Gene Sequence Clustering Based on the Profile Hidden Markov Model with Differential Identifiability

Table 1

Gene sequence clustering models’ performance.

Model	Availability^1 (%)	Efficiency	Security
DKHC [28]	98.26	Slow	×
DEGCA [14]	96.7	Slow	×
CD-HIT [29]	95	Fast	×
GeneRage [30]	95	Fast	×
DI-GSCA	CS^2: 0.77	Slow	✓

¹The availability data were the highest value in their respective references. ²CS: cosine similarity.