ValueError: Input contains infinity or a value too large for dtype('float32').

[chenjy327]

Hi Kevin

There was a bug when I tried to use 'scaden process':

INFO Scaling using log_min_max functions.py:65
Traceback (most recent call last):
File "/data/software/Python-3.8.5/bin/scaden", line 8, in
sys.exit(main())
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/scaden/main.py", line 48, in main
cli()
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/click/core.py", line 829, in call
return self.main(*args, **kwargs)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/click/core.py", line 782, in main
rv = self.invoke(ctx)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/click/core.py", line 1259, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/click/core.py", line 1066, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/click/core.py", line 610, in invoke
return callback(*args, **kwargs)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/scaden/main.py", line 155, in process
processing(
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/scaden/process.py", line 35, in processing
preprocess_h5ad_data(raw_input_path=training_data,
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/scaden/model/functions.py", line 67, in preprocess_h5ad_data
raw_input.X = sample_scaling(raw_input.X, scaling_option)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/scaden/model/functions.py", line 42, in sample_scaling
x = mms.fit_transform(x.T).T
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/sklearn/base.py", line 699, in fit_transform
return self.fit(X, **fit_params).transform(X)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/sklearn/preprocessing/_data.py", line 363, in fit
return self.partial_fit(X, y)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/sklearn/preprocessing/_data.py", line 396, in partial_fit
X = self._validate_data(X, reset=first_pass,
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/sklearn/base.py", line 421, in _validate_data
X = check_array(X, **check_params)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/sklearn/utils/validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/sklearn/utils/validation.py", line 663, in check_array
_assert_all_finite(array,
File "/data/software/Python-3.8.5/lib/python3.8/site-packages/sklearn/utils/validation.py", line 103, in _assert_all_finite
raise ValueError(
ValueError: Input contains infinity or a value too large for dtype('float32').

After that I checked the simulated data (data.h5ad) and found the 'inf' value in the simulated data.

May I have your suggestion on this issue? Thanks a lot!

Jianyu

[KevinMenden]

Hi @chenjy327 ,

are you using the latest version of Scaden? This sounds like a bug that was already solved.
If you're using the latest version, what steps have you been following? Is this reproducible when simulating again?

Sorry for the late reply by the way!
Cheers,
Kevin

[jadonWong]

HI Kevin,
I have the same problem，the version is scaden, version 1.1.1
steps as follow:

1. generate three data set "sclc_counts.txt, sclc_bulk_data.txt, sclc_celltypes.txt" from raw counts matrix; didn't apply any transform or normalize, just intersect genes between bulk and scRNA；
2. run scaden simulate to generate data.h5ad;
3. run scaden process , but i got this problem?

any suggestion? thank you very much!

[jadonWong]

HI Kevin, I have the same problem，the version is scaden, version 1.1.1 steps as follow:

1. generate three data set "sclc_counts.txt, sclc_bulk_data.txt, sclc_celltypes.txt" from raw counts matrix; didn't apply any transform or normalize, just intersect genes between bulk and scRNA；
2. run scaden simulate to generate data.h5ad;
3. run scaden process , but i got this problem?

any suggestion? thank you very much!

I solved this problem by update scaden to version 1.1.2 !!