Figure 4 of CRISPR MultiTargeter paper

Figure4_data/Figure4A.R

@@ -0,0 +1,5 @@
+x = c(0.975, 0.71, 0.51, 0.49)
+par(mar=c(7,20,6,1))
+
+barplot(x, width = 1, names.arg = c("Genes with isoform-specific sgRNA sites", "Transcripts with isoform-specific sgRNA sites", "Sites in the sense strand", "Sites in the anti-sense strand"), horiz = TRUE, col = c(1,2,3,4), las=1, cex.names = 1.1, cex.axis = 1.2, xlim = c(0, 1))
+rect(par("usr")[1],par("usr")[3],par("usr")[2],par("usr")[4],col = rgb(1, 1, 1, alpha=0.2))

Figure4_data/genes_selecter.py

@@ -0,0 +1,30 @@
+
+read_fh = open("zebrafish_transcript_table.txt", 'r')
+
+alt_genes  = {}
+
+for line in read_fh: 
+	# remove the newline
+	line = line.strip('\n')
+
+	# get the information on the gene and transcript ID
+	(trID, geneID, seq) = line.split("\t")
+
+	# record the number of transcripts are associated with any specific gene
+	if geneID in alt_genes:
+		alt_genes[geneID] += 1
+	else:
+		alt_genes[geneID] = 1
+
+
+# make a new file handle for writing
+outputFH = open('genes_with_alternative_transcripts.txt', 'w')
+
+# output the genes with multiple transcript isoforms		
+for gene in alt_genes:
+	if alt_genes[gene] >= 2:
+		outputFH.write(gene)
+		outputFH.write('\n')
+
+
+outputFH.close()