OOIR: Observatory of International Research

Papers

(The TQCC of Nature Machine Intelligence is 26. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 500 papers]. The publications cover those that have been published in the past four years, i.e., from 2019-09-01 to 2023-09-01.)

Article	Citations
From local explanations to global understanding with explainable AI for trees	2125
The global landscape of AI ethics guidelines	1215
An interpretable mortality prediction model for COVID-19 patients	617
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans	498
Shortcut learning in deep neural networks	384
Secure, privacy-preserving and federated machine learning in medical imaging	371
Principles alone cannot guarantee ethical AI	366
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators	359
Drug discovery with explainable artificial intelligence	302
Predicting the state of charge and health of batteries using data-driven machine learning	259
Deep learning for tomographic image reconstruction	168
Machine learning pipeline for battery state-of-health estimation	166
AI for radiographic COVID-19 detection selects shortcuts over signal	161
In situ training of feed-forward and recurrent convolutional memristor networks	156
An open source machine learning framework for efficient and transparent systematic reviews	137
Machine learning for active matter	135
Inverse design of nanoporous crystalline reticular materials with deep generative models	129
Deep learning optoacoustic tomography with sparse data	126
Finding key players in complex networks through deep reinforcement learning	123
Causal inference and counterfactual prediction in machine learning for actionable healthcare	119
Improved protein structure prediction by deep learning irrespective of co-evolution information	119
Predicting drug–protein interaction using quasi-visual question answering system	115
Ensemble deep learning in bioinformatics	115
End-to-end privacy preserving deep learning on multi-institutional medical imaging	112
Expanding functional protein sequence spaces using generative adversarial networks	111

Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks	100
The rise of robots in surgical environments during COVID-19	96
Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks	96
The carbon impact of artificial intelligence	94
Rapid online learning and robust recall in a neuromorphic olfactory circuit	94
Fully portable and wireless universal brain–machine interfaces enabled by flexible scalp electronics and deep learning algorithm	92
Shared human–robot proportional control of a dexterous myoelectric prosthesis	88
Molecular contrastive learning of representations via graph neural networks	88
Clinically applicable deep learning framework for organs at risk delineation in CT images	86
Generative molecular design in low data regimes	85
Concept whitening for interpretable image recognition	84
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation	84
Mapping the space of chemical reactions using attention-based neural networks	83
Geometry-enhanced molecular representation learning for property prediction	82
Prediction of drug combination effects with a minimal set of experiments	81
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC	78
A topology-based network tree for the prediction of protein–protein binding affinity changes following mutation	78
Exploring the limit of using a deep neural network on pileup data for germline variant calling	75
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing	74
Artificial intelligence cooperation to support the global response to COVID-19	73
A soft robot that adapts to environments through shape change	71
High-accuracy prostate cancer pathology using deep learning	70
Machine learning and computation-enabled intelligent sensor design	70
Neural circuit policies enabling auditable autonomy	68
Human action recognition with a large-scale brain-inspired photonic computer	68
Making deep neural networks right for the right scientific reasons by interacting with their explanations	67
Deep learning incorporating biologically inspired neural dynamics and in-memory computing	67
Prediction of water stability of metal–organic frameworks using machine learning	66
Code-free deep learning for multi-modality medical image classification	66
Deep learning robotic guidance for autonomous vascular access	66
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network	66
Origami-inspired miniature manipulator for teleoperated microsurgery	65
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis	65
Behavioural evidence for a transparency–efficiency tradeoff in human–machine cooperation	65
Towards a new generation of artificial intelligence in China	65
Automating turbulence modelling by multi-agent reinforcement learning	64
Bioinspired acousto-magnetic microswarm robots with upstream motility	63
Deep-learning-based prediction of late age-related macular degeneration progression	63
Deep learning-based prediction of the T cell receptor–antigen binding specificity	62
Trusting artificial intelligence in cybersecurity is a double-edged sword	62
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms	62
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors	61
Homeostasis and soft robotics in the design of feeling machines	60
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science	60
Towards ethical and socio-legal governance in AI	59
Geometric deep learning on molecular representations	58
Estimation of continuous valence and arousal levels from faces in naturalistic conditions	58
Machine learning and algorithmic fairness in public and population health	55
An embedded ethics approach for AI development	55
Morphological and molecular breast cancer profiling through explainable machine learning	55

Benchmarks for progress in neuromorphic computing	55
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion	54
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images	54
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	53
Dual use of artificial-intelligence-powered drug discovery	51
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations	51
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks	50
Using online verification to prevent autonomous vehicles from causing accidents	49
Extraction of protein dynamics information from cryo-EM maps using deep learning	48
A neural network trained for prediction mimics diverse features of biological neurons and perception	46
A definition, benchmark and database of AI for social good initiatives	45
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning	45
Simultaneous deep generative modelling and clustering of single-cell genomic data	44
A portable three-degrees-of-freedom force feedback origami robot for human–robot interactions	44
Governing AI safety through independent audits	43
Teaching recurrent neural networks to infer global temporal structure from local examples	42
Development of metaverse for intelligent healthcare	42
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions	42
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes	42
Deep neural networks identify sequence context features predictive of transcription factor binding	42
A soft thumb-sized vision-based sensor with accurate all-round force perception	41
Machine Learning for COVID-19 needs global collaboration and data-sharing	41
Learning functional properties of proteins with language models	41
Stable learning establishes some common ground between causal inference and machine learning	41
Improving performance of deep learning models with axiomatic attribution priors and expected gradients	41
Automated abnormality detection in lower extremity radiographs using deep learning	40
A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional computed tomography image datasets	40
Improving the quality of machine learning in health applications and clinical research	40
Predicting disease-associated mutation of metal-binding sites in proteins using a deep learning approach	40
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design	40
Predicting tumour mutational burden from histopathological images using multiscale deep learning	40
A geometric deep learning approach to predict binding conformations of bioactive molecules	39
Predictive control of aerial swarms in cluttered environments	39
Validity of machine learning in biology and medicine increased through collaborations across fields of expertise	39
Deep variational network for rapid 4D flow MRI reconstruction	38
Chemically programmable microrobots weaving a web from hormones	38
The challenges of deploying artificial intelligence models in a rapidly evolving pandemic	38
When causal inference meets deep learning	38
Advances, challenges and opportunities in creating data for trustworthy AI	38
External validation demonstrates limited clinical utility of the interpretable mortality prediction model for patients with COVID-19	38
Deep learning of circulating tumour cells	37
Controllable protein design with language models	37
Fast and energy-efficient neuromorphic deep learning with first-spike times	36
Self-supervised retinal thickness prediction enables deep learning from unlabelled data to boost classification of diabetic retinopathy	36
Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media	35
A machine learning platform to estimate anti-SARS-CoV-2 activities	35
Improving representations of genomic sequence motifs in convolutional networks with exponential activations	35
A case-based interpretable deep learning model for classification of mass lesions in digital mammography	34
Tracking the debate on COVID-19 surveillance tools	34
Combining automated microfluidic experimentation with machine learning for efficient polymerization design	34
The transformational role of GPU computing and deep learning in drug discovery	34
Learning function from structure in neuromorphic networks	33
Deep convolutional neural networks in the face of caricature	33
Radiological tumour classification across imaging modality and histology	32
Chemical language models enable navigation in sparsely populated chemical space	32
An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data	32
Skills for physical artificial intelligence	31
A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data	31
Interpretable deep-learning models to help achieve the Sustainable Development Goals	31
Real-world embodied AI through a morphologically adaptive quadruped robot	30
Enhancing optical-flow-based control by learning visual appearance cues for flying robots	30
A biological perspective on evolutionary computation	30
Increasing generality in machine learning through procedural content generation	30
Biological underpinnings for lifelong learning machines	30
Accurate data-driven prediction does not mean high reproducibility	29
Deep recurrent optical flow learning for particle image velocimetry data	29
Combinatorial optimization with physics-inspired graph neural networks	29
Molecular convolutional neural networks with DNA regulatory circuits	29
A fast neural network approach for direct covariant forces prediction in complex multi-element extended systems	29
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	28
A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories	28
Large language models associate Muslims with violence	28
Multiscale simulations of complex systems by learning their effective dynamics	28
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks	28
AmoebaContact and GDFold as a pipeline for rapid de novo protein structure prediction	28
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data	27
AI-generated characters for supporting personalized learning and well-being	26
Institutionalizing ethics in AI through broader impact requirements	26
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	26
Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding	26