Nature Machine Intelligence

Article	Citations
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators	732
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans	628
Shortcut learning in deep neural networks	604
Drug discovery with explainable artificial intelligence	462
An open source machine learning framework for efficient and transparent systematic reviews	274
Deep learning for tomographic image reconstruction	269
Machine learning pipeline for battery state-of-health estimation	262
AI for radiographic COVID-19 detection selects shortcuts over signal	251
Molecular contrastive learning of representations via graph neural networks	222
Inverse design of nanoporous crystalline reticular materials with deep generative models	189
Expanding functional protein sequence spaces using generative adversarial networks	184
The carbon impact of artificial intelligence	182
Geometry-enhanced molecular representation learning for property prediction	178
End-to-end privacy preserving deep learning on multi-institutional medical imaging	175
Ensemble deep learning in bioinformatics	171
Causal inference and counterfactual prediction in machine learning for actionable healthcare	168
Development of metaverse for intelligent healthcare	150
Improved protein structure prediction by deep learning irrespective of co-evolution information	145
Mapping the space of chemical reactions using attention-based neural networks	136
Advances, challenges and opportunities in creating data for trustworthy AI	130
Concept whitening for interpretable image recognition	128
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data	123
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation	123
Deep learning-based prediction of the T cell receptor–antigen binding specificity	122
Geometric deep learning on molecular representations	119

Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion	117
The rise of robots in surgical environments during COVID-19	112
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing	110
Neural circuit policies enabling auditable autonomy	108
Dual use of artificial-intelligence-powered drug discovery	107
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC	106
Bioinspired acousto-magnetic microswarm robots with upstream motility	105
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science	105
Code-free deep learning for multi-modality medical image classification	105
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms	104
Estimation of continuous valence and arousal levels from faces in naturalistic conditions	104
Machine learning and computation-enabled intelligent sensor design	104
Making deep neural networks right for the right scientific reasons by interacting with their explanations	103
A soft robot that adapts to environments through shape change	103
Prediction of water stability of metal–organic frameworks using machine learning	100
High-accuracy prostate cancer pathology using deep learning	100
Origami-inspired miniature manipulator for teleoperated microsurgery	100
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network	99
Machine learning and algorithmic fairness in public and population health	97
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors	97
Three types of incremental learning	96
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	94
Automating turbulence modelling by multi-agent reinforcement learning	94
The transformational role of GPU computing and deep learning in drug discovery	90
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks	88
Learning functional properties of proteins with language models	87
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning	87
Controllable protein design with language models	87
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis	87
AI-generated characters for supporting personalized learning and well-being	87
A definition, benchmark and database of AI for social good initiatives	86
Stable learning establishes some common ground between causal inference and machine learning	83
A geometric deep learning approach to predict binding conformations of bioactive molecules	81
A soft thumb-sized vision-based sensor with accurate all-round force perception	80
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	80
Parameter-efficient fine-tuning of large-scale pre-trained language models	79
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images	79
Using online verification to prevent autonomous vehicles from causing accidents	77
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations	77
Biological underpinnings for lifelong learning machines	76
Morphological and molecular breast cancer profiling through explainable machine learning	76
Large pre-trained language models contain human-like biases of what is right and wrong to do	76
Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support	76
Improving performance of deep learning models with axiomatic attribution priors and expected gradients	76
An embedded ethics approach for AI development	75
Governing AI safety through independent audits	73
Encoding of tactile information in hand via skin-integrated wireless haptic interface	72
Predictive control of aerial swarms in cluttered environments	72
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design	70
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	69

Teaching recurrent neural networks to infer global temporal structure from local examples	68
Large-scale chemical language representations capture molecular structure and properties	67
Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework	65
Combinatorial optimization with physics-inspired graph neural networks	65
A case-based interpretable deep learning model for classification of mass lesions in digital mammography	64
Deep neural networks identify sequence context features predictive of transcription factor binding	63
Molecular convolutional neural networks with DNA regulatory circuits	62
Simultaneous deep generative modelling and clustering of single-cell genomic data	62
Fast and energy-efficient neuromorphic deep learning with first-spike times	61
Extraction of protein dynamics information from cryo-EM maps using deep learning	61
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes	60
Learning function from structure in neuromorphic networks	59
Interpretable deep-learning models to help achieve the Sustainable Development Goals	57
Benchmarking saliency methods for chest X-ray interpretation	57
Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media	57
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling	56
When causal inference meets deep learning	56
Chemical language models enable navigation in sparsely populated chemical space	54
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions	53
Chemically programmable microrobots weaving a web from hormones	53
Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding	50
Multiscale simulations of complex systems by learning their effective dynamics	50
Self-supervised retinal thickness prediction enables deep learning from unlabelled data to boost classification of diabetic retinopathy	50
Large language models associate Muslims with violence	50
Improving the quality of machine learning in health applications and clinical research	50
Deep recurrent optical flow learning for particle image velocimetry data	49
Experimental discovery of structure–property relationships in ferroelectric materials via active learning	48
A biological perspective on evolutionary computation	47
Improving representations of genomic sequence motifs in convolutional networks with exponential activations	47
Radiological tumour classification across imaging modality and histology	46
Responsible artificial intelligence in agriculture requires systemic understanding of risks and externalities	46
External validation demonstrates limited clinical utility of the interpretable mortality prediction model for patients with COVID-19	45
Multimodal data fusion for cancer biomarker discovery with deep learning	44
Real-world embodied AI through a morphologically adaptive quadruped robot	44
Deep learning-inferred multiplex immunofluorescence for immunohistochemical image quantification	44
A machine learning platform to estimate anti-SARS-CoV-2 activities	44
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	44
Algorithms to estimate Shapley value feature attributions	43
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks	43
Interpretable bilinear attention network with domain adaptation improves drug–target prediction	43
A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware	42
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices	42
A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data	41
Predicting myocardial infarction through retinal scans and minimal personal information	41
An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data	41
The neural resource allocation problem when enhancing human bodies with extra robotic limbs	41
Automatic strain sensor design via active learning and data augmentation for soft machines	41
Institutionalizing ethics in AI through broader impact requirements	41
Skills for physical artificial intelligence	41
Increasing generality in machine learning through procedural content generation	41
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks	40
Deep learning-based robust positioning for all-weather autonomous driving	40
Bringing artificial intelligence to business management	40
The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires	39
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition	39
Empirical observation of negligible fairness–accuracy trade-offs in machine learning for public policy	39
Large language models challenge the future of higher education	39
Enhancing optical-flow-based control by learning visual appearance cues for flying robots	38
Visual speech recognition for multiple languages in the wild	38
Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports	37
Cross-validation is safe to use	37
Autoregressive neural-network wavefunctions for ab initio quantum chemistry	37
Intelligent problem-solving as integrated hierarchical reinforcement learning	36
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	36
Accelerated rational PROTAC design via deep learning and molecular simulations	35
Multi-objective goal-directed optimization of de novo stable organic radicals for aqueous redox flow batteries	35
Quantifying the spatial homogeneity of urban road networks via graph neural networks	34
A deep generative model enables automated structure elucidation of novel psychoactive substances	34
Automating crystal-structure phase mapping by combining deep learning with constraint reasoning	33
Neurons learn by predicting future activity	33
Mixed-modality speech recognition and interaction using a wearable artificial throat	33
Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling	33
Variational neural annealing	33
Regression Transformer enables concurrent sequence regression and generation for molecular language modelling	33
A multi-use deep learning method for CITE-seq and single-cell RNA-seq data integration with cell surface protein prediction and imputation	33
Minimal-uncertainty prediction of general drug-likeness based on Bayesian neural networks	33
Stretchable e-skin and transformer enable high-resolution morphological reconstruction for soft robots	32
Adversarial interference and its mitigations in privacy-preserving collaborative machine learning	31
Deep learning STEM-EDX tomography of nanocrystals	31
An automated framework for efficiently designing deep convolutional neural networks in genomics	31

Accelerating evidence-informed decision-making for the Sustainable Development Goals using machine learning	31
Recovery of continuous 3D refractive index maps from discrete intensity-only measurements using neural fields	31
Artificial microtubules for rapid and collective transport of magnetic microcargoes	30
Direct-to-consumer medical machine learning and artificial intelligence applications	30
The AI writing on the wall	30
Global voxel transformer networks for augmented microscopy	30
Neutralizing the impact of atmospheric turbulence on complex scene imaging via deep learning	30
Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider	30
AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy	30
Regulating AI in medicine in the United States and Europe	29
Designing clinically translatable artificial intelligence systems for high-dimensional medical imaging	29
Segmentation of neurons from fluorescence calcium recordings beyond real time	29
Understanding adversarial examples requires a theory of artefacts for deep learning	29
Reconstructing Kinetic Models for Dynamical Studies of Metabolism using Generative Adversarial Networks	29
A deep generative model for molecule optimization via one fragment modification	29