AssayRouter：用于冻结分子预测器路由的历史效用先验
AssayRouter: Historical Utility Priors for Frozen Molecular Predictor Routing
浏览论文内容
中文总结 AI 辅助
AssayRouter利用历史测定作为伪目标，通过预测候选冻结预测器的拟合后效用，为新测定选择四个源并拟合凸组合器，在24个外部回归测定上显著降低NLL，实现跨接口家族的迁移路由。
中文摘要 AI 辅助
实验室经常面临一个新的分子测定，仅有16-64个标签，以及一组预测器，其训练数据和参数不可用。实际问题是在小型本地模型中应包含哪些冻结输出。AssayRouter将已完成的测定视为伪目标，并根据拟合后效用为每个候选标记：即当候选被添加到本地目标预测器时，留出发现损失的减少量。一个共享回归器学习根据候选在支持集上的行为来预测此效用，而不依赖源身份；在新测定上，一个冻结排名选择四个源，单独的标签拟合一个凸组合器。我们仅在已完成的ChEMBL-MT测定上训练，并评估六个冻结接口家族中的24个外部回归测定。AssayRouter-C相对于Support-CV@4将严格四次调用的负对数似然（NLL）降低了0.0409。冻结候选标签排列确认候选-效用对应关系携带了转移信息，而留一接口外训练表明该映射泛化到未见过的预测器家族。因此，已完成的测定为通过冻结预测接口的稀缺标签路由提供了可转移的监督。
英文摘要
Laboratories often face a new molecular assay with 16-64 labels and a bank of predictors whose training data and parameters are unavailable. The practical question is which frozen outputs to include in a small local model. AssayRouter treats completed assays as pseudo-targets and labels each candidate by its post-fit utility: the reduction in held-out discovery loss when the candidate is added to the local target predictor. A shared regressor learns to predict this utility from candidate behavior on the support set, without source identity; on a new assay, one frozen ranking selects four sources and separate labels fit a convex combiner. We train only on completed ChEMBL-MT assays and evaluate 24 external regression assays across six frozen interface families. AssayRouter-C lowers strict four-call negative log-likelihood (NLL) by 0.0409 relative to Support-CV@4. Frozen candidate-label permutations confirm that candidate-utility correspondence carries the transferred information, and leave-one-interface-out training shows that the mapping generalizes to unseen predictor families. Completed assays therefore provide transferable supervision for scarce-label routing through frozen prediction interfaces.
发表机构
- Shenzhen University（深圳大学）
- EasternDawn（东方黎明）
- University of Nottingham Ningbo（宁波诺丁汉大学）
机构由 AI 辅助整理，请以论文原文为准。
