Parameters in training model for integrating datasets with scVI in R

joweihsieh · March 1, 2025, 8:00am

Thanks for developing this tool!!

I was trying to use scVI to integrate my datasets. Following the instructions (Integrating datasets with scVI in R — scvi-tools), I was able to run the script successfully without changing any parameters in the training model. My next step was trying to change some parameters in the training model, but I encountered errors. Could you please help me resolve these issues? Thanks!

============

model ← scvi$model$SCVI(adata_5_in_1, n_latent = 5)

Error in py_call_impl(callable, call_args$unnamed, call_args$named) :
TypeError: empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType), but expected one of:

(tuple of ints size, *, tuple of names names, torch.memory_format memory_format = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False)
(tuple of ints size, *, torch.memory_format memory_format = None, Tensor out = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False)

reticulate::py_last_error()

── Python Exception Message ──────────────────────────────────────────────────────────────────────────────────────
Traceback (most recent call last):
File “/home/f06b22037/SSD2/utility/miniconda3/envs/scvi-env/lib/python3.12/site-packages/scvi/model/_scvi.py”, line 162, in init
self.module = self._module_cls(
^^^^^^^^^^^^^^^^^
File “/home/f06b22037/SSD2/utility/miniconda3/envs/scvi-env/lib/python3.12/site-packages/scvi/module/_vae.py”, line 235, in init
self.z_encoder = Encoder(
^^^^^^^^
File “/home/f06b22037/SSD2/utility/miniconda3/envs/scvi-env/lib/python3.12/site-packages/scvi/nn/_base_components.py”, line 260, in init
self.mean_encoder = nn.Linear(n_hidden, n_output)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/home/f06b22037/SSD2/utility/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/nn/modules/linear.py”, line 106, in init
torch.empty((out_features, in_features), **factory_kwargs)
TypeError: empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType), but expected one of:

(tuple of ints size, *, tuple of names names, torch.memory_format memory_format = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False)
(tuple of ints size, *, torch.memory_format memory_format = None, Tensor out = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False)

── R Traceback ───────────────────────────────────────────────────────────────────────────────────────────────────
▆

└─scvi$model$SCVI(adata_5_in_1, n_latent = 5)
└─reticulate:::py_call_impl(callable, call_args$unnamed, call_args$named)
See reticulate::py_last_error()$r_trace$full_call for more details.

cane11 · March 1, 2025, 8:14am

Hi, I assume reticulate has issues interpreting 5. Can you try:

n_latent_value <- as.integer(5)
model <- scvi$model$SCVI(adata_5_in_1, n_latent = n_latent_value)

joweihsieh · March 1, 2025, 7:51pm

Hi,

n_latent_value ← as.integer(5)
model ← scvi$model$SCVI$create(adata_5_in_1, n_latent = n_latent_value)

I tried but still have errors.

Error in py_get_attr(x, name) :
AttributeError: type object ‘SCVI’ has no attribute ‘create’
Run reticulate::py_last_error() for details.

reticulate::py_last_error()

── Python Exception Message ──────────────────────────────────────────────────────────────────────────────────────
AttributeError: type object ‘SCVI’ has no attribute ‘create’

── R Traceback ───────────────────────────────────────────────────────────────────────────────────────────────────
▆

├─scvi$model$SCVI$create
└─reticulate:::$.python.builtin.object(scvi$model$SCVI, create)
└─reticulate:::py_get_attr_or_item(x, name, TRUE)
```
└─reticulate::py_get_attr(x, name)
```

See reticulate::py_last_error()$r_trace$full_call for more details.

── Python Exception Message ──────────────────────────────────────────────────────────────────────────────────────
AttributeError: type object ‘SCVI’ has no attribute ‘create’

── R Traceback ───────────────────────────────────────────────────────────────────────────────────────────────────
▆

├─scvi$model$SCVI$create
└─reticulate:::$.python.builtin.object(scvi$model$SCVI, create)
└─reticulate:::py_get_attr_or_item(x, name, TRUE)
```
└─reticulate::py_get_attr(x, name)
```

See reticulate::py_last_error()$r_trace$full_call for more details.

reticulate::py_last_error()$r_trace$full_call
[[1]]
scvi$model$SCVI$create

[[2]]
$.python.builtin.object(scvi$model$SCVI, create)

[[3]]
py_get_attr_or_item(x, name, TRUE)

[[4]]
py_get_attr(x, name)

cane11 · March 1, 2025, 8:09pm

See edit above. Sorry for the typo.

joweihsieh · March 1, 2025, 8:21pm

It works!! Thank you!!

joweihsieh · March 2, 2025, 11:30pm

Could you please share some suggestions on which parameters we can adjust to enhance the integration performance? I am planning to try n_hidden, n_layers and n_latent_value.

Thanks!!

ori-kron-wis · March 3, 2025, 8:29am

Hi,
Practically all model/training parameters are open for tune and can affect the integration performance. Also the selection of batch key is a crucial factor of course. You can use our autotune to try to find an optimal set of parameters, check our documentation in the subject.

joweihsieh · March 5, 2025, 8:04am

Hi,

I would like to use GPU to speed up the process. I got some errors…It seems to result from PyTorch and CUDA so I tried to re-install PyTorch. But it still failed…
Just wonder if you have any idea? Thanks!!!

========

Sys.setenv(CUDA_VISIBLE_DEVICES = “1”)
torch$cuda$is_available()
[1] TRUE
scvi$model$SCVI$setup_anndata(adata_5_in_1, batch_key = “batch”)
model ← scvi$model$SCVI(adata_5_in_1)
model$train(accelerator=“gpu”)
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
Error in py_call_impl(callable, call_args$unnamed, call_args$named) :
torch.cuda.DeferredCudaCallError: CUDA call failed lazily at initialization with error: device >= 0 && device < num_gpus INTERNAL ASSERT FAILED at “…/aten/src/ATen/cuda/CUDAContext.cpp”:49, please report a bug to PyTorch. device=1, num_gpus=

<…truncated…> 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 264, in
_lazy_call(_check_capability)
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 261, in _lazy_call
_queued_calls.append((callable, traceback.format_stack()))

Run reticulate::py_last_error() for details.

── Python Exception Message ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Traceback (most recent call last):
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 332, in _lazy_init
queued_call()
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 200, in _check_capability
capability = get_device_capability(d)
^^^^^^^^^^^^^^^^^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 509, in get_device_capability
prop = get_device_properties(device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 527, in get_device_properties
return _get_device_properties(device) # type: ignore[name-defined]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: device >= 0 && device < num_gpus INTERNAL ASSERT FAILED at “…/aten/src/ATen/cuda/CUDAContext.cpp”:49, please report a bug to PyTorch. device=1, num_gpus=

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/scvi/model/base/_training_mixin.py”, line 161, in train
return runner()
^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/scvi/train/_trainrunner.py”, line 96, in call
self.trainer.fit(self.training_plan, self.data_splitter)
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/scvi/train/_trainer.py”, line 210, in fit
super().fit(*args, **kwargs)
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/pytorch/trainer/trainer.py”, line 539, in fit
call._call_and_handle_interrupt(
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/pytorch/trainer/call.py”, line 47, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/pytorch/trainer/trainer.py”, line 575, in _fit_impl
self._run(model, ckpt_path=ckpt_path)
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/pytorch/trainer/trainer.py”, line 938, in _run
self.strategy.setup_environment()
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/pytorch/strategies/strategy.py”, line 129, in setup_environment
self.accelerator.setup_device(self.root_device)
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/pytorch/accelerators/cuda.py”, line 46, in setup_device
_check_cuda_matmul_precision(device)
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/fabric/accelerators/cuda.py”, line 161, in _check_cuda_matmul_precision
if not torch.cuda.is_available() or not _is_ampere_or_later(device):
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/lightning/fabric/accelerators/cuda.py”, line 155, in _is_ampere_or_later
major, _ = torch.cuda.get_device_capability(device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 509, in get_device_capability
prop = get_device_properties(device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 523, in get_device_properties
_lazy_init() # will define _get_device_properties
^^^^^^^^^^^^
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 338, in _lazy_init
raise DeferredCudaCallError(msg) from e
torch.cuda.DeferredCudaCallError: CUDA call failed lazily at initialization with error: device >= 0 && device < num_gpus INTERNAL ASSERT FAILED at “…/aten/src/ATen/cuda/CUDAContext.cpp”:49, please report a bug to PyTorch. device=1, num_gpus=

CUDA call was originally invoked at:

File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/anndata/init.py”, line 39, in
from .io import read_h5ad, read_zarr
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/anndata/io.py”, line 7, in
from ._io.h5ad import read_h5ad, write_h5ad
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/anndata/_io/h5ad.py”, line 25, in
from …experimental import read_dispatched
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/anndata/experimental/init.py”, line 12, in
from .pytorch import AnnLoader
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/anndata/experimental/pytorch/init.py”, line 3, in
from ._annloader import AnnLoader
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/anndata/experimental/pytorch/_annloader.py”, line 19, in
import torch
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/init.py”, line 1954, in
_C._initExtension(_manager_path())
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 122, in _find_and_load_hook
return _run_hook(name, _hook)
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 96, in _run_hook
module = hook()
File “/home/guest001/miniconda3/envs/scvi-env/lib/R/library/reticulate/python/rpytools/loader.py”, line 120, in _hook
return find_and_load(name, import)
File “”, line 1360, in _find_and_load
File “”, line 1331, in _find_and_load_unlocked
File “”, line 935, in _load_unlocked
File “”, line 999, in exec_module
File “”, line 488, in _call_with_frames_removed
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 264, in
_lazy_call(_check_capability)
File “/home/guest001/miniconda3/envs/scvi-env/lib/python3.12/site-packages/torch/cuda/init.py”, line 261, in _lazy_call
_queued_calls.append((callable, traceback.format_stack()))

── R Traceback ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
▆

└─model$train(accelerator = “gpu”)
└─reticulate:::py_call_impl(callable, call_args$unnamed, call_args$named)
See reticulate::py_last_error()$r_trace$full_call for more details.

=============
Here is my GPU information:

±----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 3725 G /usr/lib/xorg/Xorg 4MiB |
| 0 N/A N/A 6867 C dorado_basecall_server 910MiB |
| 0 N/A N/A 1438629 C guppy_basecaller 6542MiB |
| 1 N/A N/A 3725 G /usr/lib/xorg/Xorg 12MiB |
| 1 N/A N/A 5471 G /usr/bin/gnome-shell 2MiB |
| 1 N/A N/A 6867 C dorado_basecall_server 40MiB |
±----------------------------------------------------------------------------------------+
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2025 NVIDIA Corporation
Built on Wed_Jan_15_19:20:09_PST_2025
Cuda compilation tools, release 12.8, V12.8.61
Build cuda_12.8.r12.8/compiler.35404655_0

======== re-installation
pip uninstall torch torchvision torchaudio -y
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

ori-kron-wis · March 5, 2025, 8:18am

kinda hard for me to understand whats going on.
I do see some anndata related messages.

My suggestion to you is to: create a new clean environment, install scvi-tools v1.3 on python 3.12 backend & make sure you can run code (any simple code, not scvi) on the GPU, given this torch + cuda settings you have in your R env, then move to try to run a scvi code, and start from a very basic dummy test.

does the same code trains on the cpu? so we will know there no data issues

joweihsieh · March 5, 2025, 8:30am

Yes! The data is able to be trained on cpu.

scvi$model$SCVI$setup_anndata(adata_5_in_1, batch_key = “batch”)
model ← scvi$model$SCVI(adata_5_in_1)
model$train()

joweihsieh · March 5, 2025, 9:41am

Thanks for the suggestions!!! It works!!

joweihsieh · March 7, 2025, 7:44am

Hi,

I tried running the autotune method you suggested, but I couldn’t get it to work.

=== Here is my script ===

Import the necessary Python modules

scvi ← import(“scvi”)
scvi_data ← import(“scvi.data”) # Import scvi.data for datasets
torch ← import(“torch”)
anndata ← import(“anndata”)
tune ← import(“ray.tune”)
ray ← import(“ray”)

adata_5_in_1 ← anndata$read_h5ad(“adata_5_in_1.h5ad”)

py$adata_5_in_1 ← adata_5_in_1

py_run_string("
from scvi.model import SCVI
from ray import tune

SCVI.setup_anndata(adata_5_in_1, batch_key=‘batch’)

def train_scvi(config):
model = SCVI(
adata_5_in_1,
n_hidden=config[‘n_hidden’],
n_layers=config[‘n_layers’],
n_latent=config[‘n_latent’],
gene_likelihood=config[‘gene_likelihood’]
)
model.train(max_epochs=100, plan_kwargs={‘lr’: config[‘lr’]})
return {‘elbo’: model.get_elbo()}

search_space = {
‘n_hidden’: tune.choice([64, 128, 256]),
‘n_layers’: tune.choice([1, 2, 3, 4]),
‘n_latent’: tune.choice([5, 10, 20, 30, 40, 50]),
‘gene_likelihood’: tune.choice([‘nb’, ‘zinb’]),
‘lr’: tune.loguniform(1e-4, 1e-2)
}

analysis = tune.run(
train_scvi,
config=search_space,
num_samples=20, # Number of trials
metric=‘elbo’,
mode=‘min’
)

best_params = analysis.best_config

ray.shutdown()
")

=== Here are the errors ====

▆

└─reticulate::py_run_string(“\nanalysis = tune.run(\n train_scvi,\n config=search_space,\n num_samples=5, # Reduce number of trials\n metric=‘elbo’,\n mode=‘min’\n)\n”)
└─reticulate:::py_run_string_impl(code, local, convert)
See reticulate::py_last_error()$r_trace$full_call for more details.

=== Then I tried some basic things and they are all good ===

#ray stop
#ray start --head --num-cpus=50 --num-gpus=1

py_run_string("
import os
import ray

ray.shutdown()

os.environ[‘CUDA_VISIBLE_DEVICES’] = ‘1’

ray.init(address=‘auto’)
print(ray.is_initialized())
")

Test Training a Single SCVI Model

py_run_string("
from scvi.model import SCVI

print(type(adata_5_in_1))

SCVI.setup_anndata(adata_5_in_1, batch_key=‘batch’)

model = SCVI(
adata_5_in_1,
n_hidden=128,
n_layers=2,
n_latent=20,
gene_likelihood=‘nb’
)
model.train(max_epochs=10, plan_kwargs={‘lr’: 0.001})
print(‘Model trained successfully’)
")

cane11 · March 7, 2025, 8:00am

Hi, could you train directly in Python? This would make the error log much simpler and avoid some errors like wrong type setting that come with reticulate.

ori-kron-wis · March 9, 2025, 12:36pm

hey @joweihsieh
I agree to try to run this directly on python, especially also because in the R code you run most of it in python code…

In any case, using scvi-tools 1.3v, we run the autotune code a bit different now. For example this was working for me in R env (just replace to your adata):

library(reticulate)
options(reticulate.verbose = TRUE)
py_module_available('scvi')
scvi <- import('scvi')
ray <- import('ray')

adata <- scvi$data$synthetic_iid()

py$adata <- adata

py_run_string("
from scvi.model import SCVI
from ray import tune
from scvi.data import synthetic_iid
from scvi.autotune import run_autotune

SCVI.setup_anndata(adata)

experiment = run_autotune(
  SCVI,
  adata,
  metrics=['elbo_validation'],
  mode='min',
  search_space={
    'model_params': {
      'n_hidden': tune.choice([64, 128, 256]),
      'n_layers': tune.choice([1, 2, 3, 4]),
      'n_latent': tune.choice([5, 10, 20, 30, 40, 50]),
      'gene_likelihood': tune.choice(['nb', 'zinb']),
    },
    'train_params': {
      'max_epochs': 100,
      'plan_kwargs': {'lr': tune.loguniform(1e-4, 1e-2)}
    },
  },
  num_samples=20,
  seed=0,
  scheduler='asha',
  searcher='hyperopt',
  ignore_reinit_error=True,
)
")

Topic		Replies	Views
Error when using scVI.model.train scvi-tools integration	2	114	August 19, 2024
Error in py_call_impl(callable, call_args$unnamed, call_args$named) scvi-tools	0	248	June 24, 2024
Getting the parameters and their names of scVI scvi-tools scvi	3	392	November 27, 2024
AttributeError: 'SCVI' object has no attribute 'named_parameters' scvi-tools scvi	1	461	October 15, 2022
Error when training model on M3 Max MPS scvi-tools	5	978	February 16, 2024

Parameters in training model for integrating datasets with scVI in R

I tried but still have errors.

=== Here is my script ===

Import the necessary Python modules

=== Here are the errors ====

=== Then I tried some basic things and they are all good ===

Test Training a Single SCVI Model

Related topics