Skip to main content

Table 4 Comparison of DNASimCLR with other tools in virus-host dataset (Acc. (Accuracy): The overall correctness of predictions. Prec. (Precision): The accuracy of positive predictions. Rec. (Recall): The proportion of actual positives correctly predicted. Spec. (Specificity): The proportion of actual negatives correctly predicted.)

From: DNASimCLR: a contrastive learning-based deep learning approach for gene sequence data classification

Method

Acc

Prec

Rec

Spec

CNN [5]

87.8

89.9

85.2

90.4

LSTM [5]

84.7

86.0

82.8

86.5

k-NN [34]

75.5

76.3

73.9

77.1

BLAST [34]

78.4

98.3

79.2

77.6

VirusBERTHP [34]

99.1

98.8

99.3

98.8

DNASimCLR

99.9

99.8

99.7

99.8

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us