Skip to main content

Table 9 Comparison of the performance of SARS-CoV-2 classification algorithms

From: New proposal of viral genome representation applied in the classification of SARS-CoV-2 with deep learning

Reference

Methodology

ACC

SEN

SPE

PRE

F1-Score

Arslan and Arslan [39]

CpG based features, KNN

\(98.4\%\)

\(99.2\%\)

\(98.4\%\)

\(98.8\%\)

Singh et al. [40]

Three-base periodicity, Random Forest

\(97.47\%\)

\(96.19\%\)

\(98.25\%\)

Randhawa et. al. [41]

k-mers, six supervised learning models.

\(100\%\)

Lopez-Rincon et at. [7]

Primer design, CNN.

\(98.73\%\)

\(100\%\)

This work

GSP, CNN.

\(99.69\%\)

\(99.74\%\)

\(94.69\%\)

\(99.95\%\)

\(99.84\%\)