In [11]:
import numpy

2. Saturation

In [12]:
x = numpy.loadtxt('/mnt/saturate/ecoli_5m-report.txt')
In [13]:
plot(x[:,0], x[:,1])
xlabel('number of reads examined')
ylabel('number of reads retained')
title('Saturation of assembly graph/information in E. coli data set')
Out[13]:
<matplotlib.text.Text at 0x7f728c769610>

3. Coverage spectrum - example 1

In [14]:
x = numpy.loadtxt('/mnt/cover1/reads.hist')
In [15]:
plot(x[:,0], x[:,1])
xlabel('read abundance')
ylabel('N reads with that abundance')
title('Coverage spectrum of artificial two-species metagenome')
Out[15]:
<matplotlib.text.Text at 0x7f728c443710>

Coverage spectrum -- example 2

In [16]:
x = numpy.loadtxt('/mnt/cover2/reads.hist')
In [17]:
plot(x[:,0], x[:,1])
axis(xmax=300)
xlabel('read abundance')
ylabel('N reads with that abundance')
title('Coverage spectrum of E. coli colony')
Out[17]:
<matplotlib.text.Text at 0x7f728c44ce10>

4. Generating an error profile

In [18]:
x = numpy.loadtxt('/mnt/error/ecoli_ref-5m.fastq.gz.errhist')
In [19]:
plot(x[:,0], x[:,2])
xlabel('position in read')
ylabel('number of errors at that position')
title('reference-free error profile for E. coli reads')
Out[19]:
<matplotlib.text.Text at 0x7f728c986a90>

5. Assembly-filtered k-mer spectrum

In [20]:
x = numpy.loadtxt('/mnt/kmercov/counts.out')
In [21]:
plot(x[:,0], x[:,1])
xlabel('k-mer abundance')
ylabel('number of k-mers with that abundance')
title('read-based abundance of k-mers that ended up in assembly')
Out[21]:
<matplotlib.text.Text at 0x465cb10>

6. Partitioning

In [22]:
x = numpy.loadtxt('/mnt/part/group0.hist')
y = numpy.loadtxt('/mnt/part/group1.hist')
In [23]:
plot(x[:, 0], x[:, 1], label='partition 0')
plot(y[:, 0], y[:, 1], label='partition 1')
axis(ymax=150)
legend()
xlabel('k-mer abundance')
ylabel('number of k-mers with that abundance')
title('partitions correlate with species abundance')
Out[23]:
<matplotlib.text.Text at 0x4684d50>
In [23]: