FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200261085> ?p ?o ?g. }

• W4200261085 endingPage "60521" @default.
• W4200261085 startingPage "60508" @default.
• W4200261085 abstract "Ultraviolet (UV)-curable thermoset shape memory polymers (TSMPs) with high recovery stress but mild glass transition temperature (Tg) are highly desired for 3D/4D printing lightweight load-bearing structures and devices. However, a bottleneck is that high recovery stress usually means high Tg. For a few TSMPs with high recovery stress, their Tg values are close to the decomposition temperature, and thus, the shape memory effect cannot be triggered safely and effectively. While machine learning (ML) has served as a useful tool to discover new materials and drugs, the grand challenge of using ML to discover new TSMPs persists in the very limited data available. Here, we report an enhanced ML approach by combining the transfer learning-variational autoencoder with a weighted-vector combination method. By learning a large data set with drug molecules in a pretraining process, we were able to effectively map the TSMPs to a hidden space that is much closer to a Gaussian distribution. Through this approach, we created a large compositional space and were able to discover five new types of UV-curable TSMPs with desired properties, one of which was validated by the experiments. Our contribution includes (1) representing the features of TSMPs by drug molecules to overcome the barrier of a limited training data set and (2) developing a ML framework that is able to overcome the barrier of mapping the molar ratio information. It is shown that this approach can effectively learn TSMP features by utilizing the relatedness between the data-scarce (and biased) TSMP target and data-abundant drug source, and the result is much more accurate and more robust than the benchmark set by the support vector machine method using direct label encoding and Morgan encoding. Therefore, it is believed that this framework is a state-of-the-art study in the TSMP field. This study opens new opportunities for discovering not only new TSMPs but also other thermoset polymers." @default.
• W4200261085 created "2021-12-31" @default.
• W4200261085 creator A5022583120 @default.
• W4200261085 creator A5036696295 @default.
• W4200261085 creator A5046330720 @default.
• W4200261085 date "2021-12-08" @default.
• W4200261085 modified "2023-10-18" @default.
• W4200261085 title "From Drug Molecules to Thermoset Shape Memory Polymers: A Machine Learning Approach" @default.
• W4200261085 cites W1978159078 @default.
• W4200261085 cites W1979414114 @default.
• W4200261085 cites W1988037271 @default.
• W4200261085 cites W1993046136 @default.
• W4200261085 cites W1996975182 @default.
• W4200261085 cites W2003226820 @default.
• W4200261085 cites W2006239176 @default.
• W4200261085 cites W2014313640 @default.
• W4200261085 cites W2019762917 @default.
• W4200261085 cites W2030405671 @default.
• W4200261085 cites W2047544230 @default.
• W4200261085 cites W2061168596 @default.
• W4200261085 cites W2064675550 @default.
• W4200261085 cites W2076595114 @default.
• W4200261085 cites W2082871271 @default.
• W4200261085 cites W2087247178 @default.
• W4200261085 cites W2091265890 @default.
• W4200261085 cites W2100905206 @default.
• W4200261085 cites W2112796928 @default.
• W4200261085 cites W2134690872 @default.
• W4200261085 cites W2140384790 @default.
• W4200261085 cites W2152932169 @default.
• W4200261085 cites W2177317049 @default.
• W4200261085 cites W2313357420 @default.
• W4200261085 cites W2510642588 @default.
• W4200261085 cites W2558999090 @default.
• W4200261085 cites W2607101357 @default.
• W4200261085 cites W2737024909 @default.
• W4200261085 cites W2759676733 @default.
• W4200261085 cites W2760905401 @default.
• W4200261085 cites W2773003563 @default.
• W4200261085 cites W2802292862 @default.
• W4200261085 cites W2804845608 @default.
• W4200261085 cites W2806061811 @default.
• W4200261085 cites W2906755148 @default.
• W4200261085 cites W2945548754 @default.
• W4200261085 cites W2945864779 @default.
• W4200261085 cites W2952832141 @default.
• W4200261085 cites W2963731249 @default.
• W4200261085 cites W2964206522 @default.
• W4200261085 cites W2964679607 @default.
• W4200261085 cites W2965344674 @default.
• W4200261085 cites W2973074478 @default.
• W4200261085 cites W2985931096 @default.
• W4200261085 cites W3006401357 @default.
• W4200261085 cites W3007665173 @default.
• W4200261085 cites W3009522030 @default.
• W4200261085 cites W3010244463 @default.
• W4200261085 cites W3032647470 @default.
• W4200261085 cites W3037095052 @default.
• W4200261085 cites W3040508291 @default.
• W4200261085 cites W3047663310 @default.
• W4200261085 cites W3083885684 @default.
• W4200261085 cites W3098269892 @default.
• W4200261085 cites W3104182741 @default.
• W4200261085 cites W3107172382 @default.
• W4200261085 cites W3108967272 @default.
• W4200261085 cites W3111189094 @default.
• W4200261085 cites W3113317199 @default.
• W4200261085 cites W3118124377 @default.
• W4200261085 cites W3160099884 @default.
• W4200261085 cites W3214689457 @default.
• W4200261085 cites W4210702584 @default.
• W4200261085 doi "https://doi.org/10.1021/acsami.1c20947" @default.
• W4200261085 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34878247" @default.
• W4200261085 hasPublicationYear "2021" @default.
• W4200261085 type Work @default.
• W4200261085 citedByCount "12" @default.
• W4200261085 countsByYear W42002610852022 @default.
• W4200261085 countsByYear W42002610852023 @default.
• W4200261085 crossrefType "journal-article" @default.
• W4200261085 hasAuthorship W4200261085A5022583120 @default.
• W4200261085 hasAuthorship W4200261085A5036696295 @default.
• W4200261085 hasAuthorship W4200261085A5046330720 @default.
• W4200261085 hasConcept C101738243 @default.
• W4200261085 hasConcept C108583219 @default.
• W4200261085 hasConcept C111919701 @default.
• W4200261085 hasConcept C122865956 @default.
• W4200261085 hasConcept C138885662 @default.
• W4200261085 hasConcept C149635348 @default.
• W4200261085 hasConcept C154945302 @default.
• W4200261085 hasConcept C159985019 @default.
• W4200261085 hasConcept C171359207 @default.
• W4200261085 hasConcept C177264268 @default.
• W4200261085 hasConcept C178790620 @default.
• W4200261085 hasConcept C185592680 @default.
• W4200261085 hasConcept C185698529 @default.
• W4200261085 hasConcept C186060115 @default.
• W4200261085 hasConcept C192562407 @default.
• W4200261085 hasConcept C199360897 @default.

• next