An Arizona State University team of researchers has built a powerful new AI tool, called Ark+, to help doctors read chest X rays better and improve health care outcomes. 

A new bionic prosthesis that directly links to the body’s muscles and nerves enables above-knee amputees to move with greater agility, precision, and sensory awareness than traditional devices, researchers report. Prosthetic limbs are widely used to help restore mobility for individuals living with limb amputations. However, their design and use have remained largely unchanged for more than a century. While modern prostheses can be tailored to an individual's needs, they still fall short in enabling a dynamic range of movement and in providing users with sensory feedback. Advancements in traditional lower-limb prostheses have focused on mechanical enhancements that improve repetitive walking, overlooking the full range and complexity of natural leg movement, especially when there is a need to change gait or balance. As a result, amputees often struggle with tasks like navigating uneven terrain or climbing stairs. Here, Tony Shu et al. present a tissue-integrated prosthetic knee that uses implanted neural interfaces to directly connect the device to the body’s physiology. According to Shu et al., the system – called the osseointegrated mechanoneural prosthesis (OMP) – combines three core innovations: direct neuromuscular control that allows fluid and adaptive movement; (2) a bone-anchored implant; and (3) agonist-antagonist myoneural interfaces (AMI) that replicate natural muscle interactions to reestablish a sense of limb position and movement. Clinical trials involved 2 above-knee amputees.  For each, the OMP system enabled superior mobility across diverse, real-world leg movements, such as terrain navigation and sit-to-stand transitions. While some limitations remain, Shu et al. suggest that greater prosthetic embodiment and function can be achieved through biologically integrated systems like the OMP, potentially yielding transformative gains in rehabilitation, mobility, and user experience following limb loss. In a related Perspective, Lee Fisher discusses the study in greater detail.

Researchers present BioEmu – a new AI model that rapidly and accurately predicts the full range of shapes a protein can adopt, offering a faster, cheaper alternative to traditional molecular simulations. Proteins and their complexes are essential to nearly every biological process and are central to advances in medicine and biotechnology. While recent breakthroughs in sequencing and deep learning have made it easier to determine a protein’s sequence and structure, understanding how proteins function by shifting between different shapes in response to other molecules remains a central challenge. These dynamic shape changes underpin key biological activities. Current molecular dynamics (MD) simulation techniques provide detailed insights into protein behavior but are slow, costly, and resource-intensive. While generative machine learning models offer a faster alternative, they have yet to match experimental data reliably. Here, Sarah Lewis and colleagues developed BioEmu – a deep learning-based biomolecular emulator designed to sample the wide range of shapes a protein can adopt at equilibrium rapidly and accurately. According to Lewis et al., BioEmu can sample thousands of realistic protein conformations in just one GPU-hour, making it orders of magnitude faster and cheaper than traditional MD approaches. This is accomplished by combining training data from AlphaFold structural predictions, large-scale MD simulations, and extensive experimental measurements of protein stability, which were refined by a novel property-prediction fine-tuning (PFFT) algorithm that enables it to match experimental observations even in the absence of structural data. However, despite its efficiency and accuracy within its training domain, BioEmu has limitations. For example, it does not natively model molecular dynamics or interactions with membranes, ligands, or varying environmental conditions like temperature or pH. Nonetheless, the authors argue that BioEmu illustrates how deep learning can amortize the high cost of simulation and experimentation, paving the way toward large-scale, data-driven prediction of protein function.

MIT researchers developed a new type of bionic knee that can help people with above-the-knee amputations walk faster, climb stairs, and avoid obstacles more easily than they could with a traditional prosthesis.

Hertz Fellow Reuben Saunders developed a powerful new CRISPRi-based screening platform to silence genes in millions of cells across living tissues. His award-winning thesis, “Pooled genetic screens with rich readouts at scale and in vivo,” is transforming how scientists study gene function in real physiological settings.