arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.23305cs.LG
收藏

虚拟染色的适当评分规则

A Proper Scoring Rule for Virtual Staining

School of Computer Science, University of Birmingham, Birmingham, UK GSK Drug Metabolism \& Pharmacokinetics, GSK Medicines Research Centre, Stevenage, UK GSK Genome Biology, Collegeville, PA, USA School of Electronics, Electrical Engineering;Computer Science, Queen's University Belfast, UK

Samuel Tonks, Steve Hood, Ryan Musso, Ceridwen Hopely, Steve Titus, Minh Doan, Iain Styles, Alexander Krull

AI总结:

本文提出信息增益作为评估虚拟染色模型的严格适当评分规则,揭示模型在不同特征上的性能差异。

摘要:

生成虚拟染色(VS)模型用于高通量筛选(HTS)时,可以为每个输入和细胞提供可能的生物特征值的估计后验分布。然而,当评估VS模型时,真实的后验分布是不可用的。现有的评估协议仅检查数据集上边缘分布的准确性,而不是预测的后验分布。我们引入信息增益(IG)作为细胞层面的评估框架,使能够直接评估预测的后验分布。IG是一种严格适当的评分规则,并具有坚实的理论动机,允许可解释性,并用于在不同模型和特征之间进行比较。我们使用IG和其他指标在广泛的HTS数据集上评估扩散和GAN基模型,并显示IG能够揭示其他指标无法揭示的显著性能差异。

英文摘要:

Generative virtual staining (VS) models for high-throughput screening (HTS) can provide an estimated posterior distribution of possible biological feature values for each input and cell. However, when evaluating a VS model, the true posterior is unavailable. Existing evaluation protocols only check the accuracy of the marginal distribution over the dataset rather than the predicted posteriors. We introduce information gain (IG) as a cell-wise evaluation framework that enables direct assessment of predicted posteriors. IG is a strictly proper scoring rule and comes with a sound theoretical motivation allowing for interpretability, and for comparing results across models and features. We evaluate diffusion- and GAN-based models on an extensive HTS dataset using IG and other metrics and show that IG can reveal substantial performance differences other metrics cannot.

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。

↑