xiaoyeye/ccst

Cell clustering for spatial transcriptomics data with graph neural network

ccst's Issues

Missing folder results and .png files

Excellent work!

README says the results are stored in folder results, and the spatial distribution of cells are illustrated in .png files. I do not find them for now. Could you please show me where can I find these two?

Value Error in Data Generation Merfish py

Hi,
I got this error when running the data_generation_merfish.py.
Here is the screenshot:

quesition about GO

Youe work is pretty impressive. Our team want to utilize your model for our task. Taking MERFISH for an instance, when we trained the model, we have no idea to design GO experiement. Could you help me with some code? Much thanks!😊

error of get_adj() function in data_generation_merfish.py

in the row of 41 and 44, It will change the position of first cell to (0,0)

error on CCST_ST_utils

When set barpolt=true, then I run the ccst, there is no results.

Run PCA repeatedly ?

Hi @lijc0804 :
Thank you to develop such a wonderful clustering architecture for spatial transcriptomics ! When I run the codes in CCST_ST_utils.py about the part of clustering, I noticed that:

X_embedding_filename =  args.embedding_data_path+'lambdaI' + str(lambda_I) + '_epoch' + str(args.num_epoch) + '_Embed_X.npy'
X_embedding = np.load(X_embedding_filename)

X_embedding = PCA_process(X_embedding, nps=30)

when I set:cluster_type == 'leiden'
it would run

adata = ad.AnnData(X_embedding)
sc.tl.pca(adata, n_comps=50, svd_solver='arpack')

The problem was occured, in function PCA_process, the embedding has been reduce to 30-d already, and do we need to run sc.tl.pca ? May I get your some advice?

Sincerely ,
LinYuX.

preprocess of DLPFC dataset

when runing the preprossing procedure 'data_generation_ST.py' on DLPFC 151507, an error accurs.
The reason is that the coordinates from 'filtered_bc_matrix.h5' have 4226 spots, and cell_types from 'metadata.csv' have 4226 spots, too. However, cell_types have 5 non-type items of 'cluster_guess'. If filtering it as the code, it will only contains 4221 items, which cause inconsistent problem between x,y, and c in the code sc_cluster = plt.scatter(x=coordinates[:,0], y=-coordinates[:,1], s=5, c=cell_types, cmap='rainbow')
Whether there is any solution of that?

Question for hyperparameters with DLPFC samples

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

老师您好!我对这个工作太着迷了!有一个地方不明白想请教一下

老师,关于使用曼惠特尼U检验找差异基因的具体步骤是怎样的,恳请老师能告知,万分感谢!