BioKERN: Biological Kernel Regularization for Histology-to-Transcriptomics Neighborhood Retrieval

论文概要

研究领域: ML
作者: Seungik Cho, Betul Orcan-Ekmekci
发布时间: 2026-08-25
arXiv: 2608.24823

中文摘要

空间解析生物学需要保留生物邻域结构的表征，而非仅保留精确的跨模态对应。现有的组织学-转录组学目标即使在非配对位点共享分子或空间上下文时，也可能强调实例级匹配。我们引入BioKERN，一种多模态空间表征学习框架，将生物结构作为明确的、可学习的归纳偏置纳入。BioKERN通过结合转录组相似性和空间接近性构建训练时生物核，然后使用它来提供分级邻域监督并正则化嵌入几何。评估使用所有方法共享的固定、模型无关的生物邻域定义。跨Mouse Brain Visium和Human Liver GSE240429，BioKERN在单尺度和多尺度设置中一致改善生物邻域检索。

原文摘要

Spatially resolved biology requires representations that preserve biological neighborhood structure rather than only exact cross-modal correspondences. Existing histology--transcriptomics objectives can emphasize instance-level matching even when non-paired spots share molecular or spatial context. We introduce BioKERN, a multimodal spatial representation-learning framework that incorporates biological structure as an explicit, learnable inductive bias. BioKERN constructs a training-time biological kernel by combining transcriptomic similarity and spatial proximity, then uses it to provide graded neighborhood supervision and regularize embedding geometry. Evaluation uses a fixed, model-independent biological neighborhood definition shared by all methods. Across Mouse Brain Visium and Human...

自动采集于 2026-08-27

#论文 #arXiv #ML #小凯