HyCoSeq：基因组序列的上下文双曲表示学习
HyCoSeq: Contextual Hyperbolic Representation Learning for Genomic Sequences
- ShanghaiTech University（上海科技大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
HyCoSeq提出一种上下文双曲表示学习框架，通过加权洛伦兹残差聚合和双向LSTM整合序列上下文，在多种基因组任务上超越现有双曲基线，且无需大规模预训练即可媲美大型DNA语言模型。
中文摘要 AI 辅助
双曲几何为基因组表示学习提供了自然的归纳偏置，但现有的双曲基因组模型主要使用洛伦兹卷积来学习局部序列表示，而其残差路径并未直接聚合完整的洛伦兹表示。我们提出了HyCoSeq，一个用于基因组序列的上下文双曲表示学习框架。HyCoSeq将加权洛伦兹残差聚合融入多曲率洛伦兹编码中，使得完整的洛伦兹表示能够直接参与几何一致的局部聚合。它进一步引入了一个双向长短期记忆网络，该网络整合来自序列两个方向的信息，以学习基因组序列内不同位置局部表示之间的上下文关系，从而将局部双曲卷积编码扩展到序列级上下文表示。在多种基因组任务上的大量实验表明，HyCoSeq优于现有的双曲基线模型，并且在没有大规模基因组预训练的情况下，其性能可与规模大得多的预训练DNA语言模型相媲美。
英文摘要
Hyperbolic geometry provides a natural inductive bias for genomic representation learning, but existing hyperbolic genomic models primarily use Lorentz convolutions to learn local sequence representations, while their residual pathways do not directly aggregate full Lorentz representations. We propose HyCoSeq, a contextual hyperbolic representation learning framework for genomic sequences. HyCoSeq incorporates weighted Lorentzian residual aggregation into multi-curvature Lorentz encoding, allowing full Lorentz representations to participate directly in geometry-consistent local aggregation. It further introduces a bidirectional long short-term memory network that integrates information from both sequence directions to learn contextual relationships among local representations at different positions within a genomic sequence, thereby extending local hyperbolic convolutional encoding to sequence-level contextualized representations. Extensive experiments across diverse genomic tasks show that HyCoSeq outperforms existing hyperbolic baselines and, without large-scale genomic pretraining, achieves competitive performance against substantially larger pretrained DNA language models.
