Department of Chemical Engineering, Virginia Tech, Blacksburg, VA 24061, USA.
Chem Commun (Camb). 2020 Aug 13;56(65):9312-9315. doi: 10.1039/d0cc02651d.
Four different machine learning (ML) regression models: artificial neural network, k-nearest neighbors, Gaussian process regression and random forest were built to backmap coarse-grained models to all-atom models. The ML models showed better predictions than the existing backmapping approaches for selected structures, suggesting the applications of the ML models for backmapping.
四种不同的机器学习 (ML) 回归模型：人工神经网络、k-最近邻、高斯过程回归和随机森林，被构建用于将粗粒度模型反向映射到全原子模型。ML 模型对选定结构的预测优于现有的反向映射方法，这表明 ML 模型在反向映射中的应用。
