I am new to this tool and I have tried using it on the sample data and it seems to work fine. I then attempted to train the model on my own dataset (200, 41966) consisting of 200 cells and 41966 gene features. When I converted the train data in CSV file to HDF5 format using the actinn_format.py, it said Dimension of the matrix after removing all-zero rows: (28, 41966). I checked my data file and there are no rows that have all zeros in since the data was scaled. This also caused me an issue when I tried to run the actinn_predict.py since the label I input is the text file containing 200 labels (not 28). Therefore, when the matrix was reduced, I received the IndexError: single positional indexer is out-of-bounds. Could you help me understand how the reducing matrix works and how to solve this issue? Thank you so much.
Hello,
I am new to this tool and I have tried using it on the sample data and it seems to work fine. I then attempted to train the model on my own dataset (200, 41966) consisting of 200 cells and 41966 gene features. When I converted the train data in CSV file to HDF5 format using the actinn_format.py, it said Dimension of the matrix after removing all-zero rows: (28, 41966). I checked my data file and there are no rows that have all zeros in since the data was scaled. This also caused me an issue when I tried to run the actinn_predict.py since the label I input is the text file containing 200 labels (not 28). Therefore, when the matrix was reduced, I received the IndexError: single positional indexer is out-of-bounds. Could you help me understand how the reducing matrix works and how to solve this issue? Thank you so much.