Survey
- Book Chapter [2209.05582] Graph Neural Networks for Molecules
- [2202.09212] Molecule Generation for Drug Design: a Graph Learning Perspective
- Nature: Machine learning for molecular and materials science
- Deep learning for molecular design—a review of the state of the art [Journal Version]
- From DFT to machine learning: recent approaches to materials science–a review
- A Critical Review of Machine Learning of Energy Materials
- Deep Learning in Chemistry
Generative Model
- ICML 21 https://icml.cc/virtual/2021/poster/8499
- ICML 21 An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
- ICML 21 Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
- ICML 21 Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
- ICML 21 Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model
- ICML 21 GraphDF: A Discrete Flow Model for Molecular Graph Generation
- ICML 21 https://icml.cc/virtual/2021/poster/8519
- JMLR: NEVAE: A Deep Generative Model for Molecular Graphs
- MolGAN: An implicit generative model for small molecular graphs
- Learning Discrete Structures for Graph Neural Networks
- Deep learning for molecular generation
- Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
- Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery
- Science: Inverse molecular design using machine learning: Generative models for matter engineering
- Generative Models for Automatic Chemical Design
- Autonomous Molecular Design: Then and Now
- SELFIES: a robust representation of semantically constrained graphs with an example application in chemistry
- Inverse Design of Solid-State Materials via a Continuous Representation
- The rise of deep learning in drug discovery
- Constrained Graph Variational Autoencoders for Molecule Design
- Conditional Molecular Design with Deep Generative Models
- ICLR 18: NerveNet: Learning Structured Policy with Graph Neural Networks
- Graph convolutional policy network for goal-directed molecular graph generation
- Molecular sets (MOSES): a benchmarking platform for molecular generation models
- GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
Molecular Graph
- Neural Message Passing for Quantum Chemistry
- NIPS 20: RetroXpert: Decompose Retrosynthesis Prediction like A Chemist
- Accelerating the discovery of materials for clean energy in the era of smart automation
- Junction tree variational autoencoder for molecular graph generation
- Schnet: A continuous-filter convolutional neural network for modeling quantum interactions
- Machine learning in computer-aided synthesis planning
- Computer-assisted retrosynthesis based on molecular similarity
- Graph networks as a universal machine learning framework for molecules and crystals
- Entangled conditional adversarial autoencoder for de novo drug discovery
- ICML 20 Directional Message Passing for Molecular Graphs
- Nature: Machine-learning-assisted materials discovery using failed experiments
- Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
- Accelerated Materials Design of Lithium Superionic Conductors Based on First‐Principles Calculations and Machine Learning Algorithms
- Scientists use machine learning to identify high-performing solar materials
- Interpretable Deep Learning in Drug Discovery
- IJCAI 18: Interpretable Drug Target Prediction Using Deep Neural Representation**
- Convolutional networks on graphs for learning molecular fingerprints.**
NIPS 2015. paper Cited by 1415
David Duvenaud, Dougal Maclaurin, Jorge Aguilera-Iparraguirre, Rafael Gómez-Bombarelli, Timothy Hirzel, Alán Aspuru-Guzik, Ryan P. Adams. - Junction tree variational autoencoder for molecular graph generation** .
ICML 2018. paper, Cited by 252
Jin, Wengong, Regina Barzilay, and Tommi Jaakkola. - Neural message passing for quantum chemistry** .
ICML 17, paper Cited by 1320
Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE. - The rise of deep learning in drug discovery** .
Drug discovery today 2018 . paper Cited by 409
Chen, Hongming, et al - Molecular Graph Convolutions: Moving Beyond Fingerprints.**
Journal of computer-aided molecular design 2016. paper Cited by 569
Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, Patrick Riley. - Retrosynthesis Prediction with Conditional Graph Logic Network.**
NeurIPS 2019. paper
Hanjun Dai, Chengtao Li, Connor Coley, Bo Dai, Le Song. - Protein Interface Prediction using Graph Convolutional Networks.**
NIPS 2017. paper Cited by 171
Alex Fout, Jonathon Byrd, Basir Shariat, Asa Ben-Hur. - Graph Transformation Policy Network for Chemical Reaction Prediction.**
KDD 2019. paper
Kien Do, Truyen Tran, Svetha Venkatesh. - Functional Transparency for Structured Data: a Game-Theoretic Approach.**
ICML 2019. paper
Guang-He Lee, Wengong Jin, David Alvarez-Melis, Tommi S. Jaakkola. - Learning Multimodal Graph-to-Graph Translation for Molecular Optimization.** ICLR 2019. paper
Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola. - A Generative Model For Electron Paths.**
ICLR 2019. paper
John Bradshaw, Matt J. Kusner, Brooks Paige, Marwin H. S. Segler, José Miguel Hernández-Lobato.