search

JinmiaoChenLab / GraphST

GNU Affero General Public License v3.0
91 stars 14 forks source link

Question with mouse olfactory bulb Stereo-seq data #23

Open zhaozhenxing0 opened 8 months ago

zhaozhenxing0 commented 8 months ago

Hi! First, GraphST is an outstanding method for spatial transcriptome data analysis.

Recently, when I was identifying spatial domains in the mouse olfactory bulb Stereo-seq data,I encountered some difficulties and obtained results that were different from yours. I wonder if you could kindly share this part of the experimental code with me, I promise that I will only use your code for research purposes and will not disclose it to anyone else without your permission.

I appreciate your time and attention, and I look forward to hearing from you soon.

My email address is:zzx18292358139@163.com

longyahui commented 7 months ago

Hi,

Thank you for your attention on our work GraphST.

For the analysis of mouse olfactory bulb Stereo-seq data, we can follow the tutorial https://deepst-tutorials.readthedocs.io/en/latest/Tutorial%203_Stereo-seq.html.

Due to the influence of random seed, it is expected that the results from different GPU environment are a bit different from that presented in the paper. Despite the difference, we can reproduce the results in the paper by adjusting random seed.

Best regards, Yahui

CocoGzh commented 7 months ago

@longyahui I can't reproduce the results either. Can you provide specific parameters or upload a jupyter? Thx!