SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework

TL;DR

SubQuad is a scalable, bias-aware pipeline for immune repertoire analysis that reduces computational costs and improves minority subgroup detection using innovative indexing, fusion, and fairness techniques.

Contribution

It introduces a near-quadratic retrieval method with adaptive weighting and fairness constraints, enabling efficient and equitable immune repertoire analysis.

Findings

Achieves near-subquadratic retrieval with GPU acceleration.

Improves recall@k, cluster purity, and subgroup equity on large datasets.

Reduces memory usage and increases throughput in repertoire mining.

Abstract

Comparative analysis of adaptive immune repertoires at population scale is hampered by two practical bottlenecks: the near-quadratic cost of pairwise affinity evaluations and dataset imbalances that obscure clinically important minority clonotypes. We introduce SubQuad, an end-to-end pipeline that addresses these challenges by combining antigen-aware, near-subquadratic retrieval with GPU-accelerated affinity kernels, learned multimodal fusion, and fairness-constrained clustering. The system employs compact MinHash prefiltering to sharply reduce candidate comparisons, a differentiable gating module that adaptively weights complementary alignment and embedding channels on a per-pair basis, and an automated calibration routine that enforces proportional representation of rare antigen-specific subgroups. On large viral and tumor repertoires SubQuad achieves measured gains in throughput and peak memory usage while preserving or improving recall@k, cluster purity, and subgroup equity. By co-designing indexing, similarity fusion, and equity-aware objectives, SubQuad offers a scalable, bias-aware platform for repertoire mining and downstream translational tasks such as vaccine target prioritization and biomarker discovery.