Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: NGS data vectorization, clustering, and finding key codons in SARS-CoV-2 variations

Fig. 4

Features that played a large role in the classification of each cluster extracted through the random forest (the closer to white, the greater the role): 3,721 variables were displayed as 61 × 61 images, and features that played a major role in classifying each cluster are displayed in bright colours. It can be confirmed that only a small number of features are mutated between clusters 9 and 1, and it can be confirmed that many mutations are occurring among other clusters

Back to article page