search

poseidonchan / TAPE

Deep learning-based tissue compositions and cell-type-specific gene expression analysis with tissue-adaptive autoencoder (TAPE)
https://sctape.readthedocs.io/
GNU General Public License v3.0
49 stars 9 forks source link

Question regarding the results #17

Closed gstaryu closed 2 months ago

gstaryu commented 2 months ago

First of all, thank you very much for your work. I have a question: I noticed that the pred results of several datasets are provided in the attachment SuppData_TAPE\TAPE\real\. I plotted box plots of CCC for monaco_pred.csv and sdy67_pred.csv, but I found a significant difference compared to the results in Figure 2-d of the paper. Should I refer to the results in the attachment SuppData_TAPE\TAPE\real\ or those in Figure 2-d of the paper? Perhaps I have misunderstood your intent?

As shown in the figure below: the top image displays the results for the monaco and sdy67 datasets from your attachment SuppData_TAPE\TAPE\real\, while the bottom image shows the results from Figure 2-d of the paper. output

paper_res

I am quite confused and may have misunderstood the meaning of the files in your attachment. Could you please clarify? Thank you.

poseidonchan commented 2 months ago

Thanks for reaching out!

I am sorry that I forget about the details since it has been a long time. But you can always reproduce the results with the notebook (https://github.com/poseidonchan/TAPE/blob/main/Experiments/TAPE_realbulk.ipynb) and corresponding data. Moreover, please bear the performance differences since different random seeds may affect the performance significantly.

Yanshuo