Out of Memory Issue During Cell Type Identification Step on 256GB RAM Machine

YangLabHKUST / SpatialScope

A unified approach for integrating spatial and single-cell transcriptomics data by leveraging deep generative models

https://spatialscope-tutorial.readthedocs.io/en/latest/

GNU General Public License v3.0

54 stars 6 forks source link

Out of Memory Issue During Cell Type Identification Step on 256GB RAM Machine #10

Open ChenJin2020 opened 9 months ago

ChenJin2020 commented 9 months ago

Hi,

I encountered an out-of-memory (OOM) error while executing the cell type identification step. Despite running the process on a machine equipped with 256 GB of RAM, the operation was terminated because it exceeded the available memory.

Is there a way to configure or limit the memory usage for this specific step to prevent OOM errors? Could you provide any recommendations or settings adjustments to optimize memory usage for machines with large RAM capacities?

Thanks,

Chen

JiaShun-Xiao commented 9 months ago

Hi,

The memory usage of SpatialScope for one slice Visium data should be less than 50 GB. I do not know why this issue happened in your case. By the way, you could try use a smaller dataset (e.g., the cropped ROI region of Visium data) to test the pipeline of SpatialScope.

Jiashun