[

,

,

;

,

,

;

021] have been used. Similarly, the quality of sequencing read

t has drawn great attention and has also been researched recently

d, et al., 2019; Woste, et al., 2020].

S-CoV-2 protease cleavage pattern discovery

ase cleavage site identification problem has been well researched

al decades. It is still an important area for studying protein

. Although the exercise in this area has been very successful, the

objective of protease cleavage site identification or protease

pattern analysis for drug design such as the inhibitor design

is still challenging. The conversion from discovered protease

profile to effective drug design is still not an easy job [Vizovisek,

16]. After evaluating recent models for the protease cleavage site

y, it has been found that most machine learning models including

rning models work very well. It has been suggested that the

s well as distributed computing should be the main method for

accurate discovery of protease cleavage sites [Li, et al., 2019].

ad the SARS-CoV-2 pandemic worldwide, urgent attention has

d to the problem of how to discover the SARS-CoV-2 viral

ic cleavage sites. For instance, the novel S1/S2 site has been

d within the spike protein of SARS-CoV-2 [Javier, et al., 2020]

urin [Xia, et al., 2020]. The question, which still waits for a good

s whether it is possible to quickly discover the cleavage pattern

oping drugs to fight against the pandemic. This may be an urgent

enging task at the moment.