# HG changeset patch # User davidvanzessen # Date 1480953613 18000 # Node ID ce25fb581ca3fb4a67e036d8b0adb69de9eb6137 # Parent 8d1c4c75f81b150aea709b31b7f3186cec1538b8 Uploaded diff -r 8d1c4c75f81b -r ce25fb581ca3 gene_identification.py --- 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) diff -r 8d1c4c75f81b -r ce25fb581ca3 shm_csr.py --- a/shm_csr.py Mon Dec 05 08:26:01 2016 -0500 +++ b/shm_csr.py Mon Dec 05 11:00:13 2016 -0500 @@ -85,7 +85,7 @@ AALength = 64 AA_mutation = [0] * AALength -AA_mutation_dic = {"IGA": AA_mutation[:], "IGG": AA_mutation[:], "IGM": AA_mutation[:], "unm": AA_mutation[:], "all": AA_mutation[:]} +AA_mutation_dic = {"IGA": AA_mutation[:], "IGG": AA_mutation[:], "IGM": AA_mutation[:], "IGE": AA_mutation[:], "unm": AA_mutation[:], "all": AA_mutation[:]} AA_mutation_empty = AA_mutation[:] aa_mutations_by_id_file = outfile[:outfile.rindex("/")] + "/aa_id_mutations.txt" diff -r 8d1c4c75f81b -r ce25fb581ca3 wrapper.sh --- a/wrapper.sh Mon Dec 05 08:26:01 2016 -0500 +++ b/wrapper.sh Mon Dec 05 11:00:13 2016 -0500 @@ -578,7 +578,7 @@ echo "The data for the 'all' transition plotDownload" >> $output echo "The data for the 'IGA' transition plotDownload" >> $output echo "The data for the 'IGA1' transition plotDownload" >> $output -echo "The data for the 'IGA1' transition plotDownload" >> $output +echo "The data for the 'IGA1' transition plotDownload" >> $output echo "The data for the 'IGG' transition plotDownload" >> $output echo "The data for the 'IGG1' transition plotDownload" >> $output echo "The data for the 'IGG2' transition plotDownload" >> $output