AI RESEARCHarXiv8d ago

Macrophage signature-based prediction of cancer treatment response using MIL-attention

Madgwick · M. · Witham · S. · Occhetta · M. · Haneklaus · M. · +6 more

Abstract

Predicting immunotherapy response from single-cell data remains difficult due to patient-level labels, extreme class imbalance, and highly heterogeneous macrophage states. We present a Multiple Instance Learning (MIL) framework that treats each patient as a bag of macrophage embeddings derived from a single-cell RNA foundation model. The architecture incorporates an attention-based pooling mechanism with reduced model complexity, dropout-enhanced regularization and explicit attention penalties t

Discussion · 0

Sign in to join the discussion.