def main(): os.chdir(wdir) file_list = glob.glob(os.path.join(wdir,'cluster_NSR','*.fasta')) save=open('all.fasta','w') for file1 in file_list: fasta = trile.read_fasta(file1) for head in fasta.keys(): save.write('>'+head+'\n') save.write(fasta.get(head)+'\n') save.close() file1 = 'all.fasta' name = 'all' cmd = uclust+' --sort '+file1 cmd+= ' --output '+file1+'.tmp' os.system(cmd) cmd = uclust+' --input '+file1+'.tmp' cmd+= ' --uc '+name+'.uc' os.system(cmd) cmd = uclust+' --input '+name+'.fasta --uc2fasta ' cmd+= name+'.uc --output ' cmd+= name+'.fasta.tmp2' os.system(cmd) os.system('mv '+name+'.fasta.tmp2 '+name+'.fasta') os.system('rm '+name+'.uc '+name+'.fasta.tmp')
def main(): try: os.mkdir(os.path.join(wdir,'cluster_NSR')) except: pass os.chdir(os.path.join(wdir,'cluster_NSR')) file_list = glob.glob(os.path.join(wdir,'format_NSR','*.fasta')) for file1 in file_list: name = os.path.basename(file1).split('.fasta')[0] cmd = uclust+' --sort '+file1 cmd+= ' --output '+os.path.basename(file1) os.system(cmd) cmd = uclust+' --input '+os.path.basename(file1) cmd+= ' --uc '+name+'.uc' os.system(cmd) cmd = uclust+' --input '+name+'.fasta --uc2fasta ' cmd+= name+'.uc --types S --output ' cmd+= name+'.fasta.tmp' os.system(cmd) os.system('mv '+name+'.fasta.tmp '+name+'.fasta') os.system('rm '+name+'.uc') fasta = trile.read_fasta(name+'.fasta') save = open(name+'.fasta','w') count = 0 for head in fasta.keys(): count+=1 save.write('>'+name+'.'+str(count)+'\n') save.write(fasta.get(head)+'\n') save.close()
def main(): try: os.mkdir(os.path.join(wdir,'format_NSR')) except: pass file_list = glob.glob(os.path.join(wdir,'NSR','*.fasta')) for file1 in file_list: name = os.path.basename(file1).split('.fasta')[0] fasta = trile.read_fasta(file1) save = open(os.path.join(wdir,'format_NSR',name+'.fasta'),'w') count = 0 for head in fasta.keys(): count+=1 save.write('>'+name+'.'+str(count)+'\n') save.write(fasta.get(head)+'\n') save.close()
def main(): os.chdir(wdir) save = open('epidemic.fasta','w') read = open('heatmap.tsv') head = next(read).split() seq_dict = trile.read_fasta('all.fasta') bool_dict = dict() for line in read: col = line.split() name = col[0] col = col[1:] for i in range(len(col)): if float(col[i])>20.0: if head[i] not in bool_dict.keys(): bool_dict[head[i]]=name else: bool_dict[head[i]]+='.'+name count = 1 for key in bool_dict.keys(): val = bool_dict.get(key) if val.count('O')==7 and 'N' not in val: save.write('>E'+str(count)+'\n') save.write(seq_dict.get(key)+'\n') count+=1