SpikGPT: A High-Accuracy and Interpretable Spiking Attention Framework for Single-Cell Annotation
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909941640462336 |
|---|---|
| author | Huang, Min Kamaleswaran, Rishikesan |
| author_facet | Huang, Min Kamaleswaran, Rishikesan |
| contents | Accurate and scalable cell type annotation remains a challenge in single-cell transcriptomics, especially when datasets exhibit strong batch effects or contain previously unseen cell populations. Here we introduce SpikGPT, a hybrid deep learning framework that integrates scGPT-derived cell embeddings with a spiking Transformer architecture to achieve efficient and robust annotation. scGPT provides biologically informed dense representations of each cell, which are further processed by a multi-head Spiking Self-Attention mechanism for energy-efficient feature extraction. Across multiple benchmark datasets, SpikGPT consistently matches or exceeds the performance of leading annotation tools. Notably, SpikGPT uniquely identifies unseen cell types by assigning low-confidence predictions to an "Unknown" category, allowing accurate rejection of cell states absent from the training reference. Together, these results demonstrate that SpikGPT is a versatile and reliable annotation tool capable of generalizing across datasets, resolving complex cellular heterogeneity, and facilitating discovery of novel or disease-associated cell populations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SpikGPT: A High-Accuracy and Interpretable Spiking Attention Framework for Single-Cell Annotation Huang, Min Kamaleswaran, Rishikesan Quantitative Methods Genomics Accurate and scalable cell type annotation remains a challenge in single-cell transcriptomics, especially when datasets exhibit strong batch effects or contain previously unseen cell populations. Here we introduce SpikGPT, a hybrid deep learning framework that integrates scGPT-derived cell embeddings with a spiking Transformer architecture to achieve efficient and robust annotation. scGPT provides biologically informed dense representations of each cell, which are further processed by a multi-head Spiking Self-Attention mechanism for energy-efficient feature extraction. Across multiple benchmark datasets, SpikGPT consistently matches or exceeds the performance of leading annotation tools. Notably, SpikGPT uniquely identifies unseen cell types by assigning low-confidence predictions to an "Unknown" category, allowing accurate rejection of cell states absent from the training reference. Together, these results demonstrate that SpikGPT is a versatile and reliable annotation tool capable of generalizing across datasets, resolving complex cellular heterogeneity, and facilitating discovery of novel or disease-associated cell populations. |
| title | SpikGPT: A High-Accuracy and Interpretable Spiking Attention Framework for Single-Cell Annotation |
| topic | Quantitative Methods Genomics |
| url | https://arxiv.org/abs/2512.03286 |