IsoAlign：基于联合嵌入预测架构的异构体感知DNA-蛋白质对齐
原标题：IsoAlign: Isoform-Aware DNA-Protein Alignment via Joint-Embedding Predictive Architectures
AI 摘要
该论文提出 IsoAlign，一个多模态框架，通过将转录本与其对应的蛋白质异构体对齐，把基因组预训练建立在异构体感知的 DNA-蛋白质对齐之上。它使用两个联合嵌入预测架构（JEPA）：DP-JEPA 通过对比对齐从 DNA 预测蛋白质表示，IM-JEPA 通过掩码蛋白质预测建模同一基因不同异构体之间的关系。在致病性、适应度、基因表达和转录因子结合等多项任务上的评估表明，这种异构体感知的跨模态对齐显著提升了功能表示和下游性能，为基因组基础模型预训练提供了新方向。
正文节选
IsoAlign: Isoform-Aware DNA-Protein Alignment via Joint-Embedding Predictive Architectures Abstract Genomic foundation models (GFMs) have emerged as a powerful paradigm for learning DNA sequence representations, yet existing self-supervised pretraining strategies overlook alternative splicing and underperform compared to specialized models. To address this gap, we introduce IsoAlign, a multimodal framework that grounds genomic pretraining in isoform-aware DNA-protein alignment to learn biologica