Added analysis of looking at Cluster 3.

GRO_seq_TFSEE/matrix_analysis.py

@@ -518,10 +518,146 @@ plt.clf()
 
 
 # Wilcox rank sum test:
+# Cluster 1 1 e-5
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D0'],cell_tf_values_std_cluster_1['ES_D2'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D0'],cell_tf_values_std_cluster_1['ES_D5'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D0'],cell_tf_values_std_cluster_1['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D0'],cell_tf_values_std_cluster_1['ES_D10'])
+
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D2'],cell_tf_values_std_cluster_1['ES_D5'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D2'],cell_tf_values_std_cluster_1['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D2'],cell_tf_values_std_cluster_1['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D5'],cell_tf_values_std_cluster_1['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D5'],cell_tf_values_std_cluster_1['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_1['ES_D7'],cell_tf_values_std_cluster_1['ES_D10'])
+
+
+# Cluster 2 1 e-5
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D0'],cell_tf_values_std_cluster_2['ES_D2'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D0'],cell_tf_values_std_cluster_2['ES_D5'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D0'],cell_tf_values_std_cluster_2['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D0'],cell_tf_values_std_cluster_2['ES_D10'])
+
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D2'],cell_tf_values_std_cluster_2['ES_D5'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D2'],cell_tf_values_std_cluster_2['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D2'],cell_tf_values_std_cluster_2['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D5'],cell_tf_values_std_cluster_2['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D5'],cell_tf_values_std_cluster_2['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_2['ES_D7'],cell_tf_values_std_cluster_2['ES_D10'])
+
+# Cluster 3 1 e-5
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D0'],cell_tf_values_std_cluster_3['ES_D2'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D0'],cell_tf_values_std_cluster_3['ES_D5'])
 scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D0'],cell_tf_values_std_cluster_3['ES_D7'])
 scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D0'],cell_tf_values_std_cluster_3['ES_D10'])
-scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D10'],cell_tf_values_std_cluster_3['ES_D7'])
-scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D0'],cell_tf_values_std_cluster_3['ES_D7'])
+
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D2'],cell_tf_values_std_cluster_3['ES_D5'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D2'],cell_tf_values_std_cluster_3['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D2'],cell_tf_values_std_cluster_3['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D5'],cell_tf_values_std_cluster_3['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D5'],cell_tf_values_std_cluster_3['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_3['ES_D7'],cell_tf_values_std_cluster_3['ES_D10'])
+
+# Cluster 4 1 e-5
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D0'],cell_tf_values_std_cluster_4['ES_D2'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D0'],cell_tf_values_std_cluster_4['ES_D5'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D0'],cell_tf_values_std_cluster_4['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D0'],cell_tf_values_std_cluster_4['ES_D10'])
+
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D2'],cell_tf_values_std_cluster_4['ES_D5'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D2'],cell_tf_values_std_cluster_4['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D2'],cell_tf_values_std_cluster_4['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D5'],cell_tf_values_std_cluster_4['ES_D7'])
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D5'],cell_tf_values_std_cluster_4['ES_D10'])
+
+scipy.stats.ranksums(cell_tf_values_std_cluster_4['ES_D7'],cell_tf_values_std_cluster_4['ES_D10'])
+
+
+# Look at Cluster 3 for expression of TF's
+cluster3_tfs = tf_cell_lines.loc[cell_tf_values_std_cluster_3.index.values]
+
+box = cluster3_tfs.boxplot(column=['ES_D0', 'ES_D2', 'ES_D5', 'ES_D7',  'ES_D10'],patch_artist=True,showfliers=False,manage_xticks=False,widths = 0.6, medianprops = medianprops)
+plt.setp(box['whiskers'], color='k', linestyle='-', linewidth = 3)
+plt.setp(box['boxes'], color='k', linestyle='-', linewidth = 3)
+
+for patch, color in zip(box['boxes'], colors):
+    patch.set_facecolor(color)
+
+plt.tick_params(axis='y', direction='out')
+plt.tick_params(axis='x', direction='out')
+plt.tick_params(top='off', right='off')
+plt.grid(b=False)
+plt.ylim((-5,65))
+plt.xticks([1,2,3,4,5], ['ES_D0', 'ES_D2', 'ES_D5', 'ES_D7',  'ES_D10'])
+plt.savefig('box_plot_cluster_3_tfs_fpkm.png')
+plt.clf()
+
+# Cluster tfs 1 e-4
+scipy.stats.ranksums(cluster3_tfs['ES_D0'],cluster3_tfs['ES_D2'])
+scipy.stats.ranksums(cluster3_tfs['ES_D0'],cluster3_tfs['ES_D5'])
+scipy.stats.ranksums(cluster3_tfs['ES_D0'],cluster3_tfs['ES_D7'])
+scipy.stats.ranksums(cluster3_tfs['ES_D0'],cluster3_tfs['ES_D10'])
+
+
+scipy.stats.ranksums(cluster3_tfs['ES_D2'],cluster3_tfs['ES_D5'])
+scipy.stats.ranksums(cluster3_tfs['ES_D2'],cluster3_tfs['ES_D7'])
+scipy.stats.ranksums(cluster3_tfs['ES_D2'],cluster3_tfs['ES_D10'])
+
+scipy.stats.ranksums(cluster3_tfs['ES_D5'],cluster3_tfs['ES_D7'])
+scipy.stats.ranksums(cluster3_tfs['ES_D5'],cluster3_tfs['ES_D10'])
+
+scipy.stats.ranksums(cluster3_tfs['ES_D7'],cluster3_tfs['ES_D10'])
+
+
+
+
+cluster3_motifs = motif_enhancers.loc[cell_tf_values_std_cluster_3.index.values]
+cluster3_enhancers = only_rpkm_values.loc[cluster3_motifs.loc[:, (cluster3_motifs != 0).all(axis=0)].columns.values]
+
+box = cluster3_enhancers.boxplot(column=['ES_D0', 'ES_D2', 'ES_D5', 'ES_D7',  'ES_D10'],patch_artist=True,showfliers=False,manage_xticks=False,widths = 0.6, medianprops = medianprops)
+plt.setp(box['whiskers'], color='k', linestyle='-', linewidth = 3)
+plt.setp(box['boxes'], color='k', linestyle='-', linewidth = 3)
+
+for patch, color in zip(box['boxes'], colors):
+    patch.set_facecolor(color)
+
+plt.tick_params(axis='y', direction='out')
+plt.tick_params(axis='x', direction='out')
+plt.tick_params(top='off', right='off')
+plt.grid(b=False)
+plt.ylim((-5,105))
+plt.xticks([1,2,3,4,5], ['ES_D0', 'ES_D2', 'ES_D5', 'ES_D7',  'ES_D10'])
+plt.savefig('box_plot_cluster_3_enhancers_rpkm.png')
+plt.clf()
+
+# Cluster tfs 1 e-4
+scipy.stats.ranksums(cluster3_enhancers['ES_D0'],cluster3_enhancers['ES_D2'])
+scipy.stats.ranksums(cluster3_enhancers['ES_D0'],cluster3_enhancers['ES_D5'])
+scipy.stats.ranksums(cluster3_enhancers['ES_D0'],cluster3_enhancers['ES_D7'])
+scipy.stats.ranksums(cluster3_enhancers['ES_D0'],cluster3_enhancers['ES_D10'])
+
+
+scipy.stats.ranksums(cluster3_enhancers['ES_D2'],cluster3_enhancers['ES_D5'])
+scipy.stats.ranksums(cluster3_enhancers['ES_D2'],cluster3_enhancers['ES_D7'])
+scipy.stats.ranksums(cluster3_enhancers['ES_D2'],cluster3_enhancers['ES_D10'])
+
+scipy.stats.ranksums(cluster3_enhancers['ES_D5'],cluster3_enhancers['ES_D7'])
+scipy.stats.ranksums(cluster3_enhancers['ES_D5'],cluster3_enhancers['ES_D10'])
+
+scipy.stats.ranksums(cluster3_enhancers['ES_D7'],cluster3_enhancers['ES_D10'])
+
+
 
 ## Analysis of only RNA-seq
 # 1. Z-score Standardize for each cell line to see important TF's