error in running scanvi integration

[olhakholod]

Hello!

I have followed the documentation and tried to run the test dataset through scib-pipeline. I have followed these steps:

########## scib-pipeline

# GENERATE TEST DATA
# Navigate to data directory
cd Desktop/scib-pipeline-main/data

# Execute code within data directory. It will output adata_norm.h5ad file
python3 generate_data.py 

# GENERATE OUTPUT FILE adata_pre.h5ad BASED ON adata_norm.h5ad
# Navigate to this path
/Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/prepare/unscaled/full_feature

# Run the script
python3 /Users/f006qpk/Desktop/scib-pipeline-main/scripts/preprocessing/runPP.py -i /Users/f006qpk/Desktop/scib-pipeline-main/data/adata_norm.h5ad -o /Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/prepare/unscaled/full_feature/adata_pre.h5ad -b batch --hvgs 0

# INTEGRATION STEP
# Navigate to this path
/Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/integration/unscaled/full_feature 

# Run the integration script
python3 /Users/f006qpk/Desktop/scib-pipeline-main/scripts/integration/runIntegration.py -i /Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/prepare/unscaled/full_feature/adata_pre.h5ad  -o /Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/integration/unscaled/full_feature/combat.h5ad -b batch --method combat

# GENERATE EMBEDDINGS
# Navigate to this path
/Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/embeddings/unscaled/full_feature 

# Run the embeddings script
python3 /Users/f006qpk/Desktop/scib-pipeline-main/scripts/visualization/save_embeddings.py --input /Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/integration/unscaled/full_feature/combat.h5ad --outfile /Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/embeddings/unscaled/full_feature/combat_full.csv --method combat --batch_key batch             --label_key celltype --result full

# scanvi 
# Navigate to this path
/Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/integration/unscaled/full_feature 

When I tried to run scanvi on my local machine
python3 /Users/f006qpk/Desktop/scib-pipeline-main/scripts/integration/runIntegration.py -i /Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/prepare/unscaled/full_feature/adata_pre.h5ad -o /Users/f006qpk/Desktop/scib-pipeline-main/data/test_data_r4/integration/unscaled/full_feature/scanvi.h5ad -b batch --method scanvi -c celltype

I have received the following error message:

Traceback (most recent call last):
  File "/Users/f006qpk/Desktop/scib-pipeline-main/scripts/integration/runIntegration.py", line 67, in <module>
    runIntegration(file, out, run, hvg, batch, celltype)
  File "/Users/f006qpk/Desktop/scib-pipeline-main/scripts/integration/runIntegration.py", line 22, in runIntegration
    integrated = method(adata, batch, celltype)
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/scib/integration.py", line 299, in scanvi
    vae = scvi(adata, batch, hvg, return_model=True, max_epochs=n_epochs_scVI)
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/scib/integration.py", line 261, in scvi
    vae.train(**train_kwargs)
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/scvi/model/base/_training_mixin.py", line 78, in train
    runner = self._train_runner_cls(
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/scvi/train/_trainrunner.py", line 85, in __init__
    self.trainer = self._trainer_cls(
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/scvi/train/_trainer.py", line 139, in __init__
    super().__init__(
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/lightning/pytorch/utilities/argparse.py", line 69, in insert_env_defaults
    return fn(self, **kwargs)
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 393, in __init__
    self._accelerator_connector = _AcceleratorConnector(
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/lightning/pytorch/trainer/connectors/accelerator_connector.py", line 157, in __init__
    self._set_parallel_devices_and_init_accelerator()
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/lightning/pytorch/trainer/connectors/accelerator_connector.py", line 391, in _set_parallel_devices_and_init_accelerator
    self._devices_flag = accelerator_cls.parse_devices(self._devices_flag)
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/lightning/pytorch/accelerators/cpu.py", line 47, in parse_devices
    devices = _parse_cpu_cores(devices)
  File "/Users/f006qpk/mambaforge/lib/python3.10/site-packages/lightning/fabric/accelerators/cpu.py", line 85, in _parse_cpu_cores
    raise TypeError("`devices` selected with `CPUAccelerator` should be an int > 0.")
TypeError: `devices` selected with `CPUAccelerator` should be an int > 0.

I was wondering if it's because I'm running the analysis on M2 MacBook Pro.

Thank you for your help!

Olha