Skip to main content

Table 1 Effect of erroneous sequences on perplexity for multiple k-values on reads: these reads are generated by NanoSim using the E.coli reference genome

From: Lerna: transformer architectures for configuring error correction tools for short- and long-read genome sequencing

k \(PPL_{err}\) \(PPL_{corr}\) \(PPL_{total}\)
15 1073.6 943.5 952.9
37 1072.8 944.5 946.8
81 1072.8 973.4 956.3
  1. \(PPL_{err}\), \(PPL_{corr}\), and \(PPL_{total}\) denote the perplexity scores on erroneous and error-free reads, and the entire dataset (i.e., erroneous and error-free sequences)