def __init__(self, model_file, bl_scaler=1.0, alphabet=('A', 'T','G','C')):
self.model_file = model_file
self.alphabet = alphabet
self.epsilon = 10.0**-10 # A small value.
self.model = self.read_model(model_file)
self.bl_scaler = bl_scaler
u.check_cmd('R')
def __init__(self,
model_file,
bl_scaler=1.0,
alphabet=('A', 'T', 'G', 'C')):
self.model_file = model_file
self.alphabet = alphabet
self.epsilon = 10.0**-10 # A small value.
self.model = self.read_model(model_file)
self.bl_scaler = bl_scaler
u.check_cmd('R')
def __init__(self, run_file, read_length, insert_size, log, rts):
self.fq_tmp = 'tmp'
self.log = log
self.run_file = run_file
self.read_length = read_length
self.insert_size = insert_size
self.isize = insert_size - 2 * read_length
self.sim_cmd = self._build_sim_cmd()
self.rts = rts
u.check_cmd('simLibrary')
u.check_cmd('simNGS')
def __init__(self, run_file, read_length, insert_size, log, rts):
self.fq_tmp = 'tmp'
self.log = log
self.run_file = run_file
self.read_length= read_length
self.insert_size= insert_size
self.isize = insert_size - 2 * read_length
self.sim_cmd = self._build_sim_cmd()
self.rts = rts
u.check_cmd('simLibrary')
u.check_cmd('simNGS')
def __init__(self, fqs, kmer_length, min_ctgl, ins_len, max_div, rts, log, clean=False, asm_dir="assembly"):
self.log = log
self.rts = rts
self.fqs = fqs
self.kmer_length= kmer_length
self.min_ctgl = min_ctgl
self.ins_len = ins_len
self.max_div = max_div
self.clean = clean
self.asm_rts = self.rts.subdir(asm_dir)
self.asm_dir = self.asm_rts.base
u.check_cmd('velveth')
u.check_cmd('velvetg')
def plot(self, plotdir, partition, annotations, reco_info=None, cpath=None, no_mds_plots=False):
if self.args.only_csv_plots:
print ' --only-csv-plots not implemented for partition plots, so returning without plotting'
return
if not utils.check_cmd('R', options=['--slave', '--version'], return_bool=True):
no_mds_plots = True
print ' note: R does not seem to be installed, so skipping mds partition plots'
print ' plotting partitions'
sys.stdout.flush()
start = time.time()
fnames = []
self.remove_failed_clusters(partition, annotations)
sorted_clusters = sorted(partition, key=lambda c: len(c), reverse=True)
fnames += self.make_shm_vs_cluster_size_plots(sorted_clusters, annotations, plotdir)
if not no_mds_plots:
fnames += self.make_mds_plots(sorted_clusters, annotations, plotdir, reco_info=reco_info, run_in_parallel=True) #, color_rule='wtf')
# fnames += self.make_laplacian_spectra_plots(sorted_clusters, annotations, plotdir, cpath=cpath)
# fnames += self.make_sfs_plots(sorted_clusters, annotations, plotdir)
csfns = self.make_cluster_size_distribution(plotdir, partition)
fnames[0] += csfns[0]
if not self.args.only_csv_plots:
self.plotting.make_html(plotdir, fnames=fnames, new_table_each_row=True, htmlfname=plotdir + '/overview.html', extra_links=[(subd, '%s/%s.html' % (plotdir, subd)) for subd in ['shm-vs-size', 'mds', 'laplacian-spectra']]) # , 'sfs
print ' partition plotting time: %.1f sec' % (time.time()-start)
def __init__(self,
fqs,
kmer_length,
min_ctgl,
ins_len,
max_div,
rts,
log,
clean=False,
asm_dir="assembly"):
self.log = log
self.rts = rts
self.fqs = fqs
self.kmer_length = kmer_length
self.min_ctgl = min_ctgl
self.ins_len = ins_len
self.max_div = max_div
self.clean = clean
self.asm_rts = self.rts.subdir(asm_dir)
self.asm_dir = self.asm_rts.base
u.check_cmd('velveth')
u.check_cmd('velvetg')
def __init__(self, log, rts):
u.check_cmd('muscle')
self.log = log
self.rts = rts.subdir('muscle')
def __init__(self, log, rts):
self.log = log
self.rts = rts
u.check_cmd('exonerate')
def __init__(self, log, rts):
self.log = log
self.rts = rts
u.check_cmd('exonerate')
def __init__(self, log, rts):
u.check_cmd('muscle')
self.log = log
self.rts = rts.subdir('muscle')