/scripts/microbes/get_builds_lengths.py

https://bitbucket.org/cistrome/cistrome-harvard/ · Python · 56 lines · 45 code · 7 blank · 4 comment · 16 complexity · 2f519fac856df81f583bd517319e3758 MD5 · raw file

  1. #!/usr/bin/env python
  2. #Dan Blankenberg
  3. import sys, os
  4. assert sys.version_info[:2] >= ( 2, 4 )
  5. def __main__():
  6. base_dir = os.path.join( os.getcwd(), "bacteria" )
  7. try:
  8. base_dir = sys.argv[1]
  9. except:
  10. pass
  11. #print "using default base_dir:", base_dir
  12. organisms = {}
  13. for result in os.walk(base_dir):
  14. this_base_dir,sub_dirs,files = result
  15. for file in files:
  16. if file[-5:] == ".info":
  17. dict = {}
  18. info_file = open(os.path.join(this_base_dir,file),'r')
  19. info = info_file.readlines()
  20. info_file.close()
  21. for line in info:
  22. fields = line.replace("\n","").split("=")
  23. dict[fields[0]]="=".join(fields[1:])
  24. if 'genome project id' in dict.keys():
  25. name = dict['genome project id']
  26. if 'build' in dict.keys():
  27. name = dict['build']
  28. if name not in organisms.keys():
  29. organisms[name] = {'chrs':{},'base_dir':this_base_dir}
  30. for key in dict.keys():
  31. organisms[name][key]=dict[key]
  32. else:
  33. if dict['organism'] not in organisms.keys():
  34. organisms[dict['organism']] = {'chrs':{},'base_dir':this_base_dir}
  35. organisms[dict['organism']]['chrs'][dict['chromosome']]=dict
  36. for org in organisms:
  37. org = organisms[org]
  38. #if no gpi, then must be a ncbi chr which corresponds to a UCSC org, w/o matching UCSC designation
  39. try:
  40. build = org['genome project id']
  41. except: continue
  42. if 'build' in org:
  43. build = org['build']
  44. chrs=[]
  45. for chrom in org['chrs']:
  46. chrom = org['chrs'][chrom]
  47. chrs.append( "%s=%s" % ( chrom['chromosome'], chrom['length'] ) )
  48. print "%s\t%s\t%s" % ( build, org['name'], ",".join( chrs ) )
  49. if __name__ == "__main__": __main__()