AI for Science

We would like to maintain a list of progress (papers, codes etc) made in applying AI to science. Please feel free to open an issue to add papers.

Table of Contents

• AI + Chess
  • Alphago
• AI + Biology
  • Protein Structure
  • Gene Prediction
  • Others
• AI + Electronics
  • Chip Design
  • Antenna Design
  • Electromagnetic Design
• AI + Medical
  • Brain–Computer Interface
  • Diagnosis
  • Vaccine
  • Medicine
• AI + Mathematics
  • Mathematical Theorem Discovery
  • Mathematical Problem Solving
• AI + Physics
  • Tokamak
  • All Optical Network
  • Celestial Observation
  • Others
• Others
  • Weather Forecasting
  • 3D Scene Reconstruction
  • Ancient Texts Discovering
  • Material Science

Paper List

AI + Chess

Alphago [Back to TOC]

• Mastering the game of Go without Human Knowledge Nature 2017 [Paper]
• Mastering the game of Go with Deep Neural Networks & Tree Search Nature 2016 [Paper]
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play Science 2018 [Paper]

AI for Chess

AI + Biology

Protein Structure [Back to TOC]

• Structural and functional properties of SARS-CoV-2 spike protein: potential antivirus drug development for COVID-19 Nature 2020 [Paper]
• Self-Supervised Graph Transformer on Large-Scale Molecular Data NeurIPS 2020 [Paper]
• Retrosynthesis Prediction with Conditional Graph Logic Network NeurIPS 2019 [Paper]
• Retroxpert: Decompose retrosynthesis prediction like a chemist NeurIPS 2020 [Paper]
• Highly accurate protein structure prediction with AlphaFold Nature 2021 [Paper]
• Improved protein structure prediction using potentials from deep learning Nature 2020 [Paper]

AI for Protein Structure

Gene Prediction [Back to TOC]

• Effective gene expression prediction from sequence by integrating long-range interactions Nature Methods 2021 [Paper]

AI for Gene Prediction

Others [Back to TOC]

• Cell cycle gene regulation dynamics revealed by RNA velocity and deep-learning Nature Communications 2022 [Paper]

AI + Electronics

Chip Design [Back to TOC]

• Networks on chip: a new paradigm for systems on chip design IEEE Xplore 2002 [Paper]
• A graph placement methodology for fast chip design Nature 2021 [Paper]

Antenna Design [Back to TOC]

• A metamaterial-enabled design enhancing decades-old short backfire antenna technology for space applications Nature Communications 2019 [Paper]

AI for Antenna Design

Electromagnetic Design [Back to TOC]

• Topology and geometry under the nonlinear electromagnetic spotlight Nature Materials 2021 [Paper]

AI for Electromagnetic Design

AI + Medical

Brain–Computer Interface [Back to TOC]

• A high-performance brain–computer interface Nature 2006 [Paper]
• Virtual typing by people with tetraplegia using a self-calibrating intracortical brain-computer interface Science 2015 [Paper]
• Rapid adaptation of brain–computer interfaces to new neuronal ensembles or participants via generative modelling Nature Biomedical Engineering 2021 [Paper]

Diagnosis [Back to TOC]

• AI-based pathology predicts origins for cancers of unknown primary Nature 2021 [Paper]
• Video-based AI for beat-to-beat assessment of cardiac function Nature 2020 [Paper]
• CancerVar: An artificial intelligence–empowered platform for clinical interpretation of somatic mutations in cancer Science 2022 [Paper]

Vaccine [Back to TOC]

• Predicting the mutational drivers of future SARS-CoV-2 variants of concern Science 2022 [Paper]

Medicine [Back to TOC]

• International evaluation of an AI system for breast cancer screening Nature 2020 [Paper]
• A clinically applicable approach to continuous prediction of future acute kidney injury Nature 2019 [Paper]
• Predicting conversion to wet age-related macular degeneration using deep learning Nature Medicine 2020 [Paper]
• Evaluation of a digitally-enabled care pathway for acute kidney injury management in hospital emergency admissions Nature Medicine 2019 [Paper]
• Prefrontal cortex as a meta-reinforcement learning system Nature Neuroscience 2018 [Paper]

AI + Mathematics

Mathematical Theorem Discovery [Back to TOC]

• Advancing mathematics by guiding human intuition with AI Nature 2021 [Paper]

Mathematical Problem Solving [Back to TOC]

• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations Communications in Mathematics and Statistics 2017 [Paper]
• The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems Communications in Mathematics and Statistics 2018 [Paper]
• Solving high-dimensional partial differential equations using deep learning PNAS 2018 [Paper]

AI + Physics

Tokamak [Back to TOC]

• Magnetic Control of Tokamak Plasmas Through Deep Reinforcement Learning Nature 2022 [Paper]

AI for Tokamak

All Optical Network [Back to TOC]

• All-optical machine learning using diffractive deep neural networks Science 2018[Paper]
• Parallel convolutional processing using an integrated photonic tensor core Nature 2021 [Paper]
• 11 TOPS photonic convolutional accelerator for optical neural networks Nature 2021 [Paper]
• Photonics for artificial intelligence and neuromorphic computing Nature Photonics 2021 [Paper]
• Ultrafast machine vision with 2D material neural network image sensors Nature 2020 [Paper]
• Physics for neuromorphic computing Nature Reviews Physics 2020 [Paper]
• Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit Nature Photonics 2021 [Paper]
• Deep physical neural networks trained with backpropagation Nature 2022 [Paper]
• Wave physics as an analog recurrent neural network SCIENCE ADVANCES 2019[Paper]

AI for All Optical Network

Celestial Observation [Back to TOC]

• High-accuracy mass, spin, and recoil predictions of generic black-hole merger remnants Phys. Rev. Lett. 2019 [Paper]
• Accelerated, scalable and reproducible AI-driven gravitational wave detection Nature Astronomy 2021 [Paper]

Others [Back to TOC]

• Deep learning for the design of photonic structures Nature Photonics 2021 [Paper]
• Equivariant Flow-Based Sampling for Lattice Gauge Theory Phys. Rev. Lett. 2020 [Paper]
• Deep learning model to predict complex stress and strain fields in hierarchical composites SCIENCE ADVANCES 2021 [Paper]
• Closed-loop optimization of fast-charging protocols for batteries with machine learning Nature 2020 [Paper]
• Predicting disruptive instabilities in controlled fusion plasmas through deep learning Nature 2019 [Paper]
• Physics-informed machine learning Nature Reviews Physics 2021 [Paper]

Others

Weather Forecasting [Back to TOC]

• Skillful Precipitation Nowcasting using Deep Generative Models of Radar Nature 2021 [Paper]

3D Scene Reconstruction [Back to TOC]

• Neural scene representation and rendering Science 2018 [Paper]

Ancient Texts Discovering [Back to TOC]

• Restoring and attributing ancient texts using deep neural networks Nature 2022 [Paper]

Material Science [Back to TOC]

• Machine-learning-assisted materials discovery using failed experiments Nature 2016 [Paper]
• Planning chemical syntheses with deep neural networks and symbolic AI Nature 2018 [Paper]