def _write_genome_summary(self, output_file):
"""Summarize classification of each genome.
Parameters
----------
output_file : str
Output file.
"""
fout = open(output_file, 'w')
fout.write('Genome id\tLength (bp)\t# sequences')
for rank in self.rank_labels:
fout.write('\t' + rank + ': taxa')
fout.write('\t' + rank + ': percent of bps')
fout.write('\t' + rank + ': percent of sequences')
fout.write('\t' + rank + ': avg. evalue')
fout.write('\t' + rank + ': avg. perc identity')
fout.write('\t' + rank + ': avg. align length (AA)')
fout.write('\n')
sorted_genome_ids = alphanumeric_sort(self.profiles.keys())
for genome_id in sorted_genome_ids:
self.profiles[genome_id].write_genome_summary(fout)
fout.close()
def _write_genome_summary(self, output_file):
"""Summarize classification of each genome.
Parameters
----------
output_file : str
Output file.
"""
fout = open(output_file, 'w')
fout.write('Genome id\tLength (bp)\t# sequences')
for rank in self.rank_labels:
fout.write('\t' + rank + ': taxa')
fout.write('\t' + rank + ': percent of bps')
fout.write('\t' + rank + ': percent of sequences')
fout.write('\t' + rank + ': avg. evalue')
fout.write('\t' + rank + ': avg. perc identity')
fout.write('\t' + rank + ': avg. align length (AA)')
fout.write('\n')
sorted_genome_ids = alphanumeric_sort(self.profiles.keys())
for genome_id in sorted_genome_ids:
self.profiles[genome_id].write_genome_summary(fout)
fout.close()
def create_html_index(self, plot_dir, genome_plots):
"""Create HTML index for navigating outlier plots.
Parameters
----------
plot_dir : str
Directory containing plots.
genome_plots : d[genome_id] -> [(plot_type, plot_filename), ...]
Hash indicating the plot types and filenames for each genome of interest.
"""
sorted_genome_ids = alphanumeric_sort(genome_plots.keys())
starting_plot_filename = genome_plots[sorted_genome_ids[0]][0][1]
starting_plot_str = sorted_genome_ids[0] + '<br>' + genome_plots[sorted_genome_ids[0]][0][0]
fout = open(os.path.join(plot_dir, 'index.html'), 'w')
fout.write('<html>\n')
fout.write('<head>')
fout.write('<title>RefineM outlier plots</title>\n')
fout.write('</head>\n')
fout.write('<frameset cols="15%,85%">\n')
fout.write('<frame src="plot_menu.html" name="menu">\n')
fout.write('<frame src="%s" name="plot">\n' % starting_plot_filename)
fout.write('</frameset>\n')
fout.write('</html>\n')
fout.close()
fout = open(os.path.join(plot_dir, 'plot_menu.html'), 'w')
fout.write('<html>\n')
fout.write('<script>\n')
fout.write(' function change_title(name) {\n')
fout.write(' document.getElementById("active_plot").innerHTML = name;\n')
fout.write(' }\n')
fout.write('</script>\n\n')
fout.write('<style>\n')
fout.write('ul {\n')
fout.write('margin-top: 0px;\n')
fout.write('margin-bottom: 12px;\n')
fout.write('}\n')
fout.write('</style>\n\n')
fout.write('<body>\n')
fout.write('<div><b>Active plot:</b>\n')
fout.write('<div id="active_plot">%s</div>\n' % starting_plot_str)
fout.write('</div>\n')
fout.write('<br>\n')
fout.write('<div><b>Plots:</b></div>\n')
for genome_id in sorted_genome_ids:
fout.write('<i> %s:</i>\n' % genome_id)
fout.write(' <ul>\n')
for (plot_type, plot_filename) in genome_plots[genome_id]:
fout.write(' <li><a href="%s" target="plot" onclick="change_title(\'%s\');">%s</a><br></li>\n' % (plot_filename,
genome_id + '<br>' + plot_type,
plot_type))
fout.write(' </ul>\n')
fout.write('</body>\n')
fout.write('</html>\n')
fout.close()
def create_html_index(self, plot_dir, genome_plots):
"""Create HTML index for navigating outlier plots.
Parameters
----------
plot_dir : str
Directory containing plots.
genome_plots : d[genome_id] -> [(plot_type, plot_filename), ...]
Hash indicating the plot types and filenames for each genome of interest.
"""
sorted_genome_ids = alphanumeric_sort(genome_plots.keys())
starting_plot_filename = genome_plots[sorted_genome_ids[0]][0][1]
starting_plot_str = sorted_genome_ids[0] + '<br>' + genome_plots[sorted_genome_ids[0]][0][0]
fout = open(os.path.join(plot_dir, 'index.html'), 'w')
fout.write('<html>\n')
fout.write('<head>')
fout.write('<title>RefineM outlier plots</title>\n')
fout.write('</head>\n')
fout.write('<frameset cols="15%,85%">\n')
fout.write('<frame src="plot_menu.html" name="menu">\n')
fout.write('<frame src="%s" name="plot">\n' % starting_plot_filename)
fout.write('</frameset>\n')
fout.write('</html>\n')
fout.close()
fout = open(os.path.join(plot_dir, 'plot_menu.html'), 'w')
fout.write('<html>\n')
fout.write('<script>\n')
fout.write(' function change_title(name) {\n')
fout.write(' document.getElementById("active_plot").innerHTML = name;\n')
fout.write(' }\n')
fout.write('</script>\n\n')
fout.write('<style>\n')
fout.write('ul {\n')
fout.write('margin-top: 0px;\n')
fout.write('margin-bottom: 12px;\n')
fout.write('}\n')
fout.write('</style>\n\n')
fout.write('<body>\n')
fout.write('<div><b>Active plot:</b>\n')
fout.write('<div id="active_plot">%s</div>\n' % starting_plot_str)
fout.write('</div>\n')
fout.write('<br>\n')
fout.write('<div><b>Plots:</b></div>\n')
for genome_id in sorted_genome_ids:
fout.write('<i> %s:</i>\n' % genome_id)
fout.write(' <ul>\n')
for (plot_type, plot_filename) in genome_plots[genome_id]:
fout.write(' <li><a href="%s" target="plot" onclick="change_title(\'%s\');">%s</a><br></li>\n' % (plot_filename,
genome_id + '<br>' + plot_type,
plot_type))
fout.write(' </ul>\n')
fout.write('</body>\n')
fout.write('</html>\n')
fout.close()
def create(self, profiles, output_file):
"""Create Krona plot.
Profiles for multiple items (e.g., genome, metagenome) can
be specified. The complete hierarchy for each unique element
should be specified as a semicolon separated string, e.g.,
k__Bacteria;c__Firmicutes;...;s__
The number of hits to each unique element is specified in
the profiles dictionary, e.g.,
d[unique_id][element_str] = 10
Parameters
----------
profiles: d[unique_id][element_str] -> count
Number of hits to specific elements for each item.
output_file : str
Name of output file.
"""
# create temporary files for each item
cmd = 'ktImportText -o %s' % output_file
tmp_dir = tempfile.mkdtemp()
for unique_id in alphanumeric_sort(list(profiles.keys())):
tmp_file = os.path.join(tmp_dir, unique_id)
fout = open(tmp_file, 'w')
for element_str, num_hits in profiles[unique_id].items():
elements = [x.strip() for x in element_str.split(';')]
fout.write(str(num_hits) + '\t' + '\t'.join(elements) + '\n')
fout.close()
cmd += ' %s,%s' % (tmp_file, unique_id)
# create krona plot
execute.run(cmd)
# clean up temporary files
shutil.rmtree(tmp_dir)
def write(self, output_file):
"""Write genome statistics to file.
Parameters
----------
output_file : str
Name of output file.
"""
fout = open(output_file, 'w')
fout.write('Genome id\tGenome size (bp)')
fout.write('\tMean GC\tMedian GC')
fout.write('\tMean scaffold length (bp)\tMedian scaffold length (bp)')
fout.write('\tMean: ' + '\tMean: '.join(self.coverage_headers))
fout.write('\tMedian: ' + '\tMedian: '.join(self.coverage_headers))
fout.write('\t' + '\t'.join(self.signature_headers))
fout.write('\n')
for genome_id in alphanumeric_sort(self.genome_stats.keys()):
stats = self.genome_stats[genome_id]
fout.write(genome_id)
fout.write('\t%d' % stats.genome_size)
fout.write('\t%.2f' % stats.mean_gc)
fout.write('\t%.2f' % stats.median_gc)
fout.write('\t%.2f' % stats.mean_scaffold_length)
fout.write('\t%.2f' % stats.median_scaffold_length)
for cov in stats.mean_coverage:
fout.write('\t%.2f' % cov)
for cov in stats.median_coverage:
fout.write('\t%.2f' % cov)
for freq in stats.mean_signature:
fout.write('\t%f' % freq)
fout.write('\n')
fout.close()
def _parse_data(self, infile):
data = {}
with open(infile) as fp:
fp.readline()
genomes = set()
for line in fp:
fields = line.rstrip().split('\t')
fields[0] = re.sub(r'_genes$', "", fields[0])
fields[2] = re.sub(r'_genes$', "", fields[2])
genomes.add(fields[0])
genomes.add(fields[2])
try:
data[fields[0]][fields[2]] = [float(fields[5]), float(fields[7])]
except KeyError:
data[fields[0]] = {}
data[fields[0]][fields[2]] = [float(fields[5]), float(fields[7])]
except IndexError as e:
print(fields)
raise e
self.perc_ids = np_zeros([len(genomes), len(genomes)])
self.perc_aln = np_zeros([len(genomes), len(genomes)])
genome_to_index = {}
self.genomes = [None] * len(genomes)
for n, g in enumerate(alphanumeric_sort(genomes)):
genome_to_index[g] = n
self.genomes[n] = g
self.genomes = np_array(self.genomes)
for g1, g2 in permutations(genomes, 2):
try:
self.perc_ids[genome_to_index[g1]][genome_to_index[g2]] = 100.0 - data[g1][g2][0]
self.perc_aln[genome_to_index[g1], genome_to_index[g2]] = data[g1][g2][1]
except:
self.perc_ids[genome_to_index[g1]][genome_to_index[g2]] = 100.0 - data[g2][g1][0]
self.perc_aln[genome_to_index[g1], genome_to_index[g2]] = data[g2][g1][1]
def _parse_data(self, infile):
data = {}
with open(infile) as fp:
fp.readline()
genomes = set()
for line in fp:
fields = line.rstrip().split('\t')
fields[0] = re.sub(r'_genes$', "", fields[0])
fields[2] = re.sub(r'_genes$', "", fields[2])
genomes.add(fields[0])
genomes.add(fields[2])
try:
data[fields[0]][fields[2]] = [float(fields[5]), float(fields[7])]
except KeyError:
data[fields[0]] = {}
data[fields[0]][fields[2]] = [float(fields[5]), float(fields[7])]
except IndexError as e:
print(fields)
raise e
self.perc_ids = np_zeros([len(genomes), len(genomes)])
self.perc_aln = np_zeros([len(genomes), len(genomes)])
genome_to_index = {}
self.genomes = [None] * len(genomes)
for n, g in enumerate(alphanumeric_sort(genomes)):
genome_to_index[g] = n
self.genomes[n] = g
self.genomes = np_array(self.genomes)
for g1, g2 in permutations(genomes, 2):
try:
self.perc_ids[genome_to_index[g1]][genome_to_index[g2]] = 100.0 - data[g1][g2][0]
self.perc_aln[genome_to_index[g1], genome_to_index[g2]] = data[g1][g2][1]
except:
self.perc_ids[genome_to_index[g1]][genome_to_index[g2]] = 100.0 - data[g2][g1][0]
self.perc_aln[genome_to_index[g1], genome_to_index[g2]] = data[g2][g1][1]
def plot(self, common_bases, quality, output_plot):
"""Create plot.
Parameters
----------
common_bases : d[unitem bid][binning method] -> percent common bases
Percentage of common bases for each binning method.
quality : d[unitem id] -> (completeness, contamination)
Completeness and contamination of bins.
output_plot : str
Desired output file.
"""
# sort bin labels
bin_labels = alphanumeric_sort(common_bases)
# sort binning method labels
binning_methods = set()
for bid in common_bases:
for bm in common_bases[bid]:
binning_methods.add(bm)
bm_labels = alphanumeric_sort(binning_methods)
# setup SVG drawing
table_start_x = 0
table_start_y = 0
if not output_plot.endswith('.svg'):
output_plot += '.svg'
self.fig_size_x = table_start_x + len(bm_labels) * self.col_width
self.fig_size_x += 2 * self.qual_col_width + 0.5 * self.col_width
self.fig_size_y = table_start_y + len(bin_labels) * self.row_height
dwg = svgwrite.Drawing(filename=output_plot,
size=(self.fig_size_x, self.fig_size_y),
profile='full',
style='font-family:Arial')
dwg.set_desc(title='UniteM shared base pair plot.')
# render legend
self._render_legend(dwg)
# render binning method labels
label_start_x = table_start_x
label_start_y = table_start_y + 0.5 * self.row_height + 0.45 * self.font_size
self._render_label_col(dwg, bin_labels, label_start_x, label_start_y,
'bin_labels')
# render completeness and contamination
header_start_y = table_start_y - 0.5 * self.font_size
label_start_x = table_start_x + 0.5 * self.col_width
label_start_y = table_start_y + 0.5 * self.row_height + 0.45 * self.font_size
self._render_genome_quality_cols(dwg, bin_labels, quality,
header_start_y, label_start_x,
label_start_y)
# move start of table to account for genome quality info
table_start_x += 2 * self.qual_col_width + 0.5 * self.col_width
# write header line
label_start_x = table_start_x
header_row_start_y = table_start_y - 0.5 * self.font_size
self._render_label_row(dwg, bm_labels, label_start_x,
header_row_start_y, 'binning_method_labels')
# render gene complement row
self._render_row(dwg, bin_labels, bm_labels, common_bases,
table_start_x, table_start_y)
dwg.save()
class Heatmap(AbstractPlot):
def __init__(self, infile, outfile):
AbstractPlot.__init__(self, None)
self.outfile = outfile
self.genomes = None
self._parse_data(infile)
self.colormap = pylab.cm.bwr
self.discreteColourMap = ListedColormap([
(141 / 255.0, 211 / 255.0, 199 / 255.0),
(255 / 255.0, 255 / 255.0, 179 / 255.0),
(190 / 255.0, 186 / 255.0, 218 / 255.0),
(251 / 255.0, 128 / 255.0, 114 / 255.0),
(128 / 255.0, 177 / 255.0, 211 / 255.0),
(253 / 255.0, 180 / 255.0, 98 / 255.0),
(179 / 255.0, 222 / 255.0, 105 / 255.0),
(252 / 255.0, 205 / 255.0, 229 / 255.0),
(217 / 255.0, 217 / 255.0, 217 / 255.0),
(188 / 255.0, 128 / 255.0, 189 / 255.0),
(204 / 255.0, 235 / 255.0, 197 / 255.0),
(255 / 255.0, 237 / 255.0, 111 / 255.0)
])
def _parse_data(self, infile):
data = {}
with open(infile) as fp:
fp.readline()
genomes = set()
for line in fp:
fields = line.rstrip().split('\t')
fields[0] = re.sub(r'_genes$', "", fields[0])
fields[2] = re.sub(r'_genes$', "", fields[2])
genomes.add(fields[0])
genomes.add(fields[2])
try:
data[fields[0]][fields[2]] = [
float(fields[5]), float(fields[7])
]
except KeyError:
data[fields[0]] = {}
data[fields[0]][fields[2]] = [
float(fields[5]), float(fields[7])
]
except IndexError, e:
print fields
raise e
self.perc_ids = np_zeros([len(genomes), len(genomes)])
self.perc_aln = np_zeros([len(genomes), len(genomes)])
genome_to_index = {}
self.genomes = [None] * len(genomes)
for n, g in enumerate(alphanumeric_sort(genomes)):
genome_to_index[g] = n
self.genomes[n] = g
self.genomes = np_array(self.genomes)
for g1, g2 in permutations(genomes, 2):
try:
self.perc_ids[genome_to_index[g1]][
genome_to_index[g2]] = 100.0 - data[g1][g2][0]
self.perc_aln[genome_to_index[g1],
genome_to_index[g2]] = data[g1][g2][1]
except:
self.perc_ids[genome_to_index[g1]][
genome_to_index[g2]] = 100.0 - data[g2][g1][0]
self.perc_aln[genome_to_index[g1],
genome_to_index[g2]] = data[g2][g1][1]