Remove Igblast from Number of sequences plot in Airrflow report

Author: Vivian0105

assets/repertoire_comparison.Rmd

@@ -77,11 +77,11 @@ tryCatch( {
     write.table(tab_seqs, file=paste0(seq_dir,"/Table_sequences_assembly.tsv"), sep="\t", quote=F, row.names=F)
 
     plot_table <- tidyr::pivot_longer(tab_seqs,
-                                      cols=Sequences:Igblast,
+                                      cols=Sequences:Representative_2,
                                       names_to = "steps",
                                       values_to ="count")
     firstcol = which(colnames(tab_seqs) == "Sequences")
-    lastcol = which(colnames(tab_seqs) == "Igblast")
+    lastcol = which(colnames(tab_seqs) == "Representative_2")
     plot_table$steps <- factor(plot_table$steps, levels=colnames(tab_seqs)[firstcol:lastcol])
 
     seqs_plot <- ggplot(data=plot_table,

bin/log_parsing.py

@@ -387,8 +387,7 @@
     "Build_consensus",
     "Assemble_pairs",
     "Unique",
-    "Representative_2",
-    "Igblast",
+    "Representative_2"
 ]
 
 print(df_process_list[0].sort_values(by=["Sample"]).pivot(index="Sample", columns="readtype"))
@@ -403,8 +402,7 @@
     df_process_list[4].set_index("Sample").loc[:, "pass_pairs"],
     df_process_list[5].set_index("Sample").loc[:, "pass_pairs"],
     df_process_list[6].set_index("Sample").loc[:, "keep"],
-    df_process_list[7].set_index("Sample").loc[:, "repres_2"],
-    df_process_list[7].set_index("Sample").loc[:, "pass_igblast"],
+    df_process_list[7].set_index("Sample").loc[:, "repres_2"]
 ]
 
 final_table = pd.concat(values, axis=1, join="outer")

bin/log_parsing_no-umi.py

@@ -313,8 +313,7 @@
     "Mask_primers_R1",
     "Mask_primers_R2",
     "Unique",
-    "Representative_2",
-    "Igblast",
+    "Representative_2"
 ]
 
 # Tables provide extra info and help debugging
@@ -342,8 +341,7 @@
     df_process_list[2].sort_values(by=["Sample"]).pivot(index="Sample", columns="readtype")["pass"]["R1"].tolist(),
     df_process_list[2].sort_values(by=["Sample"]).pivot(index="Sample", columns="readtype")["pass"]["R2"].tolist(),
     df_process_list[3].sort_values(by=["Sample"]).loc[:, "keep"].tolist(),
-    df_process_list[4].sort_values(by=["Sample"]).loc[:, "repres_2"].tolist(),
-    df_process_list[4].sort_values(by=["Sample"]).loc[:, "pass_igblast"].tolist(),
+    df_process_list[4].sort_values(by=["Sample"]).loc[:, "repres_2"].tolist()
 ]
 
 final_table = dict(zip(colnames, values))