Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
EmerGNN, a method to predict interactions for emerging drugs, may improve patient care and drug development by providing insight into the effects of using biomedical networks in interaction predictions.
Using registry data from Denmark, Lehmann et al. create individual-level trajectories of events related to health, education, occupation, income and address, and also apply transformer models to build rich embeddings of life-events and to predict outcomes ranging from time of death to personality.
A diffusion model that generates chemical reactions in 3D with all desired symmetries preserved is established and shown to reduce transition state search from days to seconds and complement intuition-based reaction exploration with generative AI.
Developing predictive mechanistic models in biology is challenging. Elektrum uses neural architecture search, kinetic models and transfer learning to discover CRISPR–Cas9 cleavage kinetics, achieving high performance and biophysical interpretability.
Signal peptides (SPs) are vital for protein–transmembrane communication. In this work, the authors introduce USPNet, a deep learning method based on a protein language model for SP prediction that shows both high sensitivity and efficiency, thereby contributing to the identification of novel SPs.
SRDTrans is a self-supervised denoising method for fluorescence images powered by spatial redundancy sampling and a dedicated transformer network that achieves good performance on fast dynamics and various imaging modalities.
VSSR-MC is a Markov chain method based on virtual adsorption sites that interfaces with a neural network force field to provide fast, accurate and comprehensive sampling of material surfaces.
Zhi Liu et al. develop a method to measure disparities in reporting delays in urban crowdsourcing systems, uncovering socioeconomic disparities and providing actionable insights for interventions that enhance the efficiency and equity of city services.
A graph-based contrastive learning framework, LACL, is proposed for geometric domain-agnostic prediction of molecular properties to alleviate the need for molecular geometry relaxation, enabling large-scale inference scenarios.
LOVAMAP is an analysis software that accurately identifies 3D pores in packed particle systems by exploiting information about the particle configuration as a basis for segmentation. Using the software, the authors were able to uncover striking relationships between particle and pore properties.
Designing accessible, interoperable and reusable software for applying deep learning to the study of gene regulation has been a challenge in genomics research. EUGENe is a toolkit that addresses this gap and streamlines end-to-end analyses.
A hybrid machine learning–physics model is developed that reduces simulation cost by two orders of magnitude while retaining high ab initio accuracy, to predict free-energy transition states for hydrogen combustion reactions.
A deep-learning model, DetaNet, is proposed to efficiently and precisely predict molecular scalars, vectorial and tensorial properties, as well as the infrared, Raman, ultraviolet–visible and nuclear magnetic resonance spectra.
A physics-informed deep learning model, PBCNet, is proposed for predicting the relative binding affinity of ligands in order to improve guiding structure-based drug lead optimization.
A graph attention neural network tool is introduced to integrate multiple spatial transcriptomics data from different individuals, technologies and developmental stages, enabling consensus spatial domain identification and three-dimensional tissue reconstruction.
This study develops a programmable quantum processor, named Abacus, and applies it to Gaussian boson sampling tasks targeting drug discovery challenges.
SurfGen is a structure-based drug design approach that delves into topological and geometric deep learning techniques for interaction learning, echoing the classical lock-and-key model.
The reasoning capabilities of OpenAI’s generative pre-trained transformer family were tested using semantic illusions and cognitive reflection tests that are typically used in human studies. While early models were prone to human-like cognitive errors, ChatGPT decisively outperformed humans, avoiding the cognitive traps embedded in the tasks.
GaUDI is a guided diffusion method for the design of molecular structures that features a flexible and scalable target function and that achieves high validity of generated molecules.
This work unifies an interdisciplinary literature of over 230 computational methods for measuring interactions from complex systems, revealing previously unreported theoretical connections and demonstrating practical benefits of broad methodological comparison.