Nature Machine Intelligence

Article	Citations
An interpretable mortality prediction model for COVID-19 patients	661
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators	596
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans	592
Shortcut learning in deep neural networks	553
Secure, privacy-preserving and federated machine learning in medical imaging	482
Drug discovery with explainable artificial intelligence	422
Deep learning for tomographic image reconstruction	240
Machine learning pipeline for battery state-of-health estimation	238
AI for radiographic COVID-19 detection selects shortcuts over signal	233
An open source machine learning framework for efficient and transparent systematic reviews	225
Molecular contrastive learning of representations via graph neural networks	188
Inverse design of nanoporous crystalline reticular materials with deep generative models	171
Finding key players in complex networks through deep reinforcement learning	170
Expanding functional protein sequence spaces using generative adversarial networks	166
Ensemble deep learning in bioinformatics	159
End-to-end privacy preserving deep learning on multi-institutional medical imaging	158
Geometry-enhanced molecular representation learning for property prediction	155
The carbon impact of artificial intelligence	154
Causal inference and counterfactual prediction in machine learning for actionable healthcare	150
Improved protein structure prediction by deep learning irrespective of co-evolution information	140
Mapping the space of chemical reactions using attention-based neural networks	121
Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks	121
Concept whitening for interpretable image recognition	121
Development of metaverse for intelligent healthcare	118
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation	114

The rise of robots in surgical environments during COVID-19	107
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC	102
Geometric deep learning on molecular representations	101
Deep learning-based prediction of the T cell receptor–antigen binding specificity	101
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing	100
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science	100
Bioinspired acousto-magnetic microswarm robots with upstream motility	99
Neural circuit policies enabling auditable autonomy	97
Advances, challenges and opportunities in creating data for trustworthy AI	96
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion	95
Code-free deep learning for multi-modality medical image classification	94
Estimation of continuous valence and arousal levels from faces in naturalistic conditions	93
Dual use of artificial-intelligence-powered drug discovery	93
A soft robot that adapts to environments through shape change	92
Making deep neural networks right for the right scientific reasons by interacting with their explanations	91
Machine learning and computation-enabled intelligent sensor design	91
Towards a new generation of artificial intelligence in China	91
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network	91
Exploring the limit of using a deep neural network on pileup data for germline variant calling	89
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms	89
Origami-inspired miniature manipulator for teleoperated microsurgery	89
High-accuracy prostate cancer pathology using deep learning	89
Prediction of water stability of metal–organic frameworks using machine learning	89
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data	88
Deep learning incorporating biologically inspired neural dynamics and in-memory computing	87
Automating turbulence modelling by multi-agent reinforcement learning	86
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors	83
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	83
Machine learning and algorithmic fairness in public and population health	82
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis	81
Artificial intelligence cooperation to support the global response to COVID-19	80
Controllable protein design with language models	77
The transformational role of GPU computing and deep learning in drug discovery	77
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks	77
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning	75
Using online verification to prevent autonomous vehicles from causing accidents	74
Three types of incremental learning	73
Improving performance of deep learning models with axiomatic attribution priors and expected gradients	72
Stable learning establishes some common ground between causal inference and machine learning	71
A definition, benchmark and database of AI for social good initiatives	71
A soft thumb-sized vision-based sensor with accurate all-round force perception	71
Morphological and molecular breast cancer profiling through explainable machine learning	71
Learning functional properties of proteins with language models	70
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images	70
An embedded ethics approach for AI development	70
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations	68
A geometric deep learning approach to predict binding conformations of bioactive molecules	68
Predictive control of aerial swarms in cluttered environments	67
Biological underpinnings for lifelong learning machines	66
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	62

Governing AI safety through independent audits	61
AI-generated characters for supporting personalized learning and well-being	61
Large pre-trained language models contain human-like biases of what is right and wrong to do	60
Teaching recurrent neural networks to infer global temporal structure from local examples	60
A neural network trained for prediction mimics diverse features of biological neurons and perception	59
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	57
A case-based interpretable deep learning model for classification of mass lesions in digital mammography	57
Extraction of protein dynamics information from cryo-EM maps using deep learning	57
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design	56
Simultaneous deep generative modelling and clustering of single-cell genomic data	56
Combinatorial optimization with physics-inspired graph neural networks	55
Learning function from structure in neuromorphic networks	54
A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional computed tomography image datasets	53
Large-scale chemical language representations capture molecular structure and properties	53
Encoding of tactile information in hand via skin-integrated wireless haptic interface	53
Predicting tumour mutational burden from histopathological images using multiscale deep learning	53
Deep neural networks identify sequence context features predictive of transcription factor binding	53
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions	52
When causal inference meets deep learning	52
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes	51
Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support	51
Interpretable deep-learning models to help achieve the Sustainable Development Goals	50
Molecular convolutional neural networks with DNA regulatory circuits	50
Fast and energy-efficient neuromorphic deep learning with first-spike times	49
Parameter-efficient fine-tuning of large-scale pre-trained language models	49
Benchmarking saliency methods for chest X-ray interpretation	48
Chemically programmable microrobots weaving a web from hormones	48
Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media	47
Self-supervised retinal thickness prediction enables deep learning from unlabelled data to boost classification of diabetic retinopathy	47
Chemical language models enable navigation in sparsely populated chemical space	46
Improving representations of genomic sequence motifs in convolutional networks with exponential activations	46
Machine Learning for COVID-19 needs global collaboration and data-sharing	46
Improving the quality of machine learning in health applications and clinical research	45
Large language models associate Muslims with violence	45
Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework	45
Radiological tumour classification across imaging modality and histology	44
Deep variational network for rapid 4D flow MRI reconstruction	44
External validation demonstrates limited clinical utility of the interpretable mortality prediction model for patients with COVID-19	43
A machine learning platform to estimate anti-SARS-CoV-2 activities	43
Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding	43
The challenges of deploying artificial intelligence models in a rapidly evolving pandemic	43
Deep recurrent optical flow learning for particle image velocimetry data	42
A biological perspective on evolutionary computation	42
Multiscale simulations of complex systems by learning their effective dynamics	42
Skills for physical artificial intelligence	40
An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data	39
Increasing generality in machine learning through procedural content generation	39
Experimental discovery of structure–property relationships in ferroelectric materials via active learning	39
Real-world embodied AI through a morphologically adaptive quadruped robot	39
Institutionalizing ethics in AI through broader impact requirements	38
A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data	38
Responsible artificial intelligence in agriculture requires systemic understanding of risks and externalities	38
Automatic strain sensor design via active learning and data augmentation for soft machines	38
Deep learning-inferred multiplex immunofluorescence for immunohistochemical image quantification	37
Combining automated microfluidic experimentation with machine learning for efficient polymerization design	37
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks	37
A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware	36
Improving healthcare operations management with machine learning	36
The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires	36
Enhancing optical-flow-based control by learning visual appearance cues for flying robots	36
A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories	36
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices	35
The neural resource allocation problem when enhancing human bodies with extra robotic limbs	34
Deep learning-based robust positioning for all-weather autonomous driving	34
Tracking the debate on COVID-19 surveillance tools	34
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks	32
Neurons learn by predicting future activity	32
Intelligent problem-solving as integrated hierarchical reinforcement learning	32
Empirical observation of negligible fairness–accuracy trade-offs in machine learning for public policy	31
Predicting myocardial infarction through retinal scans and minimal personal information	31
Bringing artificial intelligence to business management	31
Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports	31
A deep generative model enables automated structure elucidation of novel psychoactive substances	31
Accelerated rational PROTAC design via deep learning and molecular simulations	31
Interpretable bilinear attention network with domain adaptation improves drug–target prediction	31
Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling	31
Accelerating evidence-informed decision-making for the Sustainable Development Goals using machine learning	31
Minimal-uncertainty prediction of general drug-likeness based on Bayesian neural networks	31
Automating crystal-structure phase mapping by combining deep learning with constraint reasoning	30
Deep learning STEM-EDX tomography of nanocrystals	30

Autoregressive neural-network wavefunctions for ab initio quantum chemistry	30
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	30
Quantifying the spatial homogeneity of urban road networks via graph neural networks	30
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	30
Artificial intelligence in a crisis needs ethics with urgency	29
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition	29
Understanding adversarial examples requires a theory of artefacts for deep learning	29