PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

With AI, researchers can now identify the smallest crystals

AI solves the century-old puzzle of uncovering the shape of atomic clusters by examining the patterns produced by an X-ray beam refracted through fine powder.

2025-04-28
(Press-News.org) One longstanding problem has sidelined life-saving drugs, stalled next-generation batteries, and kept archaeologists from identifying the origins of ancient artifacts. 

For more than 100 years, scientists have used a method called crystallography to determine the atomic structure of materials. The method works by shining an X-ray beam through a material sample and observing the pattern it produces. From this pattern – called a diffraction pattern – it is theoretically possible to calculate the exact arrangement of atoms in the sample. The challenge, however, is that this technique only works well when researchers have large, pure crystals. When they have to settle for a powder of minuscule pieces — called nanocrystals — the method only hints at the unseen structure.

Scientists at Columbia Engineering have created a machine learning algorithm that can observe the pattern produced by nanocrystals to infer the material’s atomic structure, as described in a new study published in Nature Materials. In many cases, their algorithm achieves near-perfect reconstruction of the atomic-scale structure from the highly degraded diffraction information — a feat unimaginable just a couple of years ago. 

“The AI solved this problem by learning everything it could from a database of many thousands of known, but unrelated, structures,” says Simon Billinge, professor of materials science and of applied physics and applied mathematics at Columbia Engineering. “Just as ChatGPT learns the patterns of language, the AI model learned the patterns of atomic arrangements that nature allows.”

Crystallography Transformed Science
Crystallography is vital to science because it’s the most effective method for understanding the properties of virtually any material. The method typically relies on a technique called X-ray diffraction, in which scientists shoot energetic beams at a crystal and record the pattern of light and dark spots it produces, sort of like a shadow. When crystallographers use this technique to analyze a large and pure sample, the resulting X-ray patterns contain all the information needed to determine its atomic-level structure. Best known for enabling the discovery of DNA’s double-helix structure, the method has opened important avenues of research in medicine, semiconductors, energy storage, forensic science, archaeology, and dozens of other fields. 

Unfortunately, researchers often only have access to samples of very small crystallites, or atomic clusters, in the form of powder or suspended in solution. In these cases, the X-ray patterns contain much less information, far too little for researchers to determine the sample’s atomic structure using existing methods. 

AI Extends the Method to Nanoparticles
The team trained a generative AI model on 40,000 known atomic structures to develop a system that is able to make sense of these inferior X-ray patterns. The machine learning technique, called diffusion generative modeling, emerged from statistical physics and recently gained notoriety for enabling AI-generated art programs like Midjourney and Sora. 

“From previous work, we knew that diffraction data from nanocrystals doesn’t contain enough information to yield the result,” Billinge said. “The algorithm used its knowledge of thousands of unrelated structures to augment the diffraction data.”

To apply the technique to crystallography, the scientists began with a dataset of 40,000 crystal structures and jumbled the atomic positions until they were indistinguishable from random placement. Then, they trained a deep neural network to connect these almost randomly placed atoms with their associated X-ray diffraction patterns. The net used these observations to reconstruct the crystal. Finally, they put the AI-generated crystals through a procedure called Rietveld refinement, which essentially “jiggles” crystals into the closest optimal state, based on the diffraction pattern.

Although early versions of this algorithm struggled, it eventually learned to reconstruct crystals far more effectively than the researchers had expected. The algorithm was able to determine the atomic structure from nanometer-sized crystals of various shapes, including samples that had proven too difficult for previous experiments to characterize. 

“The powder crystallography challenge is a sister problem to the famous protein folding problem where the shape of a molecule is derived indirectly from a linear data signature,” said Hod Lipson, James and Sally Scapa Professor of Innovation and chair of the Department of Mechanical Engineering at Columbia Engineering, who, with Billinge, co-proposed the study. “What particularly excites me is that with relatively little background knowledge in physics or geometry, AI was able to learn to solve a puzzle that has baffled human researchers for a century. This is a sign of things to come for many other fields facing long-standing challenges.”

The century-old powder crystallography puzzle is particularly meaningful to Lipson, who is the grandson of Henry Lipson CBE FRS (1910–1991) who pioneered computational crystallography methods. In the 1930s, Henry Lipson worked with Bragg and other contemporaries to develop early mathematical techniques that were broadly used to solve the first complex molecules, such as penicillin, leading to the 1964 Nobel prize in Chemistry.

Gabe Guo BS’24, currently a PhD student at Stanford University, who led the project while he was a senior at Columbia, said, “When I was in middle school, the field was struggling to build algorithms that could tell cats from dogs. Now, studies like ours underscore the massive power of AI to augment the power of human scientists and accelerate innovation to new levels.”

END


ELSE PRESS RELEASES FROM THIS DATE:

Every dose counts: Safeguarding the success of vaccination in Europe

2025-04-28
Marking European Immunization Week (EIW) 2025, the European Centre for Disease Prevention and Control (ECDC) highlights the risks of suboptimal vaccination coverage in Europe and publishes a set of operational tools that public health authorities can use to improve vaccination acceptance and uptake. The tenfold surge of reported measles cases in the European Union and European Economic Area (EU/EEA) and the detection of vaccine-derived poliovirus in four EU/EEA countries in 2024 are two clear signals of the need to achieve and maintain high immunisation coverage to protect European populations. Vaccines ...

Can exercise and rehab services be integrated into breast cancer care?

2025-04-28
A recent randomized controlled trial reveals the potential of a program designed to connect patients who have breast cancer to needed exercise and rehabilitation services starting at diagnosis and throughout care. Participants provided positive feedback about the program, supporting efforts to integrate exercise and rehabilitation services as part of routine cancer care. The trial’s findings are published by Wiley online in CANCER, a peer-reviewed journal of the American Cancer Society. Exercise services for ...

Simple test could better predict your risk of heart disease

2025-04-28
For almost 60 years, measuring cholesterol levels in the blood has been the best way to identify individuals at high risk of cardiovascular disease. In a new study, led by Chalmers University of Technology in Sweden and Harvard University in the USA, researchers have shown comprehensively that a combination of two lipoprotein markers, measured in a simple blood test, can give more accurate information about individual risk of heart disease than the current blood cholesterol test, potentially saving lives. According to the World Health Organization (WHO), cardiovascular diseases (CVDs) are the leading cause of death globally. Most cases could be prevented by addressing ...

Global study links consumption of ultraprocessed foods to preventable premature deaths

2025-04-28
Ann Arbor, April 28, 2025 - A study analyzing data from nationally representative dietary surveys and mortality data from eight countries (Australia, Brazil, Canada, Chile, Colombia, Mexico, United Kingdom, and United States) shows that premature deaths attributable to consumption of ultraprocessed foods (UPFs) increase significantly according to their share in individuals’ total energy intake. The new study, appearing in the American Journal of Preventive Medicine, published by Elsevier, reinforces the call for global action to reduce UPF consumption, supported by regulatory and fiscal policies that foster healthier environments. UPFs are ready-to-eat-or-heat ...

Accurate and rapid arthritis diagnosis in just 10 minutes

2025-04-28
Dr. Ho Sang Jung and his research team from the Advanced Bio and Healthcare Materials Research Division at the Korea Institute of Materials Science (KIMS), in collaboration with Seoul St. Mary’s Hospital, have developed a technology that enables the diagnosis of osteoarthritis and rheumatoid arthritis within 10 minutes using synovial fluid. This marks the first such achievement in Korea. According to some studies, over 50% of the population aged 65 and older experience symptoms of osteoarthritis, while rheumatoid arthritis is known to be a serious chronic disease that affects ...

Hospital-based outbreak detection system saves lives

2025-04-28
An infectious diseases detection platform developed by University of Pittsburgh scientists working with UPMC infection preventionists proved over a two-year trial that it stops outbreaks, saves lives and cuts costs. The results are published today in the journal Clinical Infectious Diseases, making the case for adoption in hospitals nationwide and the development of a national early outbreak detection database. “We saved lives while saving money. This isn’t theoretical – this happened in a real hospital with real patients,” said lead author Alexander Sundermann, Dr.P.H., assistant professor of infectious diseases ...

AACR: Topical treatment offers relief from painful skin rash caused by targeted cancer therapy

2025-04-27
ABSTRACT CT018 FINDINGS Researchers from the UCLA Health Jonsson Comprehensive Cancer Center and The University of Texas MD Anderson Cancer Center have demonstrated that a novel topical BRAF inhibitor gel called LUT014 significantly reduces the severity of an acne-like rash, a common and painful side effect experienced by patients undergoing anti-EGFR therapies for colorectal cancer. The findings of the clinical trial confirm the treatment’s safety and effectiveness. “The findings offer the first real solution in two decades for managing this ...

Buprenorphine treatment in pregnancy and maternal-infant outcomes

2025-04-27
About The Study: In this cohort study of pregnant individuals with opioid use disorder, buprenorphine treatment was associated with improved outcomes for the mother and infant, underscoring the need to improve access to treatment nationwide. Corresponding Author: To contact the corresponding author, Stephen W. Patrick, MD, MPH, MS, email stephen.patrick@emory.edu. To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/ (doi:10.1001/jamahealthforum.2025.1814) Editor’s ...

Donor lungs safely preserved up to 20 hours out-of-body prior to transplantation

2025-04-27
27 April 2025, Boston—A study on donor lungs preserved outside the body before transplantation demonstrated that the hypothermic oxygenated machine perfusion (HOPE) technique is a safe and effective lung preservation method, even with total out-of-body times approaching 20 hours.   Jitte Jennekens, MSc, organ perfusionist/transplant coordinator at the UMC Utrecht in the Netherlands, presented the study results at today’s Annual Meeting and Scientific Sessions of the International Society of Heart and Lung Transplantation (ISHLT) in Boston.   “This technique is being used to preserve donor livers and ...

Experts at ISHLT report urgent need for pediatric heart support devices

2025-04-27
Embargoed until 2:00 PM EST, Sunday, 27 April, 2025   EXPERTS AT ISHLT REPORT URGENT NEED FOR PEDIATRIC HEART SUPPORT DEVICES 27 April 2025, Boston—At today’s Annual Meeting and Scientific Sessions of the International Society for Heart and Lung Transplantation (ISHLT) in Boston, Angela Lorts, MD, MBA, issued an urgent call for improved mechanical circulatory support (MCS) devices for children with life-threatening heart conditions. “Advances in pediatric cardiac disease are underfunded and understudied. Therapies are rarely developed for children. We modify adult therapies to use in pediatrics,” ...

LAST 30 PRESS RELEASES:

Osteoporosis treatment benefits people older than 80

Consuming more protein may protect patients taking anti-obesity drug from muscle loss

Thyroid treatment may improve gut health in people with hypothyroidism

Combination of obesity medication tirzepatide and menopause hormone therapy fuels weight loss

High blood sugar may have a negative impact on men’s sexual health

Emotional health of parents tied to well-being of children with growth hormone deficiency

Oxytocin may reduce mood changes in women with disrupted sleep

Mouse study finds tirzepatide slowed obesity-associated breast cancer growth

CMD-OPT model enables the discovery of a potent and selective RIPK2 inhibitor as preclinical candidate for the treatment of acute liver injury

Melatonin receptor 1a alleviates sleep fragmentation-aggravated testicular injury in T2DM by suppression of TAB1/TAK1 complex through FGFR1

Single-cell RNA sequencing reveals Shen-Bai-Jie-Du decoction retards colorectal tumorigenesis by regulating the TMEM131–TNF signaling pathway-mediated differentiation of immunosuppressive dendritic ce

Acta Pharmaceutica Sinica B Volume 15, Issue 7 Publishes

New research expands laser technology

Targeted radiation offers promise in patients with metastasized small cell lung cancer to the brain

A high clinically translatable strategy to anti-aging using hyaluronic acid and silk fibroin co-crosslinked hydrogels as dermal regenerative fillers

Mount Sinai researchers uncover differences in how males and females change their mind when reflecting on past mistakes

CTE and normal aging are difficult to distinguish, new study finds

Molecular arms race: How the genome defends itself against internal enemies

Tiny chip speeds up antibody mapping for faster vaccine design

KTU experts reveal why cultural heritage is important for community unity

More misfolded proteins than previously known may contribute to Alzheimer’s and dementia

“Too much going on”: Autistic adults overwhelmed by non-verbal social cues

What’s driving America’s deep freezes in a warming world?

A key role of brain protein in learning and memory is deciphered by scientists

Heart attacks don’t follow a Hollywood script

Erin M. Schuman wins 2026 Nakasone Award for discovery on neural synapse function and change during formation of memories

Global ocean analysis could replace costly in-situ sound speed profiles in seafloor positioning, study finds

Power in numbers: Small group professional coaching reduces rates of physician burnout by nearly 30%

Carbon capture, utilization, and storage: A comprehensive review of CCUS-EOR

New high-temperature stable dispersed particle gel for enhanced profile control in CCUS applications

[Press-News.org] With AI, researchers can now identify the smallest crystals
AI solves the century-old puzzle of uncovering the shape of atomic clusters by examining the patterns produced by an X-ray beam refracted through fine powder.