Polymer Informatics at Scale with Multitask Graph Neural Networks

© 2023 The Authors. Published by American Chemical Society.

Bibliographische Detailangaben
Veröffentlicht in:Chemistry of materials : a publication of the American Chemical Society. - 1998. - 35(2023), 4 vom: 28. Feb., Seite 1560-1567
1. Verfasser: Gurnani, Rishi (VerfasserIn)
Weitere Verfasser: Kuenneth, Christopher, Toland, Aubrey, Ramprasad, Rampi
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:Chemistry of materials : a publication of the American Chemical Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM35379502X
003 DE-627
005 20231226060832.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1021/acs.chemmater.2c02991  |2 doi 
028 5 2 |a pubmed24n1179.xml 
035 |a (DE-627)NLM35379502X 
035 |a (NLM)36873627 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Gurnani, Rishi  |e verfasserin  |4 aut 
245 1 0 |a Polymer Informatics at Scale with Multitask Graph Neural Networks 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 07.03.2023 
500 |a published: Electronic-eCollection 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a © 2023 The Authors. Published by American Chemical Society. 
520 |a Artificial intelligence-based methods are becoming increasingly effective at screening libraries of polymers down to a selection that is manageable for experimental inquiry. The vast majority of presently adopted approaches for polymer screening rely on handcrafted chemostructural features extracted from polymer repeat units-a burdensome task as polymer libraries, which approximate the polymer chemical search space, progressively grow over time. Here, we demonstrate that directly "machine learning" important features from a polymer repeat unit is a cheap and viable alternative to extracting expensive features by hand. Our approach-based on graph neural networks, multitask learning, and other advanced deep learning techniques-speeds up feature extraction by 1-2 orders of magnitude relative to presently adopted handcrafted methods without compromising model accuracy for a variety of polymer property prediction tasks. We anticipate that our approach, which unlocks the screening of truly massive polymer libraries at scale, will enable more sophisticated and large scale screening technologies in the field of polymer informatics 
650 4 |a Journal Article 
700 1 |a Kuenneth, Christopher  |e verfasserin  |4 aut 
700 1 |a Toland, Aubrey  |e verfasserin  |4 aut 
700 1 |a Ramprasad, Rampi  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t Chemistry of materials : a publication of the American Chemical Society  |d 1998  |g 35(2023), 4 vom: 28. Feb., Seite 1560-1567  |w (DE-627)NLM098194763  |x 0897-4756  |7 nnns 
773 1 8 |g volume:35  |g year:2023  |g number:4  |g day:28  |g month:02  |g pages:1560-1567 
856 4 0 |u http://dx.doi.org/10.1021/acs.chemmater.2c02991  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_11 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 35  |j 2023  |e 4  |b 28  |c 02  |h 1560-1567