# HG changeset patch
# User davidvanzessen
# Date 1451039706 18000
# Node ID 672d5e010b1ff40f0a02e37af3c840019fd3626f
# Parent 431797cd74c81dca3c71d801f9075b99580172ea
Uploaded
diff -r 431797cd74c8 -r 672d5e010b1f experimental_design.xml
--- a/experimental_design.xml Mon Dec 21 07:23:37 2015 -0500
+++ b/experimental_design.xml Fri Dec 25 05:35:06 2015 -0500
@@ -19,7 +19,7 @@
-
+
Takes the ARGalaxy proprietary format and merges several samples and/or patients together.
diff -r 431797cd74c8 -r 672d5e010b1f experimental_design/experimental_design.py
--- a/experimental_design/experimental_design.py Mon Dec 21 07:23:37 2015 -0500
+++ b/experimental_design/experimental_design.py Fri Dec 25 05:35:06 2015 -0500
@@ -22,7 +22,13 @@
blast_files += 1
files.append(df)
patients[sample_id] = files
- columns = [u'ID', u'VDJ Frame', u'Top V Gene', u'Top D Gene', u'Top J Gene', u'CDR1 Seq', u'CDR1 Length', u'CDR2 Seq', u'CDR2 Length', u'CDR3 Seq', u'CDR3 Length', u'CDR3 Seq DNA', u'CDR3 Length DNA', u'Strand', u'CDR3 Found How', u'Functionality', 'V-REGION identity %', 'V-REGION identity nt', 'D-REGION reading frame', 'AA JUNCTION', 'Functionality comment', 'Sequence', 'FR1-IMGT', 'FR2-IMGT', 'FR3-IMGT', 'CDR3-IMGT', 'JUNCTION', 'J-REGION', 'FR4-IMGT', 'P3V-nt nb', 'N1-REGION-nt nb', 'P5D-nt nb', 'P3D-nt nb', 'N2-REGION-nt nb', 'P5J-nt nb', '3V-REGION trimmed-nt nb', '5D-REGION trimmed-nt nb', '3D-REGION trimmed-nt nb', '5J-REGION trimmed-nt nb', u'Sample', u'Replicate']
+ columns = [u'ID', u'VDJ Frame', u'Top V Gene', u'Top D Gene', u'Top J Gene', u'CDR1 Seq', u'CDR1 Length', u'CDR2 Seq', u'CDR2 Length',
+ u'CDR3 Seq', u'CDR3 Length', u'CDR3 Seq DNA', u'CDR3 Length DNA', u'Strand', u'CDR3 Found How', u'Functionality', 'V-REGION identity %',
+ 'V-REGION identity nt', 'D-REGION reading frame', 'AA JUNCTION', 'Functionality comment', 'Sequence', 'FR1-IMGT', 'FR2-IMGT',
+ 'FR3-IMGT', 'CDR3-IMGT', 'JUNCTION', 'J-REGION', 'FR4-IMGT', 'P3V-nt nb', 'N1-REGION-nt nb', 'P5D-nt nb', 'P3D-nt nb', 'N2-REGION-nt nb',
+ 'P5J-nt nb', '3V-REGION trimmed-nt nb', '5D-REGION trimmed-nt nb', '3D-REGION trimmed-nt nb', '5J-REGION trimmed-nt nb', u'Sample', u'Replicate']
+ if "N-REGION-nt nb" in files[0].columns:
+ columns.insert(30, "N-REGION-nt nb")
if blast_files is not 0:
print "Has a parsed blastn file, using limited columns."
columns = [u'ID', u'VDJ Frame', u'Top V Gene', u'Top D Gene', u'Top J Gene', u'CDR1 Seq', u'CDR1 Length', u'CDR2 Seq', u'CDR2 Length', u'CDR3 Seq', u'CDR3 Length', u'CDR3 Seq DNA', u'CDR3 Length DNA', u'Strand', u'CDR3 Found How', u'Sample', u'Replicate']
diff -r 431797cd74c8 -r 672d5e010b1f imgt_loader/imgt_loader.py
--- a/imgt_loader/imgt_loader.py Mon Dec 21 07:23:37 2015 -0500
+++ b/imgt_loader/imgt_loader.py Fri Dec 25 05:35:06 2015 -0500
@@ -26,7 +26,8 @@
added_summary_columns = [u'Functionality', u'V-REGION identity %', u'V-REGION identity nt', u'D-REGION reading frame', u'AA JUNCTION', u'Functionality comment', u'Sequence']
added_sequence_columns = [u'FR1-IMGT', u'FR2-IMGT', u'FR3-IMGT', u'CDR3-IMGT', u'JUNCTION', u'J-REGION', u'FR4-IMGT']
-added_junction_columns = [u"P3'V-nt nb", u'N1-REGION-nt nb', u"P5'D-nt nb", u"P3'D-nt nb", u'N2-REGION-nt nb', u"P5'J-nt nb", u"3'V-REGION trimmed-nt nb", u"5'D-REGION trimmed-nt nb", u"3'D-REGION trimmed-nt nb", u"5'J-REGION trimmed-nt nb"]
+added_junction_columns = [u"P3'V-nt nb", u'N-REGION-nt nb', u'N1-REGION-nt nb', u"P5'D-nt nb", u"P3'D-nt nb", u'N2-REGION-nt nb', u"P5'J-nt nb", u"3'V-REGION trimmed-nt nb",
+ u"5'D-REGION trimmed-nt nb", u"3'D-REGION trimmed-nt nb", u"5'J-REGION trimmed-nt nb"]
outFile = args.output
@@ -63,7 +64,11 @@
outFrame = tmp
-outFrame.columns = [u'ID', u'VDJ Frame', u'Top V Gene', u'Top D Gene', u'Top J Gene', u'CDR1 Seq', u'CDR1 Length', u'CDR2 Seq', u'CDR2 Length', u'CDR3 Seq', u'CDR3 Length', u'CDR3 Seq DNA', u'CDR3 Length DNA', u'Strand', u'CDR3 Found How', u'Functionality', 'V-REGION identity %', 'V-REGION identity nt', 'D-REGION reading frame', 'AA JUNCTION', 'Functionality comment', 'Sequence', 'FR1-IMGT', 'FR2-IMGT', 'FR3-IMGT', 'CDR3-IMGT', 'JUNCTION', 'J-REGION', 'FR4-IMGT', 'P3V-nt nb', 'N1-REGION-nt nb', 'P5D-nt nb', 'P3D-nt nb', 'N2-REGION-nt nb', 'P5J-nt nb', '3V-REGION trimmed-nt nb', '5D-REGION trimmed-nt nb', '3D-REGION trimmed-nt nb', '5J-REGION trimmed-nt nb']
+outFrame.columns = [u'ID', u'VDJ Frame', u'Top V Gene', u'Top D Gene', u'Top J Gene', u'CDR1 Seq', u'CDR1 Length', u'CDR2 Seq', u'CDR2 Length', u'CDR3 Seq', u'CDR3 Length',
+ u'CDR3 Seq DNA', u'CDR3 Length DNA', u'Strand', u'CDR3 Found How', u'Functionality', 'V-REGION identity %', 'V-REGION identity nt', 'D-REGION reading frame',
+ 'AA JUNCTION', 'Functionality comment', 'Sequence', 'FR1-IMGT', 'FR2-IMGT', 'FR3-IMGT', 'CDR3-IMGT', 'JUNCTION', 'J-REGION', 'FR4-IMGT', 'P3V-nt nb',
+ 'N-REGION-nt nb', 'N1-REGION-nt nb', 'P5D-nt nb', 'P3D-nt nb', 'N2-REGION-nt nb', 'P5J-nt nb', '3V-REGION trimmed-nt nb', '5D-REGION trimmed-nt nb', '3D-REGION trimmed-nt nb',
+ '5J-REGION trimmed-nt nb']
"""
IGHV[0-9]-[0-9ab]+-?[0-9]?D?
diff -r 431797cd74c8 -r 672d5e010b1f report_clonality/RScript.r
--- a/report_clonality/RScript.r Mon Dec 21 07:23:37 2015 -0500
+++ b/report_clonality/RScript.r Fri Dec 25 05:35:06 2015 -0500
@@ -584,6 +584,14 @@
if(all(imgtcolumns %in% colnames(inputdata)))
{
print("found IMGT columns, running junction analysis")
+
+ if(locus %in% c("IGK","IGL", "TRA", "TRG")){
+ print("VJ recombination, using N column for junction analysis")
+ print(names(PRODF))
+ print(head(PRODF$N.REGION.nt.nb, 30))
+ PRODF$N1.REGION.nt.nb = PRODF$N.REGION.nt.nb
+ }
+
newData = data.frame(data.table(PRODF)[,list(unique=.N,
VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
P1=mean(.SD$P3V.nt.nb, na.rm=T),