Structure–reactivity modeling using mixture-based representation of chemical reactions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15110%2F17%3A73585002" target="_blank" >RIV/61989592:15110/17:73585002 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007%2Fs00018-017-2574-1" target="_blank" >https://link.springer.com/article/10.1007%2Fs00018-017-2574-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10822-017-0044-3" target="_blank" >10.1007/s10822-017-0044-3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Structure–reactivity modeling using mixture-based representation of chemical reactions

Popis výsledku v původním jazyce

We describe a novel approach of reaction representation as a combination of two mixtures: a mixture of reactants and a mixture of products. In turn, each mixture can be encoded using an earlier reported approach involving simplex descriptors (SiRMS). The feature vector representing these two mixtures results from either concatenated product and reactant descriptors or the difference between descriptors of products and reactants. This reaction representation doesn&apos;t need an explicit labeling of a reaction center. The rigorous &quot;product-out&quot; cross-validation (CV) strategy has been suggested. Unlike the na &lt; ve &quot;reaction-out&quot; CV approach based on a random selection of items, the proposed one provides with more realistic estimation of prediction accuracy for reactions resulting in novel products. The new methodology has been applied to model rate constants of E2 reactions. It has been demonstrated that the use of the fragment control domain applicability approach significantly increases prediction accuracy of the models. The models obtained with new &quot;mixture&quot; approach performed better than those required either explicit (Condensed Graph of Reaction) or implicit (reaction fingerprints) reaction center labeling.

Název v anglickém jazyce

Structure–reactivity modeling using mixture-based representation of chemical reactions

Popis výsledku anglicky

We describe a novel approach of reaction representation as a combination of two mixtures: a mixture of reactants and a mixture of products. In turn, each mixture can be encoded using an earlier reported approach involving simplex descriptors (SiRMS). The feature vector representing these two mixtures results from either concatenated product and reactant descriptors or the difference between descriptors of products and reactants. This reaction representation doesn&apos;t need an explicit labeling of a reaction center. The rigorous &quot;product-out&quot; cross-validation (CV) strategy has been suggested. Unlike the na &lt; ve &quot;reaction-out&quot; CV approach based on a random selection of items, the proposed one provides with more realistic estimation of prediction accuracy for reactions resulting in novel products. The new methodology has been applied to model rate constants of E2 reactions. It has been demonstrated that the use of the fragment control domain applicability approach significantly increases prediction accuracy of the models. The models obtained with new &quot;mixture&quot; approach performed better than those required either explicit (Condensed Graph of Reaction) or implicit (reaction fingerprints) reaction center labeling.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10608 - Biochemistry and molecular biology

Projekt

—

Návaznosti

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of Computer-Aided Molecular Design

ISSN

0920-654X

e-ISSN

—

Svazek periodika

31

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

11

Strana od-do

829-839

Kód UT WoS článku

000412668900005

EID výsledku v databázi Scopus

—