analysis/GRO_seq_TFSEE/find_the_clusters.py

+from sklearn.cluster import KMeans
+from sklearn.metrics import silhouette_samples, silhouette_score
+
+import matplotlib.pyplot as plt
+import matplotlib.cm as cm
+import numpy as np
+
+
+
+range_n_clusters = [2, 3, 4, 5, 6,7,8,9,10]
+X = cell_tf_values_std
+
+for n_clusters in range_n_clusters:
+    # Create a subplot with 1 row and 2 columns
+    fig, (ax1, ax2) = plt.subplots(1, 2)
+    fig.set_size_inches(18, 7)
+    # The 1st subplot is the silhouette plot
+    # The silhouette coefficient can range from -1, 1 but in this example all
+    # lie within [-0.1, 1]
+    ax1.set_xlim([-0.1, 1])
+    # The (n_clusters+1)*10 is for inserting blank space between silhouette
+    # plots of individual clusters, to demarcate them clearly.
+    ax1.set_ylim([0, len(X) + (n_clusters + 1) * 10])
+    # Initialize the clusterer with n_clusters value and a random generator
+    # seed of 10 for reproducibility.
+    clusterer = KMeans(n_clusters=n_clusters, random_state=10)
+    cluster_labels = clusterer.fit_predict(X)
+    # The silhouette_score gives the average value for all the samples.
+    # This gives a perspective into the density and separation of the formed
+    # clusters
+    silhouette_avg = silhouette_score(X, cluster_labels)
+    print("For n_clusters =", n_clusters,
+          "The average silhouette_score is :", silhouette_avg)

analysis/GRO_seq_TFSEE/input_list.csv

+experiment,file
+ES_D0,/Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/ChIP-seq/ES_D0/Input/merge-bams.sh-1.0.0/merged.filtered.no_dups.bam
+ES_D2,/Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/ChIP-seq/ES_D2/Input/merge-bams.sh-1.0.0/merged.filtered.no_dups.bam
+ES_D5,/Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/ChIP-seq/ES_D5/Input/merge-bams.sh-1.0.0/merged.filtered.no_dups.bam
+ES_D7,/Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/ChIP-seq/ES_D7/Input/merge-bams.sh-1.0.0/merged.filtered.no_dups.bam
+ES_D10,/Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/ChIP-seq/ES_D10/Input/merge-bams.sh-1.0.0/merged.filtered.no_dups.bam

analysis/GRO_seq_TFSEE/mem_awk_script.sh

+
+
+awk '{
+if ($1 ~ /^SUNP_/) print toupper($0);
+else if ( $1 ~ /^SSP_/) print toupper($0);
+else print $0;
+}'  /Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/Motif/MEME_op_ES_D0_gro-seq_enhancers_1kb_zoops/meme.txt > MEME_op_ES_D0_gro-seq_enhancers_1kb_zoops/meme.txt
+
+awk '{
+if ($1 ~ /^SUNP_/) print toupper($0);
+else if ( $1 ~ /^SSP_/) print toupper($0);
+else print $0;
+}'  /Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/Motif/MEME_op_ES_D2_gro-seq_enhancers_1kb_zoops/meme.txt > MEME_op_ES_D2_gro-seq_enhancers_1kb_zoops/meme.txt
+
+awk '{
+if ($1 ~ /^SUNP_/) print toupper($0);
+else if ( $1 ~ /^SSP_/) print toupper($0);
+else print $0;
+}'  /Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/Motif/MEME_op_ES_D5_gro-seq_enhancers_1kb_zoops/meme.txt > MEME_op_ES_D5_gro-seq_enhancers_1kb_zoops/meme.txt
+
+awk '{
+if ($1 ~ /^SUNP_/) print toupper($0);
+else if ( $1 ~ /^SSP_/) print toupper($0);
+else print $0;
+}'  /Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/Motif/MEME_op_ES_D7_gro-seq_enhancers_1kb_zoops/meme.txt > MEME_op_ES_D7_gro-seq_enhancers_1kb_zoops/meme.txt
+
+awk '{
+if ($1 ~ /^SUNP_/) print toupper($0);
+else if ( $1 ~ /^SSP_/) print toupper($0);
+else print $0;
+}'  /Volumes/project/GCRB/Lee_Lab/s163035/Matrix_analysis_PMIT_25842977/Motif/MEME_op_ES_D10_gro-seq_enhancers_1kb_zoops/meme.txt > MEME_op_ES_D10_gro-seq_enhancers_1kb_zoops/meme.txt

analysis/GRO_seq_TFSEE/tfsee_processing.sh

+
+# Get All GRO-seq enhancers
+cut -f1,2,3,4  ../SUNP_filtered_peaks.bed > t
+cut -f1,2,3,4 ../SSP_filtered_peaks_merged.bed >> t
+sort-bed t | uniq > GRO-seq_enhancers.bed
+
+# Histone Processing
+
+./rpkm.py --peaks GRO-seq_enhancers.bed --experiments h3k27ac_list.csv -f H3K27ac --minimum 0
+./rpkm.py --peaks GRO-seq_enhancers.bed --experiments h3k4me1_list.csv -f H3K4me1 --minimum 0
+./rpkm.py --peaks GRO-seq_enhancers.bed --experiments input_list.csv -f Input --minimum 0
+
+
+#GRO-seq Processing
+grep name SSP_filtered_peaks_sum.tsv | cut -f2,3,4,5,6,7 > GRO_filtered_peaks.tsv
+cut -f2,3,4,5,6,7 SSP_filtered_peaks_sum.tsv | grep -v name >> GRO_filtered_peaks.tsv
+cut  -f4,7,8,9,10,11 SUNP_filtered_peaks.tsv | grep -v name >> GRO_filtered_peaks.tsv
+
+
+# RNA-seq