Articles in 2025

Jian Ma et al. present HuDiff, a diffusion-based deep learning framework that humanizes antibodies and nanobodies (a small type of antibody) without templates. The model achieves improved humanness while preserving or enhancing binding strength, and the authors show promising results in virus neutralization experiments.

Designing and optimizing proteins by mutagenesis suffers from the overwhelming space of possible variants. A recent study developed µProtein, a reinforcement learning model coupled with a protein language model as a surrogate oracle, to accelerate this process towards high-functioning proteins.

A small and fast diffusion model is presented, which is able to efficiently generate long protein backbones.

Diamond, a statistically rigorous method, is capable of finding meaningful feature interactions within machine learning models, making black-box models more interpretable for science and medicine.

A lightweight, modular assistive soft exosuit is introduced, which supports shoulder and elbow movement in individuals with cervical spinal cord injury. The device enhances endurance and range of motion, reduces muscle effort and improves clinical test scores.

Drakopoulos et al. present a model that captures the transformation from sound waves to neural activity patterns underlying early auditory processing. The model reproduces neural responses to a range of complex sounds and key neurophysiological phenomena.

Inhibiting AKT1 kinase can have potentially positive uses against many types of cancer. To find novel molecules targeting this protein, a graph adversarial network is trained as a generative model.

Ilievski et al. examine differences and similarities in the various ways human and AI systems generalize. The insights are important for effectively supporting alignment in human–AI teams.

Artificial intelligence is transforming scientific discovery through (semi-)autonomous agents capable of reasoning, planning, and interacting with digital and physical environments. This Comment explores the foundations and frontiers of agentic science, outlining its emerging directions, current limitations, and the pathways for responsible integration into scientific practice.

A sampling-based manifold learning method is proposed to study the cluster structure of high-dimensional data. Its applicability and scalability have been verified in single-cell data analysis and anomaly detection in electrocardiogram signals.

The next major challenge for artificial intelligence in drug development lies in proving its value in real-world settings. A new technology not only supports the generation of novel chemical entities but also accelerates a range of real-world molecular design tasks.

Lancelot, a compute-efficient federated learning framework using homomorphic encryption to prevent information leakage, is presented, achieving 20 times faster processing speeds through advanced cryptographic and encrypted sorting techniques.

TCR-TRANSLATE, a deep learning framework adapting machine translation to immune design, demonstrates the successful generation of a functional T cell receptor sequence for a cancer epitope from the target sequence alone.

μProtein, combining deep learning and reinforcement learning, is developed to design high-function proteins. This framework, trained only on single-mutation data, discovers multi-site β-lactamase mutants with up to 2,000× growth rates.

AI copilots are integrated into brain–computer interfaces, enabling a paralysed participant to achieve improved control of computer cursors and robotic arms. This shared autonomy approach offers a promising path to increase BCI performance and clinical viability.

Zhu, Hua and Chen propose Fountain, a deep learning framework for batch integration of scATAC-seq data that utilizes regularized barycentric mapping. It preserves biological heterogeneity, enabling online and original dimensionality integration.