def generate_base_weblogo(options, allsequences, output):
import weblogolib as wl
from weblogolib.colorscheme import ColorScheme, ColorGroup
from corebio import seq_io
from StringIO import StringIO
ecliptic_color_scheme = ColorScheme([
ColorGroup('A', iwork_colors.blue),
ColorGroup('C', iwork_colors.green),
ColorGroup('G', iwork_colors.yellow),
ColorGroup('UT', iwork_colors.red),
])
fastainput = StringIO(''.join('>%d\n%s\n' % s for s in enumerate(allsequences)))
rna = wl.std_alphabets['rna']
seqs = wl.read_seq_data(fastainput, alphabet=rna)
logo = wl.LogoData.from_seqs(seqs)
logooptions = wl.LogoOptions()
logooptions.unit_name = 'probability'
logooptions.color_scheme = ecliptic_color_scheme
logooptions.show_fineprint = False
logooptions.first_index = -options.flanking_window
logooptions.title = "Ecliptic"
format = wl.LogoFormat(logo, logooptions)
wl.pdf_formatter(logo, format, open(output, 'w'))
def printlogo(pwm, filename, alphabet="ACGT", mode="pdf"):
myAlphabet = {"A": 0, "C": 1, "G": 2, "T": 3}
translate = np.array([myAlphabet[i] for i in alphabet])
pwm = pwm[:, translate]
"Prints logo from nucleotides as a pdf"
import cPickle
cPickle.dump(pwm, open(filename + ".pkl", 'wb'), -1)
import weblogolib as wl # @UnresolvedImport
PWMdata = np.array(pwm)
data = wl.LogoData.from_counts(wl.std_alphabets["dna"], PWMdata)
options = wl.LogoOptions(resolution=300)
options.title = filename
options.color_scheme = wl.colorscheme.nucleotide
formatt = wl.LogoFormat(data, options)
if mode == "pdf":
fout = open(filename + ".pdf", 'wb')
fout.write(wl.pdf_formatter(data, formatt))
elif mode == "png":
fout = open(filename + ".png", 'wb')
fout.write(wl.png_formatter(data, formatt))
else:
fout = open(filename + ".{0}".format(mode), 'wb')
exec("""fout.write(wl.{0}_formatter(data, format))""".format(mode))
fout.close()
def generate_logos(motifs, foldername, filetype='png'):
options = wl.LogoOptions()
options.color_scheme = wl.std_color_schemes["chemistry"]
for i, motif in enumerate(motifs):
if motif:
my_format = wl.LogoFormat(motif.data, options)
if 'png' in filetype:
to_write = wl.png_print_formatter(motif.data, my_format)
foo = open(
os.path.join(foldername,
str(i) + '_' + str(len(motif.seqs)) + ".png"),
"wb")
foo.write(to_write)
foo.close()
if 'pdf' in filetype:
to_write = wl.pdf_formatter(motif.data, my_format)
foo = open(
os.path.join(foldername,
str(i) + '_' + str(len(motif.seqs)) + ".pdf"),
"wb")
foo.write(to_write)
foo.close()
if 'txt' in filetype:
to_write = ''.join(["%s\n" % str(seq) for seq in motif.seqs])
foo = open(
os.path.join(foldername,
str(i) + '_' + str(len(motif.seqs)) + ".txt"),
"w")
foo.write(to_write)
foo.close()
else:
raise ValueError(
'Invalid filetype. Available options: png, pdf or txt. ')
def printlogo(pwm, filename, alphabet="ACGT", mode="pdf"):
myAlphabet = {"A":0, "C":1, "G":2, "T":3}
translate = np.array([myAlphabet[i] for i in alphabet])
pwm = pwm[:, translate]
"Prints logo from nucleotides as a pdf"
import cPickle
cPickle.dump(pwm, open(filename + ".pkl", 'wb'), -1)
import weblogolib as wl # @UnresolvedImport
PWMdata = np.array(pwm)
data = wl.LogoData.from_counts(wl.std_alphabets["dna"], PWMdata)
options = wl.LogoOptions(resolution=300)
options.title = filename
options.color_scheme = wl.colorscheme.nucleotide
formatt = wl.LogoFormat(data, options)
if mode == "pdf":
fout = open(filename + ".pdf", 'wb')
fout.write(wl.pdf_formatter(data, formatt))
elif mode == "png":
fout = open(filename + ".png", 'wb')
fout.write(wl.png_formatter(data, formatt))
else:
fout = open(filename + ".{0}".format(mode), 'wb')
exec("""fout.write(wl.{0}_formatter(data, format))""".format(mode))
fout.close()
def main():
args = docopt.docopt(__doc__)
root = args['<workspace>']
round = args['<round>']
output_path = args['<pdf_output>']
# Right now I'm looking at validated designs by default, but the user may
# be interested in fixbb designs or restrained models as well.
workspace = pipeline.ValidatedDesigns(root, round)
workspace.check_paths()
designs = [structures.Design(x) for x in workspace.output_subdirs]
sequences = corebio.seq.SeqList(
[corebio.seq.Seq(x.resfile_sequence) for x in designs],
alphabet=corebio.seq.unambiguous_protein_alphabet,
)
logo_data = weblogo.LogoData.from_seqs(sequences)
logo_options = weblogo.LogoOptions()
logo_options.title = workspace.focus_dir
logo_format = weblogo.LogoFormat(logo_data, logo_options)
with open(output_path, 'wb') as logo_file:
document = weblogo.pdf_formatter(logo_data, logo_format)
logo_file.write(document)
def mutect_weblogo_sub(sampN, inFileN, outFileN, pdfFileN):
inFile = open(inFileN, 'r')
inFile.readline() #comment line
headerL = inFile.readline().rstrip().split('\t')
idxH = {}
for i in range(len(headerL)):
idxH[headerL[i]] = i
outFile = open(outFileN, 'w')
for line in inFile:
colL = line.rstrip().split('\t')
context = colL[idxH['context']]
ref = colL[idxH['ref_allele']]
alt = colL[idxH['alt_allele']]
status = colL[idxH['judgement']]
if status == 'REJECT':
continue
head = context[:3]
tail = context[-3:]
context = head + ref + tail
if ref not in ['C', 'T']:
context = mybasic.rc(context)
ref = mybasic.rc(ref)
alt = mybasic.rc(alt)
if ref == 'C' and alt == 'T': ## TMZ context only
outFile.write('%s\n' % context)
outFile.flush()
outFile.close()
fin = open(outFileN, 'r')
seqs = weblogolib.read_seq_data(fin)
data = weblogolib.LogoData.from_seqs(seqs)
options = weblogolib.LogoOptions()
options.show_fineprint = False
options.first_index = -3
options.logo_title = sampN
format = weblogolib.LogoFormat(data, options)
fout = open(pdfFileN, 'w')
weblogolib.pdf_formatter(data, format, fout)
def mutect_weblogo_sub(sampN, inFileN, outFileN, pdfFileN):
inFile = open(inFileN, 'r')
inFile.readline() #comment line
headerL = inFile.readline().rstrip().split('\t')
idxH = {}
for i in range(len(headerL)):
idxH[headerL[i]] = i
outFile = open(outFileN,'w')
for line in inFile:
colL = line.rstrip().split('\t')
context = colL[idxH['context']]
ref = colL[idxH['ref_allele']]
alt = colL[idxH['alt_allele']]
status = colL[idxH['judgement']]
if status == 'REJECT':
continue
head = context[:3]
tail = context[-3:]
context = head + ref + tail
if ref not in ['C','T']:
context = mybasic.rc(context)
ref = mybasic.rc(ref)
alt = mybasic.rc(alt)
if ref == 'C' and alt == 'T':## TMZ context only
outFile.write('%s\n' % context)
outFile.flush()
outFile.close()
fin = open(outFileN,'r')
seqs = weblogolib.read_seq_data(fin)
data = weblogolib.LogoData.from_seqs(seqs)
options = weblogolib.LogoOptions()
options.show_fineprint = False
options.first_index = -3
options.logo_title = sampN
format = weblogolib.LogoFormat(data, options)
fout = open(pdfFileN, 'w')
weblogolib.pdf_formatter(data, format, fout)
def plot_motif_from_sites( sites, img_format='png', smallText=None ):
ldata = wl.LogoData.from_seqs(wl.SeqList(sites, wl.unambiguous_dna_alphabet))
options = wl.LogoOptions()
if smallText is not None:
options.fineprint = smallText ##os.path.dirname(self.dbfile) + ' ' + self.organism
format = wl.LogoFormat(ldata, options)
format.color_scheme = wl.classic
format.resolution = 150
if img_format == 'png':
tmp = wl.png_formatter( ldata, format )
output = cStringIO.StringIO(tmp)
img = mpimg.imread(output)
plt.axis('off')
imgplot = plt.imshow( img )
return plt
elif img_format == 'svg':
tmp = wl.svg_formatter( ldata, format )
return tmp
elif img_format == 'pdf':
tmp = wl.pdf_formatter( ldata, format )
return tmp
def plot_motif_from_sites( sites, img_format='png', smallText=None ):
ldata = wl.LogoData.from_seqs(wl.SeqList(sites, wl.unambiguous_dna_alphabet))
options = wl.LogoOptions()
if smallText is not None:
options.fineprint = smallText ##os.path.dirname(self.dbfile) + ' ' + self.organism
format = wl.LogoFormat(ldata, options)
format.color_scheme = wl.classic
format.resolution = 150
if img_format == 'png':
tmp = wl.png_formatter( ldata, format )
output = cStringIO.StringIO(tmp)
img = mpimg.imread(output)
plt.axis('off')
imgplot = plt.imshow( img )
return plt
elif img_format == 'svg':
tmp = wl.svg_formatter( ldata, format )
return tmp
elif img_format == 'pdf':
tmp = wl.pdf_formatter( ldata, format )
return tmp
def do_seqlogo(self, input_fasta, output_seqlogo, col_list):
"""
create sequence logo of given fasta file and then label it with col_list
"""
import weblogolib
import corebio
from weblogolib.colorscheme import ColorScheme
from weblogolib.colorscheme import ColorGroup
#assigning colors
hydrophobicity = ColorScheme([
ColorGroup("RKDENQ", "blue"),
ColorGroup("SGHTAP", "green"),
ColorGroup("YVMCLFIW", "black"),
ColorGroup("O", "dark orange")
])
#Here i changed this so that the column begins with 1 not 0
col_list2 = [i+1 for i in col_list]
fin = open(input_fasta)
seqs = weblogolib.read_seq_data(fin)
seqs.alphabet = corebio.seq.Alphabet('ACDEFGHIKLMNPQRSTVWYO')
data = weblogolib.LogoData.from_seqs(seqs)
data.composition = 'equiprobable'
options = weblogolib.LogoOptions()
options.yaxis_scale = 4.5
options.yaxis_tic_interval = 2.25
options.annotate = col_list2
options.stack_width = 30
options.stacks_per_line = 35
options.scale_width = 'No'
options.color_scheme = hydrophobicity
format_logo = weblogolib.LogoFormat(data, options)
fout = open(output_seqlogo, 'w')
pdf_logo = weblogolib.pdf_formatter(data, format_logo)
fout.write(pdf_logo)
fout.close()
def draw_logo(df,seq_dict,inv_dict,dicttype):
'''Draw logo of sequences.'''
#Set Logo options
'''stack width in points, not default size of 10.8, but set to this
in weblogo call below'''
stackwidth = 9.5
barheight = 5.5 # height of bars in points if using overlay
barspacing = 2.0 # spacing between bars in points if using overlay
'''ratio of stack height:width, doesn't count part going
over maximum value of 1'''
stackaspectratio = 4.4
ymax = 1.0
logo_options = weblogolib.LogoOptions()
logo_options.fineprint = None
#logo_options.stacks_per_line = nperline
logo_options.stack_aspect_ratio = stackaspectratio
logo_options.show_errorbars = True
logo_options.errorbar_fraction = .75
logo_options.errorbar_gray = .9
logo_options.errorbar_width_fraction = .9
logo_options.stack_width = stackwidth
#Command to uncomment if you want each column to have height = 1
#logo_options.unit_name = 'probability'
logo_options.show_yaxis = False
#logo_options.yaxis_scale = ymax
#for dna
if dicttype == 'dna':
al = weblogolib.unambiguous_dna_alphabet
column_headers = ['freq_' + inv_dict[i] for i in range(len(seq_dict))]
counts_arr = np.array(df[column_headers])
data = weblogolib.LogoData.from_counts(al,counts_arr)
colormapping = {}
colormapping['A'] = '#008000'
colormapping['T'] = '#FF0000'
colormapping['C'] = '#0000FF'
colormapping['G'] = '#FFA500'
color_scheme = weblogolib.colorscheme.ColorScheme()
for x in [inv_dict[i] for i in range(len(seq_dict))]:
if hasattr(color_scheme, 'rules'):
color_scheme.rules.append(weblogolib.colorscheme.SymbolColor(x, colormapping[x], "'%s'" % x))
else:
# this part is needed for weblogo 3.4
color_scheme.groups.append(
weblogolib.colorscheme.ColorGroup(x, colormapping[x], "'%s'" % x))
logo_options.color_scheme = color_scheme
#for protein
if dicttype == 'protein':
al = weblogolib.unambiguous_protein_alphabet
column_headers = ['freq_' + inv_dict[i] for i in range(len(seq_dict))]
counts_arr = np.array(df[column_headers])
data = weblogolib.LogoData.from_counts(al,counts_arr)
#for rna
if dicttype == 'rna':
al = weblogolib.unambiguous_rna_alphabet
column_headers = ['freq_' + inv_dict[i] for i in range(len(seq_dict))]
counts_arr = np.array(df[column_headers])
data = weblogolib.LogoData.from_counts(al,counts_arr)
#set logo format and output
myformat = weblogolib.LogoFormat(data,logo_options)
myimage = weblogolib.pdf_formatter(data,myformat)
return myimage
import weblogolib as wll
import pickle
seqs = ['attcgtgatagctgtcgtaaag','ttttgttacctgcctctaactt','aagtgtgacgccgtgcaaataa','tgccgtgattatagacactttt','atttgcgatgcgtcgcgcattt','taatgagattcagatcacatat','taatgtgacgtcctttgcatac','gaaggcgacctgggtcatgctg','aggtgttaaattgatcacgttt','cgatgcgaggcggatcgaaaaa','aaattcaatattcatcacactt','agatgtgagccagctcaccata','agatgtgattagattattattc','aattgtgatgtgtatcgaagtg','ttatttgaaccagatcgcatta','aaatgtaagctgtgccacgttt','aagtgtgacatggaataaatta','ttgtttgatttcgcgcatattc','aaacgtgatttcatgcgtcatt','atgtgtgcggcaattcacattt','taatgttatacatatcactcta','ttttatgacgaggcacacacat','aagttcgatatttctcgttttt','ttttgcgatcaaaataacactt','aaacgtgatcaacccctcaatt','taatgtgagttagctcactcat','aattgtgagcggataacaattt','ttgtgtgatctctgttacagaa','TAAtgtggagatgcgcacaTAA','TTTtgcaagcaacatcacgAAA','GACctcggtttagttcacaGAA','aattgtgacacagtgcaaattc','aaccgtgctcccactcgcagtc','TCTTGTGATTCAGATCACAAAG','ttttgtgagttttgtcaccaaa','aaatgttatccacatcacaatt','ttatttgccacaggtaacaaaa','atgcctgacggagttcacactt','taacgtgatcatatcaacagaa','Ttttgtggcctgcttcaaactt','ttttatgatttggttcaattct','aattgtgaacatcatcacgttc','ttttgtgatctgtttaaatgtt','agaggtgattttgatcacggaa','atttgtgagtggtcgcacatat','gattgtgattcgattcacattt','gtgtgtaaacgtgaacgcaatc','aactgtgaaacgaaacatattt','TCTTGTGATGTGGTTAACCAAT']
#fIn = open('/Users/biggus/SourceCodeEtc/weblogo-3.0/tests/data/cap.fas')
#seqs = wll.read_seq_data(fIn)
for i in range(len(seqs)):
seqs[i] = wll.Seq(seqs[i])
seqs = wll.SeqList(seqs)
seqs.alphabet = wll.which_alphabet(seqs)
data = wll.LogoData.from_seqs(seqs)
#pickle.dump(data,open('/Users/biggus/SourceCodeEtc/weblogo-3.0/tests/out/fromList.data.pkl','w'))
#exit('Just Dumped List Pkl')
options = wll.LogoOptions()
options.title = 'A Logo Title'
format = wll.LogoFormat(data, options)
fout = open('/Users/biggus/SourceCodeEtc/weblogo-3.0/tests/out/cap2.xmpl.pdf', 'w')
wll.pdf_formatter( data, format, fout)
None
print 'done'
