caibinsh / scar-reproducibility Goto Github PK

Hello,

I noticed in the scRNA-seq and CRISPR screen tutorial you had different thresholds for the cell-free and droplet cutoffs.
I'm assuming the most important part is the cell-free portion, which should be under and after the knee like the 20k hgmm sample?
Or would it much after the knee like the A549 sample?
I'm mainly using this for CRISPR guide calling if that helps guide your advice.

Thanks,
Chang

"from . import _data_loader as dataloader" in line 4 of main.py is throwing an exception. As the module is obsolete, removing the import statement will fix the issue

Dear authors,

Is it correct to take all droplets with <12 UMI counts as the cell-free droplets or is there a heuristic to determine it?

I am looking forward to use this package!

Regards,
Mikhael

Hello,

In your preprint you used scAR to denoise the sgRNA calls, I was wondering if you could provide a tutorial for that?

Best,
Chang

Hello,

I'm trying out the CRISPR tutorial, I was wondering if you'd recommend collapsing all the counts for the sgRNAs before running scAR?

Best,
Chang

Hi,

I am following the tutorial provided for denoising CITE-seq and the ambient profile data that is refer in the jupyter notebook is missing: https://github.com/CaibinSh/scAR-reproducibility/blob/main/reproducibility/scAR_tutorial_denoising_CITEseq.ipynb

#ambient_profile = pd.read_pickle('../data/CITEseq_PBMCs_5k_ADT_ambient_profile.pickle')

Thank you,
Diego

Hi Caibin,

Could you briefly explain the interpretation of denoised counts given by scAR? I noticed that it returns floats, not counts. How should I then normalise the data? Just log2(x+1) after scaling by library size?

Regards,
Mikhael

Dear Caibin,

I encountered an error upon calling the train() method. Below is the abridged

scar_obj.train(epochs=400, batch_size=256,)

..Running VAE using the following param set:
......scAR mode:  scRNAseq
......count model:  binomial
......num_input_feature:  15604
......NN_layer1:  150
......NN_layer2:  100
......latent_space:  15
......dropout_prob:  0
......kld_weight:  1e-05
......lr:  0.001
......lr_step_size:  5
......lr_gamma:  0.97
===========================================
  Training.....
  0%|          | 0/400 [00:00<?, ?it/s]
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [12], in <module>
----> 1 scar_obj.train(epochs=400, batch_size=256,)

File /scAR/lib/python3.8/site-packages/torch/distributions/distribution.py:55, in Distribution.__init__(self, batch_shape, event_shape, validate_args)
     53 valid = constraint.check(value)
     54 if not valid.all():
---> 55     raise ValueError(
     56         f"Expected parameter {param} "
     57         f"({type(value).__name__} of shape {tuple(value.shape)}) "
     58         f"of distribution {repr(self)} "
     59         f"to satisfy the constraint {repr(constraint)}, "
     60         f"but found invalid values:\n{value}"
     61     )
     62 if not constraint.check(getattr(self, param)).all():
     63     raise ValueError("The parameter {} has invalid values".format(param))

ValueError: Expected parameter loc (Tensor of shape (256, 15)) of distribution Normal(loc: torch.Size([256, 15]), scale: torch.Size([256, 15])) to satisfy the constraint Real(), but found invalid values:
tensor([[nan, nan, nan,  ..., nan, nan, nan],
        [nan, nan, nan,  ..., nan, nan, nan],
        [nan, nan, nan,  ..., nan, nan, nan],
        ...,
        [nan, nan, nan,  ..., nan, nan, nan],
        [nan, nan, nan,  ..., nan, nan, nan],
        [nan, nan, nan,  ..., nan, nan, nan]], device='cuda:0',
       grad_fn=<AddmmBackward0>)

I have also tried running scAR on my CITEseq data and at least so far the model is training. Perhaps there's something wrong with my RNA count matrix, which I feel quite unlikely.

I am happy to provide further information should you need it. Thanks in advance.

Regards,
Mikhael