[!TIP]
The MultiMolecule team has confirmed that the provided model and checkpoints are producing the same intermediate representations as the original implementation.
The team releasing scBasset did not write this model card for this model so this model card has been written by the MultiMolecule team.
Model Details
scBasset is a convolutional neural network (CNN) that predicts per-cell chromatin accessibility of a DNA peak sequence. The model consumes a fixed-length 1344 bp one-hot encoded DNA sequence and applies a pre-activation convolution stem, a reducing convolution tower, a pointwise convolution, and a dense bottleneck before a final cell-embedding layer that produces one accessibility logit per single cell.
scBasset uses a pre-activation block layout: each convolution block applies the activation (the sigmoid approximation of GELU, sigmoid(1.702 * x) * x) before the convolution, then batch normalization and max pooling. The dense bottleneck flattens the convolution output in Keras channels-last (length-major) order.
[!IMPORTANT]
The final cell-embedding (dense) layer of scBasset is dataset-specific: it has one row per single cell in the training atlas. The Buenrostro2018 hematopoiesis tutorial dataset distributed by the scBasset authors has 2034 single cells (so num_labels = 2034). A different scBasset dataset would have a different number of cells and a differently sized cell-embedding layer.
The cell-embedding layer is exposed through the shared [SequencePredictionHead][multimolecule.SequencePredictionHead]; the per-cell accessibility task is modeled as a binary problem (problem_type="binary").
Each of the 2034 logits is a per-cell accessibility score for the Buenrostro2018 hematopoiesis atlas.
Interface
Input length: fixed 1344 bp DNA peak window
Output: per-cell accessibility logits (2034 cells in the Buenrostro2018 hematopoiesis atlas; cell count is dataset-specific)
Training Details
scBasset was trained to predict the per-cell chromatin accessibility of DNA peak sequences across a single-cell ATAC-seq atlas.
Training Data
The scBasset model uses the Buenrostro2018 hematopoiesis tutorial model trained on the Buenrostro et al. 2018 single-cell ATAC-seq hematopoiesis dataset (2034 single cells). Each 1344 bp peak is associated with a per-cell binary accessibility vector.
Training Procedure
Pre-training
The model was trained to minimize a per-cell binary cross-entropy loss, comparing its predicted per-cell accessibility probabilities (sigmoid of the cell-embedding logits) against the observed single-cell ATAC-seq accessibility labels.
Optimizer: Adam
Loss: Per-cell binary cross-entropy
Regularization: Batch normalization and dropout
Citation
bibtex
1@article{yuan2022scbasset,
2 author = {Yuan, Han and Kelley, David R.},
3 title = {scBasset: sequence-based modeling of single-cell ATAC-seq using convolutional neural networks},
4 journal = {Nature Methods},
5 volume = 19,
6 number = 9,
7 pages = {1088--1096},
8 year = 2022,
9 publisher = {Nature Publishing Group},
10 doi = {10.1038/s41592-022-01562-8}
11}
[!NOTE]
The artifacts distributed in this repository are part of the MultiMolecule project.
If MultiMolecule supports your research, please cite the MultiMolecule project as follows:
bibtex
1@software{chen_2024_12638419,
2 author = {Chen, Zhiyuan and Zhu, Sophia Y.},
3 title = {MultiMolecule},
4 doi = {10.5281/zenodo.12638419},
5 publisher = {Zenodo},
6 url = {https://doi.org/10.5281/zenodo.12638419},
7 year = 2024,
8 month = may,
9 day = 4
10}
Contact
Please use GitHub issues of MultiMolecule for any questions or comments on the model card.
Please contact the authors of the scBasset paper for questions or comments on the paper/model.
