API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Feb 28th, 2015
171
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 8.97 KB | None | 0 0
raw download clone embed print report
  1. import pandas as pd
  2. import csv
  3.  
  4. # ----------------------------------- Input variables -----------------------------------
  5.  
  6. # Input should be a .csv file with 2 columns (PrEST ID, PrEST Sequence)
  7. data_file = 'Master Thesis 14 PrESTs'
  8. protease_name = 'Trypsin'
  9. #protease_name = 'Lys-C'
  10.  
  11. # ---------------------------------------------------------------------------------------
  12.  
  13. data = pd.read_csv(data_file + '.csv', sep=';')
  14. proteasome = 'Non-Unique Reference (' + protease_name + ') (UniProt, canonical).csv'
  15.  
  16. # Create peptide reference Set
  17. ref_set = set()
  18. with open(proteasome, 'rU') as in_file:
  19. reader_2 = csv.reader(in_file)
  20. for row in reader_2:
  21. (ref_set.add(str(row).replace("'","").replace(",","")
  22. .replace("[","").replace("]","").replace(" ","")))
  23. print(str(len(ref_set)) + ' peptides in reference')
  24.  
  25. def protease(PrEST_seq, a, type):
  26. if protease_name == 'Trypsin':
  27. if type == 1:
  28. if PrEST_seq[a+1:a+2] != 'P' and (PrEST_seq[a:a+1] == 'R' or PrEST_seq[a:a+1] == 'K'):
  29. return 1
  30. else:
  31. return 0
  32. else:
  33. if PrEST_seq[a+2:a+3] != 'P' and (PrEST_seq[a+1:a+2] == 'R' or PrEST_seq[a+1:a+2] == 'K'):
  34. return 1
  35. else:
  36. return 0
  37. if protease_name == 'Lys-C':
  38. if PrEST_seq[a:a+1] == 'K':
  39. return 1
  40. else:
  41. return 0
  42.  
  43. # Initiate variables
  44. Peptide_list = [] # List for Peptides (resets for each PrEST)
  45. ID_list = [] # List for PrEST IDs (resets for each PrEST)
  46. Non_Uniques = [] # List for non-unique peptides
  47. Non_Uniques_ID = [] # List for non-unique PrEST IDs
  48. Peptide = '' # Current peptide (no missed cleavages)
  49. Peptide_MC1 = '' # Current peptide with 1 missed cleavage
  50. Peptide_MC2 = '' # Current peptide with 2 missed cleavages
  51.  
  52. PrEST_data = pd.DataFrame()
  53. # ------------------------------------------------ Main PrEST for-loop ------------------------------------------------
  54. for row in data.iterrows(): # For every PrEST (row)
  55. First = 'Y'
  56. PrEST_seq = row[1][1]
  57. Pep_Count = 0
  58. MC_Pep_Count = 0
  59. Non_Unique_Count = 0
  60.  
  61. # ----------------------------------------- No missed cleavages for-loop ------------------------------------------
  62. for n in range(len(PrEST_seq)): # For every AA in every PrEST
  63.  
  64. if protease(PrEST_seq, n, 1) == 1:
  65. if First != 'Y': # Does not count first peptide + MCs (part of ABP)
  66. Peptide += PrEST_seq[n:n+1]
  67. if len(Peptide) >= 6: # Only appends peptide if longer than 6 AA
  68. if Peptide not in ref_set:
  69. ID_list.append(row[1][0])
  70. Peptide_list.append(Peptide)
  71. Pep_Count += 1
  72. else:
  73. Non_Uniques_ID.append(row[1][0])
  74. Non_Uniques.append(Peptide)
  75. Non_Unique_Count += 1
  76. ID_list.append(row[1][0] + ' (Not unique)')
  77. Peptide_list.append(Peptide)
  78.  
  79. # ----------------------------------- One missed cleavage while-loop ----------------------------------
  80. Peptide_MC1 = Peptide
  81. m = n
  82. while m+1 <= len(PrEST_seq):
  83. m += 1
  84. if protease(PrEST_seq, m, 1) == 1:
  85. Peptide_MC1 += PrEST_seq[m:m+1]
  86. if len(Peptide_MC1) >= 6:
  87. if Peptide_MC1 not in ref_set:
  88. ID_list.append(row[1][0])
  89. Peptide_list.append(Peptide_MC1)
  90. MC_Pep_Count += 1
  91. break
  92. else:
  93. Non_Uniques_ID.append(row[1][0])
  94. Non_Uniques.append(Peptide_MC1)
  95. Non_Unique_Count += 1
  96. ID_list.append(row[1][0] + ' (Not unique)')
  97. Peptide_list.append(Peptide_MC1)
  98. else:
  99. Peptide_MC1 += PrEST_seq[m:m+1]
  100.  
  101. # ---------------------------------- Two missed cleavages while-loop ----------------------------------
  102. Peptide_MC2 = Peptide_MC1
  103. k = m
  104. while k+1 <= len(PrEST_seq):
  105. k += 1
  106. if protease(PrEST_seq, k, 1) == 1:
  107. Peptide_MC2 += PrEST_seq[k:k+1]
  108. if len(Peptide_MC2) >= 6:
  109. if Peptide_MC2 not in ref_set:
  110. ID_list.append(row[1][0])
  111. Peptide_list.append(Peptide_MC2)
  112. MC_Pep_Count += 1
  113. break
  114. else:
  115. Non_Uniques_ID.append(row[1][0])
  116. Non_Uniques.append(Peptide_MC2)
  117. Non_Unique_Count += 1
  118. ID_list.append(row[1][0] + ' (Not unique)')
  119. Peptide_list.append(Peptide_MC2)
  120. else:
  121. Peptide_MC2 += PrEST_seq[k:k+1]
  122. # -------------------------------------------------------------------------------------------------
  123.  
  124. # Resets variables
  125. Peptide = ''
  126. Peptide_MC1 = ''
  127. Peptide_MC2 = ''
  128. elif First == 'Y': # Doesn't count first cleavage (contains ABP)
  129. Peptide = ''
  130. First = 'N'
  131. else: # Non-cleavable AAs - Peptide grows
  132. Peptide += PrEST_seq[n:n+1]
  133.  
  134. # Appends PrEST data
  135. K = row[1][1].count('K')
  136. R = row[1][1].count('R')
  137. PrEST_data = PrEST_data.append(pd.DataFrame(data=[[row[1][0], Pep_Count, MC_Pep_Count, Non_Unique_Count, K, R]],
  138. columns=['PrEST ID', '# Peptides', '# MC Peptides', '# Non-Uniques',
  139. '# K', 'R']))
  140. # Writes PrEST data to file
  141. PrEST_data = PrEST_data[['PrEST ID', '# Peptides', '# MC Peptides', '# Non-Uniques', '# K', 'R']]
  142. ew = pd.ExcelWriter(data_file + ' Results.xlsx', encoding='iso-8859-1')
  143. PrEST_data.to_excel(ew, sheet_name='PrESTs (' + protease_name + ')', index=False)
  144.  
  145. # Creates peptide list for Perseus and writes to file
  146. peptides = pd.DataFrame(Peptide_list, columns=['Peptides']).join(pd.DataFrame(ID_list, columns=['PrEST ID']))
  147. peptides['temp'] = peptides['Peptides'].str.len()
  148. peptides = peptides.sort(['PrEST ID', 'temp'], ascending=[True, False]).drop('temp', axis=1)
  149. peptides.to_excel(ew, sheet_name='Peptide list for Perseus', index=False)
  150.  
  151. # List for non-unique peptides
  152. NU_peptides = pd.DataFrame(Non_Uniques, columns=['Peptides']).join(pd.DataFrame(Non_Uniques_ID, columns=['PrEST ID']))
  153. NU_peptides['temp'] = NU_peptides['Peptides'].str.len()
  154. NU_peptides = NU_peptides.sort(['PrEST ID', 'temp'], ascending=[True, False]).drop('temp', axis=1)
  155. NU_peptides.to_excel(ew, sheet_name='Non-unique peptides', index=False)
  156.  
  157. ew.save()
  158.  
  159. def protease(PrEST_seq, a, type):
  160. if protease_name == 'Trypsin':
  161. if type == 1:
  162. if PrEST_seq[a+1:a+2] != 'P' and (PrEST_seq[a:a+1] == 'R' or PrEST_seq[a:a+1] == 'K'):
  163. return 1
  164. else:
  165. return 0
  166. else:
  167. if PrEST_seq[a+2:a+3] != 'P' and (PrEST_seq[a+1:a+2] == 'R' or PrEST_seq[a+1:a+2] == 'K'):
  168. return 1
  169. else:
  170. return 0
  171. if protease_name == 'Lys-C':
  172. if PrEST_seq[a:a+1] == 'K':
  173. return 1
  174. else:
  175. return 0
  176.  
  177. def protease(PrEST_seq, a, type):
  178. if protease_name == 'Trypsin':
  179. if type != 1:
  180. a+=1
  181. return PrEST_seq[a+1] != 'P' and (PrEST_seq[a] in ['R','K']):
  182. assert(protease_name == 'Lys-C')
  183. return PrEST_seq[a] == 'K'
  184.  
  185. m = n
  186. while m+1 <= len(PrEST_seq):
  187. m += 1
  188. stuff_about(m)
  189.  
  190. for m in range(n+1, len(PrEST_seq)+1):
  191. stuff_about(m)
  192.  
  193. if len(Peptide) >= 6: # Only appends peptide if longer than 6 AA
  194. if Peptide not in ref_set:
  195. ID_list.append(row[1][0])
  196. Peptide_list.append(Peptide)
  197. Pep_Count += 1
  198. else:
  199. Non_Uniques_ID.append(row[1][0])
  200. Non_Uniques.append(Peptide)
  201. Non_Unique_Count += 1
  202. ID_list.append(row[1][0] + ' (Not unique)')
  203. Peptide_list.append(Peptide)
  204.  
  205. if len(Peptide) >= 6: # Only appends peptide if longer than 6 AA
  206. Peptide_list.append(Peptide)
  207.  
  208. if Peptide not in ref_set:
  209. ID_list.append(row[1][0])
  210. Pep_Count += 1
  211. else:
  212. Non_Uniques_ID.append(row[1][0])
  213. Non_Uniques.append(Peptide)
  214. ID_list.append(row[1][0] + ' (Not unique)')
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!