4, 1, figsize=(16, 16))
     for (component, axis) in enumerate(axes):
         pd.Series(
@@ -880,7 +886,7 @@ def codon_influence_in_components(
 
 def codon_usage_pca(
         usage_data,
-        figs_dir=None, hue="chrom", exclude_cols=None,
+        figs_dir=None, hue="chrom", exclude_cols=None, plot_more_components=False,
         formats=None, cols_are_codons=True):
     """
     Perform Principal Component Analysis on *usage_data*.
@@ -922,14 +928,36 @@ def codon_usage_pca(
         pca.transform(usage_data),
         index=usage_data.index).reset_index(level=hue)
     render_md(
-        "Plotting genes on the first 4 components\n")
+        "Plotting genes on the first components\n")
+    if plot_more_components:
+        (fig, axes) = plt.subplots(3, 2, figsize=(16, 25))
+        sns.scatterplot(
+            data=transformed_data,
+            x=0, y=1, hue=hue, marker=".", ax=axes[0,0])
+        sns.scatterplot(
+            data=transformed_data,
+            x=2, y=3, hue=hue, marker=".", ax=axes[0,1])
+        sns.scatterplot(
+            data=transformed_data,
+            x=4, y=5, hue=hue, marker=".", ax=axes[1,0])
+        sns.scatterplot(
+            data=transformed_data,
+            x=6, y=7, hue=hue, marker=".", ax=axes[1,1])
+        sns.scatterplot(
+            data=transformed_data,
+            x=8, y=9, hue=hue, marker=".", ax=axes[2,0])
+        sns.scatterplot(
+            data=transformed_data,
+            x=10, y=11, hue=hue, marker=".", ax=axes[2,1])
+    else:
         (fig, axes) = plt.subplots(1, 2, figsize=(16, 8))
         sns.scatterplot(
             data=transformed_data,
-        x=0, y=1, hue=hue, marker=".", ax=axes[0])
+            x=0, y=1, hue=hue, marker=".", ax=axes[0,0])
         sns.scatterplot(
             data=transformed_data,
-        x=2, y=3, hue=hue, marker=".", ax=axes[1])
+            x=2, y=3, hue=hue, marker=".", ax=axes[0,1])
+
     if figs_dir is not None and formats is not None:
         for ext in formats:
             plt.savefig(
@@ -940,7 +968,7 @@ def codon_usage_pca(
     if cols_are_codons:
         codon_influence_in_components(
             pca.components_, usage_data.columns,
-            figs_dir=figs_dir, formats=formats)
+            figs_dir=figs_dir, more_components=plot_more_components, formats=formats)
     return (pca, transformed_data)