Skip to main content
. 2024 Aug 12;22:756. doi: 10.1186/s12967-024-05567-z

Fig. 4.

Fig. 4

The RUN0 model representation learning of potential feature patterns in the HERV dataset. Visualization of (A) SparsePCA and (B) TruncatedSVD downscaled components of the original DNA sequences. Visualization of (C) PCA and (D) t-SNE downscaled components of the last hidden layer in the fine-tuned model