Data for "Literature-data-driven explainable machine learning for applicability-domain-constrained virtual screening of Ru-based CO₂ methanation catalysts"

This dataset supports the manuscript entitled “Literature-data-driven explainable machine learning for applicability-domain-constrained virtual screening of Ru-based CO₂ methanation catalysts”. The dataset contains 556 experimental entries for Ru-based CO₂ methanation collected and curated from 41 literature DOI sources. It includes catalyst composition and preparation parameters, Ru loading, support and promoter information, active-phase particle size, BET surface area, pretreatment conditions, reaction temperature, pressure, gas hourly space velocity (GHSV), H₂/CO₂ ratio, CO₂ conversion, and CH₄ selectivity. The data were used to develop machine-learning models for CO₂ conversion regression and high-CH₄-selectivity classification (CH₄ selectivity ≥ 95%), together with explainability analysis and applicability-domain-constrained virtual screening. Associated code and screening results are provided to facilitate reproducibility and further analysis. The dataset is derived from previously published literature and is intended for research and academic use.本数据集支撑题为《基于文献数据的可解释机器学习用于钌（Ru）基CO₂甲烷化催化剂的适用域约束虚拟筛选》的研究论文。 本数据集包含从41篇文献的DOI来源中收集并整理得到的556条钌基CO₂甲烷化实验条目，涵盖催化剂组成与制备参数、钌负载量、载体与助剂信息、活性相粒径、BET比表面积（BET surface area）、预处理条件、反应温度、反应压力、气时空速（gas hourly space velocity，GHSV）、H₂/CO₂比例、CO₂转化率以及CH₄选择性。 该数据集被用于构建CO₂转化率回归模型与高CH₄选择性分类模型（CH₄选择性≥95%），并开展可解释性分析与适用域约束虚拟筛选研究。 本数据集附带相关代码与筛选结果，以保障研究可复现性并支持后续分析。本数据集源自已发表的文献，仅用于科研与学术用途。