└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Generative models for molecules [Out of date, too many papers] 2 | 3 | Models capable of generating novel molecular structures recently got a lot of attention. 4 | This is an attempt to track the relevant publications regarding the topic. Please let me know if I forgot something. 5 | 6 | ## Reviews 7 | To get an overview you can have a look at the following review articles: 8 | [Deep learning for molecular generation and optimization - a review of the state of the art (2019)](http://arxiv.org/abs/1903.04388) 9 | [Inverse molecular design using machine learning: Generative models for matter engineering (2018)](https://science.sciencemag.org/content/361/6400/360) 10 | 11 | ## Evaluation: 12 | [Fréchet ChemNet Distance: A metric for generative models for molecules in drug discovery (2018)](https://doi.org/10.1021/acs.jcim.8b00234) 13 | [GuacaMol: Benchmarking Models for De Novo Molecular Design (2018)](http://arxiv.org/abs/1811.09621) 14 | [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models (2018)](http://arxiv.org/abs/1811.12823) 15 | 16 | ## Methods: 17 | [Conditional Molecular Design with Deep Generative Models (2019)](https://doi.org/10.1021/acs.jcim.8b00263) 18 | [Mol-CycleGAN - a generative model for molecular optimization (2019)](http://arxiv.org/abs/1902.02119) 19 | [Exploring the GDB-13 chemical space using deep generative models (2019)](https://doi.org/10.1186/s13321-019-0341-z) 20 | [Accelerating Prototype-Based Drug Discovery using Conditional Diversity Networks (2018)](http://arxiv.org/abs/1804.02668) 21 | [Molecular generative model based on conditional variational autoencoder for de novo molecular design (2018)](https://doi.org/10.1186/s13321-018-0286-7) 22 | [Deep reinforcement learning for de novo drug design (2018)](http://advances.sciencemag.org/content/4/7/eaap7885) 23 | [Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search (2018)](http://papers.nips.cc/paper/7335-combinatorial-optimization-with-graph-convolutional-networks-and-guided-tree-search.pdf) 24 | [Learning Multimodal Graph-to-Graph Translation for Molecule Optimization (2018)](https://openreview.net/forum?id=B1xJAsA5F7) 25 | [Constrained Graph Variational Autoencoders for Molecule Design (2018)](http://papers.nips.cc/paper/8005-constrained-graph-variational-autoencoders-for-molecule-design.pdf) 26 | [Generative Recurrent Networks for De Novo Drug Design (2018)](nan) 27 | [Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design (2018)](https://openreview.net/forum?id=HkcTe-bR-) 28 | [Hunting for Organic Molecules with Artificial Intelligence: Molecules Optimized for Desired Excitation Energies (2018)](nan) 29 | [De Novo Design of Bioactive Small Molecules by Artificial Intelligence (2018)](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5838524/) 30 | [Molecular Hypergraph Grammar with its Application to Molecular Optimization (2018)](http://arxiv.org/abs/1809.02745) 31 | [h-detach: Modifying the LSTM Gradient Towards Better Optimization (2018)](https://openreview.net/forum?id=HJMXTsCqYQ¬eId=HJMXTsCqYQ) 32 | [NeVAE: A Deep Generative Model for Molecular Graphs (2018)](http://arxiv.org/abs/1802.05283) 33 | [Reinforced Adversarial Neural Computer for de Novo Molecular Design (2018)](https://doi.org/10.1021/acs.jcim.7b00690) 34 | [De Novo Generation of Hit-like Molecules from Gene Expression Signatures Using Artificial Intelligence (2018)](https://chemrxiv.org/articles/De_Novo_Generation_of_Hit-like_Molecules_from_Gene_Expression_Signatures_Using_Artificial_Intelligence/7294388) 35 | [Entangled Conditional Adversarial Autoencoder for de Novo Drug Discovery (2018)](nan) 36 | [Improving Chemical Autoencoder Latent Space and Molecular De Novo Generation Diversity with Heteroencoders (2018)](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6316879/) 37 | [Learning Deep Generative Models of Graphs (2018)](http://arxiv.org/abs/1803.03324) 38 | [Optimization of Molecules via Deep Reinforcement Learning (2018)](http://arxiv.org/abs/1810.08678) 39 | [Junction Tree Variational Autoencoder for Molecular Graph Generation (2018)](http://arxiv.org/abs/1802.04364) 40 | [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models (2018)](http://arxiv.org/abs/1802.08773) 41 | [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (2018)](http://papers.nips.cc/paper/7877-graph-convolutional-policy-network-for-goal-directed-molecular-graph-generation.pdf) 42 | [MolGAN: An implicit generative model for small molecular graphs (2018)](http://arxiv.org/abs/1805.11973) 43 | [Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules (2018)](https://doi.org/10.1021/acscentsci.7b00572) 44 | [DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation (2018)](https://openreview.net/forum?id=Bygre3R9Fm¬eId=rkeqNivN5m) 45 | [Adversarial Threshold Neural Computer for Molecular de Novo Design (2018)](https://doi.org/10.1021/acs.molpharmaceut.7b01137) 46 | [Syntax-Directed Variational Autoencoder for Structured Data (2018)](http://arxiv.org/abs/1802.08786) 47 | [Learning Continuous and Data-Driven Molecular Descriptors by Translating Equivalent Chemical Representations (2018)](https://chemrxiv.org/articles/Learning_Continuous_and_Data-Driven_Molecular_Descriptors_by_Translating_Equivalent_Chemical_Representations/6871628) 48 | [Multi-Objective De Novo Drug Design with Conditional Graph Generative Model (2018)](http://arxiv.org/abs/1801.07299) 49 | [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders (2018)](http://arxiv.org/abs/1802.03480) 50 | [Deep Generative Models for Molecular Science (2018)](https://onlinelibrary.wiley.com/doi/abs/10.1002/minf.201700133) 51 | [Designing Random Graph Models Using Variational Autoencoders With Applications to Chemical Design (2018)](http://arxiv.org/abs/1802.05283) 52 | [Prototype-Based Compound Discovery Using Deep Generative Models (2018)](http://pubs.acs.org/doi/10.1021/acs.molpharmaceut.8b00474) 53 | [Mol-CycleGAN - a generative model for molecular optimization (2018)](https://openreview.net/forum?id=BklKFo09YX) 54 | [Population-based de novo molecule generation, using grammatical evolution (2018)](http://arxiv.org/abs/1804.02134) 55 | [Application of generative autoencoder in de novo molecular design (2017)](http://arxiv.org/abs/1711.07839) 56 | [Constrained Bayesian Optimization for Automatic Chemical Design (2017)](http://arxiv.org/abs/1709.05501) 57 | [Grammar Variational Autoencoder (2017)](http://arxiv.org/abs/1703.01925) 58 | [Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models (2017)](http://arxiv.org/abs/1705.10843) 59 | [In silico generation of novel, drug-like chemical matter using the LSTM neural network (2017)](http://arxiv.org/abs/1712.07449) 60 | [druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico (2017)](https://doi.org/10.1021/acs.molpharmaceut.7b00346) 61 | [Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks (2017)](http://arxiv.org/abs/1701.01329) 62 | [De novo drug design with deep generative models : an empirical study (2017)](https://openreview.net/forum?id=SkkC41HYl) 63 | [Molecular de-novo design through deep reinforcement learning (2017)](https://doi.org/10.1186/s13321-017-0235-x) 64 | [ChemTS: an efficient python library for de novo molecular generation (2017)](https://doi.org/10.1080/14686996.2017.1401424) 65 | [Molecular Generation with Recurrent Neural Networks (RNNs) (2017)](http://arxiv.org/abs/1705.04612) 66 | [Bayesian molecular design with a chemical language model (2017)](https://doi.org/10.1007/s10822-016-0008-z) 67 | [Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC) (2017)](https://chemrxiv.org/articles/ORGANIC_1_pdf/5309668) 68 | [Learning a Generative Model for Validity in Complex Discrete Structures (2017)](http://arxiv.org/abs/1712.01664) 69 | [ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity? (2017)](http://arxiv.org/abs/1708.08227) 70 | [Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control (2016)](http://arxiv.org/abs/1611.02796) 71 | [The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology (2016)](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5355231/) 72 | [Molpher: a software framework for systematic chemical space exploration (2014)](https://doi.org/10.1186/1758-2946-6-7) 73 | [Generative Models for Chemical Structures (2010)](https://doi.org/10.1021/ci9004089) 74 | --------------------------------------------------------------------------------