Mercurial > repos > davidvanzessen > combined_immune_repertoire_imgt
changeset 6:8418fab78894 draft
Uploaded
| author | davidvanzessen |
|---|---|
| date | Tue, 10 Dec 2013 08:06:50 -0500 |
| parents | 3ce07f5889ad |
| children | c134f2d0a484 |
| files | imgtconvert.py |
| diffstat | 1 files changed, 4 insertions(+), 4 deletions(-) [+] |
line wrap: on
line diff
--- a/imgtconvert.py Tue Dec 10 07:22:25 2013 -0500 +++ b/imgtconvert.py Tue Dec 10 08:06:50 2013 -0500 @@ -18,7 +18,7 @@ old_sequence_columns = [u'CDR1-IMGT', u'CDR2-IMGT', u'CDR3-IMGT'] old_junction_columns = [u'JUNCTION'] -added_summary_columns = [u'V-REGION identity %', u'V-REGION identity nt', u'D-REGION reading frame', u'AA JUNCTION', u'Functionality comment', u'Sequence'] +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"] @@ -107,7 +107,7 @@ outFrame = outFrame.append(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', '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', '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'] vPattern = re.compile(r"IGHV[1-9]-[0-9ab]+-?[1-9]?") dPattern = re.compile(r"IGHD[1-9]-[0-9ab]+") @@ -133,7 +133,7 @@ tmp = tmp.replace("null", "Out-of-frame") tmp = tmp.replace("out-of-frame", "Out-of-frame") outFrame["VDJ Frame"] = tmp -outFrame["CDR3 Length"] = outFrame["CDR3 Seq DNA"].map(str).map(len) +outFrame["CDR3 Length DNA"] = outFrame["CDR3 Seq DNA"].map(str).map(len) safeLength = lambda x: len(x) if type(x) == str else 0 outFrame = outFrame[(outFrame["CDR3 Seq DNA"].map(safeLength) > 0) & (outFrame["Top V Gene"] != "NA") & (outFrame["Top D Gene"] != "NA") & (outFrame["Top J Gene"] != "NA")] #filter out weird rows? -outFrame.to_csv(outFile, sep="\t", index=False) \ No newline at end of file +outFrame.to_csv(outFile, sep="\t", index=False, index_label="index")