发表机构
Department of Oncology KU Leuven（鲁汶大学肿瘤学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对细胞类型反卷积难题，提出数据驱动软标签估计读取的条件细胞类型分布，集成到新框架Syto，在人体39种细胞类型图谱上表现出色，为大型细胞类型面板建模奠基，软标签方案可用于多对多映射场景。
AI 中文摘要
细胞类型反卷积是计算生物学核心问题。依赖DNA甲基化等表观遗传标记的方法丢弃个体DNA读取的模式级信息，现有读取级方法稀缺且限于少数类别设置。为此提出数据驱动软标签，集成到Syto框架。在39种人类细胞类型的全身图谱上，Syto比SoTA将MSE降低2.56倍，成果可迁移，为大型细胞类型面板建模奠定基础，软标签方案可用于多对多信号到标签映射的任何设置。
英文摘要
Cell-type deconvolution, the task of estimating the proportions of constituent cell types in a heterogeneous biological sample, is a core problem in computational biology. Methods that rely on epigenetic marks such as DNA methylation typically operate on aggregated methylation estimates, discarding the pattern-level information carried by individual DNA reads. Existing read-level approaches that exploit this information are scarce, and all remain restricted to few-class settings; scaling them further is an open problem because, at scale, non-discriminative reads dominate and hard labels conflict with the many-to-many mapping between methylation patterns and cell types, preventing classifier convergence. To overcome this, we propose data-driven soft labels that estimate the conditional cell-type distribution for each read, and integrate this scheme into $Syto$, a new modular framework for read-level classification-based deconvolution. On a whole-body atlas of 39 human cell types, $Syto$ reduces MSE by 3.7$\times$ over the best examined baseline, with gains transferring to an out-of-distribution dataset spanning 16 tissues. $Syto$ lays the foundation for modeling increasingly large cell-type panels, with improved applications in biology and healthcare. The proposed soft-labeling scheme is further translatable to any setting with a many-to-many signal-to-label mapping.
CommentsAccepted at NeurIPS 2026 (Main Track), poster
