Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.6
5.0
Journals
Polymers
Special Issues
Machine Learning and Simulation of Polymers
share announcement

Machine Learning and Simulation of Polymers

A special issue of Polymers (ISSN 2073-4360). This special issue belongs to the section "Polymer Physics and Theory".

Deadline for manuscript submissions: closed (30 June 2023) | Viewed by 1813

Special Issue Editor

Prof. Dr. Jianfeng Li

E-Mail Website
Guest Editor
Department of Macromolecular Science, Fudan University, Shanghai, China
Interests: machine learning of polymers

Special Issue Information

Dear Colleagues,

In the past decade, machine learning and deep learning have evolved into powerful tools in object recognition, natural language processing, AI recommendation systems, and many other areas. In recent years, they have also played an important role in polymer science in solving problems in multifactor correlation, synergistic and antagonistic effects, pattern and boundary identification, critical behavior, and phase transition. This Special Issue aims to serve as a platform to allow polymer researchers to exchange exciting results, recent progress, and emerging ideas on advances in machine-learning methods developed for polymer science and the applications of machine-learning methods in solving problems in simulations or experiments. The issue welcomes reports and reviews covering any aspect of machine learning related to polymer science. Potential topics include but are not limited to the following: notation and description of a polymer chain in machine learning; structural prediction of polymer (protein) chains; pattern and boundary identification; machine-learning methods in material genome projects; machine-learning methods in polymer rheology.

Prof. Dr. Jianfeng Li
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Polymers is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning framework for polymer discovery
  • machine learning in polymerization process
  • machine learning for the nanomaterials&ndash
  • biology interface
  • machine learning for drug discovery

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

13 pages, 4374 KiB  
Article
Harnessing Data Augmentation and Normalization Preprocessing to Improve the Performance of Chemical Reaction Predictions of Data-Driven Model
by Boyu Zhang, Jiaping Lin, Lei Du and Liangshun Zhang
Polymers 2023, 15(9), 2224; https://doi.org/10.3390/polym15092224 - 08 May 2023
Cited by 2 | Viewed by 1331
Abstract
As a template-free, data-driven methodology, the molecular transformer model provides an alternative by which to predict the outcome of chemical reactions and design the route of the retrosynthetic plane in the field of organic synthesis and polymer chemistry. However, in consideration of the [...] Read more.
As a template-free, data-driven methodology, the molecular transformer model provides an alternative by which to predict the outcome of chemical reactions and design the route of the retrosynthetic plane in the field of organic synthesis and polymer chemistry. However, in consideration of the small datasets of chemical reactions, the data-driven model suffers from the difficulty of low accuracy in the prediction tasks of chemical reactions. In this contribution, we integrate the molecular transformer model with the strategies of data augmentation and normalization preprocessing to accomplish the three tasks of chemical reactions, including the forward predictions of chemical reactions, and single-step retrosynthetic predictions with and without the reaction classes. It is clearly demonstrated that the prediction accuracy of the molecular transformer model can be significantly raised by the use of proposed strategies for the three tasks of chemical reactions. Notably, after the introduction of the 40-level data augmentation and normalization preprocessing, the top-1 accuracy of the forward prediction increases markedly from 71.6% to 84.2% and the top-1 accuracy of the single-step retrosynthetic prediction with additional reaction class increases from 53.2% to 63.4%. Furthermore, it is found that the superior performance of the data-driven model originates from the correction of the grammatical errors of the SMILES strings, especially for the case of the reaction classes with small datasets. Full article
(This article belongs to the Special Issue Machine Learning and Simulation of Polymers)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop