search

xiaoyeye / CCST

Cell clustering for spatial transcriptomics data with graph neural network
58 stars 11 forks source link

Question for hyperparameters with DLPFC samples #7

Open zy-fang opened 1 year ago

zy-fang commented 1 year ago

Hi yeye,

I am interested in your method CCST. It is a nice method for analyzing spatial transcriptomics!

I tried to cluster DLPFC samples with CCST. I did not find the hyperparameter settings for the DLPFC sample in the paper. So I set the hyperparameters according to the human Breast Cancer datasets. I found that the results of my run were quite different from the results of your paper. I wonder if the hyperparameter settings are inconsistent. I would like you to provide a list of hyperparameters for each sample.

Best, Zhaoyu

KaishinShaw commented 3 months ago

Hi yeye,

I am interested in your method CCST. It is a nice method for analyzing spatial transcriptomics!

I tried to cluster DLPFC samples with CCST. I did not find the hyperparameter settings for the DLPFC sample in the paper. So I set the hyperparameters according to the human Breast Cancer datasets. I found that the results of my run were quite different from the results of your paper. I wonder if the hyperparameter settings are inconsistent. I would like you to provide a list of hyperparameters for each sample.

Best, Zhaoyu

Hi Zhaoyu,

I am also very interested in the CCST method and its applications in spatial transcriptomics. It's great to see others working with this project!

I noticed your comment regarding the challenges in clustering DLPFC samples using CCST. Like you, I have faced difficulties in replicating the results presented in the paper when applying the method to different datasets. Would you consider sharing the replication code for the DLPFC dataset on your GitHub repository? Having access to this could greatly assist me in overcoming these replication challenges.

Thank you for your consideration and for your contributions to advancing this method.

Best regards