Why it's high time we stopped anthropomorphising ants We have long drawn parallels between ants and humans. Now we are comparing the insects to computers. Pollution is making many cities unlivable for their human inhabitants, but it is also tearing ant families and communities apart. Ants recognise each other by sniffing a thin layer of hydrocarbons on the outside of their exoskeletons; each colony has a specific "smell". But a new study reveals that ozone emissions can change the structure of these hydrocarbons.

RNA plays a pivotal role in translating genetic instructions into functional outcomes, underscoring its importance in biological processes and disease mechanisms.

Addressing these challenges requires scale. To that end we introduce ProteinGym, a large-scale and holistic set of benchmarks specifically designed for protein fitness prediction and design.

However,whenlargeamounts ofannotated dataareavailable, models thatallow end-to-end training such as neural networks are often preferred.

Why biological clocks get our'true age' wrong - and how AI could help Your chronological age can't always tell you the state of your health, which is why biological clocks have been developed to show our risk of developing diseases or dying - but they're not all they are cracked up to be, says columnist Graham Lawton You may be chronologically older than your "true age" When I first started writing about ageing years ago, there was a buzz around something called biological clocks, also known as ageing clocks or "true age" measurements. In principle, these are quite simple: we all have a chronological age, the number of years since birth, but this doesn't necessarily reflect how far we are down the slippery slope from birth to decrepitude. On average, this follows a fairly predictable trajectory, with gradual declines in almost every physical and mental attribute throughout adulthood. When we judge how old somebody is, we are intuitively totting up many of these tell-tale signs we see - the wrinkles and grey hair, or changes in posture, gait, voice, mental acuity and so on. The goal of measuring biological age is to capture this decline in a single metric, evaluated scientifically and expressed in years. The results tell us something we intuitively know: some people age better than others.

Artificial intelligence for scientific discovery has recently generated significant interest within the machine learning and scientific communities, particularly in the domains of chemistry, biology, and material discovery. For these scientific problems, molecules serve as the fundamental building blocks, and machine learning has emerged as a highly effective and powerful tool for modeling their geometric structures. Nevertheless, due to the rapidly evolving process of the field and the knowledge gap between science ({\eg}, physics, chemistry, \& biology) and machine learning communities, a benchmarking study on geometrical representation for such data has not been conducted. To address such an issue, in this paper, we first provide a unified view of the current symmetry-informed geometric methods, classifying them into three main categories: invariance, equivariance with spherical frame basis, and equivariance with vector frame basis. Then we propose a platform, coined Geom3D, which enables benchmarking the effectiveness of geometric strategies. Geom3D contains 16 advanced symmetry-informed geometric representation models and 14 geometric pretraining methods over 52 diverse tasks, including small molecules, proteins, and crystalline materials. We hope that Geom3D can, on the one hand, eliminate barriers for machine learning researchers interested in exploring scientific problems; and, on the other hand, provide valuable guidance for researchers in computational chemistry, structural biology, and materials science, aiding in the informed selection of representation techniques for specific applications.

The advancement of human healthspan and bioengineering relies heavily on predicting the behavior of complex biological systems. While high-throughput multiomics data is becoming increasingly abundant, converting this data into actionable predictive models remains a bottleneck. High-capacity, datadriven simulation systems are critical in this landscape; unlike classical mechanistic models restricted by prior knowledge, these architectures can infer latent interactions directly from observational data, allowing for the simulation of temporal trajectories and the anticipation of downstream intervention effects in personalized medicine and synthetic biology. To address this challenge, we introduce Neural Ordinary Differential Equations (NODEs) as a dynamic framework for learning the complex interplay between the proteome and metabolome. We applied this framework to time-series data derived from engineered Escherichia coli strains, modeling the continuous dynamics of metabolic pathways. The proposed NODE architecture demonstrates superior performance in capturing system dynamics compared to traditional machine learning pipelines. Our results show a greater than 90% improvement in root mean squared error over baselines across both Limonene (up to 94.38% improvement) and Isopentenol (up to 97.65% improvement) pathway datasets. Furthermore, the NODE models demonstrated a 1000x acceleration in inference time, establishing them as a scalable, high-fidelity tool for the next generation of metabolic engineering and biological discovery.

This is the fourth in a series of short reports that help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. Here, we ask whether assigning personas to models improves performance on difficult objective multiple - choice questions. We study both domain - specific expert personas and low - knowledge personas, evaluating six models on GPQA Diamond (Rein et al. 2024) and MMLU - Pro (Wang et al. 2024), graduate - level questions spanning science, engineering, and law. We tested three approaches: In-Domain Experts: Assigning the model an expert persona ("you are a physics expert") matched to the problem type (physics problems) had no significant impact on performance (with the exception of the Gemini 2.0 Flash model). Off-Domain Experts (Domain-Mismatched): Assigning the model an expert persona ("you are a physics expert") not matched to the problem type (law problems) resulted in marginal differences. Low-Knowledge Personas: We assigned the model negative capability personas (layperson, young child, toddler), which were generally harmful to benchmark accuracy. Across both benchmarks, persona prompts generally did not improve accuracy relative to a no-persona baseline. Expert personas showed no consistent benefit across models, with few exceptions.