Mercurial > repos > abims-sbr > cds_search

annotate scripts/S01_find_orf_on_multiple_alignment.py @ 1:567d5b771a90 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
author lecorguille
date Thu, 13 Apr 2017 09:47:57 -0400
parents
children 0d2f72caea10
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
1 #!/usr/bin/python
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
2 ## Author: Eric Fontanillas
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
3 ## Last modification: 03/09/14 by Julie BAFFARD
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
4
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
5 ## Description: Predict potential ORF on the basis of 2 criteria + 1 optional criteria
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
6 ## CRITERIA 1 ## Longest part of the alignment of sequence without codon stop "*", tested in the 3 potential ORF
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
7 ## CRITERIA 2 ## This longest part should be > 150nc or 50aa
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
8 ## CRITERIA 3 ## [OPTIONNAL] A codon start "M" should be present in this longuest part, before the last 50 aa
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
9 ## OUTPUTs "05_CDS_aa" & "05_CDS_nuc" => NOT INCLUDE THIS CRITERIA
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
10 ## OUTPUTs "06_CDS_with_M_aa" & "06_CDS_with_M_nuc" => INCLUDE THIS CRITERIA
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
11
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
12
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
13 ###############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
14 ##### DEF 1 : Dico fasta #####
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
15 ###############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
16 def dico(fasta_file_path):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
17 F2 = open(fasta_file_path, "r")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
18 dicoco = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
19 while 1:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
20 next2 = F2.readline()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
21 if not next2:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
22 break
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
23 if next2[0] == ">":
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
24 fasta_name_query = next2[:-1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
25 Sn = string.split(fasta_name_query, "||")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
26 fasta_name_query = Sn[0]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
27 next3 = F2.readline()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
28 fasta_seq_query = next3[:-1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
29 dicoco[fasta_name_query]=fasta_seq_query
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
30 F2.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
31 return(dicoco)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
32 ############################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
33
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
34
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
35 ####################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
36 ###### DEF 2 : Create bash for genetic code ########
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
37 ####################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
38 ### KEY = codon
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
39 ### VALUE = Amino Acid
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
40
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
41 def code_universel(F1):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
42 bash_codeUniversel = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
43 while 1:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
44 next = F1.readline()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
45 if not next: break
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
46 L1 = string.split(next, " ")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
47 length1 = len(L1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
48 if length1 == 3:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
49 key = L1[0]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
50 value = L1[2][:-1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
51 bash_codeUniversel[key] = value
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
52 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
53 key = L1[0]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
54 value = L1[2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
55 bash_codeUniversel[key] = value
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
56 F1.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
57 return(bash_codeUniversel)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
58 ###########################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
59
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
60
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
61 ######################################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
62 ##### DEF 3 : Test if the sequence is a multiple of 3, and if not correct the sequence to become a multiple of 3 #####
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
63 ######################################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
64 ### WEAKNESS OF THAT APPROACH = I remove extra base(s) at the end of the sequence ==> I can lost a codon, when I test ORF (as I will decay the ORF)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
65 def multiple3(seq):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
66 leng = len(seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
67 modulo = leng%3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
68 if modulo == 0: # the results of dividing leng per 3 is an integer
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
69 new_seq = seq
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
70 elif modulo == 1: # means 1 extra nc (nucleotid) needs to be removed (the remaining of modulo indicate the part which is non-dividable per 3)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
71 new_seq = seq[:-1] # remove the last nc
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
72 elif modulo == 2: # means 2 extra nc (nucleotid) needs to be removed (the remaining of modulo indicate the part which is non-dividable per 3)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
73 new_seq = seq[:-2] # remove the 2 last nc
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
74 len1 = len(new_seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
75 return(new_seq, modulo)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
76 ##########################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
77
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
78
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
79 #############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
80 ###### DEF 4 : GET ORF ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
81 #############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
82 ##- MULTIPLE SEQUENCE BASED : Based on ALIGNMENT of several sequences
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
83 ##- CRITERIA1: Get the segment in the alignment with no codon stop
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
84
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
85
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
86 ###### DEF 4 - Part 1 - ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
87 ##############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
88 def simply_get_ORF(seq_dna, bash_codeUniversel):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
89 seq_aa = ""
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
90 i = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
91 len1 = len(seq_dna)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
92 while i < len1:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
93 base1 = seq_dna[i]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
94 base1 = string.capitalize(base1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
95 base2 = seq_dna[i+1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
96 base2 = string.capitalize(base2)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
97 base3 = seq_dna[i+2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
98 base3 = string.capitalize(base3)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
99
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
100 codon = base1+base2+base3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
101 codon = string.replace(codon, "T", "U")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
102
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
103 if codon in bash_codeUniversel.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
104 aa = bash_codeUniversel[codon]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
105 seq_aa = seq_aa + aa
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
106 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
107 seq_aa = seq_aa +"?" ### Take account for gap "-" and "N"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
108 i = i + 3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
109
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
110 return(seq_aa)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
111 ##########################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
112
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
113
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
114 ###### DEF 4 - Part 2 - ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
115 ##############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
116 def find_good_ORF_criteria_3(bash_aligned_nc_seq, bash_codeUniversel):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
117
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
118 ## 1 ## Get the list of aligned aa seq for the 3 ORF:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
119 bash_of_aligned_aa_seq_3ORF = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
120 bash_of_aligned_nuc_seq_3ORF = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
121 BEST_LONGUEST_SUBSEQUENCE_LIST_POSITION = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
122 for fasta_name in bash_aligned_nc_seq.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
123 ## 1.1. ## Get the raw sequence
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
124 sequence_nc = bash_aligned_nc_seq[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
125
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
126 ## 1.2. ## Check whether the sequence is multiple of 3, and correct it if not:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
127 new_sequence_nc, modulo = multiple3(sequence_nc) ### DEF 3 ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
128
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
129 ## 1.3. ## Get the 3 ORFs (nuc) for each sequence
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
130 seq_nuc_ORF1 = new_sequence_nc
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
131 seq_nuc_ORF2 = new_sequence_nc[1:-2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
132 seq_nuc_ORF3 = new_sequence_nc[2:-1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
133 seq_reversed=ReverseComplement2(seq_nuc_ORF1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
134 seq_nuc_ORF4=seq_reversed
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
135 seq_nuc_ORF5=seq_reversed[1:-2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
136 seq_nuc_ORF6=seq_reversed[2:-1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
137
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
138 LIST_6_ORF_nuc = [seq_nuc_ORF1, seq_nuc_ORF2, seq_nuc_ORF3,seq_nuc_ORF4,seq_nuc_ORF5,seq_nuc_ORF6]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
139 bash_of_aligned_nuc_seq_3ORF[fasta_name] = LIST_6_ORF_nuc ### For each seq of the multialignment => give the 6 ORFs (in nuc)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
140
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
141 ## 1.4. ## Get the 3 ORFs (aa) for each sequence
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
142 seq_prot_ORF1 = simply_get_ORF(seq_nuc_ORF1,bash_codeUniversel) ### DEF 4 - Part 1 - ##
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
143 seq_prot_ORF2 = simply_get_ORF(seq_nuc_ORF2,bash_codeUniversel) ### DEF 4 - Part 1 - ##
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
144 seq_prot_ORF3 = simply_get_ORF(seq_nuc_ORF3,bash_codeUniversel) ### DEF 4 - Part 1 - ##
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
145 seq_prot_ORF4 = simply_get_ORF(seq_nuc_ORF4,bash_codeUniversel) ### DEF 4 - Part 1 - ##
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
146 seq_prot_ORF5 = simply_get_ORF(seq_nuc_ORF5,bash_codeUniversel) ### DEF 4 - Part 1 - ##
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
147 seq_prot_ORF6 = simply_get_ORF(seq_nuc_ORF6,bash_codeUniversel) ### DEF 4 - Part 1 - ##
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
148
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
149 LIST_6_ORF_aa = [seq_prot_ORF1, seq_prot_ORF2, seq_prot_ORF3,seq_prot_ORF4,seq_prot_ORF5,seq_prot_ORF6]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
150 bash_of_aligned_aa_seq_3ORF[fasta_name] = LIST_6_ORF_aa ### For each seq of the multialignment => give the 6 ORFs (in aa)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
151
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
152 ## 2 ## Test for the best ORF (Get the longuest segment in the alignment with no codon stop ... for each ORF ... the longuest should give the ORF)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
153 BEST_MAX = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
154 for i in [0,1,2,3,4,5]: ### Test the 6 ORFs
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
155 ORF_Aligned_aa = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
156 ORF_Aligned_nuc = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
157
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
158
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
159 ## 2.1 ## Get the alignment of sequence for a given ORF
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
160 ## Compare the 1rst ORF between all sequence => list them in ORF_Aligned_aa // them do the same for the second ORF, and them the 3rd
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
161 for fasta_name in bash_of_aligned_aa_seq_3ORF.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
162 ORFsequence = bash_of_aligned_aa_seq_3ORF[fasta_name][i]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
163 aa_length = len(ORFsequence)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
164 ORF_Aligned_aa.append(ORFsequence) ### List of all sequences in the ORF nb "i" =
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
165
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
166 n = i+1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
167
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
168 for fasta_name in bash_of_aligned_nuc_seq_3ORF.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
169 ORFsequence = bash_of_aligned_nuc_seq_3ORF[fasta_name][i]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
170 nuc_length = len(ORFsequence)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
171 ORF_Aligned_nuc.append(ORFsequence) ### List of all sequences in the ORF nb "i" =
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
172
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
173 ## 2.2 ## Get the list of sublist of positions whithout codon stop in the alignment
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
174 ## For each ORF, now we have the list of sequences available (i.e. THE ALIGNMENT IN A GIVEN ORF)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
175 ## Next step is to get the longuest subsequence whithout stop
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
176 ## We will explore the presence of stop "*" in each column of the alignment, and get the positions of the segments between the positions with "*"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
177 MAX_LENGTH = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
178 LONGUEST_SEGMENT_UNSTOPPED = ""
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
179 j = 0 # Start from first position in alignment
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
180 List_of_List_subsequences = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
181 List_positions_subsequence = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
182 while j < aa_length:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
183 column = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
184 for seq in ORF_Aligned_aa:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
185 column.append(seq[j])
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
186 j = j+1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
187 if "*" in column:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
188 List_of_List_subsequences.append(List_positions_subsequence) ## Add previous list of positions
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
189 List_positions_subsequence = [] ## Re-initialyse list of positions
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
190 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
191 List_positions_subsequence.append(j)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
192
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
193 ## 2.3 ## Among all the sublists (separated by column with codon stop "*"), get the longuest one (BETTER SEGMENT for a given ORF)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
194 LONGUEST_SUBSEQUENCE_LIST_POSITION = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
195 MAX=0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
196 for sublist in List_of_List_subsequences:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
197 if len(sublist) > MAX and len(sublist) > MINIMAL_CDS_LENGTH:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
198 MAX = len(sublist)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
199 LONGUEST_SUBSEQUENCE_LIST_POSITION = sublist
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
200
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
201 ## 2.4. ## Test if the longuest subsequence start exactly at the beginning of the original sequence (i.e. means the ORF maybe truncated)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
202 if LONGUEST_SUBSEQUENCE_LIST_POSITION != []:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
203 if LONGUEST_SUBSEQUENCE_LIST_POSITION[0] == 0:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
204 CDS_maybe_truncated = 1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
205 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
206 CDS_maybe_truncated = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
207 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
208 CDS_maybe_truncated = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
209
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
210
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
211 ## 2.5 ## Test if this BETTER SEGMENT for a given ORF, is the better than the one for the other ORF (GET THE BEST ORF)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
212 ## Test whether it is the better ORF
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
213 if MAX > BEST_MAX:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
214 BEST_MAX = MAX
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
215 BEST_ORF = i+1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
216 BEST_LONGUEST_SUBSEQUENCE_LIST_POSITION = LONGUEST_SUBSEQUENCE_LIST_POSITION
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
217
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
218
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
219 ## 3 ## ONCE we have this better segment (BEST CODING SEGMENT)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
220 ## ==> GET THE STARTING and ENDING POSITIONS (in aa position and in nuc position)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
221 ## And get the INDEX of the best ORF [0, 1, or 2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
222 if BEST_LONGUEST_SUBSEQUENCE_LIST_POSITION != []:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
223 pos_MIN_aa = BEST_LONGUEST_SUBSEQUENCE_LIST_POSITION[0]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
224 pos_MIN_aa = pos_MIN_aa - 1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
225 pos_MAX_aa = BEST_LONGUEST_SUBSEQUENCE_LIST_POSITION[-1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
226
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
227
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
228 BESTORF_bash_of_aligned_aa_seq = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
229 BESTORF_bash_of_aligned_aa_seq_CODING = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
230 for fasta_name in bash_of_aligned_aa_seq_3ORF.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
231 index_BEST_ORF = BEST_ORF-1 ### cause list going from 0 to 2 in LIST_3_ORF, while the ORF nb is indexed from 1 to 3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
232 seq = bash_of_aligned_aa_seq_3ORF[fasta_name][index_BEST_ORF]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
233 seq_coding = seq[pos_MIN_aa:pos_MAX_aa]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
234 BESTORF_bash_of_aligned_aa_seq[fasta_name] = seq
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
235 BESTORF_bash_of_aligned_aa_seq_CODING[fasta_name] = seq_coding
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
236
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
237 ## 4 ## Get the corresponding position (START/END of BEST CODING SEGMENT) for nucleotides alignment
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
238 pos_MIN_nuc = pos_MIN_aa * 3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
239 pos_MAX_nuc = pos_MAX_aa * 3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
240
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
241 BESTORF_bash_aligned_nc_seq = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
242 BESTORF_bash_aligned_nc_seq_CODING = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
243 for fasta_name in bash_aligned_nc_seq.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
244 seq = bash_of_aligned_nuc_seq_3ORF[fasta_name][index_BEST_ORF]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
245 seq_coding = seq[pos_MIN_nuc:pos_MAX_nuc]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
246 BESTORF_bash_aligned_nc_seq[fasta_name] = seq
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
247 BESTORF_bash_aligned_nc_seq_CODING[fasta_name] = seq_coding
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
248
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
249 else: ### no CDS found ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
250 BESTORF_bash_aligned_nc_seq = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
251 BESTORF_bash_aligned_nc_seq_CODING = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
252 BESTORF_bash_of_aligned_aa_seq = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
253 BESTORF_bash_of_aligned_aa_seq_CODING ={}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
254
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
255
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
256
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
257 ### Check whether their is a "M" or not, and if at least 1 "M" is present, that it is not in the last 50 aa
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
258 ###########################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
259
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
260 BESTORF_bash_of_aligned_aa_seq_CDS_with_M = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
261 BESTORF_bash_of_aligned_nuc_seq_CDS_with_M = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
262
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
263 Ortho = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
264 for fasta_name in BESTORF_bash_of_aligned_aa_seq_CODING.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
265 seq_aa = BESTORF_bash_of_aligned_aa_seq_CODING[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
266 Ortho = detect_Methionine(seq_aa, Ortho) ### DEF6 ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
267
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
268 ## CASE 1: A "M" is present and correctly localized (not in last 50 aa)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
269 if Ortho == 1:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
270 BESTORF_bash_of_aligned_aa_seq_CDS_with_M = BESTORF_bash_of_aligned_aa_seq_CODING
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
271 BESTORF_bash_of_aligned_nuc_seq_CDS_with_M = BESTORF_bash_aligned_nc_seq_CODING
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
272
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
273 ## CASE 2: in case the CDS is truncated, so the "M" is maybe missing:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
274 if Ortho == 0 and CDS_maybe_truncated == 1:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
275 BESTORF_bash_of_aligned_aa_seq_CDS_with_M = BESTORF_bash_of_aligned_aa_seq_CODING
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
276 BESTORF_bash_of_aligned_nuc_seq_CDS_with_M = BESTORF_bash_aligned_nc_seq_CODING
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
277
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
278 ## CASE 3: CDS not truncated AND no "M" found in good position (i.e. before the last 50 aa):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
279 ## => the 2 bash "CDS_with_M" are left empty ("{}")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
280
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
281 return(BESTORF_bash_aligned_nc_seq, BESTORF_bash_aligned_nc_seq_CODING, BESTORF_bash_of_aligned_nuc_seq_CDS_with_M, BESTORF_bash_of_aligned_aa_seq, BESTORF_bash_of_aligned_aa_seq_CODING, BESTORF_bash_of_aligned_aa_seq_CDS_with_M)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
282 ##########################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
283
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
284
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
285 ##################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
286 ###### DEF 5 : Detect all indices corresponding to all occurance of a substring in a string ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
287 ##################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
288 def allindices(string, sub):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
289 listindex=[]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
290 offset=0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
291 i = string.find(sub, offset)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
292 while i >= 0:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
293 listindex.append(i)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
294 i = string.find(sub, i + 1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
295 return listindex
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
296 ######################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
297
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
298
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
299 ############################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
300 ###### DEF 6 : Detect if methionin in the aa sequence ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
301 ############################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
302 def detect_Methionine(seq_aa, Ortho):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
303
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
304 ln = len(seq_aa)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
305 nbre = sys.argv[2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
306 CUTOFF_Last_50aa = ln - MINIMAL_CDS_LENGTH
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
307 #Ortho = 0 ## means orthologs not found
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
308
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
309 ## Find all indices of occurances of "M" in a string of aa
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
310 list_indices = allindices(seq_aa, "M") ### DEF5 ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
311
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
312 ## If some "M" are present, find whether the first "M" found is not in the 50 last aa (indice < CUTOFF_Last_50aa) ==> in this case: maybenot a CDS
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
313 if list_indices != []:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
314 first_M = list_indices[0]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
315 if first_M < CUTOFF_Last_50aa:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
316 Ortho = 1 ## means orthologs found
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
317
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
318 return(Ortho)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
319 ###################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
320
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
321
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
322
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
323
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
324
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
325
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
326 ############################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
327 ###### DEF 7 : Reverse complement DNA sequence ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
328 ###### Reference: http://crazyhottommy.blogspot.fr/2013/10/python-code-for-getting-reverse.html
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
329 ############################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
330
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
331
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
332 def ReverseComplement2(seq):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
333 # too lazy to construct the dictionary manually, use a dict comprehension
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
334 seq1 = 'ATCG-TAGC-atcg-tagc-'
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
335 seq_dict = { seq1[i]:seq1[i+5] for i in range(20) if i < 5 or 10<=i<15 }
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
336 return "".join([seq_dict[base] for base in reversed(seq)])
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
337
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
338 ###################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
339
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
340
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
341
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
342 #######################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
343 ##### RUN RUN RUN #####
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
344 #######################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
345 import string, os, time, re, zipfile, sys
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
346
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
347 MINIMAL_CDS_LENGTH = int(sys.argv[3]) ## in aa number
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
348
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
349 ## INPUT / OUTPUT
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
350 list_file = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
351 zfile = zipfile.ZipFile(sys.argv[1])
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
352 for name in zfile.namelist() :
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
353 list_file.append(name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
354 zfile.extract(name, "./")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
355
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
356 F2 = open(sys.argv[2], 'r')
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
357
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
358 os.mkdir("04_BEST_ORF_nuc")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
359 Path_OUT1 = "04_BEST_ORF_nuc"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
360 os.mkdir("04_BEST_ORF_aa")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
361 Path_OUT2 = "04_BEST_ORF_aa"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
362
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
363 os.mkdir("05_CDS_nuc")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
364 Path_OUT3 = "05_CDS_nuc"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
365 os.mkdir("05_CDS_aa")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
366 Path_OUT4 = "05_CDS_aa"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
367
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
368 os.mkdir("06_CDS_with_M_nuc")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
369 Path_OUT5 = "06_CDS_with_M_nuc"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
370 os.mkdir("06_CDS_with_M_aa")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
371 Path_OUT6 = "06_CDS_with_M_aa"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
372
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
373
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
374 ### Get Universal Code
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
375 bash_codeUniversel = code_universel(F2) ### DEF2 ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
376 F2.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
377
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
378 ### Get the Bash corresponding to an alignment file in fasta format
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
379 count_file_processed = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
380 count_file_with_CDS = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
381 count_file_without_CDS = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
382 count_file_with_CDS_plus_M = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
383
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
384 for file in list_file:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
385 count_file_processed = count_file_processed + 1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
386 fasta_file_path = "./%s" %file
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
387 bash_fasta = dico(fasta_file_path) ### DEF 1 ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
388 BESTORF_nuc, BESTORF_nuc_CODING, BESTORF_nuc_CDS_with_M, BESTORF_aa, BESTORF_aa_CODING, BESTORF_aa_CDS_with_M = find_good_ORF_criteria_3(bash_fasta, bash_codeUniversel) ### DEF 4 - PART 2 - ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
389
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
390 ## a ## OUTPUT BESTORF_nuc
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
391 if BESTORF_nuc != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
392 count_file_with_CDS = count_file_with_CDS +1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
393 OUT1 = open("%s/%s" %(Path_OUT1,file), "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
394 for fasta_name in BESTORF_nuc.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
395 seq = BESTORF_nuc[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
396 OUT1.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
397 OUT1.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
398 OUT1.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
399 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
400 count_file_without_CDS = count_file_without_CDS + 1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
401
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
402
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
403 ## b ## OUTPUT BESTORF_nuc_CODING ===> THE MOST INTERESTING!!!
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
404 if BESTORF_aa != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
405 OUT2 = open("%s/%s" %(Path_OUT2,file), "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
406 for fasta_name in BESTORF_aa.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
407 seq = BESTORF_aa[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
408 OUT2.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
409 OUT2.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
410 OUT2.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
411
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
412 ## c ## OUTPUT BESTORF_aa
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
413 if BESTORF_nuc_CODING != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
414 OUT3 = open("%s/%s" %(Path_OUT3,file), "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
415 for fasta_name in BESTORF_nuc_CODING.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
416 seq = BESTORF_nuc_CODING[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
417 OUT3.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
418 OUT3.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
419 OUT3.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
420
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
421 ## d ## OUTPUT BESTORF_aa_CODING
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
422 if BESTORF_aa_CODING != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
423 OUT4 = open("%s/%s" %(Path_OUT4,file), "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
424 for fasta_name in BESTORF_aa_CODING.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
425 seq = BESTORF_aa_CODING[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
426 OUT4.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
427 OUT4.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
428 OUT4.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
429
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
430 ## e ## OUTPUT BESTORF_nuc_CDS_with_M
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
431 if BESTORF_nuc_CDS_with_M != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
432 count_file_with_CDS_plus_M = count_file_with_CDS_plus_M + 1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
433 OUT5 = open("%s/%s" %(Path_OUT5,file), "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
434 for fasta_name in BESTORF_nuc_CDS_with_M.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
435 seq = BESTORF_nuc_CDS_with_M[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
436 OUT5.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
437 OUT5.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
438 OUT5.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
439
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
440 ## f ## OUTPUT BESTORF_aa_CDS_with_M
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
441 if BESTORF_aa_CDS_with_M != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
442 OUT6 = open("%s/%s" %(Path_OUT6,file), "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
443 for fasta_name in BESTORF_aa_CDS_with_M.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
444 seq = BESTORF_aa_CDS_with_M[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
445 OUT6.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
446 OUT6.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
447 OUT6.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
448
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
449 os.system("rm -rf %s" %file)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
450
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
451 ## Print
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
452 print "*************** CDS detection ***************"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
453 print "\nFiles processed: %d" %count_file_processed
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
454 print "\tFiles with CDS: %d" %count_file_with_CDS
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
455 print "\t\tFiles with CDS plus M (codon start): %d" %count_file_with_CDS_plus_M
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
456 print "\tFiles without CDS: %d \n" %count_file_without_CDS
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
457 print ""
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
458
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
459 ## Zipfile
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
460 f_bestORF_nuc = zipfile.ZipFile("ORF_Search_bestORF_nuc.zip", "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
461 f_bestORF_aa = zipfile.ZipFile("ORF_Search_bestORF_aa.zip", "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
462 f_CDS_nuc = zipfile.ZipFile("ORF_Search_CDS_nuc.zip", "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
463 f_CDS_aa = zipfile.ZipFile("ORF_Search_CDS_aa.zip", "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
464 f_CDSM_nuc = zipfile.ZipFile("ORF_Search_CDSM_nuc.zip", "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
465 f_CDSM_aa = zipfile.ZipFile("ORF_Search_CDSM_aa.zip", "w")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
466
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
467 os.chdir("%s" %Path_OUT1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
468 folder = os.listdir("./")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
469 for i in folder :
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
470 f_bestORF_nuc.write("./%s" %i)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
471
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
472 os.chdir("../%s" %Path_OUT2)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
473 folder = os.listdir("./")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
474 for i in folder :
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
475 f_bestORF_aa.write("./%s" %i)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
476
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
477 os.chdir("../%s" %Path_OUT3)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
478 folder = os.listdir("./")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
479 for i in folder :
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
480 f_CDS_nuc.write("./%s" %i)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
481
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
482 os.chdir("../%s" %Path_OUT4)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
483 folder = os.listdir("./")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
484 for i in folder :
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
485 f_CDS_aa.write("./%s" %i)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
486
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
487 os.chdir("../%s" %Path_OUT5)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
488 folder = os.listdir("./")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
489 for i in folder :
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
490 f_CDSM_nuc.write("./%s" %i)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
491
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
492 os.chdir("../%s" %Path_OUT6)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
493 folder = os.listdir("./")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
494 for i in folder :
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
495 f_CDSM_aa.write("./%s" %i)