SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes

TL;DR

SwiftRepertoire introduces a method for rapid, interpretable immune signature analysis that adapts to new tasks with minimal data by synthesizing compact, task-specific modules from learned prototypes.

Contribution

It presents a novel framework for few-shot immune repertoire analysis using dynamic kernel codes and lightweight adapters, enabling efficient adaptation without full model retraining.

Findings

Enables immediate adaptation to new immune tasks with few examples.

Provides interpretable motif-aware signals linked to sequence-level features.

Achieves practical, sample-efficient immune repertoire analysis.

Abstract

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.