SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910155547869184 |
|---|---|
| author | Fu, Rong Qi, Muge Li, Yang Jin, Yabin Wu, Jiekai Lu, Jiaxuan Meng, Chunlei Wang, Youjin Su, Zeli Gao, Juntao Bao, Li Zhao, Qi Luo, Wei Fong, Simon |
| author_facet | Fu, Rong Qi, Muge Li, Yang Jin, Yabin Wu, Jiekai Lu, Jiaxuan Meng, Chunlei Wang, Youjin Su, Zeli Gao, Juntao Bao, Li Zhao, Qi Luo, Wei Fong, Simon |
| contents | Repertoire-level analysis of T cell receptors offers a biologically grounded signal for disease detection and immune monitoring, yet practical deployment is impeded by label sparsity, cohort heterogeneity, and the computational burden of adapting large encoders to new tasks. We introduce a framework that synthesizes compact task-specific parameterizations from a learned dictionary of prototypes conditioned on lightweight task descriptors derived from repertoire probes and pooled embedding statistics. This synthesis produces small adapter modules applied to a frozen pretrained backbone, enabling immediate adaptation to novel tasks with only a handful of support examples and without full model fine-tuning. The architecture preserves interpretability through motif-aware probes and a calibrated motif discovery pipeline that links predictive decisions to sequence-level signals. Together, these components yield a practical, sample-efficient, and interpretable pathway for translating repertoire-informed models into diverse clinical and research settings where labeled data are scarce and computational resources are constrained. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01051 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes Fu, Rong Qi, Muge Li, Yang Jin, Yabin Wu, Jiekai Lu, Jiaxuan Meng, Chunlei Wang, Youjin Su, Zeli Gao, Juntao Bao, Li Zhao, Qi Luo, Wei Fong, Simon Machine Learning Repertoire-level analysis of T cell receptors offers a biologically grounded signal for disease detection and immune monitoring, yet practical deployment is impeded by label sparsity, cohort heterogeneity, and the computational burden of adapting large encoders to new tasks. We introduce a framework that synthesizes compact task-specific parameterizations from a learned dictionary of prototypes conditioned on lightweight task descriptors derived from repertoire probes and pooled embedding statistics. This synthesis produces small adapter modules applied to a frozen pretrained backbone, enabling immediate adaptation to novel tasks with only a handful of support examples and without full model fine-tuning. The architecture preserves interpretability through motif-aware probes and a calibrated motif discovery pipeline that links predictive decisions to sequence-level signals. Together, these components yield a practical, sample-efficient, and interpretable pathway for translating repertoire-informed models into diverse clinical and research settings where labeled data are scarce and computational resources are constrained. |
| title | SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.01051 |