Developing Hybrid Machine Learning Frameworks for Polymer Property Prediction Based on Composition and Sequence Features

序列(生物学) 作文(语言) 财产(哲学) 计算机科学 人工智能 机器学习 化学 语言学 生物化学 认识论 哲学
作者
Quan Li,Siqi Zhan,Zhanjie Liu,Caibo Dong,Hengheng Zhao,Tongkui Yue,Qingsong Zhao,Liqun Zhang,Ying Li,Jun Liu
出处
期刊:Journal of Chemical Information and Modeling [American Chemical Society]
卷期号:65 (14): 7478-7492 被引量:6
标识
DOI:10.1021/acs.jcim.5c00745
摘要

Artificial intelligence (AI) plays a significant role in advancing polymer science and engineering. Considering the critical role of the glass transition temperature (Tg) in determining the physical properties of polymers, this study systematically investigates the influence of their composition and sequence structure on Tg using machine learning (ML) models. To clarify the complex relationship between polymer composition and Tg, the k-nearest neighbor mega-trend diffusion (kNNMTD) method was employed for data augmentation, and various ML models were constructed for Tg prediction. Among them, the Random Forest model demonstrated the best performance for the generated data, achieving an R2 of 0.85 and an RMSE of 0.38. To explore the effect of polymer sequence structure on Tg, we further introduced natural language processing (NLP) techniques to represent polymer sequences. The data was augmented using the Wasserstein generative adversarial network (GAN) with gradient penalty (WGAN-GP) model, and Tg predictions were made using a convolutional neural network-long short-term memory (CNN-LSTM) model. This integrated framework achieved excellent predictive performance, with an R2 of 0.95 and an RMSE of 0.23, and demonstrated strong generalization across different data sets. In summary, this study introduces an innovative application of kNNMTD for augmenting polymer composition data combined with NLP techniques for representing polymer sequences. The proposed ML framework offers a valuable contribution to the advancement of polymer material design and optimization.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
晨晓发布了新的文献求助10
刚刚
刚刚
刚刚
Hhhhhhhh发布了新的文献求助10
刚刚
小郑完成签到 ,获得积分10
刚刚
今后应助王潇东采纳,获得10
刚刚
qi完成签到 ,获得积分10
刚刚
ww完成签到 ,获得积分20
1秒前
胖达完成签到,获得积分10
1秒前
1秒前
orixero应助幸福遥采纳,获得10
1秒前
huang完成签到,获得积分10
1秒前
热电CAT完成签到,获得积分10
1秒前
1秒前
阳光的梦寒完成签到,获得积分10
1秒前
2秒前
阳光珍发布了新的文献求助10
2秒前
科研通AI6.4应助小北采纳,获得10
2秒前
zyw发布了新的文献求助10
2秒前
伊尔发布了新的文献求助10
2秒前
六六六完成签到,获得积分10
2秒前
科研狗-加班族完成签到,获得积分10
3秒前
3秒前
无辣不欢完成签到,获得积分10
3秒前
严晓博完成签到,获得积分10
3秒前
dyy发布了新的文献求助10
3秒前
科研通AI6.2应助大强采纳,获得10
3秒前
whisper完成签到,获得积分10
3秒前
柿子完成签到,获得积分10
4秒前
h_cl完成签到,获得积分10
4秒前
4秒前
Willow发布了新的文献求助10
5秒前
wjh发布了新的文献求助30
5秒前
Ly完成签到,获得积分10
5秒前
5秒前
5秒前
6秒前
逝水发布了新的文献求助10
6秒前
cdercder应助dududu采纳,获得10
6秒前
6秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
The anomeric effect 1000
Principles of town planning: translating concepts to applications 1000
Navigating Normative Orders: Interdisciplinary Perspectives 750
1 Peter and Christ's Descent to the Dead in Its Early Christian Reception 700
Organizational Behavior 510
Management and the Arts 510
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7733223
求助须知:如何正确求助?哪些是违规求助? 9283978
关于积分的说明 20162036
捐赠科研通 7311162
什么是DOI,文献DOI怎么找? 3304284
关于科研通互助平台的介绍 2457078
邀请新用户注册赠送积分活动 2313527