.png){kind=icon}
返回
Evaluating Polymer Representations via Quantifying Structure-Property Relationships
.png){kind=icon}
OA
AI
DOI：10.1021/acs.jcim.9b00358.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Machine learning techniques are being applied in quantifying structure-property relationships for a wide variety of materials, where the properly represented materials play key roles. Although algorithms for representation learning are extensively studied, their applications to domain-specific areas, such as polymers, are limited largely due to the lack of benchmark databases. In this work, we investigate different types of polymer representations, including Morgan fingerprint (MF), molecular embedding (ME), and molecular graph (MG), based on the benchmark database from a subset of the well-known web-based polymer databases, PolyInfo. We evaluate the quality of different polymer representations via quantifying the relationships between the representations and polymer properties, including density, melting temperature, and glass transition temperature. Different representation learning schemes for MEs, such as supervised learning, semisupervised learning, and transfer learning, are investigated. In supervised learning, only labeled molecules in our benchmark database are used for representation learning, in semisupervised learning, both labeled and unlabeled molecules in our benchmark database are used, and in transfer learning, molecules from an external database that is different from the benchmark database are used for representation learning. It is found that ME (with the R-2 of 0.724 in the density case, 0.684 in the melting temperature case, and 0.865 in the glass transition temperature case) outperforms the other representations for structure-property relationship quantification in all cases studied, and MG (with the R-2 of 0.260 in the density case, -0.149 in the melting temperature case, and 0.711 in the glass transition case) is shown to be much inferior to ME and MF (with the R-2 of 0.562 in the density case, 0.645 in the melting temperature case, and 0.849 in the glass transition case), likely due to the relatively small volumes of training data available. For MEs, it is found that the similarities of substructure MEs under different learning schemes (e.g., SL, SSL, and TL) are differently estimated, thus leading to different performance scores in structure-property relation quantification. Combinations of MEs show little effect on predictive performance when comparing to the single MEs in the corresponding regression tasks, proving no information gain in mixing MEs.
Keyword:
GRAPHICAL REPRESENTATION
NETWORKS
DESCRIPTORS
PREDICTION
BIOMARKERS
PROTEOMICS
DESIGN
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.3
论文数:
9.1K
被引数:
4.0W
机构
引用论文
Mol2vec: Unsupervised Machine Learning Approach with Chemical IntuitionMol2vec: 具有化学直觉的无监督机器学习方法OAAI
OAAI分享收藏Modeling and anaysis of an energy-efficient MAC protocol for wireless sensor networks一种节能的无线传感器网络MAC协议的建模与分析
PREAI
分享收藏Learning distributed word representation with multi-contextual mixed embedding基于多上下文混合嵌入的分布式词表示学习
PREAI
分享收藏Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules使用数据驱动的分子连续表示的自动化学设计.png)
ACS CENTRAL SCIENCEOAAI
ACS CENTRAL SCIENCEIF10.4
OAAI分享收藏分享收藏
查看更多内容