Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Raw signal from MinION and its segmentation to events.

The plot was generated from the E. coli data (http://www.ebi.ac.uk/ena/data/view/ERR1147230).

More »

Fig 1 Expand

Table 1.

Accuracy of base callers on two R7.3 testing data sets.

The results of base calling were aligned to the reference using BWA-MEM [28]. The accuracy was computed as the number of matches in the alignment divided by the length of the alignment.

More »

Table 1 Expand

Fig 2.

Schematics of a bidirectional recurrent neural network.

More »

Fig 2 Expand

Table 2.

Sizes of experimental data sets.

The sizes differ between strands because only base calls mapping to the reference were used. Note that the counts of 2D events are based on the size of the alignment.

More »

Table 2 Expand

Fig 3.

DeepNano reduces bias in 6-mer composition.

Comparison of 6-mer content in Klebsiella reference genome and base-called reads by Metrichor (left) and DeepNano (right). From top to bottom: template, complement, 2D.

More »

Fig 3 Expand

Fig 4.

Abudances for repetitive 6-mers.

More »

Fig 4 Expand

Table 3.

Accuracy and running time on R9 data.

The results of base calling were aligned to the reference using BWA-MEM [28]. The first column reports the percentage of reads that aligned to the reference on at least 90% of their length. The accuracy was computed as the number of matches in the alignment divided by the length of the alignment. The speed is measured in events per second.

More »

Table 3 Expand