Nature Machine Intelligence

Papers
(The TQCC of Nature Machine Intelligence is 27. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-02-01 to 2024-02-01.)
ArticleCitations
An interpretable mortality prediction model for COVID-19 patients644
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans570
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators523
Shortcut learning in deep neural networks520
Secure, privacy-preserving and federated machine learning in medical imaging450
Drug discovery with explainable artificial intelligence383
Predicting the state of charge and health of batteries using data-driven machine learning311
Deep learning for tomographic image reconstruction219
AI for radiographic COVID-19 detection selects shortcuts over signal215
Machine learning pipeline for battery state-of-health estimation211
An open source machine learning framework for efficient and transparent systematic reviews199
Molecular contrastive learning of representations via graph neural networks162
Inverse design of nanoporous crystalline reticular materials with deep generative models160
Finding key players in complex networks through deep reinforcement learning158
Machine learning for active matter158
Expanding functional protein sequence spaces using generative adversarial networks154
End-to-end privacy preserving deep learning on multi-institutional medical imaging147
Ensemble deep learning in bioinformatics145
Predicting drug–protein interaction using quasi-visual question answering system140
Geometry-enhanced molecular representation learning for property prediction139
Causal inference and counterfactual prediction in machine learning for actionable healthcare138
The carbon impact of artificial intelligence134
Improved protein structure prediction by deep learning irrespective of co-evolution information130
Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks118
Concept whitening for interpretable image recognition117
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation107
Mapping the space of chemical reactions using attention-based neural networks105
The rise of robots in surgical environments during COVID-19104
Rapid online learning and robust recall in a neuromorphic olfactory circuit104
Generative molecular design in low data regimes104
A topology-based network tree for the prediction of protein–protein binding affinity changes following mutation96
Deep learning-based prediction of the T cell receptor–antigen binding specificity96
Development of metaverse for intelligent healthcare93
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC92
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing92
Bioinspired acousto-magnetic microswarm robots with upstream motility92
Geometric deep learning on molecular representations90
Neural circuit policies enabling auditable autonomy89
A soft robot that adapts to environments through shape change89
Making deep neural networks right for the right scientific reasons by interacting with their explanations88
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science85
Exploring the limit of using a deep neural network on pileup data for germline variant calling85
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network85
Estimation of continuous valence and arousal levels from faces in naturalistic conditions85
Prediction of water stability of metal–organic frameworks using machine learning84
High-accuracy prostate cancer pathology using deep learning84
Code-free deep learning for multi-modality medical image classification84
Origami-inspired miniature manipulator for teleoperated microsurgery82
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion82
Towards a new generation of artificial intelligence in China82
Deep learning incorporating biologically inspired neural dynamics and in-memory computing82
Machine learning and computation-enabled intelligent sensor design82
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms81
Deep learning robotic guidance for autonomous vascular access79
Advances, challenges and opportunities in creating data for trustworthy AI79
Automating turbulence modelling by multi-agent reinforcement learning77
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis77
Artificial intelligence cooperation to support the global response to COVID-1976
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors75
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks73
Dual use of artificial-intelligence-powered drug discovery72
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning71
Deep-learning-based prediction of late age-related macular degeneration progression69
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data69
Morphological and molecular breast cancer profiling through explainable machine learning68
Machine learning and algorithmic fairness in public and population health68
A soft thumb-sized vision-based sensor with accurate all-round force perception66
A definition, benchmark and database of AI for social good initiatives65
An embedded ethics approach for AI development64
Controllable protein design with language models64
The transformational role of GPU computing and deep learning in drug discovery64
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning64
Learning functional properties of proteins with language models63
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images63
Stable learning establishes some common ground between causal inference and machine learning61
Using online verification to prevent autonomous vehicles from causing accidents60
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations60
Predictive control of aerial swarms in cluttered environments60
Improving performance of deep learning models with axiomatic attribution priors and expected gradients60
A geometric deep learning approach to predict binding conformations of bioactive molecules59
A neural network trained for prediction mimics diverse features of biological neurons and perception58
Three types of incremental learning58
Extraction of protein dynamics information from cryo-EM maps using deep learning56
Governing AI safety through independent audits55
Biological underpinnings for lifelong learning machines54
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning53
Teaching recurrent neural networks to infer global temporal structure from local examples53
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design52
A case-based interpretable deep learning model for classification of mass lesions in digital mammography52
Large pre-trained language models contain human-like biases of what is right and wrong to do52
Deep neural networks identify sequence context features predictive of transcription factor binding51
AI-generated characters for supporting personalized learning and well-being51
Learning function from structure in neuromorphic networks51
A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional computed tomography image datasets50
Predicting tumour mutational burden from histopathological images using multiscale deep learning49
Simultaneous deep generative modelling and clustering of single-cell genomic data49
Combinatorial optimization with physics-inspired graph neural networks48
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes48
Fast and energy-efficient neuromorphic deep learning with first-spike times48
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin46
Interpretable deep-learning models to help achieve the Sustainable Development Goals46
Chemically programmable microrobots weaving a web from hormones45
Molecular convolutional neural networks with DNA regulatory circuits45
When causal inference meets deep learning45
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions45
Machine Learning for COVID-19 needs global collaboration and data-sharing44
Improving the quality of machine learning in health applications and clinical research44
Deep learning of circulating tumour cells44
Self-supervised retinal thickness prediction enables deep learning from unlabelled data to boost classification of diabetic retinopathy44
Improving representations of genomic sequence motifs in convolutional networks with exponential activations44
Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media44
Deep variational network for rapid 4D flow MRI reconstruction43
Chemical language models enable navigation in sparsely populated chemical space43
Encoding of tactile information in hand via skin-integrated wireless haptic interface43
A machine learning platform to estimate anti-SARS-CoV-2 activities42
Large-scale chemical language representations capture molecular structure and properties41
The challenges of deploying artificial intelligence models in a rapidly evolving pandemic41
Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support41
External validation demonstrates limited clinical utility of the interpretable mortality prediction model for patients with COVID-1941
Benchmarking saliency methods for chest X-ray interpretation40
Large language models associate Muslims with violence40
A biological perspective on evolutionary computation39
Deep recurrent optical flow learning for particle image velocimetry data39
Radiological tumour classification across imaging modality and histology38
Combining automated microfluidic experimentation with machine learning for efficient polymerization design37
An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data37
Skills for physical artificial intelligence37
Real-world embodied AI through a morphologically adaptive quadruped robot37
Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding37
Enhancing optical-flow-based control by learning visual appearance cues for flying robots36
Responsible artificial intelligence in agriculture requires systemic understanding of risks and externalities35
Multiscale simulations of complex systems by learning their effective dynamics35
A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data35
The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires34
Tracking the debate on COVID-19 surveillance tools34
Institutionalizing ethics in AI through broader impact requirements34
Increasing generality in machine learning through procedural content generation34
A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories33
Experimental discovery of structure–property relationships in ferroelectric materials via active learning33
Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework33
Neurons learn by predicting future activity32
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks32
Deep learning-inferred multiplex immunofluorescence for immunohistochemical image quantification32
The neural resource allocation problem when enhancing human bodies with extra robotic limbs31
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices31
Improving healthcare operations management with machine learning31
Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling30
Deep learning STEM-EDX tomography of nanocrystals30
Parameter-efficient fine-tuning of large-scale pre-trained language models30
Accelerating evidence-informed decision-making for the Sustainable Development Goals using machine learning30
A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware30
Minimal-uncertainty prediction of general drug-likeness based on Bayesian neural networks30
Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports29
Automatic strain sensor design via active learning and data augmentation for soft machines29
Understanding adversarial examples requires a theory of artefacts for deep learning28
Predicting myocardial infarction through retinal scans and minimal personal information28
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments28
Direct-to-consumer medical machine learning and artificial intelligence applications27
Artificial intelligence in a crisis needs ethics with urgency27
Accelerated rational PROTAC design via deep learning and molecular simulations27
Bringing artificial intelligence to business management27
Intelligent problem-solving as integrated hierarchical reinforcement learning27
Automating crystal-structure phase mapping by combining deep learning with constraint reasoning27
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition27
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence27
0.057691812515259