Mercurial > repos > davidvanzessen > shm_csr
diff gene_identification.py @ 26:ce25fb581ca3 draft
Uploaded
author | davidvanzessen |
---|---|
date | Mon, 05 Dec 2016 11:00:13 -0500 |
parents | 012a738edf5a |
children | 69baebd10e54 |
line wrap: on
line diff
--- a/gene_identification.py Mon Dec 05 08:26:01 2016 -0500 +++ b/gene_identification.py Mon Dec 05 11:00:13 2016 -0500 @@ -164,7 +164,8 @@ varsInCM = 0 varsInCE = 0 - +def round_int(val): + return int(round(val)) first = True seq_write_count=0 @@ -193,27 +194,27 @@ ca1hits = currentIDHits["ca1"] ca2hits = currentIDHits["ca2"] if ca1hits >= ca2hits: - o.write(ID + "\tIGA1\t" + str(int(ca1hits / varsInCA * 100)) + "\t" + str(int(cahits / possibleca * 100)) + "\t" + start_location[ID + "_ca"] + "\n") + o.write(ID + "\tIGA1\t" + str(round_int(ca1hits / varsInCA * 100)) + "\t" + str(round_int(cahits / possibleca * 100)) + "\t" + start_location[ID + "_ca"] + "\n") else: - o.write(ID + "\tIGA2\t" + str(int(ca2hits / varsInCA * 100)) + "\t" + str(int(cahits / possibleca * 100)) + "\t" + start_location[ID + "_ca"] + "\n") + o.write(ID + "\tIGA2\t" + str(round_int(ca2hits / varsInCA * 100)) + "\t" + str(round_int(cahits / possibleca * 100)) + "\t" + start_location[ID + "_ca"] + "\n") elif cghits >= cahits and cghits >= cmhits and cghits >= cehits: #its a cg gene cg1hits = currentIDHits["cg1"] cg2hits = currentIDHits["cg2"] cg3hits = currentIDHits["cg3"] cg4hits = currentIDHits["cg4"] if cg1hits >= cg2hits and cg1hits >= cg3hits and cg1hits >= cg4hits: #cg1 gene - o.write(ID + "\tIGG1\t" + str(int(cg1hits / varsInCG * 100)) + "\t" + str(int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") + o.write(ID + "\tIGG1\t" + str(round_int(cg1hits / varsInCG * 100)) + "\t" + str(round_int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") elif cg2hits >= cg1hits and cg2hits >= cg3hits and cg2hits >= cg4hits: #cg2 gene - o.write(ID + "\tIGG2\t" + str(int(cg2hits / varsInCG * 100)) + "\t" + str(int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") + o.write(ID + "\tIGG2\t" + str(round_int(cg2hits / varsInCG * 100)) + "\t" + str(round_int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") elif cg3hits >= cg1hits and cg3hits >= cg2hits and cg3hits >= cg4hits: #cg3 gene - o.write(ID + "\tIGG3\t" + str(int(cg3hits / varsInCG * 100)) + "\t" + str(int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") + o.write(ID + "\tIGG3\t" + str(round_int(cg3hits / varsInCG * 100)) + "\t" + str(round_int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") else: #cg4 gene - o.write(ID + "\tIGG4\t" + str(int(cg4hits / varsInCG * 100)) + "\t" + str(int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") + o.write(ID + "\tIGG4\t" + str(round_int(cg4hits / varsInCG * 100)) + "\t" + str(round_int(cghits / possiblecg * 100)) + "\t" + start_location[ID + "_cg"] + "\n") else: #its a cm or ce gene if cmhits >= cehits: - o.write(ID + "\tIGM\t100\t" + str(int(cmhits / possiblecm * 100)) + "\t" + start_location[ID + "_cm"] + "\n") + o.write(ID + "\tIGM\t100\t" + str(round_int(cmhits / possiblecm * 100)) + "\t" + start_location[ID + "_cm"] + "\n") else: - o.write(ID + "\tIGE\t100\t" + str(int(cehits / possiblece * 100)) + "\t" + start_location[ID + "_ce"] + "\n") + o.write(ID + "\tIGE\t100\t" + str(round_int(cehits / possiblece * 100)) + "\t" + start_location[ID + "_ce"] + "\n") seq_write_count += 1 print "Time: %i" % (int(time.time() * 1000) - starttime)