\makeatletter
\@ifundefined{HCode}
{\documentclass[screen,CRCHIM,Unicode,biblatex,published]{cedram}
\addbibresource{crchim20250838.bib}
\newenvironment{noXML}{}{}
\def\tsup#1{$^{{#1}}$}
\def\tsub#1{$_{{#1}}$}
\def\thead{\noalign{\relax}\hline}
\def\tbody{\noalign{\relax}}
\def\endthead{\noalign{\relax}\hline}
\RequirePackage{etoolbox}
\usepackage{upgreek}
\def\hyphen{\text{-}}
\def\jobid{crchim20250838}
%\graphicspath{{/tmp/\jobid_figs/web/}}
\graphicspath{{./figures/}}
\newcounter{runlevel}
\let\MakeYrStrItalic\relax
\csdef{Seqnsplit}{\\}
\def\botline{\\\hline}
\def\refinput#1{}
\def\back#1{}
\def\0{\phantom{0}}
\def\ubreak{\break}
\def\inlinefig#1{\begin{center}\includegraphics{#1}\end{center}}
\def\tabnote#1{\vskip4pt\parbox{.78\linewidth}{#1}}
\newenvironment{inftab}{}{}
\usepackage{multirow} 
\def\nrow#1{\@tempcnta #1\relax%
\advance\@tempcnta by 1\relax%
\xdef\lenrow{\the\@tempcnta}}
\def\morerows#1#2{\nrow{#1}\multirow{\lenrow}{*}{#2}}
\DOI{10.5802/crchim.431}
\datereceived{2025-10-20}
\daterevised{2025-10-28}
\dateaccepted{2025-11-19}
\ItHasTeXPublished
\makeatletter
\g@addto@macro{\UrlBreaks}{\UrlOrds}
\gappto{\UrlBreaks}{\UrlOrds}
\makeatother
}
{\documentclass[crchim]{article}
\def\CDRdoi{10.5802/crchim.431}
\let\refinput\input
\def\href#1#2{\url[#1]{#2}}
\makeatletter
\def\CDRsupplementaryTwotypes#1#2{}
}
\makeatother

\usepackage{upgreek}

\dateposted{2026-01-22}
\begin{document}

\begin{noXML}

\CDRsetmeta{articletype}{research-article}

\editornote{Article submitted by invitation}
\alteditornote{Article soumis sur invitation}

\title{Electro-induced carbamoylation of arenes optimized by a machine
learning model}

\alttitle{Carbamoylation d'ar\`{e}nes \'{e}lectro-induite optimis\'{e}e
par un mod\`{e}le d'apprentissage}

\author{\firstname{Virgile} \lastname{Rouffeteau}\CDRorcid{0000-0002-4414-8088}}
\address{Chimie Physique et Chimie du Vivant (CPCV), D\'{e}partement de
Chimie, \'{E}cole Normale Sup\'{e}rieure, PSL University, Sorbonne
Universit\'{e}, CNRS, 75005 Paris, France}
\email[V. Rouffeteau]{virgile.rouffeteau@ens.psl.eu}

\author{\firstname{Clara} \lastname{Perrier}}
\addressSameAs{1}{Chimie Physique et Chimie du Vivant (CPCV),
D\'{e}partement de Chimie, \'{E}cole Normale Sup\'{e}rieure, PSL
University, Sorbonne Universit\'{e}, CNRS, 75005 Paris, France}
%\email{clara.perrier@ens.psl.eu}

\author{\firstname{Maximilian} \lastname{Fleck}}
\address{Chimie ParisTech, Universit\'{e} PSL, CNRS, Institute of
Chemistry for Life and Health Sciences, 75005 Paris, France}
%\email{maximilian.fleck@chimieparistech.psl.eu}

\author{\firstname{Geoffrey} \lastname{Gontard}\CDRorcid{0000-0002-4099-5423}}
\address{Institut Parisien de Chimie Mol\'{e}culaire, CNRS UMR 8232,
Sorbonne Universit\'{e}, 75252 Paris Cedex 5, France}
%\email{geoffrey.gontard@sorbonne-universite.fr}

\author{\firstname{Maxime\nobreakauthor R.} \lastname{Vitale}\CDRorcid{0000-0002-6740-2472}\IsCorresp}
\addressSameAs{1}{Chimie Physique et Chimie du Vivant (CPCV),
D\'{e}partement de Chimie, \'{E}cole Normale Sup\'{e}rieure, PSL
University, Sorbonne Universit\'{e}, CNRS, 75005 Paris, France}
\email[M. R. Vitale]{maxime.vitale@ens.psl.eu}

\author{\firstname{Laurence} \lastname{Grimaud}\CDRorcid{0000-0003-3904-1822}\IsCorresp}
\addressSameAs{1}{Chimie Physique et Chimie du Vivant (CPCV),
D\'{e}partement de Chimie, \'{E}cole Normale Sup\'{e}rieure, PSL
University, Sorbonne Universit\'{e}, CNRS, 75005 Paris, France}
\email[L. Grimaud]{laurence.grimaud@ens.psl.eu}

\shortrunauthors

\keywords{\kwd{Electrosynthesis}\kwd{Multicomponent
reaction}\kwd{C(sp\textsuperscript{2})--H
functionalization}\kwd{Carbamoylation}\kwd{Bayesian optimization}}

\altkeywords{\kwd{Electrosynth\`{e}se}\kwd{R\'{e}action
multicomposantes}\kwd{Fonctionnalisation de liaisons
C(sp\textsuperscript{2})--H}\kwd{Carbamoylation}\kwd{Optimisation Bay\'{e}sienne}}

\thanks{ENS-PSL, CNRS, ANR (ANR-20-CE07-0020), Ecole Polytechnique
(AMX)}

\begin{abstract}
In this article, we report the electro-induced C--H functionalization
of aromatic compounds by isocyanides and water, to produce
arylcarboxamides. This controlled oxidation of electron-rich aromatic
compounds leads to an eco-efficient synthesis of secondary
benzocarboxamides, along with cyanide group formation.  The
optimization process was guided by a Bayesian optimization-based model,
and good yields were quickly obtained.
\end{abstract}

\begin{altabstract}
Dans cet article, nous pr\'{e}sentons une fonctionnalisation
\'{e}lectro-induite de liaisons C(sp\textsuperscript{2})--H de compos\'{e}s
aromatiques par des isonitriles et de l'eau pour synth\'{e}tiser de
arylcarboxamides. Cette oxydation contr\^{o}l\'{e}e de substrats
aromatiques riches en \'{e}lectrons permet une synth\`{e}se efficace et
respectueuse de l'environnement de benzocarboxamides secondaires et de
nitriles. L'optimisation a \'{e}t\'{e} guid\'{e}e par un mod\`{e}le d'
apprentissage automatique fond\'{e} sur l'optimisation bay\'{e}sienne,
et de bons rendements ont \'{e}t\'{e} rapidement obtenus.
\end{altabstract}

%\input{CR-pagedemetas} 

\maketitle

\twocolumngrid

\end{noXML}

\section{Introduction}\label{sec1}

\vspace*{-2pt}

Multicomponent reactions (MCRs) have seen a surge in interest
due to their significant abilities of building complex scaffolds from
easy-to-access starting materials, all the while respecting the
principles of green chemistry~\cite{1}.\ A subclass of this field is the
isocyanide-based multicomponent reactions (\mbox{IMCRs}), the
Passerini~\cite{2} and Ugi~\cite{3} reactions being prime examples.
They employ the unique properties of isocyanide moieties: they
classically first react as nucleophiles, to generate nitrilium species,
which can then be trapped by other nucleophiles, to efficiently
construct complex patterns in one step~\cite{4}.

\begin{scheme*}
{\vspace*{-.1pc}}
\includegraphics{sc01}
{\vspace*{.4pc}}
\caption{\label{sch1}Previous and current strategies for direct
oxidative C(sp$^{2}$)--H functionalization.}
{\vspace*{-.6pc}}
\end{scheme*}

Electrosynthesis can also be a major contributor to respecting green
chemistry principles, by replacing costly and stoichiometric oxidants
(often toxic and with poor atom-economy), or rare-earth-based
catalysts~\cite{5,6}. In this endeavour, our
group~\mbox{\cite{7,8,9,10}} and many others~\cite{11} merged the two
concepts, electrosynthesis and IMCR, to avoid the use of unstable
substrates, additives, or catalysts, toward the synthesis of Passerini
and Ugi adducts among other structures.\ However, synthetizing a
benzamide group from a non-substituted aromatic compound without using
a metal-based catalysis and functionalization of the aromatic ring
remained elusive. Inspired by previous electro-induced \mbox{C(sp$^{2}$)--H}
bond functionalizations~\cite{12,13,14,15} (Scheme~\ref{sch1}), we
proposed a method merging \mbox{electrosynthesis} and~IMCR~toward the
production of arylcarboxamides.\looseness=1

Indeed, building on the mechanistic studies of Goo{\ss}en
et~al.~\cite{13}, we surmised that a radical cation, produced at the
anode from the direct oxidation of an arene, could be trapped by an
isocyanide and a water molecule to build arylcarboxamides. The released
protons would in turn be converted into dihydrogen at the cathode,
closing the electrical circuit (Scheme~\ref{sch2}). This original
carboxamide synthesis would avoid the use of catalyst and
\mbox{stoichiometric} oxidants, using green energy (94\% of low-carbon
electricity in France's electricity mix in 2024, 96\% in 2025) to
convert available substrates into high-value products~\cite{16}.\looseness=1

\begin{scheme*}
\includegraphics{sc02}
{\vspace*{.6pc}}
\caption{\label{sch2}Proposed mechanism.}
{\vspace*{-.4pc}}
\end{scheme*}

\begin{scheme*}
\includegraphics{sc03}
{\vspace*{.6pc}}
\caption{\label{sch3}Starting point.}
\end{scheme*}

\section{Results and discussion} \label{sec2}

With this strategy in mind and using our in-house expertise on
electro-induced IMCRs, we selected mesitylene \textbf{1a} as a
prototypical oxidizable arene along with cyclohexyl isocyanide (Cy-CN)
\textbf{2a} as partner in acetonitrile as solvent.\ A quick
pre-optimization led to choose $N$-tetrabutylammonium tetrafluoroborate
($n$-Bu$_4$NBF$_4$) as supporting electrolyte, graphite as cathode and
stainless steel as anode. These conditions led to the isolation of
desired product \textbf{3a} in 38\% yield, which constituted the
starting point of the optimization process.

\begin{scheme*}
{\vspace*{.3pc}}
\includegraphics{sc04}
{\vspace*{.7pc}}
\caption{\label{sch4}Products formed according to isocyanide
equivalents.}
{\vspace*{-.1pc}}
\end{scheme*}

Subsequent tests fixed the temperature at 20~{\textdegree}C (a 41\%
yield at 60~{\textdegree}C was not significant enough to continue using
high temperature) and showed that the stirring had no impact on the
outcome. These observations fixed half of the reaction parameters (see
Table~S1 in Supplementary material), however, the rest of the
parameters (in italic in Scheme~\ref{sch3}) could hardly be optimized
the usual way, one at a time, as they could be interdependent. Thus, we
resorted to a machine learning model, as it was capable of optimizing
several parameters at the same time~\mbox{\cite{17,18,19,20}}. The
model chosen was EDBO, created by the Doyle group in 2021~\cite{21} for
its low resource cost and availability (\url{https://edboplus.org/}).
While this work was in progress, the Ackerman group also used machine
learning to optimize an electro-induced annulation via palladium
catalysis~\cite{22}, while the Sigman group reported using EDBO for the
design of palladium catalyst for the fluorination of arylboronic acids
\cite{23}, proving the usefulness of this strategy. In order
to use this model, several questions needed to be answered: (1)~Which
outcome(s) is (are) of concern to us, and whether its maximization or
minimization were desired? (2)~How to \mbox{measure} the chosen
outcome, and how to interact with the model? (3)~What is the research
space for the model to investigate? (4)~What is (are) the stop
\mbox{condition(s)}?

In our case, maximizing the yield was the main goal, which would be
measured by ${}^{1}$H NMR against an internal standard, the supporting
electrolyte (it was proven to be stable with external standards). The
research space was designed as neutral as possible, to avoid
introducing human bias into the model (see Table~\ref{tab1}). As an
example, various amounts of the isocyanide led to different products,
\textbf{3a} and \textbf{4a} (see Scheme~\ref{sch4}, structure of
\textbf{4a} was elucidated by \mbox{X-ray} analyses). Thus, the number
of isocyanide equiv had to be limited between $0.33''$ and 3 (0.33
experimentally means 1 equiv of isocyanide and 3 equiv of mesitylene).
\looseness=-1

\begin{table*}[t!]%tab1
\tabcolsep=8pt
\caption{\label{tab1}Research space}
\begin{tabular}{cccccccc}
\thead
Parameters & \multicolumn{7}{c}{Values}\\
\endthead
Cy-NC equiv & 0.33 & 0.5 & 0.75 & 1 & 1.5 & 2 & 3\\
Water equiv & 1 & 5 & 10 & 25 & 50 &&\\
$n$-Bu$_4$NBF$_4$ equiv & 0.5\0 & 1 & 2 &&&&\\
Current density (mA${\cdot}$cm$^{-2}$) & 5 & 10 & 15 & 20 & 25 &&\\
Limiting reagent concentration (M) & 0.05 & 0.1 & 0.15 & 0.2 &&&\\
Charge ($F{\cdot}$mol$^{-1}$) & 2 & 3 & 4 & 5 & 6 &&
\botline
\end{tabular}
\end{table*}

Similarly, using more than 50 equiv of water was meaningless, so its
limits were set at 1 and 50 equiv. Standard values often found in the
literature for the supporting electrolyte were between 0.5 and 2~equiv;
for the concentration of the reagents, they were above 0.05~M and below
0.5~M, and the current density was bounded between 5 and
25~mA${\cdot}$cm$^{-2}$. Finally, based on our proposed mechanism (see
Scheme~\ref{sch2}), this reaction would need at least 2 electrons per
molecule of mesitylene. Using the same limits as for the isocyanide,
the upper limit for the charge was set at 6~$F{\cdot}$mol$^{-1}$. These
studies led to the following research space (Table~\ref{tab1}).

The resulting number of possible combinations was 10~500, and, as an
example, a human would conduct 29 (0.3\% of the research space)
experiments with this table: one experiment for each value of each
parameter, with all other parameters fixed, following the classical
OFAT (one factor at a time) method~\cite{24}. For the purpose of this
study, we decided to fix the total number of experiments to 15, which
represents half the effort required with the OFAT method (below 0.15\%
of the research space). The results of this EDBO-led optimization are
displayed in\break Figure~\ref{fig1}. 

\begin{scheme*}
{\vspace*{.2pc}}
\includegraphics{sc05}
{\vspace*{.6pc}}
\caption{\label{sch5}Final conditions found by EDBO.}
{\vspace*{-.6pc}}
\end{scheme*}

\begin{scheme*}
\includegraphics{sc06}
{\vspace*{.6pc}}
\caption{\label{sch6}Scope of the studied reaction.}
{\vspace*{-.4pc}}
\end{scheme*}

\begin{figure}
\includegraphics{fig01}
{\vspace*{-.2pc}}
\caption{\label{fig1}Evolution of yield with EDBO.}
{\vspace*{-.2pc}}
\end{figure}

It became clear that EDBO was able to quickly increase the yield from
the starting 38\%, reaching 50\% after 5 experiments, 70\% at the 9th,
and stopping at its 15th experiment, in which the starting yield of
38\% was doubled to reach a high yield of 74\%. The differences between
the starting point (Scheme~\ref{sch3}) and the best conditions found by
EDBO (Scheme~\ref{sch5}) were counter-intuitive compared to commonly
used values (isocyanide in default, high current density and
concentration), highlighting the importance of an unbiased design of
the research space.

With these optimized conditions, the scope of the reaction's
applicability was then tested (Scheme~\ref{sch6}). \looseness=1

Primary and secondary isocyanides were found to work under these
conditions (74\% for cyclohexyl \mbox{isocyanide}, 52\% for 1-pentyl
isocyanide, and 31\% for benzyl isocyanide), while the aromatic
isocyanide gave a low amount of the desired product (5\%).
Interestingly, tertiary isocyanides were found to fragment to give the
cyano compound in good yield (up~to 91\% NMR yield, 52\% isolated
yield)\footnote{This benzonitrile is prone to sublimation, which
explains the difference between the two yields.}. 
Its formation is supposed to take place when the
iminyl radical is produced: this structure may fragment to release a
stabilized tertiary carbon-centered radical and the benzonitrile
compound, favoring this elimination. \looseness=1

Alternative aromatic compounds were also tested, and $m$-xylene was
functionalized with an acceptable 36\% yield. Anisole was found to
polymerize (black tar formation), resulting in low yield (17\%), while
\textit{tert}-butylbenzene also gave the \textit{para}-product in low
yield (7\%, also prone to polymerization). Several other aromatic
compounds were tested, and none produced the desired amide in
detectable\break amounts. 

\section{Conclusion}\label{sec3}

In this article, we report a previously unknown electro-induced
isocyanide-based multicomponent reaction toward the synthesis of
arylcarboxamides, with an AI-guided optimization. In respect with green
chemistry objectives, this work avoids the use of chemical oxidants,
coupling agents, or catalysts by relying on electrosynthesis. The
optimization was conducted with a minimal number of experiments, thanks
to guidance by a Bayesian optimization-based model (EDBO). Overall,
this work opens a path toward more challenging electro-induced methods
and the use of AI in the laboratory. Subsequent work on other
electro-induced IMCRs is currently under investigation in our team.

\section*{CRediT authorship contribution statement}

\textbf{Virgile Rouffeteau:} Data curation, Writing---original draft. 

\noindent
\textbf{Clara Perrier:} Data curation, Writing---review \& editing. 

\noindent
\textbf{Maximilian  Fleck:} Software, Writing---review \& editing.

\noindent
\textbf{Geoffrey Gontard:} Formal analysis, Writing---review \& editing.

\noindent
\textbf{Maxime R. Vitale:} Funding acquisition, Conceptualization, Supervision, Writing---review
\& editing. 

\noindent
\textbf{Laurence Grimaud:} Funding acquisition, Conceptualization, Supervision, Writing---review \& editing.

\section*{Acknowledgments}

Drs. A.~Simon and S.~Bachollet are thanked for early investigations.

\section*{Declaration of interests}

The authors do not work for, advise, own shares in, or receive funds
from any organization that could benefit from this article, and have
declared no affiliations other than their research organizations.

\section*{Funding}

ENS-PSL, CNRS, and the Agence Nationale de la Recherche
(ANR-20-CE07-0020) are thanked for financial support. VR thanks Ecole
Polytechnique for a PhD grant (AMX). CP thanks CNRS for a placement
grant.\ MF acknowledges support under the Major Research Program of PSL
Research University ``ChemAI'' launched by PSL Research University and
implemented by ANR with the references ANR-10-IDEX-0001.

\CDRGrant[ANR]{ANR-20-CE07-0020}
\CDRGrant[ANR]{ANR-10-IDEX-0001}

\section*{Supplementary materials}
Supporting information for this article is available on the journal's
website under \printDOI\ or from the author.

Deposition Number CCDC 2492104 contain the supplementary
crystallographic data for compound \textbf{4a}. These data can be
accessed free of charge via the Cambridge Crystallographic Data Centre
(CDCC).

\CDRsupplementaryTwotypes{supplementary-material}{\cdrattach{crchim-431-suppl.pdf}}

\back{}

\vspace*{-.2pc}

\printbibliography
\refinput{crchim20250838-reference.tex}

\end{document}