def __init__(self, prot_sequence, monoisotopic=False):
if prot_sequence.islower():
self.sequence = Seq(prot_sequence.upper(), IUPAC.protein)
else:
self.sequence = Seq(prot_sequence, IUPAC.protein)
self.amino_acids_content = None
self.amino_acids_percent = None
self.length = len(self.sequence)
self.monoisotopic = monoisotopic
def posterior(seq, emission_mat, transition_mat, k_counter, seeds, rec_num,
counter):
"""
calculates the most probable state for every base in seq
:param seq: sequence
:param emission_mat
:param transition_mat
:param k_counter: num of states
:return: seq of states, aligned to original seq
"""
N = len(seq)
forward_table = forward(seq, emission_mat, transition_mat, k_counter)
backward_table = backward(seq, emission_mat, transition_mat, k_counter)
posterior_table = forward_table + backward_table
# motif_order = EMPTY_STRING
seq_obj = Seq(N - 2, rec_num)
last_motif_0 = FIRST_MOTIF_STATE + len(seeds[0]) - 1
first_motif_1 = last_motif_0 + 1
last_motif_1 = first_motif_1 + len(seeds[1]) - 1
first_motif_2 = last_motif_1 + 1
last_motif_2 = first_motif_2 + len(seeds[2]) - 1
# decide states
for j in range(1, N - 1):
curr_k = int(np.argmax(posterior_table[:, j]))
if FIRST_MOTIF_STATE <= curr_k <= last_motif_0:
# motif_order += MOTIF_0
seq_obj.add_motif_base(0, (seq[j], curr_k - FIRST_MOTIF_STATE),
j - 1)
elif first_motif_1 <= curr_k <= last_motif_1:
# motif_order += MOTIF_1
seq_obj.add_motif_base(1, (seq[j], curr_k - first_motif_1), j - 1)
elif first_motif_2 <= curr_k <= last_motif_2:
# motif_order += MOTIF_2
seq_obj.add_motif_base(2, (seq[j], curr_k - first_motif_2), j - 1)
elif curr_k == 2:
# motif_order += TELO_BACKGROUND
seq_obj.add_telo_background(seq[j], j - 1)
elif curr_k == 1:
# motif_order += 'P'
seq_obj.add_pre_telo((seq[j], curr_k))
else:
# motif_order += BACKGROUND
seq_obj.add_normal_dna_base((seq[j], curr_k))
# print_results(seq[1:-1], motif_order)
seq_obj.print_statistics(doc=None, counter=counter)
seq_obj.save_to_file()
return
def ungap(seq):
"""given a sequence with gap encoding, return the ungapped sequence"""
#TODO - Fix this? It currently assumes the outmost AlphabetEncoder
#is for the gap. Consider HasStopCodon(Gapped(Protein())) as a test case.
gap = seq.gap_char
letters = []
for c in seq.data:
if c != gap:
letters.append(c)
return Seq.Seq("".join(letters), seq.alphabet.alphabet)
def reduce_sequence(seq, reduction_table, new_alphabet=None):
""" given an amino-acid sequence, return it in reduced alphabet form based
on the letter-translation table passed. Some "standard" tables are in
Alphabet.Reduced.
seq: a Seq.Seq type sequence
reduction_table: a dictionary whose keys are the "from" alphabet, and values
are the "to" alphabet"""
if new_alphabet is None:
new_alphabet = Alphabet.single_letter_alphabet
new_alphabet.letters = ''
for letter in reduction_table:
new_alphabet.letters += letter
new_alphabet.size = len(new_alphabet.letters)
new_seq = Seq.Seq('', new_alphabet)
for letter in seq:
new_seq += reduction_table[letter]
return new_seq
#!/usr/bin/env python
#-*- coding:utf-8 -*-
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from Seq import *
PDPI = 0.0
DPI = 0.0
DPMM = 0.0
symbols = dict()
icons = dict()
shortcuts = dict()
defaultTextStyles = []
docName = QString()
dataPath = QString()
mscoreGlobalShare = QString("share\\")
mscore = 0
gscore = 0
seq = Seq()
recentScores = QStringList()
revision = QString()
instrumentGroups = list()
articulation = list()
actions = dict()
import os
class RfamSearch():
def __init__(self):
pass
def cmscan(self, seq):
print seq
# make tmp file
f = open('/tmp/ss.fa', 'w')
f.write('>test\n')
f.write(seq.seq)
f.close()
old_pwd = os.getcwd()
os.chdir('/home/magnus/work/rfamdb')
cmd = 'cmscan -E 1 Rfam.cm /tmp/ss.fa > /tmp/cmscan.txt'
subprocess.Popen(cmd, shell=True)
self.output = open('/tmp/cmscan.txt').read()
os.chdir(old_pwd)
return self.output
#main
if __name__ == '__main__':
import Seq
seq = Seq.Seq("GGCGCGGCACCGUCCGCGGAACAAACGG")
rs = RfamSearch()
rs.cmscan(seq)
