We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
Octopus Group

Download Mobile App


ATTENTION: Due to the COVID-19 PANDEMIC, many events are being rescheduled for a later date, converted into virtual venues, or altogether cancelled. Please check with the event organizer or website prior to planning for any forthcoming event.

AI Combined with Molecule-Making Machine Could Make Complex Chemistry Automated and Accessible

By LabMedica International staff writers
Posted on 31 Oct 2022
Print article
Image: The team combined powerful AI and a molecule-making machine to find the best conditions for automated complex chemistry (Photo courtesy of University of Illinois at Urbana-Champaign)
Image: The team combined powerful AI and a molecule-making machine to find the best conditions for automated complex chemistry (Photo courtesy of University of Illinois at Urbana-Champaign)

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. A team of researchers had earlier pioneered the development of simple chemical building blocks for small molecules. They had also developed an automated molecule-making machine that snaps together the buildings blocks to create a wide range of possible structures. Now, the team has combined artificial intelligence (AI), “building-block” chemistry and a molecule-making machine 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 at Urbana-Champaign (Champaign, IL, USA), the Polish Academy of Sciences’ Institute for Organic Chemistry (IOC PAS, Warsaw, Poland), and the University of Toronto (Toronto, ON, 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. An automated approach with generalized conditions could help standardize how chemists make some products, addressing the problem of reproducibility.

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, according to the researchers. 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, 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.

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. The machine-learning process could also 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.

“Generality is critical for automation, and thus making molecular innovation accessible even to nonchemists,” said study co-leader Dr. Martin D. Burke. “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.”

Related Links:
University of Illinois at Urbana-Champaign 
University of Toronto 

Gold Supplier
Automated, Random Access Chemistry Analyzer
LIDA 300
Silver Supplier
Auto Molecular Diagnostic System
ELITe InGenius
Gold Supplier
Virus Detection System
Radiotherapy Toxicity Measurement Assay
Radiotherapy Toxicity Measurement Assay

Print article


Molecular Diagnostics

view channel
Image: Researchers have identified the origin of subset of autoantibodies that worsen lupus (Photo courtesy of Pexels)

Lupus Biomarker Testing Could Help Identify Patients That Need Early and Aggressive Treatment

Systemic lupus erythematosus (SLE) is an autoimmune disease that occurs when the body's antibodies, which usually protect against infections, attack healthy cells and proteins. These autoantibodies can... Read more


view channel
Image: A genetic test could guide the use of cancer chemotherapy (Photo courtesy of Pexels)

Genetic Test Predicts Whether Bowel Cancer Patients Can Benefit From Chemotherapy

Late-stage bowel cancer patients usually undergo a series of chemotherapies and targeted medicines for cancer treatment. However, the responses to the last-line chemotherapy treatment trifluridine/tipiracil... Read more


view channel
Image: Use of DBS samples can break barriers in hepatitis C diagnosis and treatment for populations at risk (Photo courtesy of Pexels)

DBS-Based Assay Effective in Hepatitis C Diagnosis and Treatment for At Risk Populations

In a bid to eliminate viral hepatitis as a public health threat by 2030, the World Health Organization (WHO) has put forth a proposed strategy. To this end, researchers at the Germans Trias i Pujol Research... Read more


view channel
Image: New research has opened a path for fast and accurate cancer diagnosis (Photo courtesy of Imagene)

AI-Based Image Analysis Software Profiles Cancer Biomarkers in Real Time

Lung cancer is the most widespread type of cancer worldwide, resulting in approximately 1.76 million fatalities annually. Non-small cell lung cancer (NSCLC) accounts for 85% of all lung cancer diagnoses... Read more


view channel
Image: Live view of non-fluorescent specimens using the glowscope frame (Photo courtesy of Winona State University)

Device Converts Smartphone into Fluorescence Microscope for Just USD 50

Fluorescence microscopes are utilized to examine specimens labeled with fluorescent stains or expressing fluorescent proteins, like those tagged with green fluorescent protein. However, since these microscopes... Read more


view channel
Image: The global antimicrobial resistance diagnostics market size is expected to reach USD 5.7 billion by 2028 (Photo courtesy of Pexels)

Global Antimicrobial Resistance Diagnostics Market Driven by Increasing Hospital-Acquired Infections

Antimicrobial drugs are intended to counteract the harmful effects of microbes and promote a healthy life. However, their excessive use can result in the development of resistance, commonly referred to... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.