comparison libs/run_auto_All_for_assemblies.py @ 10:53efef402c51 draft

planemo upload commit a4fb57231f274270afbfebd47f67df05babffa4a-dirty

9:acc5cd06a36a

#!/usr/bin/env python



import os
from Bio import SeqIO

  try:
    os.rename(file1, file2)
    real_file=file2
  except:
    real_file=file1
  #print("###The genome name:",file1
  dirpath = os.path.abspath(os.path.dirname(os.path.realpath(__file__)))###01/27/2015
  os.system('touch result.txt')
  database_path="database"###01/27/2015
  os.system('python '+dirpath+'/Otype_determine_analysis.py '+database_path+'/Typhimurium_LT2_gnd_galF.fasta '+real_file+' '+database_path+'/new_Oserotype.fasta >temp_result_'+str(q)+'O.txt')
  os.system('cat temp_result_'+str(q)+'O.txt>>data_log.txt')
  handle=open('temp_result_'+str(q)+'O.txt',"r")
  handle=handle.readlines()
  for line in handle:
    if "$$$ Most" in line and "O_type" in line:

    if O3_10=="+":
      Otype="3,10"
    elif O1_3_19=="+":
      Otype="1,3,19"
    else:
      print("No_O3,10_O1,3,19_spe_sequences")
  os.system('python '+dirpath+'/H_combination_output_analysis.py '+real_file+' '+database_path+'/H_new_fliC_protein_database.fasta '+database_path+'/H_new_fljB_protein_database.fasta >temp_result_'+str(q)+'H.txt')
  os.system('cat temp_result_'+str(q)+'H.txt>>data_log.txt')
  handle2=open('temp_result_'+str(q)+'H.txt',"r")
  handle2=handle2.readlines()
  suspect="no" #for the first choice doesn't hit core sequence
  for line in handle2:

      fljB=line.split("fljB_type:  ")[1].split("_")[0].strip()
    elif "$$$ No" in line and "fljB" in line:
      fljB="-"
      #print line,
  if Otype=="9" and fliC=="g,m" and fljB=="-":
    os.system('python '+dirpath+'/special_gene_test_assemblies.py '+database_path+'/specific_genes.fasta '+real_file+' sdf >temp_result_'+str(q)+'sdf.txt')
    os.system('cat temp_result_'+str(q)+'sdf.txt>>data_log.txt')
    handle3=open('temp_result_'+str(q)+'sdf.txt',"r")
    sdf=""
    for line in handle3:
      if "$$$" in line and "got a hit" in line:

  star=""
  star_line=""
  if len(seronames)>1:
    star="*"
    star_line="The predicted serotypes share the same general formula:\t"+Otype+":"+fliC+":"+fljB+"\n"##
  #print("$$$The most possible formula is: (by the order O:H1:H2) ",Otype,":",fliC,":",fljB
  #print("$$$The possible serotyes are:",seronames
  m=0
  for y in seronames:
    if y in file1:
      #print("$$$ Is the judgement true? Answer:Yes!"       #here we use file1, because we want ":", while file2 turned it to "__"
      answer="Yes"
      m=1
  if m==0:
    #print("$$$ Is the judgement true? Answer: Need to check the records and file names"
    answer="Not sure"
  print("\n","\n")
  predict_form=Otype+":"+fliC+":"+fljB
  predict_sero=(" or ").join(seronames)
  if predict_form=="9:g,m:-":#
    predict_form=predict_form+"\nSdf prediction:"+sdf #
    if sdf=="-":#

    for j in xrange(len(jobs)):
      jobs[j].join()
      txt_names.append(file_names[j+i].replace(' ','_').replace(":","__").replace("[","").replace("]","")+".txt")
    print txt_names
    for j in xrange(len(txt_names)):
      print(i,"and",j)
      print(i+j+1)
      file=open(txt_names[j],"r")
      handle=list(file)
      b=handle[0].split("\t")
      print(b)
      sheet.write(i+j+1,0,b[0])
      sheet.write(i+j+1,1,b[1])
      sheet.write(i+j+1,2,b[2])
      sheet.write(i+j+1,3,b[3])
      sheet.write(i+j+1,4,b[4])
      sheet.write(i+j+1,5,b[5])
      sheet.write(i+j+1,6,b[6])
      sheet.write(i+j+1,7,b[7])

  print("End time,",time.time())
  file3.save("Seqsero_result2.xls")
  '''


if __name__ == '__main__':

10:53efef402c51

#!/usr/bin/env python2.7



import os
from Bio import SeqIO

  try:
    os.rename(file1, file2)
    real_file=file2
  except:
    real_file=file1
  #print "###The genome name:",file1
  dirpath = os.path.abspath(os.path.dirname(os.path.realpath(__file__)))###01/27/2015
  os.system('touch result.txt')
  database_path="database"###01/27/2015
  os.system('python2.7 '+dirpath+'/Otype_determine_analysis.py '+database_path+'/Typhimurium_LT2_gnd_galF.fasta '+real_file+' '+database_path+'/new_Oserotype.fasta >temp_result_'+str(q)+'O.txt')
  os.system('cat temp_result_'+str(q)+'O.txt>>data_log.txt')
  handle=open('temp_result_'+str(q)+'O.txt',"r")
  handle=handle.readlines()
  for line in handle:
    if "$$$ Most" in line and "O_type" in line:

    if O3_10=="+":
      Otype="3,10"
    elif O1_3_19=="+":
      Otype="1,3,19"
    else:
      print "No_O3,10_O1,3,19_spe_sequences"
  os.system('python2.7 '+dirpath+'/H_combination_output_analysis.py '+real_file+' '+database_path+'/H_new_fliC_protein_database.fasta '+database_path+'/H_new_fljB_protein_database.fasta >temp_result_'+str(q)+'H.txt')
  os.system('cat temp_result_'+str(q)+'H.txt>>data_log.txt')
  handle2=open('temp_result_'+str(q)+'H.txt',"r")
  handle2=handle2.readlines()
  suspect="no" #for the first choice doesn't hit core sequence
  for line in handle2:

      fljB=line.split("fljB_type:  ")[1].split("_")[0].strip()
    elif "$$$ No" in line and "fljB" in line:
      fljB="-"
      #print line,
  if Otype=="9" and fliC=="g,m" and fljB=="-":
    os.system('python2.7 '+dirpath+'/special_gene_test_assemblies.py '+database_path+'/specific_genes.fasta '+real_file+' sdf >temp_result_'+str(q)+'sdf.txt')
    os.system('cat temp_result_'+str(q)+'sdf.txt>>data_log.txt')
    handle3=open('temp_result_'+str(q)+'sdf.txt',"r")
    sdf=""
    for line in handle3:
      if "$$$" in line and "got a hit" in line:

  star=""
  star_line=""
  if len(seronames)>1:
    star="*"
    star_line="The predicted serotypes share the same general formula:\t"+Otype+":"+fliC+":"+fljB+"\n"##
  #print "$$$The most possible formula is: (by the order O:H1:H2) ",Otype,":",fliC,":",fljB
  #print "$$$The possible serotyes are:",seronames
  m=0
  for y in seronames:
    if y in file1:
      #print "$$$ Is the judgement true? Answer:Yes!"       #here we use file1, because we want ":", while file2 turned it to "__"
      answer="Yes"
      m=1
  if m==0:
    #print "$$$ Is the judgement true? Answer: Need to check the records and file names"
    answer="Not sure"
  print "\n","\n"
  predict_form=Otype+":"+fliC+":"+fljB
  predict_sero=(" or ").join(seronames)
  if predict_form=="9:g,m:-":#
    predict_form=predict_form+"\nSdf prediction:"+sdf #
    if sdf=="-":#

    for j in xrange(len(jobs)):
      jobs[j].join()
      txt_names.append(file_names[j+i].replace(' ','_').replace(":","__").replace("[","").replace("]","")+".txt")
    print txt_names
    for j in xrange(len(txt_names)):
      print i,"and",j
      print i+j+1
      file=open(txt_names[j],"r")
      handle=list(file)
      b=handle[0].split("\t")
      print b
      sheet.write(i+j+1,0,b[0])
      sheet.write(i+j+1,1,b[1])
      sheet.write(i+j+1,2,b[2])
      sheet.write(i+j+1,3,b[3])
      sheet.write(i+j+1,4,b[4])
      sheet.write(i+j+1,5,b[5])
      sheet.write(i+j+1,6,b[6])
      sheet.write(i+j+1,7,b[7])

  print "End time,",time.time()
  file3.save("Seqsero_result2.xls")
  '''


if __name__ == '__main__':