Mercurial > repos > davidvanzessen > complete_immunerepertoire_igg
diff imgt_loader.py @ 7:a9053212a462 draft
Uploaded
| author | davidvanzessen |
|---|---|
| date | Mon, 05 Jan 2015 09:30:08 -0500 |
| parents | 3287f7b9c47d |
| children |
line wrap: on
line diff
--- a/imgt_loader.py Mon Sep 08 04:24:04 2014 -0400 +++ b/imgt_loader.py Mon Jan 05 09:30:08 2015 -0500 @@ -128,7 +128,6 @@ outFrame["Top D Gene"] = outFrame["Top D Gene"].apply(lambda x: filterGenes(x, dPattern)) outFrame["Top J Gene"] = outFrame["Top J Gene"].apply(lambda x: filterGenes(x, jPattern)) -print outFrame tmp = outFrame["VDJ Frame"] tmp = tmp.replace("in-frame", "In-frame") @@ -137,6 +136,6 @@ outFrame["VDJ Frame"] = tmp 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 J Gene"] != "NA")] #filter out weird rows? +#outFrame = outFrame[(outFrame["CDR3 Seq DNA"].map(safeLength) > 0) & (outFrame["Top V Gene"] != "NA") & (outFrame["Top J Gene"] != "NA")] #filter out weird rows? #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, index_label="index")