search

zhoux85 / STAligner

STAligner is a tool for alignment and integration of spatially resolved transcriptomics data.
MIT License
29 stars 5 forks source link

Question about random seeds #14

Open czwdcm opened 9 months ago

czwdcm commented 9 months ago

Hello,

This is a wonderful way to analyze spatial transcriptomics!

Following the tutorial you provided, I tried to integrate DLPFC slices via SLAlinger. I found that the results fluctuate a lot each time, for example, I get slices 151674 with ARI around 0.61 to 0.67. I noticed that the random seed has been set to 666 when using mclust clustering, is there any other way to keep the results stable? Would you be able to share with me? Thank you very much!

zhoux85 commented 9 months ago

Hi. I have fixed the random seed of torch in train_STAligner.py, but it dosen't work, which may be limited by the underlying mechanism of PyG (PyTorch Geometric). If new solution available, I will update STAligner timely.