MetaGraph enables scalable indexing of large sets of DNA, RNA or protein sequences using annotated de Bruijn graphs.

An optical slab waveguide with highly programmable nonlinear functionality is described, enabling the demonstration of versatile control over broadband second-harmonic generation across the spectral, spatial and spatio-spectral domains.

The authors introduce a method that combines physics and machine learning to design dynamic unstructured proteins with tunable ensemble properties like size, shape, sensing and binding.

The recent surge in generative AI has introduced exciting possibilities for computational chemistry. Generative AI methods have made significant pr...

We propose a novel framework that leverages large language models (LLMs) to transform synthetically infeasible inorganic crystal structures into synthetically feasible ones. Unlike previous studies on...

This Review summarizes recent technical advancements in generative AI, outlines how new models might improve healthcare and discusses validation approaches—using lessons from recent successes and failures in the field.

This study presents a generative artificial intelligence approach for the high-throughput discovery of antimicrobials against multidrug-resistant bacteria.

Characterization of atomic-scale materials traditionally requires human experts with months to years of specialized training. Even for trained human operators, accurate and reliable characterization r...

META-SiM brings foundation model power to single-molecule time traces, excelling across diverse analysis tasks. Paired with the web-based META-SiM Projector and entropy mapping, it rapidly reveals hidden molecular behaviors inaccessible by other means.

Simulated quantum annealing enhances probabilistic Ising Machines by enabling faster, more reliable solutions to complex optimization problems using interacting copies of the system guided by a time-d...

Heat recharges enzyme-free DNA circuits, enabling complex logic operations and neural networks to perform multiple computations, offering a universal energy source for molecular machines and advancing autonomous behaviours in artificial chemical systems.

Adaptive optical vision Fourier transformer (AOViFT) is a machine learning-based framework for accurately inferring aberrations and restoring diffraction-limited performance in diverse biological specimens.

The activity and stability of supported metal catalysts is in large part influenced by their interaction with the support. Now, neural network molecular dynamics simulations are combined with interpretable machine learning to reveal the governing factors of metal–support interactions for Pt nanoparticles on various oxide supports, identifying key features and proposing sinter-resistant supports.

A framework rooted in perturbation theory extends machine-learning interatomic potential approaches, capturing complex dynamics and energetics at electrified solid-liquid interfaces.

Multi-step planning is a challenge for LLMs. Here, the authors introduce a brain-inspired Modular Agentic Planner that decomposes planning into specialized LLM modules, improving performance across tasks and highlighting the value of cognitive neuroscience for LLM design.

Accurately solving the Schrödinger equation is challenging. Here, authors present QiankunNet, a Transformer-based framework that efficiently captures quantum correlations, achieving high accuracy in complex molecular systems using neural network quantum states.

Predictive chemistry often faces data scarcity, limiting the performance of machine learning (ML) models. This is particularly the case for specialized tasks such as reaction rate or selectivity predi...

YouTube video by Jorge Bravo Abad

An infrared metasurface combined with physics-informed AI enables sensing of nanoscale protein dynamics in solution.

YouTube video by FundacionAreces

Recent advances in quantum technologies have demonstrated that quantum systems can outperform classical ones in specific tasks, a concept known as quantum advantage. Although previous efforts have foc...

A low-cost robotic platform using mainly optical detection to quantify yields of products and by-products allows the analysis of multidimensional chemical reaction hyperspaces and networks much faster than is possible by human chemists.

FlexConsensus is a multi-autoencoder-based algorithm for merging different conformational landscapes from cryogenic electron microscopy heterogeneity analysis into a common latent space for the identification of similarities and differences among various methods. This helps in the validation of estimated conformational landscape and provides tools to streamline the heterogeneity workflow.

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 temporal-signal processor based on two in-materia computing hardware platforms—reconfigurable nonlinear-processing units (RNPUs) and analogue in-memory computing (AIMC)—is used for both feature extr...

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

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.

A foundation machine learning model, SurFF, enables DFT-accurate predictions of surface energies and morphologies in intermetallic catalysts, achieving over 105-fold acceleration for high-throughput m...

This study reports a complete photonic neuron integrated on a silicon-nitride chip, enabling ultrafast all-optical computing with nonlinear multi-kernel convolution for image recognition and motion ge...

The authors report a memristor-based system that analyzes raw analog signals from a genomic sequencer directly in memory. By bypassing slow data conversion, the system achieves substantial improvement...

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 ano...

Humans and other organisms make decisions choosing between different options, with the aim of maximizing the reward and minimizing the cost. The ma...

Mutational effect transfer learning (METL) is a protein language model framework that unites machine learning and biophysical modeling. Transformer-based neural networks are pretrained on biophysical ...

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 muta...

Leveraging in-memory computing with emerging gain-cell devices, the authors accelerate attention—a core mechanism in large language models. They train a 1.5-billion-parameter model, achieving up to a ...

It has recently been shown that synaptic transmission delays enhance the computational capabilities of spiking neural networks. In this manuscript, the authors introduce an exact, event-based training...

For decades, researchers have explored DNA not just as genetic material but as a programmable medium for computation. Using enzyme-free strand displacement—a process where an invading strand binds to ...

Reactive transport in porous media is crucial for catalysis. Here, authors use deep learning to visualize and predict reaction rates in porous catalysts, identifying key structural features that influ...

Large-scale screening of materials via machine learning is emerging as an effective strategy for accelerating scientific discovery and industrial applications. Machine learning methods for transition state (TS)-based screening for catalysts remain underexplored due to the scarcity of TS data sets and the inherent challenges of TS searching tasks. Here, we present a framework for large-scale transition states screening for catalysts (CaTS), which uniquely bridges microscopic reaction kinetics and macroscopic computational efficiency by leveraging TS energy, a mechanistically rigorous yet computationally prohibitive descriptor. CaTS integrates automated structure generation with a machine learning force field-based nudged elastic band (NEB) method, enabling high-throughput TS exploration at 104 the speed of density functional theory (DFT). Initially optimized and validated on a small-molecule TS database comprising 10,000 reactions (achieving sub-0.2 eV errors in TS energy prediction) and further applied to a metal–organic complex catalyst (0.16 eV MAE with only 327 training samples), CaTS achieves DFT-level accuracy at 0.01% computational cost. Scaling to over 1000 unseen metal–organic complex structures, it identifies top candidates validated by rigorous DFT. AI-assisted analysis using ChatGPT o3 and SHAP confirms that the predictions are consistent with mechanistic heuristics, providing theoretical validation for large-scale prediction. This paradigm shift from static descriptors to kinetic-resolution screening enables industrial-scale catalyst discovery with atomistic precision.

The fine-tuning of halide perovskite materials for both performance and stability calls for innovative tools that streamline high-throughput experimentation. Here, we present two complementary systems designed to accelerate the development of solution-processed thin-film semiconductors. HITSTA (High-Throughput Stab