Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167144918> ?p ?o ?g. }
- W3167144918 abstract "Retrosynthetic planning is a fundamental problem in chemistry for finding a pathway of reactions to synthesize a target molecule. Recently, search algorithms have shown promising results for solving this problem by using deep neural networks (DNNs) to expand their candidate solutions, i.e., adding new reactions to reaction pathways. However, the existing works on this line are suboptimal; the retrosynthetic planning problem requires the reaction pathways to be (a) represented by real-world reactions and (b) executable using building block molecules, yet the DNNs expand reaction pathways without fully incorporating such requirements. Motivated by this, we propose an end-to-end framework for directly training the DNNs towards generating reaction pathways with the desirable properties. Our main idea is based on a self-improving procedure that trains the model to imitate successful trajectories found by itself. We also propose a novel reaction augmentation scheme based on a forward reaction model. Our experiments demonstrate that our scheme significantly improves the success rate of solving the retrosynthetic problem from 86.84% to 96.32% while maintaining the performance of DNN for predicting valid reactions." @default.
- W3167144918 created "2021-06-22" @default.
- W3167144918 creator A5033954037 @default.
- W3167144918 creator A5035397475 @default.
- W3167144918 creator A5035865220 @default.
- W3167144918 creator A5041027404 @default.
- W3167144918 date "2021-06-09" @default.
- W3167144918 modified "2023-09-23" @default.
- W3167144918 title "Self-Improved Retrosynthetic Planning" @default.
- W3167144918 cites W1500036797 @default.
- W3167144918 cites W1522301498 @default.
- W3167144918 cites W1988037271 @default.
- W3167144918 cites W1990896272 @default.
- W3167144918 cites W2041548070 @default.
- W3167144918 cites W2580919858 @default.
- W3167144918 cites W2618097077 @default.
- W3167144918 cites W2621742623 @default.
- W3167144918 cites W2747592475 @default.
- W3167144918 cites W2753921001 @default.
- W3167144918 cites W2766447205 @default.
- W3167144918 cites W2769423117 @default.
- W3167144918 cites W2792783390 @default.
- W3167144918 cites W2803664624 @default.
- W3167144918 cites W2804182511 @default.
- W3167144918 cites W2931903779 @default.
- W3167144918 cites W29374554 @default.
- W3167144918 cites W2947835681 @default.
- W3167144918 cites W2950955377 @default.
- W3167144918 cites W2962974709 @default.
- W3167144918 cites W2963396480 @default.
- W3167144918 cites W2970089374 @default.
- W3167144918 cites W2970365156 @default.
- W3167144918 cites W2972608805 @default.
- W3167144918 cites W2995284558 @default.
- W3167144918 cites W3013312987 @default.
- W3167144918 cites W3035172872 @default.
- W3167144918 cites W3035505522 @default.
- W3167144918 cites W3094771832 @default.
- W3167144918 cites W3101473090 @default.
- W3167144918 cites W3103092523 @default.
- W3167144918 cites W3110229430 @default.
- W3167144918 cites W3215077721 @default.
- W3167144918 hasPublicationYear "2021" @default.
- W3167144918 type Work @default.
- W3167144918 sameAs 3167144918 @default.
- W3167144918 citedByCount "0" @default.
- W3167144918 crossrefType "posted-content" @default.
- W3167144918 hasAuthorship W3167144918A5033954037 @default.
- W3167144918 hasAuthorship W3167144918A5035397475 @default.
- W3167144918 hasAuthorship W3167144918A5035865220 @default.
- W3167144918 hasAuthorship W3167144918A5041027404 @default.
- W3167144918 hasConcept C134306372 @default.
- W3167144918 hasConcept C154945302 @default.
- W3167144918 hasConcept C160145156 @default.
- W3167144918 hasConcept C178790620 @default.
- W3167144918 hasConcept C185592680 @default.
- W3167144918 hasConcept C199360897 @default.
- W3167144918 hasConcept C2524010 @default.
- W3167144918 hasConcept C2777210771 @default.
- W3167144918 hasConcept C33923547 @default.
- W3167144918 hasConcept C35753019 @default.
- W3167144918 hasConcept C41008148 @default.
- W3167144918 hasConcept C42437451 @default.
- W3167144918 hasConcept C77618280 @default.
- W3167144918 hasConceptScore W3167144918C134306372 @default.
- W3167144918 hasConceptScore W3167144918C154945302 @default.
- W3167144918 hasConceptScore W3167144918C160145156 @default.
- W3167144918 hasConceptScore W3167144918C178790620 @default.
- W3167144918 hasConceptScore W3167144918C185592680 @default.
- W3167144918 hasConceptScore W3167144918C199360897 @default.
- W3167144918 hasConceptScore W3167144918C2524010 @default.
- W3167144918 hasConceptScore W3167144918C2777210771 @default.
- W3167144918 hasConceptScore W3167144918C33923547 @default.
- W3167144918 hasConceptScore W3167144918C35753019 @default.
- W3167144918 hasConceptScore W3167144918C41008148 @default.
- W3167144918 hasConceptScore W3167144918C42437451 @default.
- W3167144918 hasConceptScore W3167144918C77618280 @default.
- W3167144918 hasOpenAccess W3167144918 @default.
- W3167144918 hasRelatedWork W2025448855 @default.
- W3167144918 hasRelatedWork W2398010056 @default.
- W3167144918 hasRelatedWork W2486265639 @default.
- W3167144918 hasRelatedWork W2559129456 @default.
- W3167144918 hasRelatedWork W2889732123 @default.
- W3167144918 hasRelatedWork W2900797118 @default.
- W3167144918 hasRelatedWork W2908702510 @default.
- W3167144918 hasRelatedWork W2962688617 @default.
- W3167144918 hasRelatedWork W2964568892 @default.
- W3167144918 hasRelatedWork W3008314020 @default.
- W3167144918 hasRelatedWork W3013121561 @default.
- W3167144918 hasRelatedWork W3016041222 @default.
- W3167144918 hasRelatedWork W3035505522 @default.
- W3167144918 hasRelatedWork W3046816307 @default.
- W3167144918 hasRelatedWork W3080920065 @default.
- W3167144918 hasRelatedWork W3085764401 @default.
- W3167144918 hasRelatedWork W3112875336 @default.
- W3167144918 hasRelatedWork W3171815375 @default.
- W3167144918 hasRelatedWork W3185043070 @default.
- W3167144918 hasRelatedWork W3201550253 @default.
- W3167144918 isParatext "false" @default.
- W3167144918 isRetracted "false" @default.