Health
Could LLMs Revolutionize Drug and Material Design?
These researchers have developed an innovative system that augments an LLM with graph-based AI models, designed specifically to handle molecular structures

A new method is changing the way we think about molecule design, bringing us closer to the possibility of using large language models (LLMs) to streamline the creation of new medicines and materials. Imagine asking, in plain language, for a molecule with specific properties, and receiving a comprehensive plan on how to synthesize it. This futuristic vision is now within reach, thanks to a collaboration between researchers from MIT and the MIT-IBM Watson AI Lab.
A New era in molecular discovery
Traditionally, discovering the right molecules for medicines and materials has been a slow and resource-intensive process. It often involves the use of vast computational power and months of painstaking work to explore the nearly infinite pool of potential molecular candidates. However, this new method, blending LLMs with other machine-learning models known as graph-based models, offers a promising solution to speed up this process.
These researchers have developed an innovative system that augments an LLM with graph-based AI models, designed specifically to handle molecular structures. The approach allows users to input natural language queries specifying the desired molecular properties, and in return, the system provides not only a molecular design but also a step-by-step synthesis plan.
LLMs and graph models
LLMs like ChatGPT have revolutionized the way we interact with text, but they face challenges when it comes to molecular design. Molecules are graph structures—composed of atoms and bonds—which makes them fundamentally different from text. LLMs typically process text as a sequence of words, but molecules do not follow a linear structure. This discrepancy has made it difficult for LLMs to understand and predict molecular configurations in the same way they handle sentences.
To bridge this gap, MIT’s researchers created Llamole—a system that uses LLMs to interpret user queries and then switches between different graph-based AI modules to generate molecular structures, explain their rationale, and devise a synthesis strategy. The system combines the power of text, graphs, and synthesis steps into a unified workflow.
As a result, this multimodal approach drastically improves performance. Llamole was able to generate molecules that were far better at meeting user specifications and more likely to have a viable synthesis plan, increasing the success rate from 5 percent to 35 percent.
Llamole’s success lies in its unique ability to seamlessly combine language processing with graph-based molecular modeling. For example, if a user requests a molecule with specific traits—such as one that can penetrate the blood-brain barrier and inhibit HIV—the LLM interprets the plain-language request and switches to a graph module to generate the appropriate molecular structure.
This switch occurs through the use of a new type of trigger token, allowing the LLM to activate specific modules as needed. The process unfolds in stages: the LLM first predicts the molecular structure, then uses a graph neural network to encode the structure, and finally, a retrosynthetic module predicts the necessary steps to synthesize the molecule. The seamless flow between these stages ensures that the LLM maintains an understanding of what each module does, further enhancing its predictive accuracy.
“The beauty of this is that everything the LLM generates before activating a particular module gets fed into that module itself. The module is learning to operate in a way that is consistent with what came before,” says Michael Sun, an MIT graduate student and co-author of the study.
Simplicity meets precision
One of the most striking aspects of this new method is its ability to generate simpler, more cost-effective molecular structures. In tests, Llamole outperformed other LLM-based methods and achieved a notable 35 percent success rate in retrosynthetic planning, up from a mere 5 percent with traditional approaches. “On their own, LLMs struggle to figure out how to synthesize molecules because it requires a lot of multistep planning. Our method can generate better molecular structures that are also easier to synthesize,” says Gang Liu, the study’s lead author.
By designing molecules with simpler structures and more accessible building blocks, Llamole could significantly reduce the time and cost involved in developing new compounds.
The road ahead
Though Llamole’s current capabilities are impressive, there is still work to be done. The researchers built two custom datasets to train Llamole, but these datasets focus on only 10 molecular properties. Moving forward, they hope to expand Llamole’s capabilities to design molecules based on a broader range of properties and improve the system’s retrosynthetic planning success rate.
In the long run, the team envisions Llamole serving as a foundation for broader applications beyond molecular design. “Llamole demonstrates the feasibility of using large language models as an interface to complex data beyond textual description, and we anticipate them to be a foundation that interacts with other AI algorithms to solve any graph problems,” says Jie Chen, a senior researcher at MIT-IBM Watson AI Lab.
With further refinements, Llamole could revolutionize fields from pharmaceuticals to material science, offering a glimpse into the future of AI-driven innovation in molecular discovery.
Health
PUPS – the AI tool that can predict where exactly proteins are in human cells
Dubbed, the Prediction of Unseen Proteins’ Subcellular Localization (or PUPS), the AI tool can account for the effects of protein mutations and cellular stress—key factors in disease progression.

Researchers from MIT, Harvard University, and the Broad Institute have unveiled a groundbreaking artificial intelligence tool that can accurately predict where proteins are located within any human cell, even if both the protein and cell line have never been studied before. The method – Prediction of Unseen Proteins’ Subcellular Localization (or PUPS) – marks a major advancement in biological research and could significantly streamline disease diagnosis and drug discovery.
Protein localization—the precise location of a protein within a cell—is key to understanding its function. Misplaced proteins are known to contribute to diseases like Alzheimer’s, cystic fibrosis, and cancer. However, identifying protein locations manually is expensive and slow, particularly given the vast number of proteins in a single cell.
The new technique leverages a protein language model and a sophisticated computer vision system. It produces a detailed image that highlights where the protein is likely to be located at the single-cell level, offering far more precise insights than many existing models, which average results across all cells of a given type.
“You could do these protein-localization experiments on a computer without having to touch any lab bench, hopefully saving yourself months of effort. While you would still need to verify the prediction, this technique could act like an initial screening of what to test for experimentally,” said Yitong Tseo, a graduate student in MIT’s Computational and Systems Biology program and co-lead author of the study, in a media statement.
Tseo’s co-lead author, Xinyi Zhang, emphasized the model’s ability to generalize: “Most other methods usually require you to have a stain of the protein first, so you’ve already seen it in your training data. Our approach is unique in that it can generalize across proteins and cell lines at the same time,” she said in a media statement.
PUPS was validated through laboratory experiments and shown to outperform baseline AI methods in predicting protein locations with greater accuracy. The tool is also capable of accounting for the effects of protein mutations and cellular stress—key factors in disease progression.
Published in Nature Methods, the research was led by senior authors Fei Chen of Harvard and the Broad Institute, and Caroline Uhler, the Andrew and Erna Viterbi Professor at MIT. Future goals include enabling PUPS to analyze protein interactions and make predictions in live human tissue rather than cultured cells.
Health
Robot Helps Elderly Sit, Stand, and Stay Safe from Falls
The innovation comes at a time when the United States faces a dramatic demographic shift

As America’s population ages faster than ever before, a team of engineers at MIT is turning to robotics to meet the growing eldercare crisis. Their latest invention, the Elderly Bodily Assistance Robot—or E-BAR—aims to provide critical physical support to seniors navigating life at home, potentially reducing the risk of injury and relieving pressure on a strained care system.
The innovation comes at a time when the United States faces a dramatic demographic shift. The nation’s median age has climbed to 38.9, nearly ten years older than in 1980. By 2050, the number of adults over 65 is projected to surge from 58 million to 82 million. As demand for care rises, the country is simultaneously grappling with shortages in care workers, escalating healthcare costs, and evolving family structures that leave many elderly adults without daily support.
“Eldercare is the next great challenge,” said Roberto Bolli, a graduate student in MIT’s Department of Mechanical Engineering and one of E-BAR’s lead designers, in a media statement. “All the demographic trends point to a shortage of caregivers, a surplus of elderly persons, and a strong desire for elderly persons to age in place.”
E-BAR is designed to address exactly that challenge. The mobile robot acts as a robotic support system, following a user from behind and offering both steadying handlebars and rapid intervention in case of a fall. It can support a person’s full weight and includes side airbags that inflate instantly to catch users if they begin to fall—without requiring them to wear any equipment or harnesses.
“Many older adults underestimate the risk of fall and refuse to use physical aids, which are cumbersome, while others overestimate the risk and may not exercise, leading to declining mobility,” said Harry Asada, the Ford Professor of Engineering at MIT, in a media statement. “Our design concept is to provide older adults having balance impairment with robotic handlebars for stabilizing their body. The handlebars go anywhere and provide support anytime, whenever they need.”
The robot consists of a heavy, 220-pound base equipped with omnidirectional wheels, allowing it to maneuver easily through typical home spaces. From its base, articulated bars extend and adjust to assist users in standing or sitting, and the handlebars provide a natural, unrestrictive grip. In testing, E-BAR successfully helped an older adult complete everyday movements such as bending, reaching, and even stepping over the edge of a bathtub.
“Seeing the technology used in real-life scenarios is really exciting,” said Bolli.
The team’s design, which will be presented later this month at the IEEE Conference on Robotics and Automation (ICRA), aims to eliminate the physical constraints and stigmas often associated with eldercare devices. Their approach prioritizes both independence and safety—key values for aging Americans seeking to remain in their homes longer.
While E-BAR currently operates via remote control, the team plans to add autonomous capabilities and streamline the device’s design for home and facility use. The researchers are also exploring ways to integrate fall-prediction algorithms, developed in a parallel project in Asada’s lab, to adapt robotic responses based on a user’s real-time risk level.
“Eldercare conditions can change every few weeks or months,” Asada noted. “We’d like to provide continuous and seamless support as a person’s disability or mobility changes with age.”
As the nation prepares for the realities of an aging population, MIT’s work offers a glimpse into a future where robotics play a central role in eldercare—enhancing both quality of life and personal dignity for millions of older adults.
Health
Scientist urges need for an Indian-specific blood parameter reference range
In India, standard blood parameter reference ranges aren’t representative of the local population; but based on conclusions derived from population studies in the West.

Prof. Ullas Kolthur-Seetharam, a leading Indian scientist in metabolism and aging, has urged for the re-optimization of standard blood parameter reference ranges to better suit Indian populations, highlighting that current values are based on Western populations and may not account for India-specific factors.
Speaking at the National Technology Day (NTD) 2025 lecture at the Biotechnology Research and Innovation Council-Rajiv Gandhi Centre for Biotechnology (BRIC-R caballoGCB), Kerala, India, Prof. Kolthur-Seetharam emphasized the need for tailored diagnostic benchmarks to improve the accuracy of diagnosing metabolic disorders like diabetes and cardiovascular diseases in India.
“Genetic, dietary, and environmental differences can significantly alter biomarkers,” said Prof. Kolthur-Seetharam, Director of the Centre for DNA Fingerprinting and Diagnostics (BRIC-CDFD), Hyderabad, India. He noted that emerging research reveals how dietary patterns influence health through mitochondrial function and epigenetic regulation, necessitating India-specific reference ranges.
Currently on deputation from the Tata Institute of Fundamental Research (TIFR), Mumbai, Prof. Kolthur-Seetharam has made significant contributions to understanding the interplay of mitochondrial function, epigenetics, and nutrition in shaping health and longevity. He also founded The Advanced Research Unit on Metabolism, Development & Aging (ARUMDA) at TIFR, a pioneering initiative tackling India’s challenges with malnutrition, non-communicable diseases, and aging through interdisciplinary research.
-
Earth3 months ago
How IIT Kanpur is Paving the Way for a Solar-Powered Future in India’s Energy Transition
-
Space & Physics2 months ago
Could dark energy be a trick played by time?
-
Society3 months ago
Starliner crew challenge rhetoric, says they were never “stranded”
-
Space & Physics5 months ago
Obituary: R. Chidambaram, Eminent Physicist and Architect of India’s Nuclear Program
-
Society4 months ago
DeepSeek: The Good, The Bad, and The Ugly
-
Space & Physics2 months ago
Sunita Williams aged less in space due to time dilation
-
Society4 months ago
Sustainable Farming: The Microgreens Model from Kerala, South India
-
EDUNEWS & VIEWS4 months ago
Indian kids use different math skills at work vs. school