SC3:多溶剂溶解度挑战与基准
SC3: The Multi-Solvent Solubility Challenge and Benchmark
AI总结:
针对多溶剂溶解度预测中现有基准的缺陷,提出SC3基准,包含可复现的数据处理流程、多层级共识集和评估指标,并揭示最佳模型与理论极限仍有5倍差距。
摘要:
溶解度预测是计算化学中的标准基准,然而据报道接近实验噪声上限(即偶然极限)的多溶剂模型尚未可靠到可以部署。我们认为这一差距部分是由于人为因素:已发表的基准在筛选策略上存在差异,评估时使用计数加权RMSE掩盖了在重尾溶剂分布上的失败,并且将广泛引用的0.6-0.8 log S实验室间数值视为偶然上限,尽管它反映的是最坏情况而非预期差异。我们引入了SC3,一个基于BigSolDB v2.1构建的多溶剂溶解度基准,包含三个贡献:(i) 一个可复现的数据处理流程,得到101,535个测量值,涵盖1,327种溶质和206种溶剂,重新校准的偶然下限为0.106 log S——约为传统数值的6倍;(ii) 嵌套的金/银/铜共识层级,包含逐点标准差、三种泄漏检查分割以及多溶剂指标套件(PS-RMSE, Z-RMSE);以及(iii) 跨六个家族的31个模型基准,其最佳铜级PS-RMSE是偶然极限的5倍,我们观察到这一差距未被任何测试过的深度替代方案所弥合。我们进行了三项后续分析:数据缩放、从量子化学溶剂化能的迁移以及特征级归因,这表明校准后的逐点不确定性是超越点预测的诊断可复用基础设施。
英文摘要:
Solubility prediction is a standard benchmark in computational chemistry, yet multi-solvent models which reportedly approach the experimental-noise ceiling (i.e. the aleatoric limit) are not yet reliable enough to be deployed. We argue that this gap is partly artefactual: published benchmarks differ in curation policies, evaluate on count-weighted RMSE that hides failure on tail-heavy solvent distributions, and treat the widely cited 0.6-0.8 log S inter-laboratory figure as the aleatoric ceiling even though it reflects worst-case, not expected, disagreement. We introduce SC3, a multi-solvent solubility benchmark built on BigSolDB v2.1 with three contributions: (i) a reproducible curation pipeline yielding 101,535 measurements over 1,327 solutes and 206 solvents, with a recalibrated aleatoric floor of 0.106 log S-roughly 6 times tighter than the conventional figure; (ii) nested Gold/Silver/Bronze consensus tiers with per-point standard deviation, three leakage-checked splits, and a multi-solvent metric suite (PS-RMSE, Z-RMSE); and (iii) a 31-model benchmark across six families, whose best Bronze PS-RMSE sits at 5 times the aleatoric limit, and we observe this is a gap unclosed by any deep alternative tested. We perform three follow-on analyses: data scaling, transfer from quantum-chemistry solvation energies, and feature-level attribution, which demonstrates that calibrated per-point uncertainty is a reusable infrastructure for diagnosis beyond point prediction.
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。