解码表型：融合基因组语言模型与神经成像的框架

中文摘要 AI 辅助

神经成像与基因检测是神经系统疾病的两项重要临床参考，可提供互补的诊断信息。然而，由于跨模态异质性，将基因组与神经成像数据整合以实现精准疾病诊断颇具挑战。现有成像-遗传学方法主要将遗传信息编码为硬编码标签，丢失了疾病相关变异周围的局部序列上下文。为解决这一局限，我们提出GeneFuse，一种多模态学习框架，用于对齐预训练基因组语言模型（Genomic Language Models, GLMs）生成的遗传表征与从图像中提取的特征。GeneFuse包含两个组件：（1）基因型条件特征调制（Genotype-Conditioned Feature Modulation, GCFM），一种受FiLM启发的模块，利用基因嵌入调制图像特征图；（2）不确定性感知基因组残差融合（Uncertainty-aware Genomic Residual Fusion, U-GRF），一种融合策略，利用成像衍生的预测不确定性来调控基因型特征的贡献。我们在早期认知衰退识别（正常对照NC vs.轻度认知障碍MCI）和痴呆筛查（NC vs.阿尔茨海默病AD）任务上评估GeneFuse。在以APOE为中心的设置中，GeneFuse分别获得0.77和0.83的AUROC值，优于现有成像-遗传学融合方法。这些结果表明，GLM衍生的遗传嵌入可为成像提供补充信息。

英文摘要

Neuroimaging and genetic testing are two important clinical references for nervous system diseases, offering complementary diagnostic information. However, integrating genomic and neuroimaging data for precise disease diagnosis is challenging due to cross-modality heterogeneity. Existing imaging-genetics approaches mainly encode genetic information as hard-coded labels, which lose the local sequence context around disease-associated variants. To address this limitation, we propose GeneFuse, a multimodal learning framework that aligns genetic representations from pre-trained Genomic Language Models (GLMs) with features extracted from images. GeneFuse integrates two components: (1) Genotype-Conditioned Feature Modulation (GCFM), a FiLM-inspired module that uses genomic embeddings to modulate image feature maps; and (2) Uncertainty-aware Genomic Residual Fusion (U-GRF), a fusion strategy that uses imaging-derived predictive uncertainty to gate the contribution of genotypic features. We evaluate GeneFuse on early cognitive decline identification (NC vs. MCI) and dementia screening (NC vs. AD). In the APOE-centered setting, GeneFuse achieves AUROCs of 0.77 and 0.83, outperforming existing imaging-genetics fusion methods. These results indicate that GLM-derived genomic embeddings provide additional information to imaging.

发表机构

• King’s College London（伦敦国王学院）
• Aston University（阿斯顿大学）
• University of Birmingham（伯明翰大学）

机构由 AI 辅助整理，请以论文原文为准。