发表机构
The Chinese University of Hong Kong, Shenzhen; Warshel Institute for Computational Biology; Guangdong Provincial Key Laboratory of Digital Biology and Drug Development; Peking Union Medical College Hospital; Chinese Academy of Medical Sciences & Peking Union Medical College（香港中文大学（深圳）; 瓦谢尔计算生物研究院; 广东省数字生物与药物开发重点实验室; 北京协和医院; 中国医学科学院 北京协和医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MIRCID框架利用推断的HubmiRs增强药物机制建模，在通路分类和MoA检索中优于TF活性，实现跨任务改进。
AI 中文摘要
药物作用机制（MoA）建模通常依赖于扰动转录组，但匹配的microRNA（miRNA）测量数据往往不可用。推断的调控特征提供了一种可扩展的方式来重用这些数据。在此，我们提出了MIRCID，一个在通路分类和基于相似性的MoA检索中比较基因表达与推断的转录因子（TF）活性和miRNA表达的框架。HubmiRNet从977个L1000标志基因中推断出414个泛癌hub miRNAs（HubmiRs），实现了87.72%的Pearson相关系数；其1,298输出变体在全miRNA任务上也优于SiCmiR（71.21%对比67.30%）。在评估的比较中，miRNA增强比TF活性提供了更一致的改进。通用嵌入对照显示了模型依赖的效用，而互补性分析识别出一种独特的、部分线性可恢复的表示，该表示保留了基因衍生的结构。说明性的挽救案例将改进的分类与具有弱转录特征的样本中生物学上合理的miRNA模式联系起来。这些发现支持推断的HubmiRs作为转录组数据的生物学知情重编码，用于扰动药物建模，而测量到的扰动miRNA响应的恢复则留待进一步验证。
英文摘要
Drug mechanism-of-action (MoA) modeling commonly relies on perturbational transcriptomes, but matched microRNA (miRNA) measurements are often unavailable. Inferred regulatory features offer a scalable way to reuse these data. Here, we present MIRCID, a framework comparing gene expression with inferred transcription factor (TF) activity and miRNA expression across pathway classification and similarity-based MoA retrieval. HubmiRNet infers 414 pan-cancer hub miRNAs (HubmiRs) from 977 L1000 landmark genes, achieving a Pearson correlation coefficient of 87.72%; its 1,298-output variant also outperformed SiCmiR on the full-miRNA task (71.21% versus 67.30%). In the evaluated comparisons, miRNA augmentation provided more consistent gains than TF activity. Generic embedding controls showed model-dependent utility, while complementarity analyses identified a distinct, partially linearly recoverable representation that retained gene-derived structure. Illustrative rescue cases linked improved classification to biologically plausible miRNA patterns in samples with weak transcriptional signatures. These findings support inferred HubmiRs as a biologically informed recoding of transcriptomic data for perturbational drug modeling, while leaving recovery of measured perturbational miRNA responses to further validation.
Comments25 pages, 6 figures, Advanced Science
