def sample(hyperparameters, rho, K, F):
"Sample from the model."
G = len(rho)
q_alpha = GammaDist(hyperparameters.a_alpha, hyperparameters.b_alpha)
alpha = q_alpha.sample()
q_beta = GammaDist(hyperparameters.a_beta, hyperparameters.b_beta)
beta = q_beta.sample()
q_gamma = GammaDist(hyperparameters.a_gamma, hyperparameters.b_gamma)
gamma = q_gamma.sample()
q_lambda = GammaDist(hyperparameters.a_lambda, hyperparameters.b_lambda)
lambda_ = q_lambda.sample()
q_tau = DirichletDist(hyperparameters.a_tau)
tau = q_tau.sample()
q_omega = DirichletDist(hyperparameters.a_omega)
omega = q_omega.sample()
q_pi_bar = BetaDist(numpy.ones(K), gamma * numpy.ones(K))
pi_bar = q_pi_bar.sample()
pi = numpy.empty_like(pi_bar)
for k in xrange(K-1):
pi[k] = pi_bar[k] * (1.-pi_bar[:k]).prod()
pi[-1] = 1. - pi[:-1].sum()
if pi[-1] < 0.: # adjust for numerical errors
pi[-1] = 0.
theta = numpy.random.dirichlet(alpha * pi, size=G)
phi = numpy.empty((K+1, F))
phi[0] = numpy.random.dirichlet(lambda_ * omega)
phi[1:] = numpy.random.dirichlet(beta * tau, size=K)
# sample the correct number of sites for each gene
sites = [None] * G
for g, rho_g in enumerate(rho):
v_g = [bernoulli(rho_i) for rho_i in rho_g]
z_g = [v_gi and discrete_sample(theta[g])+1 or 0 for v_gi in v_g]
x_g = [discrete_sample(phi[z_gi]) for z_gi in z_g]
sites[g] = (v_g, z_g, x_g)
result_type = namedtuple('Sample', 'alpha beta gamma lambda_ tau omega pi_bar pi theta phi sites')
return result_type(
alpha=alpha,
beta=beta,
gamma=gamma,
lambda_=lambda_,
tau=tau,
omega=omega,
pi_bar=pi_bar,
pi=pi,
theta=theta,
phi=phi,
sites=sites,
)
def convert_base(b):
if 'a' == b or 'A' == b: return 0
if 'c' == b or 'C' == b: return 1
if 'g' == b or 'G' == b: return 2
if 't' == b or 'T' == b: return 3
raise RuntimeError('Unknown base: %s' % str(b))
def convert_seq(seq):
return map(convert_base, seq)
sites_filename = os.path.join('c:\\', 'Dev', 'MyProjects', 'Vincent',
'transfac_matrix_sites.txt')
TransfacSiteSet = namedtuple('TransfacSiteSet', 'matrix name seqs')
def load_transfac_sites(sites_filename=sites_filename):
return dict((matrix, TransfacSiteSet(matrix=matrix, name=name, seqs=seqs))
for matrix, name, seqs in read_sites(open(sites_filename)))
def convert_transfac_sites(sites):
result = dict()
for matrix, site_set in sites.iteritems():
try:
converted_seqs = map(convert_seq,
site_set.seqs) # convert to feature values
if not converted_seqs: # if no sequences ignore
continue
else:
seqs.append(line)
def convert_base(b):
if 'a' == b or 'A' == b: return 0
if 'c' == b or 'C' == b: return 1
if 'g' == b or 'G' == b: return 2
if 't' == b or 'T' == b: return 3
raise RuntimeError('Unknown base: %s' % str(b))
def convert_seq(seq):
return map(convert_base, seq)
sites_filename = os.path.join('c:\\', 'Dev', 'MyProjects', 'Vincent', 'transfac_matrix_sites.txt')
TransfacSiteSet = namedtuple('TransfacSiteSet', 'matrix name seqs')
def load_transfac_sites(sites_filename=sites_filename):
return dict(
(matrix, TransfacSiteSet(matrix=matrix, name=name, seqs=seqs))
for matrix, name, seqs
in read_sites(open(sites_filename))
)
def convert_transfac_sites(sites):
result = dict()
for matrix, site_set in sites.iteritems():
try:
converted_seqs = map(convert_seq, site_set.seqs) # convert to feature values
if not converted_seqs: # if no sequences ignore
continue
Code to run MEME algorithm.
"""
import subprocess
import re
import time
import warnings
from cookbook.interval import Interval
from stempy import ensure_dir_exists, logging, os, parse_options
from cookbook.named_tuple import namedtuple
logger = logging.getLogger(__name__)
Start = namedtuple(
'Start', 'w0 nsites0 cons0 cons w nsites sig em_time niters cons_after_em')
if False:
warnings.warn('Using debug MEME')
_meme_binary = '/home/john/local/debug/bin/meme.bin'
else:
_meme_binary = '/home/john/local/bin/meme.bin'
def run_meme(fasta, options, extra_args=None):
"""
Runs MEME.
"""
# set up command line
"""
Code to analyse distances (spacings) between pairs of occurrences of TFs.
"""
import logging
logger = logging.getLogger(__name__)
from cookbook.named_tuple import namedtuple
import pyicl
import numpy
import pylab
from collections import defaultdict
from .scan import footprint
from scipy.special import gammaln
PairOccurrence = namedtuple('PairOccurrence', 'spacing seq pos strand')
Spacing = namedtuple(
'Spacing', 'primary secondary same_strand upstream distance')
def add_max_distance_option(parser):
parser.add_option(
"-d",
"--max-distance",
type=int,
default=30,
help="Only look for occurrences of motifs up to MAX_DISTANCE "
"base pairs apart",
metavar="MAX_DISTANCE"
)
#
"""
Test read sequences.
"""
#
# Trickery to find update path to import stempy from
#
from setup_environment import init_test_env, fasta_dir
init_test_env(__file__)
import stempy, os
from cookbook.named_tuple import namedtuple
Start = namedtuple('Start', 'seed num_sites score model best_w_mers')
options = stempy.get_default_options()
options.output_dir = os.path.join('output', 'test-em')
seed = 'CACTTT'
W = len(seed)
# read the sequences and build STEME object from index
fasta = os.path.join(fasta_dir(), 'em-1-test.fa')
algorithm = stempy.Algorithm(options)
algorithm._initialise(fasta)
motif_finder = algorithm.create_motif_finder()
model = algorithm.create_model_of_input(W)
model.bs.seed(seed, True)
start = Start(seed=seed, num_sites=10, score=0., model=model, best_w_mers=stempy.InstanceVec())
logger = logging.getLogger(__name__)
from . import html_copy_static
import os
import pyicl
import pylab
import numpy
import bisect
from cookbook.named_tuple import namedtuple
from collections import defaultdict
from itertools import ifilter
from cookbook.pylab_utils import pylab_context_ioff, create_format_cycler
# from cookbook.pylab_utils import simple_marker_styles
SeqInfo = namedtuple('SeqInfo', 'name length')
Occurrence = namedtuple(
'Occurrence', 'motif wmer seq pos strand Z score pvalue')
def footprint(occ):
"""Return the footprint (interval) of the occurrence.
"""
return pyicl.IntInterval(occ.pos, occ.pos + len(occ.wmer))
def parse_occurrence(line):
"""Parse one occurrence in the format outputted by steme-pwm-scan.
"""
fields = line.strip().split(',')
if 8 != len(fields):