Exception on motif enrichment analysis

[Mitmischer]

Describe the bug
I'm currently preparing a motif enrichment analysis. Preliminarily, I wanted to test the enrichment on just a single gene, but the program terminates prematurely.

To Reproduce
Steps to reproduce the behavior:

$ gimme motifs IFIH1.fasta -p consensus_pwms_stripped.jaspar gimme_out -g Homo_sapiens.GRCh38.dna_sm.primary_assembly.fa -f 0.99 --known -N 36

IFIH1.fasta and consensus_pwms_stripped.jaspar are attached: consensus_pwms_stripped.zip
IFIH1.zip
Homo_sapiens.GRCh38.dna_sm.primary_assembly.fa can be downloaded from
here.

Expected behavior
I expected the program to run in full or to provide a concise error message.

Error logs

2024-03-15 15:58:49,937 - WARNING - Will use the sequences from the FASTA input. If size is specified, this will be ignored.
2024-03-15 15:58:49,938 - INFO - creating background (matched GC%)
2024-03-15 16:00:17,614 - INFO - creating motif scan tables
Scanning: 100%|████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 20.18 sequences/s]Scanning: 100%|████████████████████████████████████████████████████████████████████████| 9992/9992 [00:01<00:00, 7159.13 sequences/s]
2024-03-15 16:00:20,133 - INFO - calculating stats
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: The least populated class in y has only 1 members, which is less than n_splits=5.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: FitFailedWarning:
1 fits failed out of a total of 5.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
1 fits failed with the following error:
Traceback (most recent call last):
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 895, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/base.py", line 1474, in wrapper
    return fit_method(estimator, *args, **kwargs)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py", line 1221, in fit
    self.coef_, self.intercept_, self.n_iter_ = _fit_liblinear(
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/svm/_base.py", line 1174, in _fit_liblinear
    raise ValueError(
ValueError: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0.0

  _warn(*args, **kwargs)
2024-03-15 16:00:22,278 - INFO - selecting non-redundant motifs
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: The least populated class in y has only 1 members, which is less than n_splits=5.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: FitFailedWarning:
1 fits failed out of a total of 5.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
1 fits failed with the following error:
Traceback (most recent call last):
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 895, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/base.py", line 1474, in wrapper
    return fit_method(estimator, *args, **kwargs)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py", line 1221, in fit
    self.coef_, self.intercept_, self.n_iter_ = _fit_liblinear(
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/svm/_base.py", line 1174, in _fit_liblinear
    raise ValueError(
ValueError: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0.0

  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: The least populated class in y has only 1 members, which is less than n_splits=5.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: FitFailedWarning:
1 fits failed out of a total of 5.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
1 fits failed with the following error:
Traceback (most recent call last):
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 895, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/base.py", line 1474, in wrapper
    return fit_method(estimator, *args, **kwargs)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py", line 1221, in fit
    self.coef_, self.intercept_, self.n_iter_ = _fit_liblinear(
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/svm/_base.py", line 1174, in _fit_liblinear
    raise ValueError(
ValueError: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0.0

  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: The least populated class in y has only 1 members, which is less than n_splits=5.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: FitFailedWarning:
1 fits failed out of a total of 5.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
1 fits failed with the following error:
Traceback (most recent call last):
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 895, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/base.py", line 1474, in wrapper
    return fit_method(estimator, *args, **kwargs)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py", line 1221, in fit
    self.coef_, self.intercept_, self.n_iter_ = _fit_liblinear(
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/svm/_base.py", line 1174, in _fit_liblinear
    raise ValueError(
ValueError: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0.0

  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: The least populated class in y has only 1 members, which is less than n_splits=5.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: FitFailedWarning:
1 fits failed out of a total of 5.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
1 fits failed with the following error:
Traceback (most recent call last):
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 895, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/base.py", line 1474, in wrapper
    return fit_method(estimator, *args, **kwargs)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py", line 1221, in fit
    self.coef_, self.intercept_, self.n_iter_ = _fit_liblinear(
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/svm/_base.py", line 1174, in _fit_liblinear
    raise ValueError(
ValueError: This solver needs samples of at least 2 classes in the data, but the data contains only one class: 0.0

  _warn(*args, **kwargs)
/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/__init__.py:30: UserWarning: No positive class found in y_true, recall is set to one for all thresholds.
  _warn(*args, **kwargs)
Traceback (most recent call last):
  File "/home/mabe/.conda/envs/mabe/bin/gimme", line 12, in <module>
    cli(sys.argv[1:])
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/cli.py", line 755, in cli
    args.func(args)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/commands/motifs.py", line 240, in motifs
    nr_motifs = select_nonredundant_motifs(
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/gimmemotifs/comparison.py", line 944, in select_nonredundant_motifs
    roc_auc = roc_auc_score(y_test, y_pred)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/utils/_param_validation.py", line 213, in wrapper
    return func(*args, **kwargs)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/metrics/_ranking.py", line 640, in roc_auc_score
    return _average_binary_score(
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/metrics/_base.py", line 75, in _average_binary_score
    return binary_metric(y_true, y_score, sample_weight=sample_weight)
  File "/home/mabe/.conda/envs/mabe/lib/python3.10/site-packages/sklearn/metrics/_ranking.py", line 382, in _binary_roc_auc_score
    raise ValueError(
ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.

Installation information (please complete the following information):

• OS: [Ubuntu 22.04.4 LTS]
• Installation [conda]
• Version [0.18.0]

Additional context
As I am new to the software, this might as well be an error on my side. Still, I think that the error message should be better!