Artificial intelligence and molecule machine join forces to generalize automated chemistry

Date
11/17/22
Pictured, from left: University of Illinois chemistry professor Martin D. Burke, materials science and engineering professor Charles M. Schroeder, graduate student Nicholas Angello and postdoctoral researcher Vandana Rathore. Photo by Fred Zwicky

By Liz Ahlberg Touchstone, Illinois News Bureau


Artificial intelligence, “building-block” chemistry and a molecule-making machine teamed up to find the best general reaction conditions for synthesizing chemicals important to biomedical and materials research – a finding that could speed innovation and drug discovery as well as make complex chemistry automated and accessible.

With the machine-generated optimized conditions, researchers at the University of Illinois Urbana-Champaign and collaborators in Poland and Canada doubled the average yield of a special, hard-to-optimize type of reaction linking carbon atoms together in pharmaceutically important molecules. The researchers say their system provides a platform that also could be used to find general conditions for other classes of reactions and solutions for similarly complex problems. They reported their findings in the journal Science.

“Generality is critical for automation, and thus making molecular innovation accessible even to nonchemists,” said study co-leader Dr. Martin D. Burke, an Illinois professor of chemistry and of the Carle Illinois College of Medicine, as well as a medical doctor. “The challenge is the haystack of possible reaction conditions is astronomical, and the needle is hidden somewhere inside. By leveraging the power of artificial intelligence and building-block chemistry to create a feedback loop, we were able to shrink the haystack. And we found the needle.”

Automated synthesis machines for proteins and nucleic acids such as DNA have revolutionized research and chemical manufacturing in those fields, but many chemicals of importance for pharmaceutical, clinical, manufacturing and materials applications are small molecules with complex structures, the researchers say.

Burke’s group has pioneered the development of simple chemical building blocks for small molecules. His lab also developed an automated molecule-making machine that snaps together the buildings blocks to create a wide range of possible structures.

However, general reaction conditions to make the automated process broadly applicable have remained elusive.

“Traditionally, chemists customize the reaction conditions for each product they are trying to make,” Burke said. “The problem is that this is a slow and very specialist-dependent process, and very hard to automate because the machine would have to be optimized every time. What we really want are conditions that work almost every time, no matter what two things you’re trying to snap together.”  

An automated approach with generalized conditions could help standardize how some products are made, addressing the problem of reproducibility, said Illinois postdoctoral researcher Vandana Rathore, a co-first author of the study.

Burke’s group teamed up with a group led by Bartosz A. Grzybowski at the Polish Academy of Sciences’ Institute for Organic Chemistry, as well as the group of Alán Aspuru-Guzik at the University of Toronto, both leaders in using artificial intelligence and machine learning to improve chemical synthesis. The team integrated AI with the molecule machine to provide real-time feedback to the machine-learning system.

“To distinguish good and bad you need to know something about the bad, but people only publish the successes,” Grzybowski said. Published studies reflect conditions that are popular or convenient, rather than the best, so a systematic approach that included diverse data and negative results was necessary, he said.

First, the team ran the entire matrix of possible combinations using the building-block chemistry through an algorithm to group together similar reactions. Then, the AI sent instructions, inputted to a machine in the Molecule Maker Lab located in the Beckman Institute for Advanced Science and Technology at Illinois, to produce representative reactions from each cluster. The information from those reactions fed back into the model; the AI learned from the data and ordered more experiments from the molecule machine.

“We were looking to see two things: an increase in yield and a decrease in uncertainty, for a broad spectrum of reactions,” said Grzybowski, who now is at Ulsan Institute of Science and Technology in South Korea. “This loop continued without us having to intervene until the problem was solved. Figuring out the generalized conditions for protein-synthesis machines took 30 years. This took us two months.”

The process identified conditions that doubled the average yield of a challenging class of reactions, called heteroaryl Suzuki-Miyaura coupling, crucial for many biological and materials-relevant compounds.

“There are all kinds of building block combinations that we didn't even study in our AI training, but because the AI had explored such a diverse space, it found good results even in those initially unexplored areas,” said Illinois graduate student Nicholas H. Angello, a co-first author of the study.

The machine-learning process described in the paper also could be applied to other broad areas of chemistry to find the best reaction conditions for other types of small molecules or even larger organic polymers, the researchers say.

“There are so many different materials classes that we want to know, target and discover for different functional properties. The extension possibility of this approach to other similar reaction chemistry, other types of carbon-carbon links, is exciting,” said study co-author Charles M. Schroeder, an Illinois professor of materials science and engineering and chemical and biomolecular engineering, and a Beckman Institute affiliate.

The Defense Advanced Research Projects Agency and the National Science Foundation supported this work.

Editor’s notes: To reach Martin Burke, email: mdburke@illinois.edu.  

The paper “Closed-loop optimization of general reaction conditions for heteroaryl Suzuki-Miyaura coupling” is available online.

DOI: 10.1126/science.adc8743

This research in the news: 

AI discovers the best general conditions yet for cross couplings, doubling yields | Research | Chemistry World

Space-based solar power gets serious, AI helps optimize chemistry, and a book on food extinction | Science | AAAS

AI teaches robots to synthesise drugs faster | Science in Poland

Related People

mdburke

Directory

scheelinAlexander
Scheeline
bjmccallBenjamin
McCall
r-gennisRobert
Gennis
j-gerltJohn
Gerlt
sgranickSteve
Granick
mgruebelMartin
Gruebele
hergenroPaul
Hergenrother
huangRaven
Huang
mlkraftMary
Kraft
leckbandDeborah
Leckband
yi-luYi
Lu
martinisSusan
Martinis
snairSatish
Nair
eoldfielEric
Oldfield
cmsCharles
Schroeder
zanZaida
Luthey-Schulten
selvinPaul
Selvin
sksScott
Silverman
s-sligarStephen
Sligar
tajkhorsEmad
Tajkhorshid
zhao5Huimin
Zhao
pbraunPaul
Braun
mdburkeMartin
Burke
jeffchanJefferson
Chan
sdenmarkScott
Denmark
dlottDana
Dlott
foutAlison
Fout
agewirthAndrew
Gewirth
ggirolamGregory
Girolami
sohirataSo
Hirata
jainPrashant
Jain
jkatzeneJohn
Katzenellenbogen
nmakriNancy
Makri
douglasmDouglas
Mitchell
jsmooreJeffrey
Moore
murphycjCatherine
Murphy
r-nuzzoRalph
Nuzzo
dimerPhilip
Phillips
rauchfuzThomas
Rauchfuss
joaquinrJoaquín
Rodríguez-López
sarlahDavid
Sarlah
kschweizKenneth
Schweizer
jsweedleJonathan
Sweedler
vddonkWilfred
van der Donk
renskeRenske
van der Veen
vuraweisJosh
Vura-Weis
mcwhite7M.
White
sczimmerSteven
Zimmerman
beakPeter
Beak
wklemperWalter
Klemperer
jdmcdonaJ.
McDonald
pogoreloTaras
Pogorelov
mshen233Mei
Shen
dewoonDavid
Woon
wboulangWilliam
Boulanger
rxbRohit
Bhargava
qchen20Qian
Chen
jianjuncJianjun
Cheng
hy66Hong
Yang
andinomaJosé
Andino Martinez
decosteDonald
DeCoste
thhuangTina
Huang
tjhummelThomas
Hummel
dkellDavid
Kell
doctorkMichael
Koerner
marvilleKelly
Marville
crrayChristian
Ray
tlbrownTheodore
Brown
rmcoatesRobert
Coates
thdjrThom
Dunning
dykstraClifford
Dykstra
j-jonasJiri
Jonas
j-lisyJames
Lisy
shapleyJohn
Shapley
pshapleyPatricia
Shapley
zumdahl2Steven
Zumdahl
ksuslickKenneth
Suslick
jcoxJenny
Cox
sqdSean
Drummond
sheeleySarah
Sheeley
jsmaddenJoseph
Madden
cknight4Connie
Knight
schulzeHeather
Schulze
kbaumgarKeena
Finney
adkssnBeatrice
Adkisson
trabari1Katie
Trabaris
metclfKara
Metcalf
ljohnso2Lori
Johnson
lchenoweLeslie
Chenoweth
wdedoWolali
Dedo
spinnerDavid
Spinner
plblumPatricia
Simpson
stevens2Chad
Stevens
lsagekarLori
Sage-Karlson
bertholdDeborah
Berthold
kecarlsoKathryn
Carlson
sdesmondSerenity
Desmond
axelson2Jordan
Axelson
scbakerStephanie
Baker
pflotschPriscila
Falagan Lotsch
dgrayDanielle
Gray
thennes2Tom
Hennessey
holdaNancy
Holda
aibarrAlejandro
Ibarra
kimshSung Hoon
Kim
kocherg2Nikolai
Kocherginsky
philipk2Philip
Kocheril
legare2Stephanie
Legare
alewandoAgnieszka
Lewandowska
smccombiStuart
McCombie
jdm5Justin
McGlauchlen
egmooreEdwin
Moore
myerscouKathleen
Myerscough
snalla2Siva
Nalla
romanovaElena
Romanova
roubakhiStanislav
Rubakhin
shvedalxAlexander
Shved
asoudaAlexander
Soudakov
xywangXiying
Wang
kwilhelKaren
Wilhelmsen
wilkeyRandy
Wilkey
silongSilong
Zhang
schlembaMary
Schlembach
trimmellAshley
Trimmell
emccarr2Elise
McCarren
cmercierChristen
Mercier
atimpermAaron
Timperman
niesShuming
Nie
hshanHee-Sun
Han
mmgMutha
Gunasekera
kknightsKatriena
Knights
lisawLisa
Williamson
keinckKatie
Einck
kneef1Kate
Neef
txiang4Tiange
Xiang
j-hummelJohn
Hummel
i-paulIain
Paul
munjanjaLloyd
Munjanja
glnGayle
Nelsen
agerardAnna
Gerard
powerskaKimberly
Powers
lolshansLisa
Olshansky
miricaLiviu
Mirica
qingcao2Qing
Cao
lisa3Lisa
Johnson
tinalambTina
Lamb
baronpBaron
Peters
bransle2Sarah
Bransley
dylanmh2Dylan
Hamilton
raegansRaegan
Smith
apm8Angad
Mehta
leverittJohn
Leveritt
xingwXing
Wang
emillrEva
Miller
jmill24Jacqueline
Miller
jlbass2Julia
Bass
ramonarRamona
Rudzinski
tlcraneTracy
Crane
cejohnstCelia
Johnston
adlAmber
LaBau
cnsolomoCandice
Solomon-Strutz
mikaelbMikael
Backlund
jacksonnNick
Jackson