Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?

Abstract As machine learning/artificial intelligence algorithms are defeating chess masters and, most recently, GO champions, there is interest – and hope – that they will prove equally useful in assisting chemists in predicting outcomes of organic reactions. This paper demonstrates, however, that t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	G. Skoraczyński, P. Dittwald, B. Miasojedow, S. Szymkuć, E. P. Gajewska, B. A. Grzybowski, A. Gambin
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c4f5d458d8274d07a332b52b041c113d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c4f5d458d8274d07a332b52b041c113d
record_format	dspace
spelling	oai:doaj.org-article:c4f5d458d8274d07a332b52b041c113d2021-12-02T12:32:24ZPredicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?10.1038/s41598-017-02303-02045-2322https://doaj.org/article/c4f5d458d8274d07a332b52b041c113d2017-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-02303-0https://doaj.org/toc/2045-2322Abstract As machine learning/artificial intelligence algorithms are defeating chess masters and, most recently, GO champions, there is interest – and hope – that they will prove equally useful in assisting chemists in predicting outcomes of organic reactions. This paper demonstrates, however, that the applicability of machine learning to the problems of chemical reactivity over diverse types of chemistries remains limited – in particular, with the currently available chemical descriptors, fundamental mathematical theorems impose upper bounds on the accuracy with which raction yields and times can be predicted. Improving the performance of machine-learning methods calls for the development of fundamentally new chemical descriptors.G. SkoraczyńskiP. DittwaldB. MiasojedowS. SzymkućE. P. GajewskaB. A. GrzybowskiA. GambinNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-9 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q G. Skoraczyński P. Dittwald B. Miasojedow S. Szymkuć E. P. Gajewska B. A. Grzybowski A. Gambin Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?
description	Abstract As machine learning/artificial intelligence algorithms are defeating chess masters and, most recently, GO champions, there is interest – and hope – that they will prove equally useful in assisting chemists in predicting outcomes of organic reactions. This paper demonstrates, however, that the applicability of machine learning to the problems of chemical reactivity over diverse types of chemistries remains limited – in particular, with the currently available chemical descriptors, fundamental mathematical theorems impose upper bounds on the accuracy with which raction yields and times can be predicted. Improving the performance of machine-learning methods calls for the development of fundamentally new chemical descriptors.
format	article
author	G. Skoraczyński P. Dittwald B. Miasojedow S. Szymkuć E. P. Gajewska B. A. Grzybowski A. Gambin
author_facet	G. Skoraczyński P. Dittwald B. Miasojedow S. Szymkuć E. P. Gajewska B. A. Grzybowski A. Gambin
author_sort	G. Skoraczyński
title	Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?
title_short	Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?
title_full	Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?
title_fullStr	Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?
title_full_unstemmed	Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?
title_sort	predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/c4f5d458d8274d07a332b52b041c113d
work_keys_str_mv	AT gskoraczynski predictingtheoutcomesoforganicreactionsviamachinelearningarecurrentdescriptorssufficient AT pdittwald predictingtheoutcomesoforganicreactionsviamachinelearningarecurrentdescriptorssufficient AT bmiasojedow predictingtheoutcomesoforganicreactionsviamachinelearningarecurrentdescriptorssufficient AT sszymkuc predictingtheoutcomesoforganicreactionsviamachinelearningarecurrentdescriptorssufficient AT epgajewska predictingtheoutcomesoforganicreactionsviamachinelearningarecurrentdescriptorssufficient AT bagrzybowski predictingtheoutcomesoforganicreactionsviamachinelearningarecurrentdescriptorssufficient AT agambin predictingtheoutcomesoforganicreactionsviamachinelearningarecurrentdescriptorssufficient
_version_	1718394119357726720

Predicting the outcomes of organic reactions via machine learning: are current descriptors sufficient?

Ejemplares similares