Extended Data Fig. 2: DeepTFni outperforms other methods. | Nature Machine Intelligence

Extended Data Fig. 2: DeepTFni outperforms other methods.

From: Inferring transcription factor regulatory networks from single-cell ATAC-seq data based on graph neural networks

Extended Data Fig. 2

(a). DeepTFni outperforms other 4 methods. (b). Receiver operator characteristic curves of DeepTFni and other 4 methods. (c). DeepTFni shows better precision and recall rate on total dataset. For each method, the number of predicted TF interactions (links) with network density are listed. (d). Benchmark of running time and memory usage. (e). Visualization of t-SNE analysis on TF degrees calculated by DeepTFni, DeepWalk, GENIE3, SCENIC and GRNBoost2. Colors represent different cell types and shades represent cell number from small (light) to large (dark). Arrow line connects the center nodes for each cell number. (f). Inter cell-type distance of t-SNE results for each cell number. R2 was calculated as Pearson correlation coefficient. (g). Inter cell-type distance of t-SNE results for each cell number. R2 was calculated as Pearson correlation coefficient.

Back to article page