Mercurial > repos > abims-sbr > cds_search

annotate scripts/S01_find_orf_on_multiple_alignment.py @ 7:35e39b4128ba 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 b7a3030ea134b5dfad89b1a869db659d72d1145c
author abims-sbr
date Wed, 28 Feb 2018 10:38:40 -0500
parents ff98ed7849fa
children 716a45028e55
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 ###### DEF 2 : Create bash for genetic code ########
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
14 ####################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
15 ### KEY = codon
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
16 ### VALUE = Amino Acid
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
17
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
18 def code_universel(F1):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
19 bash_codeUniversel = {}
7
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
20 with open(F1, "r") as file:
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
21 for line in file.readlines():
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
22 L1 = string.split(line, " ")
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
23 length1 = len(L1)
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
24 if length1 == 3:
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
25 key = L1[0]
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
26 value = L1[2][:-1]
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
27 bash_codeUniversel[key] = value
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
28 else:
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
29 key = L1[0]
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
30 value = L1[2]
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
31 bash_codeUniversel[key] = value
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
32 return(bash_codeUniversel)
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 ######################################################################################################################
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
37 ##### DEF 3 : Test if the sequence is a multiple of 3, and if not correct the sequence to become a multiple of 3 #####
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
38 ######################################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
39 ### 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
40 def multiple3(seq):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
41 leng = len(seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
42 modulo = leng%3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
43 if modulo == 0: # the results of dividing leng per 3 is an integer
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
44 new_seq = seq
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
45 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
46 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
47 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
48 new_seq = seq[:-2] # remove the 2 last nc
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
49 len1 = len(new_seq)
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
50 return(new_seq, modulo)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
51 ##########################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
52
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
53
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
54 #############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
55 ###### DEF 4 : GET ORF ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
56 #############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
57 ##- 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
58 ##- 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
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 ###### DEF 4 - Part 1 - ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
62 ##############################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
63 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
64 seq_aa = ""
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
65 i = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
66 len1 = len(seq_dna)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
67 while i < len1:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
68 base1 = seq_dna[i]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
69 base1 = string.capitalize(base1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
70 base2 = seq_dna[i+1]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
71 base2 = string.capitalize(base2)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
72 base3 = seq_dna[i+2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
73 base3 = string.capitalize(base3)
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
74
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
75 codon = base1+base2+base3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
76 codon = string.replace(codon, "T", "U")
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 if codon in bash_codeUniversel.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
79 aa = bash_codeUniversel[codon]
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
80 seq_aa = seq_aa + aa
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
81 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
82 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
83 i = i + 3
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 return(seq_aa)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
86 ##########################################################
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
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
89 ###### DEF 4 - Part 2 - ######
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
90 ##############################
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
91 def find_good_ORF_criteria_3(bash_aligned_nc_seq, bash_codeUniversel):
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
92
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
93 ## 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
94 bash_of_aligned_aa_seq_3ORF = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
95 bash_of_aligned_nuc_seq_3ORF = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
96 BEST_LONGUEST_SUBSEQUENCE_LIST_POSITION = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
97 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
98 ## 1.1. ## Get the raw sequence
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
99 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
100
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
101 ## 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
102 new_sequence_nc, modulo = multiple3(sequence_nc) ### DEF 3 ###
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
103
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
104 ## 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
105 seq_nuc_ORF1 = new_sequence_nc
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
106 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
107 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
108 seq_reversed=ReverseComplement2(seq_nuc_ORF1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
109 seq_nuc_ORF4=seq_reversed
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
110 seq_nuc_ORF5=seq_reversed[1:-2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
111 seq_nuc_ORF6=seq_reversed[2:-1]
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
112
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
113 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
114 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
115
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
116 ## 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
117 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
118 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
119 seq_prot_ORF3 = simply_get_ORF(seq_nuc_ORF3,bash_codeUniversel) ### DEF 4 - Part 1 - ##
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
120 seq_prot_ORF4 = simply_get_ORF(seq_nuc_ORF4,bash_codeUniversel) ### DEF 4 - Part 1 - ##
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
121 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
122 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
123
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
124 LIST_6_ORF_aa = [seq_prot_ORF1, seq_prot_ORF2, seq_prot_ORF3,seq_prot_ORF4,seq_prot_ORF5,seq_prot_ORF6]
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
125 bash_of_aligned_aa_seq_3ORF[fasta_name] = LIST_6_ORF_aa ### For each seq of the multialignment => give the 6 ORFs (in aa)
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
126
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
127 ## 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
128 BEST_MAX = 0
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
129 for i in [0,1,2,3,4,5]: ### Test the 6 ORFs
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
130 ORF_Aligned_aa = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
131 ORF_Aligned_nuc = []
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
132
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
133
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
134 ## 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
135 ## 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
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
136 for fasta_name in bash_of_aligned_aa_seq_3ORF.keys():
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
137 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
138 aa_length = len(ORFsequence)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
139 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
140
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
141 n = i+1
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
142
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
143 for fasta_name in bash_of_aligned_nuc_seq_3ORF.keys():
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
144 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
145 nuc_length = len(ORFsequence)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
146 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
147
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
148 ## 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
149 ## 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
150 ## 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
151 ## 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
152 MAX_LENGTH = 0
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
153 LONGUEST_SEGMENT_UNSTOPPED = ""
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
154 j = 0 # Start from first position in alignment
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
155 List_of_List_subsequences = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
156 List_positions_subsequence = []
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
157 while j < aa_length:
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
158 column = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
159 for seq in ORF_Aligned_aa:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
160 column.append(seq[j])
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
161 j = j+1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
162 if "*" in column:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
163 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
164 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
165 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
166 List_positions_subsequence.append(j)
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
167
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
168 ## 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
169 LONGUEST_SUBSEQUENCE_LIST_POSITION = []
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
170 MAX=0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
171 for sublist in List_of_List_subsequences:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
172 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
173 MAX = len(sublist)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
174 LONGUEST_SUBSEQUENCE_LIST_POSITION = sublist
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
175
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
176 ## 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
177 if LONGUEST_SUBSEQUENCE_LIST_POSITION != []:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
178 if LONGUEST_SUBSEQUENCE_LIST_POSITION[0] == 0:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
179 CDS_maybe_truncated = 1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
180 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
181 CDS_maybe_truncated = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
182 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
183 CDS_maybe_truncated = 0
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
184
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
185
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
186 ## 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
187 ## Test whether it is the better ORF
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
188 if MAX > BEST_MAX:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
189 BEST_MAX = MAX
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
190 BEST_ORF = i+1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
191 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
192
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
193
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
194 ## 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
195 ## ==> 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
196 ## 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
197 if BEST_LONGUEST_SUBSEQUENCE_LIST_POSITION != []:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
198 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
199 pos_MIN_aa = pos_MIN_aa - 1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
200 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
201
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
202
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
203 BESTORF_bash_of_aligned_aa_seq = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
204 BESTORF_bash_of_aligned_aa_seq_CODING = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
205 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
206 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
207 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
208 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
209 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
210 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
211
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
212 ## 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
213 pos_MIN_nuc = pos_MIN_aa * 3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
214 pos_MAX_nuc = pos_MAX_aa * 3
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
215
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
216 BESTORF_bash_aligned_nc_seq = {}
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
217 BESTORF_bash_aligned_nc_seq_CODING = {}
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
218 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
219 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
220 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
221 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
222 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
223
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
224 else: ### no CDS found ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
225 BESTORF_bash_aligned_nc_seq = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
226 BESTORF_bash_aligned_nc_seq_CODING = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
227 BESTORF_bash_of_aligned_aa_seq = {}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
228 BESTORF_bash_of_aligned_aa_seq_CODING ={}
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
229
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
230
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
231
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
232 ### 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
233 ###########################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
234
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
235 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
236 BESTORF_bash_of_aligned_nuc_seq_CDS_with_M = {}
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
237
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
238 Ortho = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
239 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
240 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
241 Ortho = detect_Methionine(seq_aa, Ortho) ### DEF6 ###
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
242
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
243 ## 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
244 if Ortho == 1:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
245 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
246 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
247
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
248 ## CASE 2: in case the CDS is truncated, so the "M" is maybe missing:
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
249 if Ortho == 0 and CDS_maybe_truncated == 1:
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
250 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
251 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
252
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
253 ## 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
254 ## => the 2 bash "CDS_with_M" are left empty ("{}")
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
255
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
256 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)
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
257 ##########################################################
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 ##################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
261 ###### 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
262 ##################################################################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
263 def allindices(string, sub):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
264 listindex=[]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
265 offset=0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
266 i = string.find(sub, offset)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
267 while i >= 0:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
268 listindex.append(i)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
269 i = string.find(sub, i + 1)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
270 return listindex
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
271 ######################################################
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
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
274 ############################################################
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
275 ###### DEF 6 : Detect if methionin in the aa sequence ######
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
276 ############################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
277 def detect_Methionine(seq_aa, Ortho):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
278
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
279 ln = len(seq_aa)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
280 nbre = sys.argv[2]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
281 CUTOFF_Last_50aa = ln - MINIMAL_CDS_LENGTH
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
282 #Ortho = 0 ## means orthologs not found
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
283
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
284 ## 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
285 list_indices = allindices(seq_aa, "M") ### DEF5 ###
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
286
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
287 ## 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
288 if list_indices != []:
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
289 first_M = list_indices[0]
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
290 if first_M < CUTOFF_Last_50aa:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
291 Ortho = 1 ## means orthologs found
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
292
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
293 return(Ortho)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
294 ###################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
295
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
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
301 ############################################################
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
302 ###### DEF 7 : Reverse complement DNA sequence ######
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
303 ###### 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
304 ############################################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
305
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
306
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
307 def ReverseComplement2(seq):
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
308 # 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
309 seq1 = 'ATCG-TAGC-atcg-tagc-'
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
310 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
311 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
312
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
313 ###################################
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
314
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
315
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
316
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 ##### RUN RUN RUN #####
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 import string, os, time, re, zipfile, sys
3
ff98ed7849fa planemo upload for repository https://github.com/abims-sbr/adaptsearch commit cf1b9c905931ca2ca25faa4844d45c908756472f
abims-sbr
parents: 2
diff changeset
321 from dico import dico
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
322
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
323 infiles = sys.argv[1]
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
324 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
325
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
326 ## INPUT / OUTPUT
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
327 list_file = str.split(infiles,",")
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
328
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
329 ### Get Universal Code
7
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
330 bash_codeUniversel = code_universel(sys.argv[2]) ### DEF2 ###
1
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 os.mkdir("04_BEST_ORF_nuc")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
333 Path_OUT1 = "04_BEST_ORF_nuc"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
334 os.mkdir("04_BEST_ORF_aa")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
335 Path_OUT2 = "04_BEST_ORF_aa"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
336
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
337 os.mkdir("05_CDS_nuc")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
338 Path_OUT3 = "05_CDS_nuc"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
339 os.mkdir("05_CDS_aa")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
340 Path_OUT4 = "05_CDS_aa"
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 os.mkdir("06_CDS_with_M_nuc")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
343 Path_OUT5 = "06_CDS_with_M_nuc"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
344 os.mkdir("06_CDS_with_M_aa")
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
345 Path_OUT6 = "06_CDS_with_M_aa"
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
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
348
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
349
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
350 ### 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
351 count_file_processed = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
352 count_file_with_CDS = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
353 count_file_without_CDS = 0
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
354 count_file_with_CDS_plus_M = 0
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 for file in list_file:
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
357 count_file_processed = count_file_processed + 1
7
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
358 fasta_file_path = "./%s" %file
35e39b4128ba planemo upload for repository https://github.com/abims-sbr/adaptsearch commit b7a3030ea134b5dfad89b1a869db659d72d1145c
abims-sbr
parents: 3
diff changeset
359 bash_fasta = dico(fasta_file_path) ### DEF 1 ###
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
360 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 - ###
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
361
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
362 ## a ## OUTPUT BESTORF_nuc
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
363 if BESTORF_nuc != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
364 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
365 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
366 for fasta_name in BESTORF_nuc.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
367 seq = BESTORF_nuc[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
368 OUT1.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
369 OUT1.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
370 OUT1.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
371 else:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
372 count_file_without_CDS = count_file_without_CDS + 1
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
373
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
374
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
375 ## 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
376 if BESTORF_aa != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
377 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
378 for fasta_name in BESTORF_aa.keys():
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
379 seq = BESTORF_aa[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
380 OUT2.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
381 OUT2.write("%s\n" %seq)
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
382 OUT2.close()
1
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 ## c ## OUTPUT BESTORF_aa
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
385 if BESTORF_nuc_CODING != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
386 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
387 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
388 seq = BESTORF_nuc_CODING[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
389 OUT3.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
390 OUT3.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
391 OUT3.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
392
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
393 ## d ## OUTPUT BESTORF_aa_CODING
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
394 if BESTORF_aa_CODING != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
395 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
396 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
397 seq = BESTORF_aa_CODING[fasta_name]
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
398 OUT4.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
399 OUT4.write("%s\n" %seq)
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
400 OUT4.close()
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 ## e ## OUTPUT BESTORF_nuc_CDS_with_M
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
403 if BESTORF_nuc_CDS_with_M != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
404 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
405 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
406 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
407 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
408 OUT5.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
409 OUT5.write("%s\n" %seq)
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
410 OUT5.close()
1
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 ## f ## OUTPUT BESTORF_aa_CDS_with_M
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
413 if BESTORF_aa_CDS_with_M != {}:
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
414 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
415 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
416 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
417 OUT6.write("%s\n" %fasta_name)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
418 OUT6.write("%s\n" %seq)
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
419 OUT6.close()
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
420
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
421 os.system("rm -rf %s" %file)
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
422
2
0d2f72caea10 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 44a89d5eeb82789bfc643b33c11f391281b6374b
abims-sbr
parents: 1
diff changeset
423 ## Print
1
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
424 print "*************** CDS detection ***************"
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
425 print "\nFiles processed: %d" %count_file_processed
567d5b771a90 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit ab76075e541dd7ece1090f6b55ca508ec0fde39d
lecorguille
parents:
diff changeset
426 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
427 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
428 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
429 print ""