Nature Machine Intelligence

Article	Citations
An interpretable mortality prediction model for COVID-19 patients	665
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators	620
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans	602
Shortcut learning in deep neural networks	577
Secure, privacy-preserving and federated machine learning in medical imaging	497
Drug discovery with explainable artificial intelligence	432
Deep learning for tomographic image reconstruction	246
Machine learning pipeline for battery state-of-health estimation	245
AI for radiographic COVID-19 detection selects shortcuts over signal	239
An open source machine learning framework for efficient and transparent systematic reviews	236
Molecular contrastive learning of representations via graph neural networks	199
Inverse design of nanoporous crystalline reticular materials with deep generative models	177
Finding key players in complex networks through deep reinforcement learning	176
Expanding functional protein sequence spaces using generative adversarial networks	172
Geometry-enhanced molecular representation learning for property prediction	165
End-to-end privacy preserving deep learning on multi-institutional medical imaging	164
The carbon impact of artificial intelligence	163
Ensemble deep learning in bioinformatics	163
Causal inference and counterfactual prediction in machine learning for actionable healthcare	155
Improved protein structure prediction by deep learning irrespective of co-evolution information	142
Concept whitening for interpretable image recognition	126
Development of metaverse for intelligent healthcare	126
Mapping the space of chemical reactions using attention-based neural networks	124
Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks	122
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation	119

Deep learning-based prediction of the T cell receptor–antigen binding specificity	112
The rise of robots in surgical environments during COVID-19	109
Advances, challenges and opportunities in creating data for trustworthy AI	108
Geometric deep learning on molecular representations	108
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC	104
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion	104
Bioinspired acousto-magnetic microswarm robots with upstream motility	102
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing	102
Neural circuit policies enabling auditable autonomy	101
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science	101
Code-free deep learning for multi-modality medical image classification	100
Dual use of artificial-intelligence-powered drug discovery	97
Estimation of continuous valence and arousal levels from faces in naturalistic conditions	97
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data	96
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network	96
High-accuracy prostate cancer pathology using deep learning	95
Towards a new generation of artificial intelligence in China	95
Machine learning and computation-enabled intelligent sensor design	95
Prediction of water stability of metal–organic frameworks using machine learning	94
Making deep neural networks right for the right scientific reasons by interacting with their explanations	93
A soft robot that adapts to environments through shape change	93
Origami-inspired miniature manipulator for teleoperated microsurgery	92
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms	91
Machine learning and algorithmic fairness in public and population health	89
Deep learning incorporating biologically inspired neural dynamics and in-memory computing	89
Automating turbulence modelling by multi-agent reinforcement learning	89
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors	88
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	88
The transformational role of GPU computing and deep learning in drug discovery	83
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis	83
Artificial intelligence cooperation to support the global response to COVID-19	81
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks	81
Three types of incremental learning	81
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning	80
Learning functional properties of proteins with language models	78
Controllable protein design with language models	78
A definition, benchmark and database of AI for social good initiatives	76
Using online verification to prevent autonomous vehicles from causing accidents	75
Stable learning establishes some common ground between causal inference and machine learning	75
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations	73
A soft thumb-sized vision-based sensor with accurate all-round force perception	73
Improving performance of deep learning models with axiomatic attribution priors and expected gradients	73
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images	72
Morphological and molecular breast cancer profiling through explainable machine learning	72
An embedded ethics approach for AI development	71
A geometric deep learning approach to predict binding conformations of bioactive molecules	71
Biological underpinnings for lifelong learning machines	69
AI-generated characters for supporting personalized learning and well-being	68
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	67
Predictive control of aerial swarms in cluttered environments	67

Large pre-trained language models contain human-like biases of what is right and wrong to do	64
Governing AI safety through independent audits	63
Teaching recurrent neural networks to infer global temporal structure from local examples	62
Encoding of tactile information in hand via skin-integrated wireless haptic interface	61
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design	60
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	59
A case-based interpretable deep learning model for classification of mass lesions in digital mammography	59
Deep neural networks identify sequence context features predictive of transcription factor binding	58
Extraction of protein dynamics information from cryo-EM maps using deep learning	57
Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support	57
Combinatorial optimization with physics-inspired graph neural networks	57
Large-scale chemical language representations capture molecular structure and properties	57
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes	56
Simultaneous deep generative modelling and clustering of single-cell genomic data	56
Fast and energy-efficient neuromorphic deep learning with first-spike times	56
Parameter-efficient fine-tuning of large-scale pre-trained language models	55
Predicting tumour mutational burden from histopathological images using multiscale deep learning	55
Molecular convolutional neural networks with DNA regulatory circuits	55
When causal inference meets deep learning	54
A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional computed tomography image datasets	54
Learning function from structure in neuromorphic networks	54
Interpretable deep-learning models to help achieve the Sustainable Development Goals	53
Benchmarking saliency methods for chest X-ray interpretation	52
Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework	52
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions	52
Chemical language models enable navigation in sparsely populated chemical space	50
Chemically programmable microrobots weaving a web from hormones	49
Self-supervised retinal thickness prediction enables deep learning from unlabelled data to boost classification of diabetic retinopathy	49
Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media	48
Machine Learning for COVID-19 needs global collaboration and data-sharing	47
Improving representations of genomic sequence motifs in convolutional networks with exponential activations	47
Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding	46
Improving the quality of machine learning in health applications and clinical research	46
Large language models associate Muslims with violence	45
Multiscale simulations of complex systems by learning their effective dynamics	45
Radiological tumour classification across imaging modality and histology	45
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
The challenges of deploying artificial intelligence models in a rapidly evolving pandemic	43
A biological perspective on evolutionary computation	43
Deep recurrent optical flow learning for particle image velocimetry data	43
A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware	41
Skills for physical artificial intelligence	41
Experimental discovery of structure–property relationships in ferroelectric materials via active learning	41
Real-world embodied AI through a morphologically adaptive quadruped robot	40
A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data	39
Increasing generality in machine learning through procedural content generation	39
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks	39
An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data	39
Automatic strain sensor design via active learning and data augmentation for soft machines	39
Improving healthcare operations management with machine learning	39
Responsible artificial intelligence in agriculture requires systemic understanding of risks and externalities	38
The neural resource allocation problem when enhancing human bodies with extra robotic limbs	38
Institutionalizing ethics in AI through broader impact requirements	38
Deep learning-inferred multiplex immunofluorescence for immunohistochemical image quantification	38
A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories	38
Predicting myocardial infarction through retinal scans and minimal personal information	37
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices	37
Enhancing optical-flow-based control by learning visual appearance cues for flying robots	37
The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires	37
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling	36
Deep learning-based robust positioning for all-weather autonomous driving	36
Bringing artificial intelligence to business management	35
Algorithms to estimate Shapley value feature attributions	35
Tracking the debate on COVID-19 surveillance tools	35
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	35
Intelligent problem-solving as integrated hierarchical reinforcement learning	35
Multimodal data fusion for cancer biomarker discovery with deep learning	34
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks	34
Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports	34
Interpretable bilinear attention network with domain adaptation improves drug–target prediction	34
Empirical observation of negligible fairness–accuracy trade-offs in machine learning for public policy	34
Automating crystal-structure phase mapping by combining deep learning with constraint reasoning	33
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	33
A deep generative model enables automated structure elucidation of novel psychoactive substances	32
Neurons learn by predicting future activity	32
Multi-objective goal-directed optimization of de novo stable organic radicals for aqueous redox flow batteries	32
Accelerated rational PROTAC design via deep learning and molecular simulations	32
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition	32
Minimal-uncertainty prediction of general drug-likeness based on Bayesian neural networks	32

Autoregressive neural-network wavefunctions for ab initio quantum chemistry	31
Quantifying the spatial homogeneity of urban road networks via graph neural networks	31
Deep learning STEM-EDX tomography of nanocrystals	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
Mixed-modality speech recognition and interaction using a wearable artificial throat	30
Direct-to-consumer medical machine learning and artificial intelligence applications	30
Large language models challenge the future of higher education	30
An automated framework for efficiently designing deep convolutional neural networks in genomics	30
Artificial intelligence in a crisis needs ethics with urgency	30
Cross-validation is safe to use	30
Visual speech recognition for multiple languages in the wild	30