2026
|
Velasco, Pablo Quijano; Leong, Chang Jie; Koay, Eleen H H; Hippalgaonkar, Kedar; Cheng, Jayce Jian Wei Qubots: open-source modular laboratory robots as building blocks for
flexible assembly of self-driving labs DIGITAL DISCOVERY, 2026, DOI: 10.1039/d6dd00280c. Abstract | BibTeX | Endnote @article{WOS:001867005000001,
title = {Qubots: open-source modular laboratory robots as building blocks for
flexible assembly of self-driving labs},
author = {Pablo Quijano Velasco and Chang Jie Leong and Eleen H H Koay and Kedar Hippalgaonkar and Jayce Jian Wei Cheng},
doi = {10.1039/d6dd00280c},
times_cited = {0},
year = {2026},
date = {2026-08-01},
journal = {DIGITAL DISCOVERY},
publisher = {ROYAL SOC CHEMISTRY},
address = {THOMAS GRAHAM HOUSE, SCIENCE PARK, MILTON RD, CAMBRIDGE CB4 0WF, CAMBS,
ENGLAND},
abstract = {Lab automation is a key enabler of algorithmic-driven research in
materials science; by increasing the throughput and accelerating
experimental workflows researchers can generate the large amounts of
experimental datasets required to validate and refine machine learning
and artificial intelligence models. Nonetheless, access to automation
remains limited to a small subset of the scientific community due to the
high cost of commercial systems, limited expertise and lack of flexible
automation tools for evolving research workflows. In response, research
groups have developed custom automation solutions by retrofitting
low-cost motion platforms, such as 3D printers or CNC machines, to
perform experimental tasks. However, these platforms have not been
originally designed to meet the requirements of materials science and
engineering (MSE) experiments, leading to solutions that do not
necessarily scale well with common laboratory infrastructure and
practices. Here we introduce the Qubot, a flexible and modular robotic
platform designed to meet the requirements of MSE experiments that is
built from standardized cost-effective components, lowering the
financial and technical barriers for adoption. We characterize the Qubot
performance using internationally recognised protocols, demonstrating
repeatability and precision superior to that of commonly used motion
platforms that are retrofitted for experimental work. Finally, we
validate the design through stress testing in representative
experimental tasks and demonstrate their flexible modularity by applying
them in two fully automated laboratory workflows related to the
preparation and characterization of shampoo formulations and polymer
electrolytes.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lab automation is a key enabler of algorithmic-driven research in
materials science; by increasing the throughput and accelerating
experimental workflows researchers can generate the large amounts of
experimental datasets required to validate and refine machine learning
and artificial intelligence models. Nonetheless, access to automation
remains limited to a small subset of the scientific community due to the
high cost of commercial systems, limited expertise and lack of flexible
automation tools for evolving research workflows. In response, research
groups have developed custom automation solutions by retrofitting
low-cost motion platforms, such as 3D printers or CNC machines, to
perform experimental tasks. However, these platforms have not been
originally designed to meet the requirements of materials science and
engineering (MSE) experiments, leading to solutions that do not
necessarily scale well with common laboratory infrastructure and
practices. Here we introduce the Qubot, a flexible and modular robotic
platform designed to meet the requirements of MSE experiments that is
built from standardized cost-effective components, lowering the
financial and technical barriers for adoption. We characterize the Qubot
performance using internationally recognised protocols, demonstrating
repeatability and precision superior to that of commonly used motion
platforms that are retrofitted for experimental work. Finally, we
validate the design through stress testing in representative
experimental tasks and demonstrate their flexible modularity by applying
them in two fully automated laboratory workflows related to the
preparation and characterization of shampoo formulations and polymer
electrolytes. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AFPablo Quijano Velasco
Chang Jie Leong
Eleen H H Koay
Kedar Hippalgaonkar
Jayce Jian Wei Cheng
- TIQubots: open-source modular laboratory robots as building blocks for
flexible assembly of self-driving labs - SODIGITAL DISCOVERY
- DTArticle
- ABLab automation is a key enabler of algorithmic-driven research in
materials science; by increasing the throughput and accelerating
experimental workflows researchers can generate the large amounts of
experimental datasets required to validate and refine machine learning
and artificial intelligence models. Nonetheless, access to automation
remains limited to a small subset of the scientific community due to the
high cost of commercial systems, limited expertise and lack of flexible
automation tools for evolving research workflows. In response, research
groups have developed custom automation solutions by retrofitting
low-cost motion platforms, such as 3D printers or CNC machines, to
perform experimental tasks. However, these platforms have not been
originally designed to meet the requirements of materials science and
engineering (MSE) experiments, leading to solutions that do not
necessarily scale well with common laboratory infrastructure and
practices. Here we introduce the Qubot, a flexible and modular robotic
platform designed to meet the requirements of MSE experiments that is
built from standardized cost-effective components, lowering the
financial and technical barriers for adoption. We characterize the Qubot
performance using internationally recognised protocols, demonstrating
repeatability and precision superior to that of commonly used motion
platforms that are retrofitted for experimental work. Finally, we
validate the design through stress testing in representative
experimental tasks and demonstrate their flexible modularity by applying
them in two fully automated laboratory workflows related to the
preparation and characterization of shampoo formulations and polymer
electrolytes. - Z90
- PUROYAL SOC CHEMISTRY
- PATHOMAS GRAHAM HOUSE, SCIENCE PARK, MILTON RD, CAMBRIDGE CB4 0WF, CAMBS,
ENGLAND - DI10.1039/d6dd00280c
- UTWOS:001867005000001
- ER
- EF
|
Li, Yahao; Wang, Yuqing; Zheng, Mei; Zhang, Chenguang; Ma, Mingyu; Hippalgaonkar, Kedar; Li, Shuzhou; Wu, Meng; Liu, Zheng; Si, Wenping Atomic-level ionic polarization in poly(heptazine imides) towards
enhanced photocatalytic H2O2 production CHEMICAL ENGINEERING JOURNAL, 538 , 2026, DOI: 10.1016/j.cej.2026.176636. Abstract | BibTeX | Endnote @article{WOS:001761156300001,
title = {Atomic-level ionic polarization in poly(heptazine imides) towards
enhanced photocatalytic H2O2 production},
author = {Yahao Li and Yuqing Wang and Mei Zheng and Chenguang Zhang and Mingyu Ma and Kedar Hippalgaonkar and Shuzhou Li and Meng Wu and Zheng Liu and Wenping Si},
doi = {10.1016/j.cej.2026.176636},
times_cited = {3},
issn = {1385-8947},
year = {2026},
date = {2026-06-01},
journal = {CHEMICAL ENGINEERING JOURNAL},
volume = {538},
publisher = {ELSEVIER SCIENCE SA},
address = {PO BOX 564, 1001 LAUSANNE, SWITZERLAND},
abstract = {Polarization provides an effective pathway to regulate charge separation
in photocatalytic materials, however, how to introduce polarization into
organic photocatalysts without destroying pi-conjugation remains
challenging. Here, we demonstrate that Na+ ions confined within the
heptazine cavities of crystalline poly(heptazine imides) (PHI) generate
intrinsic ionic polarization while preserving the pi-conjugated
framework of carbon nitride. Detailed characterizations reveal that the
atomic-level dipoles are induced by structural and electronic asymmetry
due to the sodium ion incorporation within the PHI lattice, directing
from sodium (Na+) to the adjacent nitrogen. Piezoresponse force
microscopy (PFM) measurements, X-ray absorption near-edge structure
(XANES) analysis, and density functional theory (DFT) calculations
collectively confirm the formation of localized dipoles and the
resulting internal electric field, establishing a direct relationship
between ionic polarization and charge separation. When applied in
photocatalytic energy conversion, this PHI-Na exhibits the H2O2
production rate of 46.6 mmol g(-1) h(-1) and 59.5 mmol g(-1) h(-1) under
visible light and AM1.5G, respectively, and the accumulated H2O2
concentration within 4 h reaches up to similar to 17 mM, which stands
out among other organic semiconductor counterparts. This work reveals a
structure-defined route to introduce ionic polarization in carbon
nitride crystal and provides new insights into designing efficient
metal-free photocatalysts for solar energy conversion.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Polarization provides an effective pathway to regulate charge separation
in photocatalytic materials, however, how to introduce polarization into
organic photocatalysts without destroying pi-conjugation remains
challenging. Here, we demonstrate that Na+ ions confined within the
heptazine cavities of crystalline poly(heptazine imides) (PHI) generate
intrinsic ionic polarization while preserving the pi-conjugated
framework of carbon nitride. Detailed characterizations reveal that the
atomic-level dipoles are induced by structural and electronic asymmetry
due to the sodium ion incorporation within the PHI lattice, directing
from sodium (Na+) to the adjacent nitrogen. Piezoresponse force
microscopy (PFM) measurements, X-ray absorption near-edge structure
(XANES) analysis, and density functional theory (DFT) calculations
collectively confirm the formation of localized dipoles and the
resulting internal electric field, establishing a direct relationship
between ionic polarization and charge separation. When applied in
photocatalytic energy conversion, this PHI-Na exhibits the H2O2
production rate of 46.6 mmol g(-1) h(-1) and 59.5 mmol g(-1) h(-1) under
visible light and AM1.5G, respectively, and the accumulated H2O2
concentration within 4 h reaches up to similar to 17 mM, which stands
out among other organic semiconductor counterparts. This work reveals a
structure-defined route to introduce ionic polarization in carbon
nitride crystal and provides new insights into designing efficient
metal-free photocatalysts for solar energy conversion. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AFYahao Li
Yuqing Wang
Mei Zheng
Chenguang Zhang
Mingyu Ma
Kedar Hippalgaonkar
Shuzhou Li
Meng Wu
Zheng Liu
Wenping Si
- TIAtomic-level ionic polarization in poly(heptazine imides) towards
enhanced photocatalytic H2O2 production - SOCHEMICAL ENGINEERING JOURNAL
- DTArticle
- ABPolarization provides an effective pathway to regulate charge separation
in photocatalytic materials, however, how to introduce polarization into
organic photocatalysts without destroying pi-conjugation remains
challenging. Here, we demonstrate that Na+ ions confined within the
heptazine cavities of crystalline poly(heptazine imides) (PHI) generate
intrinsic ionic polarization while preserving the pi-conjugated
framework of carbon nitride. Detailed characterizations reveal that the
atomic-level dipoles are induced by structural and electronic asymmetry
due to the sodium ion incorporation within the PHI lattice, directing
from sodium (Na+) to the adjacent nitrogen. Piezoresponse force
microscopy (PFM) measurements, X-ray absorption near-edge structure
(XANES) analysis, and density functional theory (DFT) calculations
collectively confirm the formation of localized dipoles and the
resulting internal electric field, establishing a direct relationship
between ionic polarization and charge separation. When applied in
photocatalytic energy conversion, this PHI-Na exhibits the H2O2
production rate of 46.6 mmol g(-1) h(-1) and 59.5 mmol g(-1) h(-1) under
visible light and AM1.5G, respectively, and the accumulated H2O2
concentration within 4 h reaches up to similar to 17 mM, which stands
out among other organic semiconductor counterparts. This work reveals a
structure-defined route to introduce ionic polarization in carbon
nitride crystal and provides new insights into designing efficient
metal-free photocatalysts for solar energy conversion. - Z93
- PUELSEVIER SCIENCE SA
- PAPO BOX 564, 1001 LAUSANNE, SWITZERLAND
- SN1385-8947
- VL538
- DI10.1016/j.cej.2026.176636
- UTWOS:001761156300001
- ER
- EF
|
2025
|
Malica, Cristiano; Novoselov, Kostya S; Barnard, Amanda S; V, Sergei Kalinin; Spurgeon, Steven R; Reuter, Karsten; Alducin, Maite; Deringer, Volker L; Csanyi, Gabor; Marzari, Nicola; Huang, Shirong; Cuniberti, Gianaurelio; Deng, Qiushi; Ordejon, Pablo; Cole, Ivan; Choudhary, Kamal; Hippalgaonkar, Kedar; Zhu, Ruiming; von Lilienfeld, Anatole O; Hibat-Allah, Mohamed; Carrasquilla, Juan; Cisotto, Giulia; Zancanaro, Alberto; Wenzel, Wolfgang; Ferrari, Andrea C; Ustyuzhanin, Andrey; Roche, Stephan Artificial intelligence for advanced functional materials: exploring
current and future directions 15 JOURNAL OF PHYSICS-MATERIALS, 8 (2), 2025, DOI: 10.1088/2515-7639/adc29d. Abstract | BibTeX | Endnote @article{WOS:001473720000001,
title = {Artificial intelligence for advanced functional materials: exploring
current and future directions},
author = {Cristiano Malica and Kostya S Novoselov and Amanda S Barnard and Sergei Kalinin V and Steven R Spurgeon and Karsten Reuter and Maite Alducin and Volker L Deringer and Gabor Csanyi and Nicola Marzari and Shirong Huang and Gianaurelio Cuniberti and Qiushi Deng and Pablo Ordejon and Ivan Cole and Kamal Choudhary and Kedar Hippalgaonkar and Ruiming Zhu and Anatole O von Lilienfeld and Mohamed Hibat-Allah and Juan Carrasquilla and Giulia Cisotto and Alberto Zancanaro and Wolfgang Wenzel and Andrea C Ferrari and Andrey Ustyuzhanin and Stephan Roche},
doi = {10.1088/2515-7639/adc29d},
times_cited = {15},
year = {2025},
date = {2025-04-01},
journal = {JOURNAL OF PHYSICS-MATERIALS},
volume = {8},
number = {2},
publisher = {IOP Publishing Ltd},
address = {No.2 The Distillery, Glassfields, Avon Street, Bristol, ENGLAND},
abstract = {This perspective addresses the topic of harnessing the tools of
artificial intelligence (AI) for boosting innovation in functional
materials design and engineering as well as discovering new materials
for targeted applications in energy storage, biomedicine, composites,
nanoelectronics or quantum technologies. It gives a current view of
experts in the field, insisting on challenges and opportunities provided
by the development of large materials databases, novel schemes for
implementing AI into materials production and characterization as well
as progress in the quest of simulating physical and chemical properties
of realistic atomic models reaching the trillion atoms scale and with
near ab initio accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This perspective addresses the topic of harnessing the tools of
artificial intelligence (AI) for boosting innovation in functional
materials design and engineering as well as discovering new materials
for targeted applications in energy storage, biomedicine, composites,
nanoelectronics or quantum technologies. It gives a current view of
experts in the field, insisting on challenges and opportunities provided
by the development of large materials databases, novel schemes for
implementing AI into materials production and characterization as well
as progress in the quest of simulating physical and chemical properties
of realistic atomic models reaching the trillion atoms scale and with
near ab initio accuracy. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AFCristiano Malica
Kostya S Novoselov
Amanda S Barnard
Sergei Kalinin V
Steven R Spurgeon
Karsten Reuter
Maite Alducin
Volker L Deringer
Gabor Csanyi
Nicola Marzari
Shirong Huang
Gianaurelio Cuniberti
Qiushi Deng
Pablo Ordejon
Ivan Cole
Kamal Choudhary
Kedar Hippalgaonkar
Ruiming Zhu
Anatole O von Lilienfeld
Mohamed Hibat-Allah
Juan Carrasquilla
Giulia Cisotto
Alberto Zancanaro
Wolfgang Wenzel
Andrea C Ferrari
Andrey Ustyuzhanin
Stephan Roche
- TIArtificial intelligence for advanced functional materials: exploring
current and future directions - SOJOURNAL OF PHYSICS-MATERIALS
- DTArticle
- ABThis perspective addresses the topic of harnessing the tools of
artificial intelligence (AI) for boosting innovation in functional
materials design and engineering as well as discovering new materials
for targeted applications in energy storage, biomedicine, composites,
nanoelectronics or quantum technologies. It gives a current view of
experts in the field, insisting on challenges and opportunities provided
by the development of large materials databases, novel schemes for
implementing AI into materials production and characterization as well
as progress in the quest of simulating physical and chemical properties
of realistic atomic models reaching the trillion atoms scale and with
near ab initio accuracy. - Z915
- PUIOP Publishing Ltd
- PANo.2 The Distillery, Glassfields, Avon Street, Bristol, ENGLAND
- VL8
- DI10.1088/2515-7639/adc29d
- UTWOS:001473720000001
- ER
- EF
|
Kazeev, Nikita; Nong, Wei; Romanov, Ignat; Zhu, Ruiming; Ustyuzhanin, Andrey; Yamazaki, Shuya; Hippalgaonkar, Kedar Wyckoff Transformer: Generation of Symmetric Crystals Singh, A; Fazel, M; Hsu, D; Lacoste-Julien, S; Berkenkamp, F; Maharaj, T; Wagstaff, K; Zhu, J (Ed.): INTERNATIONAL CONFERENCE ON MACHINE LEARNING, pp. 29495-29526, JMLR-JOURNAL MACHINE LEARNING RESEARCH, 1269 LAW ST, SAN DIEGO, CA, UNITED STATES, 2025, (42nd International Conference on Machine Learning-ICML-Annual,
Vancouver, CANADA, JUL 13-19, 2025). Abstract | BibTeX | Endnote @inproceedings{WOS:001693126000256,
title = {Wyckoff Transformer: Generation of Symmetric Crystals},
author = {Nikita Kazeev and Wei Nong and Ignat Romanov and Ruiming Zhu and Andrey Ustyuzhanin and Shuya Yamazaki and Kedar Hippalgaonkar},
editor = {A Singh and M Fazel and D Hsu and S Lacoste-Julien and F Berkenkamp and T Maharaj and K Wagstaff and J Zhu},
times_cited = {0},
issn = {2640-3498},
year = {2025},
date = {2025-01-01},
booktitle = {INTERNATIONAL CONFERENCE ON MACHINE LEARNING},
volume = {267},
pages = {29495-29526},
publisher = {JMLR-JOURNAL MACHINE LEARNING RESEARCH},
address = {1269 LAW ST, SAN DIEGO, CA, UNITED STATES},
series = {Proceedings of Machine Learning Research},
abstract = {Crystal symmetry plays a fundamental role in determining its physical,
chemical, and electronic properties such as electrical and thermal
conductivity, optical and polarization behavior, and mechanical
strength. Almost all known crystalline materials have internal symmetry.
However, this is often inadequately addressed by existing generative
models, making the consistent generation of stable and symmetrically
valid crystal structures a significant challenge. We introduce WyFormer,
a generative model that directly tackles this by formally conditioning
on space group symmetry. It achieves this by using Wyckoff positions as
the basis for an elegant, compressed, and discrete structure
representation. To model the distribution, we develop a
permutation-invariant autoregressive model based on the Transformer
encoder and an absence of positional encoding. Extensive experimentation
demonstrates WyFormer's compelling combination of attributes: it
achieves best-in-class symmetry-conditioned generation, incorporates a
physics-motivated inductive bias, produces structures with competitive
stability, predicts material properties with competitive accuracy even
without atomic coordinates, and exhibits unparalleled inference speed.
https://github.com/SymmetryAdvantage/WyckoffTransformer},
note = {42nd International Conference on Machine Learning-ICML-Annual,
Vancouver, CANADA, JUL 13-19, 2025},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Crystal symmetry plays a fundamental role in determining its physical,
chemical, and electronic properties such as electrical and thermal
conductivity, optical and polarization behavior, and mechanical
strength. Almost all known crystalline materials have internal symmetry.
However, this is often inadequately addressed by existing generative
models, making the consistent generation of stable and symmetrically
valid crystal structures a significant challenge. We introduce WyFormer,
a generative model that directly tackles this by formally conditioning
on space group symmetry. It achieves this by using Wyckoff positions as
the basis for an elegant, compressed, and discrete structure
representation. To model the distribution, we develop a
permutation-invariant autoregressive model based on the Transformer
encoder and an absence of positional encoding. Extensive experimentation
demonstrates WyFormer's compelling combination of attributes: it
achieves best-in-class symmetry-conditioned generation, incorporates a
physics-motivated inductive bias, produces structures with competitive
stability, predicts material properties with competitive accuracy even
without atomic coordinates, and exhibits unparalleled inference speed.
https://github.com/SymmetryAdvantage/WyckoffTransformer - FNClarivate Analytics Web of Science
- VR1.0
- PTMisc
- AFNikita Kazeev
Wei Nong
Ignat Romanov
Ruiming Zhu
Andrey Ustyuzhanin
Shuya Yamazaki
Kedar Hippalgaonkar
- TIWyckoff Transformer: Generation of Symmetric Crystals
- DTInproceedings
- ABCrystal symmetry plays a fundamental role in determining its physical,
chemical, and electronic properties such as electrical and thermal
conductivity, optical and polarization behavior, and mechanical
strength. Almost all known crystalline materials have internal symmetry.
However, this is often inadequately addressed by existing generative
models, making the consistent generation of stable and symmetrically
valid crystal structures a significant challenge. We introduce WyFormer,
a generative model that directly tackles this by formally conditioning
on space group symmetry. It achieves this by using Wyckoff positions as
the basis for an elegant, compressed, and discrete structure
representation. To model the distribution, we develop a
permutation-invariant autoregressive model based on the Transformer
encoder and an absence of positional encoding. Extensive experimentation
demonstrates WyFormer's compelling combination of attributes: it
achieves best-in-class symmetry-conditioned generation, incorporates a
physics-motivated inductive bias, produces structures with competitive
stability, predicts material properties with competitive accuracy even
without atomic coordinates, and exhibits unparalleled inference speed.
https://github.com/SymmetryAdvantage/WyckoffTransformer - Z90
- PUJMLR-JOURNAL MACHINE LEARNING RESEARCH
- PA1269 LAW ST, SAN DIEGO, CA, UNITED STATES
- SN2640-3498
- VL267
- BP29495
- EP29526
- UTWOS:001693126000256
- ER
- EF
|
Velasco, Pablo Quijano; Hippalgaonkar, Kedar; Ramalingam, Balamurugan Emerging trends in the optimization of organic synthesis through
high-throughput tools and machine learning 17 BEILSTEIN JOURNAL OF ORGANIC CHEMISTRY, 21 , pp. 10-38, 2025, DOI: 10.3762/bjoc.21.3. Abstract | BibTeX | Endnote @article{WOS:001390361600001,
title = {Emerging trends in the optimization of organic synthesis through
high-throughput tools and machine learning},
author = {Pablo Quijano Velasco and Kedar Hippalgaonkar and Balamurugan Ramalingam},
doi = {10.3762/bjoc.21.3},
times_cited = {17},
issn = {1860-5397},
year = {2025},
date = {2025-01-01},
journal = {BEILSTEIN JOURNAL OF ORGANIC CHEMISTRY},
volume = {21},
pages = {10-38},
publisher = {BEILSTEIN-INSTITUT},
address = {TRAKEHNER STRASSE 7-9, FRANKFURT AM MAIN, 60487, GERMANY},
abstract = {The discovery of the optimal conditions for chemical reactions is a
labor-intensive, time-consuming task that requires exploring a
high-dimensional parametric space. Historically, the optimization of
chemical reactions has been performed by manual experimentation guided
by human intuition and through the design of experiments where reaction
variables are modified one at a time to find the optimal conditions for
a specific reaction outcome. Recently, a paradigm change in chemical
reaction optimization has been enabled by advances in lab automation and
the introduction of machine learning algorithms. Therein, multiple
reaction variables can be synchronously optimized to obtain the optimal
reaction conditions, requiring a shorter experimentation time and
minimal human intervention. Herein, we review the currently used
state-of-the-art high-throughput automated chemical reaction platforms
and machine learning algorithms that drive the optimization of chemical
reactions, highlighting the limitations and future opportunities of this
new field of research.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The discovery of the optimal conditions for chemical reactions is a
labor-intensive, time-consuming task that requires exploring a
high-dimensional parametric space. Historically, the optimization of
chemical reactions has been performed by manual experimentation guided
by human intuition and through the design of experiments where reaction
variables are modified one at a time to find the optimal conditions for
a specific reaction outcome. Recently, a paradigm change in chemical
reaction optimization has been enabled by advances in lab automation and
the introduction of machine learning algorithms. Therein, multiple
reaction variables can be synchronously optimized to obtain the optimal
reaction conditions, requiring a shorter experimentation time and
minimal human intervention. Herein, we review the currently used
state-of-the-art high-throughput automated chemical reaction platforms
and machine learning algorithms that drive the optimization of chemical
reactions, highlighting the limitations and future opportunities of this
new field of research. - FNClarivate Analytics Web of Science
- VR1.0
- PTJ
- AFPablo Quijano Velasco
Kedar Hippalgaonkar
Balamurugan Ramalingam
- TIEmerging trends in the optimization of organic synthesis through
high-throughput tools and machine learning - SOBEILSTEIN JOURNAL OF ORGANIC CHEMISTRY
- DTArticle
- ABThe discovery of the optimal conditions for chemical reactions is a
labor-intensive, time-consuming task that requires exploring a
high-dimensional parametric space. Historically, the optimization of
chemical reactions has been performed by manual experimentation guided
by human intuition and through the design of experiments where reaction
variables are modified one at a time to find the optimal conditions for
a specific reaction outcome. Recently, a paradigm change in chemical
reaction optimization has been enabled by advances in lab automation and
the introduction of machine learning algorithms. Therein, multiple
reaction variables can be synchronously optimized to obtain the optimal
reaction conditions, requiring a shorter experimentation time and
minimal human intervention. Herein, we review the currently used
state-of-the-art high-throughput automated chemical reaction platforms
and machine learning algorithms that drive the optimization of chemical
reactions, highlighting the limitations and future opportunities of this
new field of research. - Z917
- PUBEILSTEIN-INSTITUT
- PATRAKEHNER STRASSE 7-9, FRANKFURT AM MAIN, 60487, GERMANY
- SN1860-5397
- VL21
- BP10
- EP38
- DI10.3762/bjoc.21.3
- UTWOS:001390361600001
- ER
- EF
|