Toggle light / dark theme

Democratizing AI scientists using ToolUniverse

AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data, and analyses into a common ecosystem. In omics, unified ecosystems have transformed research by enabling interoperability, reuse, and community-driven development; AI scientists require comparable infrastructure. We present ToolUniverse, an ecosystem for building AI scientists from any language or reasoning model, whether open or closed. TOOLUNIVERSE standardizes how AI scientists identify and call tools, integrating more than 600 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design. It automatically refines tool interfaces for correct use by AI scientists, creates new tools from natural language descriptions, iteratively optimizes tool specifications, and composes tools into agentic workflows. In a case study of hypercholesterolemia, ToolUniverse was used to create an AI scientist to identify a potent analog of a drug with favorable predicted properties. The open-source ToolUniverse is available at https://aiscientist.tools.

Engineers create first artificial neurons that could directly communicate with living cells

A team of engineers at the University of Massachusetts Amherst has announced the creation of an artificial neuron with electrical functions that closely mirror those of biological ones. Building on their previous work using protein nanowires synthesized from electricity-generating bacteria, the team’s discovery means that we could see immensely efficient computers built on biological principles which could interface directly with living cells.

“Our brain processes an enormous amount of data,” says Shuai Fu, a graduate student in electrical and engineering at UMass Amherst and lead author of the study published in Nature Communications. “But its power usage is very, very low, especially compared to the amount of electricity it takes to run a Large Language Model, like ChatGPT.”

The human body is over 100 times more electrically efficient than a computer’s electrical circuit. The is composed of billions of neurons, specialized cells that send and receive all over the body. While it takes only about 20 watts for your brain to, say, write a story, an LLM might consume well over a megawatt of electricity to do the same task.

Your pancreas may be making its own version of Ozempic

Alpha cells in the pancreas can produce GLP1, not just glucagon, offering a surprising backup system for blood sugar control.

Duke University scientists have discovered that pancreatic alpha cells, long believed to only produce glucagon, actually generate powerful amounts of GLP-1 — the same hormone mimicked by popular diabetes drugs like semaglutide (Ozempic and Wegovy). Even more surprisingly, when glucagon production is blocked, alpha cells “switch gears” and boost GLP-1 output, enhancing insulin release and blood sugar control.

A new study from Duke University School of Medicine is challenging long-standing views on blood sugar regulation — and pointing to a surprising new ally in the fight against type 2 diabetes.

HIV mystery uncovered: How the virus reprograms host cells to create perfect hiding places

For over three decades, HIV has played an elaborate game of hide-and-seek with researchers, making treating—and possibly even curing—the disease a seemingly insurmountable obstacle to achieve.

But scientists at Case Western Reserve University have made a breakthrough discovery that could fundamentally change strategies for treating HIV.

The team identified for the first time how HIV enters a in infected cells that allows the virus to “hide” from the immune system and current treatments.

Enlarged cancer cell nuclei may limit spread rather than signal severity

In tissue biopsies, cancer cells are frequently observed to have nuclei (the cell’s genetic information storage) that are larger than normal. Until now, this was considered a sign that the cancer was worsening, but the exact cause and effect had not been elucidated.

In a new study, a KAIST research team has found that cancer cell nuclear hypertrophy is not a cause of malignancy but a temporary response to replication stress, and that it can, in fact, suppress metastasis. This discovery is expected to lead to the development of new diagnostic and therapeutic strategies for cancer and metastasis inhibition.

The research team, led by Professor Joon Kim of the Graduate School of Medical Science and Engineering, in collaboration with the research teams of Professor Ji Hun Kim and Professor You-Me Kim, confirmed that DNA replication stress (the burden and error signal that occurs when a cell copies its DNA), which is common in , causes the “actin” protein inside the nucleus to aggregate (polymerize), which is the direct cause of the nuclear enlargement.

PA-915 molecule shows long-lasting antidepressant effects without common side effects in mice

Depression and anxiety disorders are among the most widespread mental health disorders, with estimates suggesting that they affect around 264 million and 284 million people worldwide, respectively. Depression is a mood disorder characterized by persistent sadness and a loss of interest in everyday activities, while anxiety disorders are marked by high levels of nervousness, worry and fear, either in specific situations or generalized.

Today, there are several for both depression and , including both pharmacological drugs and specific types of psychotherapy. Yet available therapeutic strategies are not effective for all affected individuals; thus, identifying alternative treatments could be highly advantageous.

Researchers at the University of Osaka, Kobe University School of Medicine, Hamamatsu University School of Medicine and other institutes have recently developed a called PA-915, which could hold some promise for the treatment of depression, anxiety and stress-related disorders. In a paper published in Molecular Psychiatry, they showed that the molecule suppressed both anxiety-like and depression-like behaviors in mice who were placed under high levels of stress.

/* */