编辑丨王多鱼 排版丨水成文 如果说之前的 基因组大模型 是在逐字认识 ATCG 的排列组合，那么 Genos 团队此次推出的 Gengram 则相当于为其配备了一本" 基因字典 "。数据显示， 搭载 Gengram 后的大模型， 不仅刷新了多项基因组任务的 SOTA 记录，让模型在剪接位点识别等任务上 AUC 提升 16.1% ，还能自己悟出 DNA 双螺旋的物理规 律。 瓶颈：只会 "读字母"的基因组模型 在生物学中，很多 DNA 的功能元件 （例如启动子、剪接位点） 往往由特定的碱基组合 （Motif） 决定，但目前主流的基因组大模型都采用 单碱基分词 的形 式，也就是把 DNA 序列拆成一个个碱基来处理，这种方式虽然精准，但效率极低。 就像 我们看 "刻舟求剑"，是一眼看懂成语的含义，而不是先分析"刻"字有几笔，"舟"字怎么写，然后一个字一个字拼在一起，这不仅浪费算力，还容易让模型在 长达数亿的碱基序列中迷路。 近日， DeepSeek 新发布的 " 外挂大脑 "模式在大模型圈内 爆火 ，仅 16 天后， 国内 一个名叫 Genos 的 团队 将这种模式引入了 生命科学 领域， 提出了 Gengram ...

Core Insights - The article discusses the introduction of Gengram, a genomic module inspired by the Engram technology, which enhances the efficiency of genomic models by utilizing a memory lookup system instead of traditional methods [1][4]. Group 1: Gengram Technology Overview - Gengram employs a hash table to store common DNA sequences (k-mers) and allows models to reference this external memory, significantly reducing computational load [3][11]. - The module is lightweight, with approximately 20 million parameters, and integrates seamlessly into larger models, enhancing their performance without substantial additional computational costs [15][19]. Group 2: Performance Improvements - Models utilizing Gengram showed significant performance improvements in various tasks, including a 16.1% increase in AUC for splice site prediction and a 22.6% increase for epigenetic prediction tasks [17]. - Gengram's implementation allows models to achieve high performance with minimal training data, outperforming models that have been trained on significantly larger datasets [18]. Group 3: Mechanisms and Adaptability - Gengram features a dynamic gating mechanism that enables the model to decide when to reference the memory based on the context, optimizing resource usage [12][13]. - The module demonstrates excellent adaptability across different model architectures, improving training efficiency and balancing expert loads in mixture of experts (MoE) configurations [19][21]. Group 4: Scientific Insights and Innovations - Gengram's design allows it to infer biological principles, such as the physical structure of DNA, without prior knowledge, showcasing its potential for scientific discovery [22][25]. - The choice of a 21 base pair window size for local aggregation aligns with the physical properties of DNA, indicating a sophisticated understanding of biological structures [23][24]. Group 5: Team Background and Capabilities - The Genos Team, responsible for Gengram, is a collaboration between Zhejiang Lab and BGI-HangzhouAI, combining expertise in AI and life sciences [33][34]. - The Genos model, which serves as the foundation for Gengram, reportedly surpasses leading industry benchmarks, indicating a strong competitive position in genomic modeling [35].