The AI writing on the wall. Federated machine learning in data-protection-compliant research. Learning from data with structured missingness. Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support. Emergent behaviour and neural dynamics in artificial agents tracking odour plumes. Phy-Q as a measure for physical reasoning intelligence. Publisher Correction: Advancing ethics review practices in AI research (Nature Machine Intelligence, (2022), 4, 12, (1061-1064), 10.1038/s42256-022-00585-2) Deep learning based on parameterized physical forward model for adaptive holographic imaging with unpaired data A cautionary tale about the adoption of medical AI in Sweden Geometric deep learning reveals the spatiotemporal features of microscopic motion Translating single-cell genomics into cell types Much to discuss in AI ethics. Advancing ethics review practices in AI research. Interpretability of artificial neural network models in artificial intelligence versus neuroscience. Language and culture internalization for human-like autotelic AI. Transferring policy of deep reinforcement learning from simulation to reality for robotics. AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy. Super-resolution generative adversarial networks of randomly-seeded fields. Deep learning models for predicting RNA degradation via dual crowdsourcing. High-speed quadrupedal locomotion by imitation-relaxation reinforcement learning. Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data. A critical problem in benchmarking and analysis of evolutionary computation methods. Simple nearest-neighbour analysis meets the accuracy of compound potency predictions using complex machine learning models. Large-scale chemical language representations capture molecular structure and properties. Data sovereignty in genomics and medical research. Federated learning and Indigenous genomic data sovereignty. Developing moral AI to support decision-making about antimicrobial use. Developing robust benchmarks for driving forward AI innovation in healthcare. Development of metaverse for intelligent healthcare. Enhanced spatio-temporal electric load forecasts using less data with active deep learning. Closed-form continuous-time neural networks. Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework. Predicting functional effect of missense variants using graph attention neural networks. Image prediction of disease progression for osteoarthritis by style-based manifold extrapolation. Author Correction: A generalized-template-based graph neural network for accurate organic reactivity prediction. Revisiting code reusability. AI model transferability in healthcare: a sociotechnical perspective. Forecasting SARS-CoV-2 transmission and clinical risk at small spatial scales by the application of machine learning architectures to syndromic surveillance data. A context-aware deconfounding autoencoder for robust prediction of personalized clinical drug response from cell-line compound screening. Encoding of tactile information in hand via skin-integrated wireless haptic interface. Collaborative creativity in AI. Distinguishing two features of accountability for AI technologies. Bio-robots step towards brain–body co-adaptation. Accelerated rational PROTAC design via deep learning and molecular simulations. Deep learning-based robust positioning for all-weather autonomous driving. Deep neural networks with controlled variable selection for the identification of putative causal genetic variants. A generalized-template-based graph neural network for accurate organic reactivity prediction. Recovery of continuous 3D refractive index maps from discrete intensity-only measurements using neural fields. Interpretable meta-score for model performance. Achieving net zero emissions with machine learning: the challenge ahead.