Extended Data Fig. 4: Benchmarking of running efficiency using the IPF dataset. | Nature Biomedical Engineering

Extended Data Fig. 4: Benchmarking of running efficiency using the IPF dataset.

From: A deep generative model for deciphering cellular dynamics and in silico drug discovery in complex diseases

Extended Data Fig. 4

a, Benchmarking of the peak memory (CPU) usage by different methods. The x-axis is the number of cells, and the y-axis is the peak memory usage of the method. b, Benchmarking of running time. The x-axis is the number of cells, the y-axis is the running time. The peak memory required to run scGNN exceeds the limits of our workstation (256GB RAM) when the number of cells surpasses 60,000. c, Benchmarking of inference time. The x-axis is the number of cells, the y-axis is the inference time.

Back to article page