Skip to main content

Table 1 Training performances on data batch 1.A

From: Lokatt: a hybrid DNA nanopore basecaller with an explicit duration hidden Markov model and a residual LSTM network

Basecaller

Identity

Insertion

Deletions

Substitution

Base per read

Entry counts

Bases (\(10^9\))

Lokatt

0.912/0.926

0.018/0.016

0.045/0.034

0.025/0.020

4803/2937

565393

2.600

Bonito Local

0.900/0.914

0.019/0.017

0.051/0.038

0.030/0.026

4724/2885

562838

2.524

Bonito Sup

0.936/0.954

0.013/0.010

0.030/0.018

0.021/0.015

4757/2829

583471

2.686

  1. *First five entries are listed as ‘mean/median’
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us