Journal & Article

Artificial Intelligence

I/F
# Journal I/F

Nature Machine Intelligence

The new NeuroAI. Connecting molecular properties with plain language. A collective AI via lifelong learning and sharing at the edge. Challenges and opportunities in translating ethical AI principles into practice for children. Generative AI for designing and validating easily synthesizable and structurally novel antibiotics. AI protein shake-up. Neural multi-task learning in drug design. Codon language embeddings provide strong signals for use in protein engineering. Is it five already? Guidelines for study protocols describing predefined validations of prediction models in medical deep learning and beyond. The dangers of using proprietary LLMs for research. Anniversary AI reflections. Improving generalization of machine learning-identified biomarkers using causal modelling with examples from immune receptor diagnostics. Generation of 3D molecules in pockets via a language model. Assessing antibody and nanobody nativeness for hit selection and humanization with AbNatiV. Autonomous 3D positional control of a magnetic microrobot using reinforcement learning Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalization Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework Capturing complex hand movements and object interactions using machine learning-powered stretchable smart textile gloves Variational autoencoder for design of synthetic viral vector serotypes Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers Leveraging large language models for predictive chemistry What comparing deep neural networks can teach us about human vision Mitigating allocative tradeoffs and harms in an environmental justice data tool Protein function prediction as approximate semantic entailment A computational framework for neural network-based variational Monte Carlo with Forward Laplacian Weak signal extraction enabled by deep neural network denoising of diffraction data State-specific protein–ligand complex structure prediction with a multiscale deep generative model Lessons from a challenge on forecasting epileptic seizures from non-cerebral signals Reusability report: Unpaired deep-learning approaches for holographic image reconstruction A causal perspective on dataset bias in machine learning for medical imaging Generating mutants of monotone affinity towards stronger protein complexes through adversarial learning Reusability report: Leveraging supervised learning to uncover phenotype-relevant biology from single-cell RNA sequencing data The democratization of global AI governance and the role of tech companies Learning high-level visual representations from a child’s perspective without strong inductive biases Author Correction: A challenge for rounded evaluation of recommender systems (Nature Machine Intelligence, (2023), 5, 2, (181-182), 10.1038/s42256-022-00606-0) Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology PocketFlow is a data-and-knowledge-driven structure-based molecular generative model Foundation model for cancer imaging biomarkers Federated learning is not a cure-all for data ethics Author Correction: A soft robot that adapts to environments through shape change (Nature Machine Intelligence, (2020), 3, 1, (51-59), 10.1038/s42256-020-00263-1) Invalid SMILES are beneficial rather than detrimental to chemical language models A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions Geometry-enhanced pretraining on interatomic potentials The curious case of the test set AUROC Reusability report: Uncovering associations in biomedical bipartite networks via a bilinear attention network with domain adaptation Tandem mass spectrum prediction for small molecules using graph transformers A neural speech decoding framework leveraging deep learning and speech synthesis Equivariant 3D-conditional diffusion model for molecular linker design A year of racing ahead with AI and not breaking things.