中心法则变换器II:一种用于理解细胞调控机制的AI显微镜
Central Dogma Transformer II: An AI Microscope for Understanding Cellular Regulatory Mechanisms
AI总结:
CDT-II通过模仿中心法则架构,利用基因组嵌入和原始细胞表达数据,预测基因扰动效应并恢复调控网络,展示出跨注意力聚焦于调控元件,为临床相关调控结构提供新的见解。
摘要:
当前的生物AI模型缺乏可解释性--其内部表示不对应研究人员可考察的生物关系。理解基因调控需要能直接检验生成可实验验证假设的模型。CDT-II在架构上模仿中心法则--DNA自注意力、RNA自注意力和转录调控的交叉注意力--仅需基因组嵌入和原始单细胞表达数据。应用于K562 CRISPRi数据时,CDT-II预测扰动效应(每基因均值r=0.84),恢复GFI1B调控网络(6.6倍富集,P=3.5×10^{-17}),并显示交叉注意力聚焦于ENCODE调控元件包括CTCF位点(均值7.67倍,28个目标,P<0.001)。基于梯度的归因准确预测扰动治疗靶点下游后果(均值r=0.82)。应用于TFRC(抗TfR1抗体PPMX-T003的目标)时,梯度分析识别出与红细胞结构、铁依赖DNA合成和氧化应激相关的基因--这些通路与I期临床试验报告的贫血和网织红细胞减少以及预临床研究中展示的铁死亡一致,无需任何临床数据输入,证明CDT-II是一种能够仅通过扰动实验揭示临床相关调控结构的AI显微镜。
英文摘要:
Motivation: Interpretability is not optional in biology: understanding gene regulation requires models whose learned structure can be directly interrogated, not merely accurate predictors whose internals resist mapping onto regulatory relationships. We ask whether an architecture mirroring the central dogma yields attention and gradient maps that recover known regulatory elements and networks in inspectable form. Results: Central Dogma Transformer II (CDT-II) mirrors the central dogma in its architecture -- DNA self-attention, RNA self-attention, and DNA-to-RNA cross-attention -- requiring only genomic embeddings and raw per-cell expression. On K562 CRISPR interference (CRISPRi) data with five genes held out entirely, CDT-II predicts perturbation effects (per-gene mean r = 0.84), recovers the GFI1B regulatory network (6.6-fold enrichment, P = 3.5 x 10^-17), and concentrates cross-attention on ENCODE regulatory elements including CTCF sites (mean 7.67x across 28 target genes, P < 0.001). Gradient attribution predicts consequences of perturbing therapeutic targets (mean r = 0.82). For TFRC, target of the anti-TfR1 antibody PPMX-T003, it identifies erythrocyte-structure, iron-dependent DNA-synthesis and oxidative-stress genes, matching anemia and ferroptosis reported clinically and preclinically -- without clinical data as input. CDT-II acts as an AI microscope, surfacing clinically relevant regulatory structure from perturbation experiments alone. Availability: Source code is available at https://github.com/nobusama/CDT2. Pre-computed embeddings, training data, and model weights are available at https://huggingface.co/datasets/nobusama17/CDT2-data.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。