https://github.com/AspirinCode/papers-for-molecular-design-using-DL
List of molecular design using Generative AI and Deep Learning
https://github.com/AspirinCode/papers-for-molecular-design-using-DL
deep-generative-models diffusion drug-design energy-based-model gan generative-ai gnns lstm molecular-design prompt-learning reinforcement-learning rnn score-based-generative-models transformer vae
Last synced: about 1 year ago
JSON representation
List of molecular design using Generative AI and Deep Learning
- Host: GitHub
- URL: https://github.com/AspirinCode/papers-for-molecular-design-using-DL
- Owner: AspirinCode
- License: gpl-3.0
- Created: 2023-02-28T07:08:10.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2024-04-13T06:46:42.000Z (about 2 years ago)
- Last Synced: 2024-04-13T20:56:34.012Z (about 2 years ago)
- Topics: deep-generative-models, diffusion, drug-design, energy-based-model, gan, generative-ai, gnns, lstm, molecular-design, prompt-learning, reinforcement-learning, rnn, score-based-generative-models, transformer, vae
- Homepage:
- Size: 3.95 MB
- Stars: 502
- Watchers: 22
- Forks: 74
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-generative-ai - Molecular design - List of molecular design using Generative AI and Deep Learning. (More lists / Music)
- awesome-generative-ai - Molecular design - List of molecular design using Generative AI and Deep Learning. (More lists / Music)
- awesome-ai - Molecular design - List of molecular design using Generative AI and Deep Learning. (More lists / Music)
- awesome-generative-ai - Molecular design - A list of molecular design papers using Generative AI and Deep Learning. (More Lists / Music)
README
[](https://github.com/AspirinCode/papers-for-molecular-design-using-DL)
[](https://github.com/AspirinCode/papers-for-molecular-design-using-DL)
# List of Molecular and Material design (molecular conformation generation) using Generative AI and Deep Learning
related to **Generative AI** and **Deep Learning** for **molecular/drug design** and **molecular conformation generation**.
**Updating ...**
## Molecular Optimization
[Molecular Optimization](https://github.com/AspirinCode/papers-for-molecular-design-using-DL/blob/main/Molecular_Optimization.md) will welcome ！！！
## Menu
**Molecular(drug) Design Using Generative Artificial Intelligence and Deep Learning**
| Menu | Menu | Menu | Menu |
| ------ | :---------- | ------ | ------ |
| [ Generative AI for Scientific Discovery](#generative-ai-for-scientific-discovery) | [ Reviews](#reviews) | [ Datasets and Benchmarks](#datasets-and-benchmarks) | [ Drug-likeness and Evaluation metrics](#drug-likeness-and-evaluation-metrics) |
| [Deep Learning-based design](#deep-learning-based-design) | [Text-driven molecular generation models](#text-driven-molecular-generation-models) | [Multi-Target based deep molecular generative models](#multi-Target-based-deep-molecular-generative-models) | [Ligand-based deep molecular generative models](#ligand-based-deep-molecular-generative-models) |
| [Pharmacophore-based deep molecular generative models](#pharmacophore-based-deep-molecular-generative-models) | [Structure-based deep molecular generative models](#structure-based-deep-molecular-generative-models) | [Fragment-based deep molecular generative models](#fragment-based-deep-molecular-generative-models) | [Scaffold-based DMGs](#scaffold-based-dmgs) |
| [Fragment-based DMGs](#fragment-based-dmgs) | [Motifs-based DMGs](#motifs-based-dmgs) | [Linkers-based DMGs](#linkers-based-dmgs) | [Chemical Reaction-based deep molecular generative models](#chemical-reaction-based-deep-molecular-generative-models) |
| [Omics-based deep molecular generative models](#omics-based-deep-molecular-generative-models) | [Multi-Objective deep molecular generative models](#multi-objective-deep-molecular-generative-models) | [Quantum deep molecular generative models](#quantum-deep-molecular-generative-models) | [Recommendations and References](#recommendations-and-references) |
| [Spectra(Mass/NMR)-based](#spectra-based) | [Mass Spectra-based](#mass-spectra-based) | [NMR Spectra-based](#nmr-spectra-based) | [Cryo-EM Maps-based](#cryo-em-maps-based) |
- [ Drug-likeness and Evaluation metrics](#drug-likeness-and-evaluation-metrics)
| Datasets | Benchmarks | Drug-likeness| Evaluation metrics |
| ------ | :---------- | ------ | ------ |
| [Datasets](#datasets) | [Benchmarks](#benchmarks) | [QED](#qed) | [SAscore](#sascore) |
| | | [QEPPI](#qeppi) | [RAscore](#rascore) |
| | | | [Evaluation metrics](#evaluation-metrics) |
| | | | [Molecular generative validation](#molecular-generative-validation) |
- [Generative AI for Molecular Conformation](#generative-ai-for-molecular-conformation)
| Menu | Menu |
| ------ | ------ |
| [Benchmark for Molecular Conformer Ensembles](#benchmark-for-molecular-conformer-ensembles) | [Reviews for Molecular Conformation Generation](#reviews-for-molecular-conformation-generation) |
| [VAE-based Molecular Conformation Generation](#vae-based-molecular-conformation-generation) | [GAN-based Molecular Conformation Generation](#gan-based-molecular-conformation-generation) |
| [Energy-based Molecular Conformation Generation](#energy-based-molecular-conformation-generation) | |
| [Diffusion-based Molecular Conformation Generation](#diffusion-based-molecular-conformation-generation) | |
| [RL-based Molecular Conformation Generation](#rl-based-molecular-conformation-generation) | |
| [GNN-based Molecular Conformation Generation](#gnn-based-molecular-conformation-generation) | |
- [Deep Learning-based drug design](#deep-learning-based-drug-design)
| Menu | Menu | Menu | Menu |
| ------ | :---------- | ------ | ------ |
| [RNN-based](#rnn-based) | [LSTM-based](#lstm-based) | [Autoregressive-models](#autoregressive-models) | [Transformer-based](#transformer-based) |
| [VAE-based](#vae-based) | [GAN-based](#gan-based) | [Flow-based](#flow-based) | [ Prompt-based](#prompt-based)|
| [Score-Based](#score-Based) | [Energy-based](#energy-based) | [Diffusion-based](#diffusion-based) | [Active Learning DMGs](#active-learning-dmgs) |
| [RL-based](#rl-based) | [Multi-task DMGs](#multi-task-dmgs) | [Monte Carlo Tree Search](#monte-carlo-tree-search) | [Genetic Algorithm-based](#genetic-algorithm-based) |
| [Evolutionary Algorithm-based](#evolutionary-algorithm-based) | [Large Language Model-based](#large-language-model-based) | | |
**Material Design Using Generative Artificial Intelligence and Deep Learning**
- [Deep Learning-based material design](#deep-learning-based-material-design)
| Menu | Menu | Menu | Menu |
| ------ | :---------- | ------ | ------ |
| | | | |
## Recommendations and References
**awesome-AI4ProteinConformation-MD**
https://github.com/AspirinCode/awesome-AI4ProteinConformation-MD
**Large Language Model for Biomedical Science, Molecule, Protein, Material Discovery**
https://github.com/HHW-zhou/LLM4Mol
**List of papers about Proteins Design using Deep Learning**
https://github.com/Peldom/papers_for_protein_design_using_DL
**Awesome Generative AI**
https://github.com/steven2358/awesome-generative-ai
**awesome-molecular-generation**
https://github.com/amorehead/awesome-molecular-generation
**A Survey of Artificial Intelligence in Drug Discovery**
https://github.com/dengjianyuan/Survey_AI_Drug_Discovery
**Geometry Deep Learning for Drug Discovery and Life Science**
https://github.com/3146830058/Geometry-Deep-Learning-for-Drug-Discovery-and-Life-Science
## Generative AI for Scientific Discovery
* **Accelerating Material Design with the Generative Toolkit for Scientific Discovery**
Manica, Matteo and Cadow, Joris and Christofidellis, Dimitrios and Dave, Ashish and Born, Jannis and Clarke, Dean and Teukam, Yves Gaetan Nana and Hoffman, Samuel C and Buchan, Matthew and Chenthamarakshan, Vijil and others
[npj Comput Mater 9, 69 (2023)](https://www.nature.com/articles/s41524-023-01028-1) | [code](https://github.com/GT4SD/gt4sd-core)
## Reviews
* **Diffusion Models for Molecules: A Survey of Methods and Tasks** [2025]
Liang Wang, Chao Song, Zhiyuan Liu, Yu Rong, Qiang Liu, Shu Wu, Liang Wang.
[arXiv:2502.09511 (2025)](https://arxiv.org/abs/2502.09511) | [code](https://github.com/AzureLeon1/awesome-molecular-diffusion-models)
* **Diffusion Models in De Novo Drug Design** [2024]
Alakhdar, Amira, Barnabas Poczos, and Newell Washburn.
[J. Chem. Inf. Model. (2024)](https://doi.org/10.1021/acs.jcim.4c01107)
* **Deep Lead Optimization: Leveraging Generative AI for Structural Modification** [2024]
Zhang, Odin, Haitao Lin, Hui Zhang, Huifeng Zhao, Yufei Huang, Yuansheng Huang, Dejun Jiang, Chang-yu Hsieh, Peichen Pan, and Tingjun Hou.
[arXiv:2404.19230 (2024)](https://arxiv.org/abs/2404.19230)
* **Unlocking the Potential of Generative Artificial Intelligence in Drug Discovery** [2024]
Romanelli, Virgilio, Carmen Cerchia, and Antonio Lavecchia.
[Applications of Generative AI (2024)](https://link.springer.com/chapter/10.1007/978-3-031-46238-2_3)
* **Recent Advances in Automated Structure-Based De Novo Drug Design** [2024]
Bai, Qifeng, Jian Ma, and Tingyang Xu.
[J. Chem. Inf. Model. (2024)](https://doi.org/10.1021/acs.jcim.4c00247)
* **AI Deep Learning Generative Models for Drug Discovery** [2024]
Bai, Qifeng, Jian Ma, and Tingyang Xu.
[Applications of Generative AI. Cham: Springer International Publishing (2024)](https://link.springer.com/chapter/10.1007/978-3-031-46238-2_23)
* **Deep Generative Models in De Novo Drug Molecule Generation** [2024]
Xiangru Tang, Howard Dai, Elizabeth Knight, Fang Wu, Yunyang Li, Tianxiao Li, Mark Gerstein
[arXiv:2402.08703 (2024)](https://arxiv.org/abs/2402.08703) | [code](https://github.com/gersteinlab/GenAI4Drug)
* **Deep Generative Models in De Novo Drug Molecule Generation** [2023]
Chao Pang, Jianbo Qiao, Xiangxiang Zeng, Quan Zou, and Leyi Wei*
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.3c01496)
* **The Hitchhiker’s Guide to Deep Learning Driven Generative Chemistry** [2023]
Yan Ivanenkov, Bogdan Zagribelnyy, Alex Malyshev, Sergei Evteev, Victor Terentiev, Petrina Kamya, Dmitry Bezrukov, Alex Aliper, Feng Ren, and Alex Zhavoronkov
[ACS Med. Chem. Lett. (2023)](https://doi.org/10.1021/acsmedchemlett.3c00041)
* **Quantum computing for near-term applications in generative chemistry and drug discovery** [2023]
Pyrkov, Alexey, Alex Aliper, Dmitry Bezrukov, Yen-Chu Lin, Daniil Polykovskiy, Petrina Kamya, Feng Ren, and Alex Zhavoronkov.
[Drug Discovery Today (2023)](https://doi.org/10.1016/j.drudis.2023.103675)
* **A Systematic Survey in Geometric Deep Learning for Structure-based Drug Design**[2023]
Zaixi Zhang, Jiaxian Yan, Qi Liu, Enhong Chen
[arXiv:2306.11768v2](https://arxiv.org/abs/2306.11768)
* **How will generative AI disrupt data science in drug discovery?**[2023]
Vert, JP.
[Nat Biotechnol (2023)](https://doi.org/10.1038/s41587-023-01789-6)
* **Generative Models as an Emerging Paradigm in the Chemical Sciences**[2023]
Anstine, Dylan M., and Olexandr Isayev.
[JACS (2023)](https://pubs.acs.org/doi/10.1021/jacs.2c13467)
* **Chemical language models for de novo drug design: Challenges and opportunities**[2023]
Grisoni, Francesca.
[Current Opinion in Structural Biology 79 (2023)](https://doi.org/10.1016/j.sbi.2023.102527)
* **Artificial intelligence in multi-objective drug design**[2023]
Luukkonen, Sohvi, Helle W. van den Maagdenberg, Michael TM Emmerich, and Gerard JP van Westen.
[Current Opinion in Structural Biology 79 (2023)](https://doi.org/10.1016/j.sbi.2023.102537)
* **Integrating structure-based approaches in generative molecular design**[2023]
Thomas, Morgan, Andreas Bender, and Chris de Graaf.
[Current Opinion in Structural Biology 79 (2023)](https://doi.org/10.1016/j.sbi.2023.102559)
* **Open data and algorithms for open science in AI-driven molecular informatics**[2023]
Brinkhaus, Henning Otto, Kohulan Rajan, Jonas Schaub, Achim Zielesny, and Christoph Steinbeck.
[Current Opinion in Structural Biology 79 (2023)](https://doi.org/10.1016/j.sbi.2023.102542)
* **Structure-based drug design with geometric deep learning**[2023]
Isert, Clemens, Kenneth Atz, and Gisbert Schneider.
[Current Opinion in Structural Biology 79 (2023)](https://doi.org/10.1016/j.sbi.2023.102548)
* **MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design**[2022]
Du, Yuanqi, Tianfan Fu, Jimeng Sun, and Shengchao Liu.
[arXiv:2203.14500 (2022)](https://arxiv.org/abs/2203.14500)
* **Deep generative molecular design reshapes drug discovery**[2022]
Zeng, Xiangxiang, Fei Wang, Yuan Luo, Seung-gu Kang, Jian Tang, Felice C. Lightstone, Evandro F. Fang, Wendy Cornell, Ruth Nussinov, and Feixiong Cheng.
[Cell Reports Medicine (2022)](https://doi.org/10.1016/j.xcrm.2022.100794)
* **Structure-based drug discovery with deep learning**[2022]
Özçelik, Rıza, Derek van Tilborg, José Jiménez-Luna, and Francesca Grisoni.
[ChemBioChem (2022)](https://doi.org/10.1002/cbic.202200776)
* **Generative models for molecular discovery: Recent advances and challenges**[2022]
Bilodeau, Camille, Wengong Jin, Tommi Jaakkola, Regina Barzilay, and Klavs F. Jensen.
[Computational Molecular Science 12.5 (2022)](https://doi.org/10.1002/wcms.1608)
* **Assessing Deep Generative Models in Chemical Composition Space**[2022]
Türk, Hanna, Elisabetta Landini, Christian Kunkel, Johannes T. Margraf, and Karsten Reuter.
[Chemistry of Materials 34.21 (2022)](https://doi.org/10.1021/acs.chemmater.2c01860)
* **Generative machine learning for de novo drug discovery: A systematic review**[2022]
Martinelli, Dominic.
[Computers in Biology and Medicine 145 (2022)](https://doi.org/10.1016/j.compbiomed.2022.105403)
* **Docking-based generative approaches in the search for new drug candidates**[2022]
Danel, Tomasz, Jan Łęski, Sabina Podlewska, and Igor T. Podolak.
[Drug Discovery Today (2022)](https://doi.org/10.1016/j.drudis.2022.103439)
* **Advances and Challenges in De Novo Drug Design Using Three-Dimensional Deep Generative Models**[2022]
Xie, Weixin, Fanhao Wang, Yibo Li, Luhua Lai, and Jianfeng Pei.
[J. Chem. Inf. Model. 2022, 62, 10, 2269–2279](https://pubs.acs.org/doi/10.1021/acs.jcim.2c00042)
* **Deep learning to catalyze inverse molecular design**[2022]
Alshehri, Abdulelah S., and Fengqi You.
[Chemical Engineering Journal 444 (2022)](https://doi.org/10.1016/j.cej.2022.136669)
* **AI in 3D compound design**[2022]
Hadfield, Thomas E., and Charlotte M. Deane.
[Current Opinion in Structural Biology 73 (2022)](https://doi.org/10.1016/j.sbi.2021.102326)
* **Deep learning approaches for de novo drug design: An overview**[2021]
Wang, Mingyang, Zhe Wang, Huiyong Sun, Jike Wang, Chao Shen, Gaoqi Weng, Xin Chai, Honglin Li, Dongsheng Cao, and Tingjun Hou.
[Current Opinion in Structural Biology 72 (2022)](https://doi.org/10.1016/j.sbi.2021.10.001)
* **Generative chemistry: drug discovery with deep learning generative models**[2021]
Bian, Yuemin, and Xiang-Qun Xie.
[Journal of Molecular Modeling 27 (2021)](https://link.springer.com/article/10.1007/s00894-021-04674-8)
* **Generative Deep Learning for Targeted Compound Design**[2021]
Sousa, Tiago, João Correia, Vítor Pereira, and Miguel Rocha.
[J. Chem. Inf. Model. 2021, 61, 11, 5343–5361](https://pubs.acs.org/doi/10.1021/acs.jcim.0c01496)
* **Generative Models for De Novo Drug Design**[2021]
Tong, Xiaochu, Xiaohong Liu, Xiaoqin Tan, Xutong Li, Jiaxin Jiang, Zhaoping Xiong, Tingyang Xu, Hualiang Jiang, Nan Qiao, and Mingyue Zheng.
[Journal of Medicinal Chemistry 64.19 (2021)](https://pubs.acs.org/doi/10.1021/acs.jmedchem.1c00927)
* **Molecular design in drug discovery: a comprehensive review of deep generative models**[2021]
Cheng, Yu, Yongshun Gong, Yuansheng Liu, Bosheng Song, and Quan Zou.
[Briefings in bioinformatics 22.6 (2021)](https://doi.org/10.1093/bib/bbab344)
* **De novo molecular design and generative models**[2021]
Meyers, Joshua, Benedek Fabian, and Nathan Brown.
[Drug Discovery Today 26.11 (2021)](https://doi.org/10.1016/j.drudis.2021.05.019)
* **Deep learning for molecular design—a review of the state of the art**[2019]
Elton, Daniel C., Zois Boukouvalas, Mark D. Fuge, and Peter W. Chung.
[Molecular Systems Design & Engineering 4.4 (2019)](https://pubs.rsc.org/en/content/articlelanding/2019/me/c9me00039a)
* **Inverse molecular design using machine learning: Generative models for matter engineering**[2018]
Sanchez-Lengeling, Benjamin, and Alán Aspuru-Guzik.
[Science 361.6400 (2018)](https://www.science.org/doi/10.1126/science.aat2663)
## Datasets and Benchmarks
### Datasets
[**DrugBank**](https://go.drugbank.com/)
[**ZINC 15**](https://zinc15.docking.org/)
[**ZINC 20**](https://zinc20.docking.org/)
[**PubChem**](https://pubchem.ncbi.nlm.nih.gov/)
[**ChEMBL** ](https://www.ebi.ac.uk/chembl/)
[**GDB Databases**](https://gdb.unibe.ch/downloads/)
[**ChemSpider**](http://www.chemspider.com/)
[**QM Dataset**](http://quantum-machine.org/datasets/)
[**COCONUT** | Collection of Open Natural Products database](https://coconut.naturalproducts.net/)
**MolData**
A Molecular Benchmark for Disease and Target Based Machine Learning
https://github.com/LumosBio/MolData
* **Machine Learning Methods for Small Data Challenges in Molecular Science** [2023]
Bozheng Dou, Zailiang Zhu, Ekaterina Merkurjev, Lu Ke, Long Chen, Jian Jiang, Yueying Zhu, Jie Liu, Bengong Zhang, and Guo-Wei Wei
[Chem. Rev (2023)](https://doi.org/10.1021/acs.chemrev.3c00189)
### Benchmarks
* **Benchmarking Study of Deep Generative Models for Inverse Polymer Design** [2024]
Yue T, Tao L, Varshney V, Li Y.
[chemrxiv-2024-gzq4r (2024)](https://doi.org/10.26434/chemrxiv-2024-gzq4r)
* **RediscMol: Benchmarking Molecular Generation Models in Biological Properties** [2024]
Weng, Gaoqi, Huifeng Zhao, Dou Nie, Haotian Zhang, Liwei Liu, Tingjun Hou, and Yu Kang.
[J. Med. Chem. 2024](https://pubs.acs.org/doi/abs/10.1021/acs.jmedchem.3c02051) | [code](https://github.com/gaoqiweng/RediscMol)
* **Generative Models Should at Least Be Able to Design Molecules That Dock Well: A New Benchmark** [2023]
Ciepliński, Tobiasz, Tomasz Danel, Sabina Podlewska, and Stanisław Jastrzȩbski.
[J. Chem. Inf. Model. 2023, 63, 11, 3238–3247](https://pubs.acs.org/doi/10.1021/acs.jcim.2c01355) | [code](https://github.com/cieplinski-tobiasz/smina-docking-benchmark)
* **Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design** [2022]
Nigam, AkshatKumar, Robert Pollice, Gary Tom, Kjell Jorner, Luca A.
[arXiv:2209.12487v1](https://arxiv.org/abs/2209.12487) | [code](https://github.com/aspuru-guzik-group/Tartarus)
* **Molecular Sets (MOSES): A benchmarking platform for molecular generation models** [2020]
Polykovskiy, Daniil, Alexander Zhebrak, Benjamin Sanchez-Lengeling, Sergey Golovanov, Oktai Tatanov, Stanislav Belyaev, Rauf Kurbanov et al.
[Frontiers in pharmacology 11 (2020)](https://doi.org/10.3389/fphar.2020.565644) | [code](https://github.com/molecularsets/moses)
* **GuacaMol: Benchmarking Models for de Novo Molecular Design** [2019]
Brown, Nathan, Marco Fiscato, Marwin HS Segler, and Alain C. Vaucher.
[J. Chem. Inf. Model. 2019, 59, 3, 1096–1108](https://pubs.acs.org/doi/10.1021/acs.jcim.8b00839) | [code](https://github.com/BenevolentAI/guacamol)
## Drug-likeness and Evaluation metrics
**Drug-likeness** may be defined as a complex balance of various molecular properties and structure features which determine whether particular molecule is similar to the known drugs. These properties, mainly hydrophobicity, electronic distribution, hydrogen bonding characteristics, molecule size and flexibility and of course presence of various pharmacophoric features influence the behavior of molecule in a living organism, including bioavailability, transport properties, affinity to proteins, reactivity, toxicity, metabolic stability and many others.
https://github.com/AspirinCode/DrugAI_Drug-Likeness
### QED
**quantitative estimation of drug-likeness**
* **Quantifying the chemical beauty of drugs** [2012]
Bickerton, G., Paolini, G., Besnard, J. et al.
[Nature Chem 4, 90–98 (2012)](https://doi.org/10.1038/nchem.1243) | [code](https://github.com/AspirinCode/DrugAI_Drug-Likeness)
### QEPPI
**quantitative estimate of protein-protein interaction targeting drug-likeness**
* **Quantitative Estimate Index for Early-Stage Screening of Compounds Targeting Protein-Protein Interactions** [2021]
Kosugi, Takatsugu, and Masahito Ohue.
[International Journal of Molecular Sciences 22.20 (2021)](https://doi.org/10.3390/ijms222010925) | [code](https://github.com/ohuelab/QEPPI)
* **Quantitative Estimate of Protein-Protein Interaction Targeting Drug-likeness** [2021]
Kosugi, Takatsugi, and Masahito Ohue.
[CIBCB. IEEE, (2021)](https://ieeexplore.ieee.org/abstract/document/9562931) | [code](https://github.com/ohuelab/QEPPI)
### SAscore
**Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions**
[J Cheminform 1, 8 (2009)](http://www.jcheminf.com/content/1/1/8) | [code](https://github.com/rdkit/rdkit/tree/master/Contrib/SA_Score)
### RAscore
**Retrosynthetic accessibility score (RAscore) – rapid machine learned synthesizability classification from AI driven retrosynthetic planning**
[Chemical Science 12.9 (2021)](https://pubs.rsc.org/en/content/articlelanding/2021/sc/d0sc05401a) | [code](https://github.com/reymond-group/RAscore)
### Evaluation metrics
* **Hamiltonian diversity: effectively measuring molecular diversity by shortest Hamiltonian circuits** [2024]
Hu, X., Liu, G., Yao, Q. et al.
[ J Cheminform 16, 94 (2024)](https://doi.org/10.1186/s13321-024-00883-4) | [code](https://github.com/HXYfighter/HamDiv)
* **Spacial Score – A Comprehensive Topological Indicator for Small Molecule Complexity** [2023]
Krzyzanowski, Adrian, Axel Pahl, Michael Grigalunas, and Herbert Waldmann.
[J. Med. Chem. (2023)](https://doi.org/10.1021/acs.jmedchem.3c00689) | [chemrxiv-2023-nd1ll](https://chemrxiv.org/engage/chemrxiv/article-details/64257af562fecd2a83add9c2) | [code](https://github.com/frog2000/Spacial-Score)
* **An automated scoring function to facilitate and standardize evaluation of goal-directed generative models for de novo molecular design** [2023]
Thomas, Morgan, Noel M. O'Boyle, Andreas Bender, and Chris De Graaf.
[chemrxiv-2023-c4867](https://doi.org/10.26434/chemrxiv-2023-c4867) | [code](https://github.com/MorganCThomas/MolScore)
* **FCD : Fréchet ChemNet Distance**
Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery
Preuer, Kristina, Philipp Renz, Thomas Unterthiner, Sepp Hochreiter, and Gunter Klambauer.
[J. Chem. Inf. Model. 2018, 58, 9, 1736–1741](https://pubs.acs.org/doi/10.1021/acs.jcim.8b00234) | [code](https://github.com/bioinf-jku/FCD)
* **Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models** [2022]
Moret, M., Grisoni, F., Katzberger, P. and Schneider, G.
[J. Chem. Inf. Model. 2022, 62, 5, 1199–1206](https://pubs.acs.org/doi/10.1021/acs.jcim.2c00079) | [code](https://github.com/ETHmodlab/CLM_perplexity)
## Molecular generative validation
* **On the difficulty of validating molecular generative models realistically: a case study on public and proprietary data** [2023]
Handa, K., Thomas, M.C., Kageyama, M. et al.
[J Cheminform 15, 112 (2023)](https://doi.org/10.1186/s13321-023-00781-1)
## Generative AI for Molecular Conformation
### Reviews for Molecular Conformation Generation
* **Prediction of Molecular Conformation Using Deep Generative Neural Networks** [2023]
Xu, Congsheng, Yi Lu, Xiaomei Deng, and Peiyuan Yu.
[Chinese Journal of Chemistry(2023)](https://doi.org/10.1002/cjoc.202300269)
### Benchmark for Molecular Conformer Ensembles
* **Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks** [2023]
Zhu, Yanqiao, Jeehyun Hwang, Keir Adams, Zhen Liu, Bozhao Nan, Brock Stenfors, Yuanqi Du et al.
[NeurIPS 2023 AI for Science Workshop. 2023 (2023)](https://openreview.net/forum?id=kFiMXnLH9x) | [code](https://github.com/SXKDZ/MARCEL)
### VAE-based Molecular Conformation Generation
* **Deep-Learning-Assisted Enhanced Sampling for Exploring Molecular Conformational Changes** [2023]
Haohao Fu, Han Liu, Jingya Xing, Tong Zhao, Xueguang Shao, and Wensheng Cai.
[J. Phys. Chem. B (2023)](https://doi.org/10.1021/acs.jpcb.3c05284)
* **An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming** [2021]
Xu, Minkai, Wujie Wang, Shitong Luo, Chence Shi, Yoshua Bengio, Rafael Gomez-Bombarelli, and Jian Tang.
[International Conference on Machine Learning. PMLR (2021)](http://proceedings.mlr.press/v139/xu21f.html) | [code](https://github.com/MinkaiXu/ConfVAE-ICML21)
### GAN-based Molecular Conformation Generation
* **Generation of molecular conformations using generative adversarial neural networks** [2024]
Xu, Congsheng, Xiaomei Deng, Yi Lu, and Peiyuan Yu.
[Digital Discovery (2024)](https://doi.org/10.1039/D4DD00179F) | [code](https://github.com/xucongs/ConfGAN)
* **COSMIC: Molecular Conformation Space Modeling in Internal Coordinates with an Adversarial Framework** [2024]
Kuznetsov, Maksim, Fedor Ryabov, Roman Schutski, Rim Shayakhmetov, Yen-Chu Lin, Alex Aliper, and Daniil Polykovskiy.
[J. Chem. Inf. Model. (2024)](https://doi.org/10.1021/acs.jcim.3c00989) | [code](https://github.com/insilicomedicine/COSMIC)
### Energy-based Molecular Conformation Generation
* **Energy-inspired molecular conformation optimization** [2022]
Guan, Jiaqi, Wesley Wei Qian, Wei-Ying Ma, Jianzhu Ma, and Jian Peng.
[International Conference on Learning Representations. (2022)](https://openreview.net/forum?id=7QfLW-XZTl) | [code](https://github.com/guanjq/confopt_officialf)
### Diffusion-based Molecular Conformation Generation
* **AGDIFF: Attention-Enhanced Diffusion for Molecular Geometry Prediction** [2025]
André Brasil Vieira Wyzykowski, Fatemeh Fathi Niazi, and Alex Dickson.
[ J. Chem. Inf. Model. (2025)](https://doi.org/10.1021/acs.jcim.4c01896) |[ChemRxiv. (2024)](https://doi.org/10.26434/chemrxiv-2024-wrvr4) | [code](https://github.com/ADicksonLab/AGDIFF)
* **Improving Structural Plausibility in 3D Molecule Generation via Property-Conditioned Training with Distorted Molecules** [2024]
Lucy Vost, Vijil Chenthamarakshan, Payel Das, Charlotte M. Deane.
[bioRxiv. (2024)](https://doi.org/10.1101/2024.09.17.613136)
* **Diffusion-based generative AI for exploring transition states from 2D molecular graphs** [204]
Kim, S., Woo, J. & Kim, W.Y.
[Nat Commun 15, 341 (2024)](https://doi.org/10.1038/s41467-023-44629-6) | [code](https://github.com/seonghann/tsdiff)
* **Physics-informed generative model for drug-like molecule conformers** [204]
David C. Williams, Neil Imana.
[ arXiv:2403.07925. (2024)](https://arxiv.org/abs/2403.07925v1) | [code](https://github.com/nobiastx/diffusion-conformer)
* **DynamicsDiffusion: Generating and Rare Event Sampling of Molecular Dynamic Trajectories Using Diffusion Models** [2023]
Petersen, Magnus, Gemma Roig, and Roberto Covino.
[NeurIPS 2023 AI4Science (2023)](https://openreview.net/forum?id=pwYCCq4xAf)
* **Generating Molecular Conformer Fields** [2023]
Yuyang Wang, Ahmed Elhag, Navdeep Jaitly, Joshua Susskind, Miguel Bautista.
[NeurIPS 2023 Generative AI and Biology (GenBio) Workshop (2023)]https://openreview.net/forum?id=Od1KtMeAYo)
* **On Accelerating Diffusion-based Molecular Conformation Generation in SE(3)-invariant Space** [2023]
Zhou, Z., Liu, R. and Yu, T.
[arXiv:2310.04915 (2023))](https://arxiv.org/abs/2310.04915)
* **Molecular Conformation Generation via Shifting Scores** [2023]
Zhou, Zihan, Ruiying Liu, Chaolong Ying, Ruimao Zhang, and Tianshu Yu.
[arXiv:2309.09985 (2023)](https://arxiv.org/abs/2309.09985)
* **EC-Conf: An Ultra-fast Diffusion Model for Molecular Conformation Generation with Equivariant Consistency** [2023]
Fan, Zhiguang, Yuedong Yang, Mingyuan Xu, and Hongming Chen.
[arXiv:2308.00237 (2023)](https://arxiv.org/abs/2308.00237)
* **Torsional diffusion for molecular conformer generation** [2022]
Jing, Bowen, Gabriele Corso, Jeffrey Chang, Regina Barzilay, and Tommi Jaakkola.
[NeurIPS. (2022)](https://proceedings.neurips.cc/paper_files/paper/2022/hash/994545b2308bbbbc97e3e687ea9e464f-Abstract-Conference.html) | [code](https://github.com/gcorso/torsional-diffusionf)
* **GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation** [2022]
Xu, Minkai, Lantao Yu, Yang Song, Chence Shi, Stefano Ermon, and Jian Tang.
[International Conference on Learning Representations. (2022)](https://openreview.net/forum?id=PzcvxEMzvQC) | [code](https://github.com/MinkaiXu/GeoDiff)
### RL-based Molecular Conformation Generation
* **Conformer-RL: A deep reinforcement learning library for conformer generation** [2022]
Jiang, Runxuan, Tarun Gogineni, Joshua Kammeraad, Yifei He, Ambuj Tewari, and Paul M. Zimmerman.
[Journal of Computational Chemistry 43.27 (2022)](https://doi.org/10.1002/jcc.26984) | [code](https://github.com/ZimmermanGroup/conformer-rl)
### GNN-based Molecular Conformation Generation
* **Leveraging 2D Molecular Graph Pretraining for Improved 3D Conformer Generation with Graph Neural Networks** [2024]
Jiang, Runxuan, Tarun Gogineni, Joshua Kammeraad, Yifei He, Ambuj Tewari, and Paul M. Zimmerman.
[Computers & Chemical Engineering (2024)](https://doi.org/10.1016/j.compchemeng.2024.108622) | [code](https://github.com/m1k2zoo/2D-3DConformerGNN)
## Deep Learning-based drug design
* **Accelerated Discovery of Carbamate Cbl-b Inhibitors Using Generative AI Models and Structure-Based Drug Design** [2024]
Quinn, T.R., Giblin, K.A., Thomson, C., Boerth, J.A., Bommakanti, G., Braybrooke, E., Chan, C., Chinn, A.J., Code, E., Cui, C. and Fan, Y.
[J. Med. Chem. (2024)](https://doi.org/10.1021/acs.jmedchem.4c01034) | [code](https://github.com/MolecularAI/REINVENT4)
* **Reinvent 4: Modern AI–driven generative molecule design** [2024]
Hannes H. Loeffler, Jiazhen He, Alessandro Tibo, Jon Paul Janet, Alexey Voronov, Lewis H. Mervin & Ola Engkvist
[Journal of Cheminformatics,16(20) (2024)](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-024-00812-5) | [code](https://github.com/MolecularAI/REINVENT4)
* **Chemistry42: An AI-Driven Platform for Molecular Design and Optimization** [2023]
Ivanenkov, Yan A., Daniil Polykovskiy, Dmitry Bezrukov, Bogdan Zagribelnyy, Vladimir Aladinskiy, Petrina Kamya, Alex Aliper, Feng Ren, and Alex Zhavoronkov.
[Journal of Chemical Information and Modeling 63.3 (2023)](https://doi.org/10.1021/acs.jcim.2c01191) | [web](https://cloud.chemistry42.com/login)
### RNN-based
* **Transcriptionally Conditional Recurrent Neural Network for De Novo Drug Design** [2024]
Matsukiyo, Y., Tengeiji, A., Li, C. and Yamanishi, Y.
[J. Chem. Inf. Model. (2024)](https://doi.org/10.1021/acs.jcim.4c00531) | [code](https://yamanishi.cs.i.nagoya-u.ac.jp/gxrnn/)
* **Prospective de novo drug design with deep interactome learning** [2024]
Atz, K., Cotos, L., Isert, C. et al.
[Nat Commun 15, 3408 (2024)](https://doi.org/10.1038/s41467-024-47613-w) | [code](https://github.com/atzkenneth/dragonfly_gen)
* **CNSMolGen: a bidirectional recurrent neural networks based generative model for de novo central nervous system drug design** [2024]
Gou, Rongpei, Jingyi Yang, Menghan Guo, Yingjun Chen, and Weiwei Xue.
[chemrxiv-2024-x4wbl (2024)](https://doi.org/10.26434/chemrxiv-2024-x4wbl) | [code](https://github.com/xueww/CNSMolGen/)
* **NovoMol: Recurrent Neural Network for Orally Bioavailable Drug Design and Validation on PDGFRα Receptor** [2023]
Rao, Ishir.
[arXiv:2312.01527 (2023)](https://arxiv.org/abs/2312.01527) | [code](https://github.com/ishirraov/NovoMol)
* **Generation of focused drug molecule library using recurrent neural network** [2023]
Zou, Jinping, Long Zhao, and Shaoping Shi.
[Journal of Molecular Modeling 29.12 (2023)](https://doi.org/10.1007/s00894-023-05772-5) | [code](https://github.com/JinPing1025/Drug_RNN)
* **ChemTSv2: Functional molecular design using de novo molecule generator** [2023]
Ishida, Shoichi, Tanuj Aasawat, Masato Sumita, Michio Katouda, Tatsuya Yoshizawa, Kazuki Yoshizoe, Koji Tsuda, and Kei Terayama.
[Wiley Interdisciplinary Reviews: Computational Molecular Science (2023)](https://doi.org/10.1002/wcms.1680) | [code](https://github.com/molecule-generator-collection/ChemTSv2)
* **Utilizing Reinforcement Learning for de novo Drug Design** [2023]
Svensson, Hampus Gummesson, Christian Tyrchan, Ola Engkvist, and Morteza Haghir Chehreghani.
[arXiv:2303.17615 (2023)](https://arxiv.org/abs/2303.17615) | [code](https://github.com/MolecularAI/SMILES-RL)
* **De novo drug design based on Stack-RNN with multi-objective reward-weighted sum and reinforcement learning** [2023]
Hu, P., Zou, J., Yu, J. et al.
[ J Mol Model 29, 121 (2023)](https://doi.org/10.1007/s00894-023-05523-6) | [code](https://github.com/PengWeiHu1/mul_RL)
* **On The Difficulty of Validating Molecular Generative Models Realistically: A Case Study on Public and Proprietary Data** [2023]
Handa, Koichi, Morgan Thomas, Michiharu Kageyama, Takeshi Iijima, and Andreas Bender.
[chemrxiv-2023-lbvgn](https://doi.org/10.26434/chemrxiv-2023-lbvgn) | [code](https://github.com/MolecularAI/Reinvent)
* **Magicmol: a light-weighted pipeline for drug-like molecule evolution and quick chemical space exploration** [2023]
Chen, Lin, Qing Shen, and Jungang Lou.
[BMC Bioinformatics (2023)](https://doi.org/10.1186/s12859-023-05286-0) | [code](https://github.com/Josefjosda/Magicmol)
* **Augmented Hill-Climb increases reinforcement learning efficiency for language-based de novo molecule generation** [2022]
Thomas, M., O’Boyle, N.M., Bender, A. et al.
[ J Cheminform (2022)](https://doi.org/10.1186/s13321-022-00646-z) | [code](https://github.com/MorganCThomas/SMILES-RNN)
* **De novo molecule design with chemical language models** [2022]
Grisoni, F., Schneider, G.
[Artificial Intelligence in Drug Design. Methods in Molecular Biology, vol 2390.(2022)](https://doi.org/10.1007/978-1-0716-1787-8_9) | [code](https://github.com/grisoniFr/de_novo_design_RNN)
* **Correlated RNN Framework to Quickly Generate Molecules with Desired Properties for Energetic Materials in the Low Data Regime** [2022]
Li, Chuan, Chenghui Wang, Ming Sun, Yan Zeng, Yuan Yuan, Qiaolin Gou, Guangchuan Wang, Yanzhi Guo, and Xuemei Pu.
[J. Chem. Inf. Model. (2022)](https://doi.org/10.1021/acs.jcim.2c00997) | [code](https://github.com/wangchenghuidream/RNNMGM)
* **Optimizing Recurrent Neural Network Architectures for De Novo Drug Design** [2021]
Santos, B. P., Abbasi, M., Pereira, T., Ribeiro, B., & Arrais, J. P.
[Paper](https://ieeexplore.ieee.org/document/9474742) | [code](https://github.com/larngroup/RNN-Drug-Generation)
* **A recurrent neural network (RNN) that generates drug-like molecules for drug discovery** [2021]
[code](https://github.com/shiwentao00/Molecule-RNN)
* **A molecule generative model used interaction fingerprint (docking pose) as constraints** [2021]
[code](https://github.com/jeah-z/IFP-RNN)
* **Bidirectional Molecule Generation with Recurrent Neural Networks** [2020]
Grisoni, F., Moret, M., Lingwood, R., & Schneider, G.
[J. Chem. Inf. Model. (2020)](https://pubs.acs.org/doi/10.1021/acs.jcim.9b00943) | [code](https://github.com/robinlingwood/BIMODAL)
* **Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks** [2019]
Kotsias, PC., Arús-Pous, J., Chen, H. *et al.*
[Nat Mach Intell 2, 254–265 (2020)](https://www.nature.com/articles/s42256-020-0174-5) | [code](https://github.com/pcko1/Deep-Drug-Coder)
* **ChemTS: An Efficient Python Library for de novo Molecular Generation** [2017]
Yang, X., Zhang, J., Yoshizoe, K., Terayama, K., & Tsuda, K.
[Science and Technology of Advanced Materials (2017)](https://www.tandfonline.com/doi/full/10.1080/14686996.2017.1401424) | [code](https://github.com/tsudalab/ChemTS)
### LSTM-based
* **RFL: Simplifying Chemical Structure Recognition with Ring-Free Language** [2025]
Chang, Q., Chen, M., Pi, C., Hu, P., Zhang, Z., Ma, J., ... & Hu, J.
[AAAI 2025 Oral. (2025)](https://arxiv.org/abs/2412.07594) | [code](https://github.com/JingMog/RFL-MSD)
* **Going beyond SMILES enumeration for generative deep learning in low data regimes** [2025]
Brinkmann, Helena, Antoine Argante, Hugo ter Steege, and Francesca Grisoni.
[ChemRxiv. (2025)](https://doi.org/10.26434/chemrxiv-2025-fdnnq) | [code](https://github.com/molML/fantasticSMILESaugmentation)
* **Stereochemistry-aware string-based molecular generation** [2024]
Tom G, Yu E, Yoshikawa N, Jorner K, Aspuru-Guzik A.
[ChemRxiv. (2024)](https://doi.org/10.26434/chemrxiv-2024-tkjr1) | [code](https://github.com/aspuru-guzik-group/stereogeneration)
* **ClickGen: Directed exploration of synthesizable chemical space via modular reactions and reinforcement learning** [2024]
Wang, M., Li, S., Wang, J. et al.
[Nat Commun 15, 10127 (2024)](https://doi.org/10.1038/s41467-024-54456-y) | [code](https://github.com/mywang1994/cligen_gen)
* **DigFrag as a digital fragmentation method used for artificial intelligence-based drug design** [2024]
Yang, R., Zhou, H., Wang, F. et al.
[Commun Chem 7, 258 (2024)](https://doi.org/10.1038/s42004-024-01346-5) | [code](https://github.com/yang1rq/MolFrag)
* **Prospective de novo drug design with deep interactome learning** [2024]
Atz, K., Cotos, L., Isert, C. et al.
[Nat Commun 15, 3408 (2024)](https://doi.org/10.1038/s41467-024-47613-w) | [code](https://github.com/atzkenneth/dragonfly_gen)
* **Computational Drug Discovery on HIV Virus with a Customized LSTM Variational Autoencoder Deep Learning Architecture** [2023]
Kutsal, Mucahit, Ferhat Ucar, and Nida Kati.
[CPT: Pharmacometrics & Systems Pharmacology. (2023)](https://doi.org/10.1002/psp4.13085) | [code](https://github.com/McahitKutsal/lstm-drug-discovery)
* **Structured State-Space Sequence Models for De Novo Drug Design** [2023]
Özçelik R, de Ruiter S, Grisoni F.
[chemrxiv-2023-jwmf3. (2023)](https://doi.org/10.26434/chemrxiv-2023-jwmf3) | [code](https://github.com/molML/s4-for-de-novo-drug-design)
* **Integrating synthetic accessibility with AI-based generative drug design** [2023]
Parrot, M., Tajmouati, H., da Silva, V.B.R. et al.
[J Cheminform 15, 83 (2023)](https://doi.org/10.1186/s13321-023-00742-8) | [code](https://github.com/iktos/generation-under-synthetic-constraint/)
* **Deep interactome learning for de novo drug design** [2023]
Atz K, Cotos Muñoz L, Isert C, Håkansson M, Focht D, Nippa DF, et al.
[chemrxiv-2023-cbq9k (2023)](https://doi.org/10.26434/chemrxiv-2023-cbq9k)
* **Deep learning driven de novo drug design based on gastric proton pump structures** [2023]
Abe, K., Ozako, M., Inukai, M. et al.
[Commun Biol 6, 956 (2023)](https://doi.org/10.1038/s42003-023-05334-8) | [code](https://doi.org/10.1038/s42003-023-05334-8)
* **Artificial Intelligence for Prediction of Biological Activities and Generation of molecular hits using Stereochemical Information** [2023]
Pereira, Tiago O., Maryam Abbasi, Rita I. Oliveira, Romina A. Guedes, Jorge AR Salvador, and Joel P. Arrais.
[Research Square. (2023)](https://doi.org/10.21203/rs.3.rs-2499317/v1) | [code](https://github.com/larngroup/targeted_generation_stereo)
* **LOGICS: Learning optimal generative distribution for designing de novo chemical structures** [2023]
Bae, B., Bae, H. & Nam, H.
[J Cheminform 15, 77 (2023)](https://doi.org/10.1186/s13321-023-00747-3) | [code](https://github.com/GIST-CSBL/LOGICS)
* **Leveraging molecular structure and bioactivity with chemical language models for de novo drug design** [2023]
Kotsias, PC., Arús-Pous, J., Chen, H. *et al.*
[Nat Commun 14, 114 (2023)](https://www.nature.com/articles/s41467-022-35692-6) | [code](https://github.com/ETHmodlab/hybridCLMs/tree/v1.0)
* **SMILES-based CharLSTM with finetuning and goal-directed generation via policy gradient** [2022]
[code](https://github.com/gmattedi/Smiles-LSTM)
* **DeLA-Drug: A Deep Learning Algorithm for Automated Design of Druglike Analogues** [2022]
Creanza, T. M., Lamanna, G., Delre, P., Contino, M., Corriero, N., Saviano, M., ... & Ancona, N.
[J. Chem. Inf. Model. (2022)](https://pubs.acs.org/doi/10.1021/acs.jcim.2c00205) | [Web](http://www.ba.ic.cnr.it/softwareic/deladrugportal/)
* **De novo design and bioactivity prediction of SARS-CoV-2 main protease inhibitors using recurrent neural network-based transfer learning** [2021]
Santana, M.V.S., Silva-Jr, F.P.
[BMC Chemistry 15, 8 (2021)](https://bmcchem.biomedcentral.com/articles/10.1186/s13065-021-00737-2) | [code](https://github.com/marcossantanaioc/De_novo_design_SARSCOV2)
* **Generative Recurrent Networks for De Novo Drug Design** [2018]
Gupta, A., Müller, A. T., Huisman, B. J., Fuchs, J. A., Schneider, P., & Schneider, G.
[Mol Inform. 2018](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5836943/) | [code](https://github.com/topazape/LSTM_Chem)
* **Generative Recurrent Neural Networks for De Novo Drug Design** [2017]
Gupta, Anvita, et al.
[Mol Inform. 2018](https://onlinelibrary.wiley.com/doi/10.1002/minf.201700111) | [code](https://github.com/SilviaAmAm/MolBot)
### Autoregressive-models
* **Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation** [2024]
Jeff Guo, Philippe Schwaller.
[ arXiv:2405.17066 (2024)](https://arxiv.org/abs/2405.17066) | [code](https://github.com/schwallergroup/saturn)
* **Enabling target-aware molecule generation to follow multi objectives with Pareto MCTS** [2024]
Yang, Y., Chen, G., Li, J. et al.
[Commun Biol 7, 1074 (2024)](https://doi.org/10.1038/s42003-024-06746-w) | [code](https://github.com/CNDOTA/ParetoDrug)
* **PocketFlow is a data-and-knowledge-driven structure-based molecular generative model** [2024]
Shengyong Yang, Yuanyuan Jiang, Guo Zhang et al.
[Nat Mach Intell (2024)](https://doi.org/10.1038/s42256-024-00808-8) | [Research Square. PREPRINT. (2023)](https://www.researchsquare.com/article/rs-3077992/v1) | [code](https://github.com/Saoge123/PocketFlow)
* **De Novo Molecule Design Towards Biased Properties via a Deep Generative Framework and Iterative Transfer Learning** [2024]
Sattari, Kianoosh, Dawei Li, Bhupalee Kalita, Yunchao Xie, Fatemeh Barmaleki Lighvan, Olexandr Isayev, and Jian Lin.
[Digital Discovery (2024)](https://pubs.rsc.org/en/content/articlehtml/2024/dd/d3dd00210a) | [code](https://github.com/linresearchgroup/RRCGAN_Molecules_Ehl)
* **Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation** [2024]
Ameya Daigavane and Song Eun Kim and Mario Geiger and Tess Smidt.
[ICLR (2024)](https://openreview.net/forum?id=MIEnYtlGyv) | [code](https://github.com/atomicarchitects/symphony)
* **Autoregressive fragment-based diffusion for pocket-aware ligand design** [2023]
Ghorbani, Mahdi, Leo Gendelev, Paul Beroza, and Michael Keiser.
[NeurIPS 2023 Generative AI and Biology (GenBio) Workshop. (2023)](https://openreview.net/forum?id=E3HN48zjam) | [code](https://github.com/ghorbanimahdi73/autofragdiff)
* **Learning on topological surface and geometric structure for 3D molecular generation** [2023]
Zhang, Odin, Tianyue Wang, Gaoqi Weng, Dejun Jiang, Ning Wang, Xiaorui Wang, Huifeng Zhao et al.
[Nat Comput Sci (2023)](https://doi.org/10.1038/s43588-023-00530-2) | [code](https://github.com/HaotianZhangAI4Science/SurfGen)
* **ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modelling** [2023]
Zhang, O., Zhang, J., Jin, J. et al.
[Nat Mach Intell (2023)](https://doi.org/10.1038/s42256-023-00712-7) | [code](https://github.com/HaotianZhangAI4Science/ResGen)
* **FFLOM: A Flow-Based Autoregressive Model for Fragment-to-Lead Optimization** [2023]
Jieyu Jin, Dong Wang, Guqin Shi, Jingxiao Bao, Jike Wang, Haotian Zhang, Peichen Pan, Dan Li, Xiaojun Yao, Huanxiang Liu, Tingjun Hou, and Yu Kang
[J. Med. Chem. (2023)](https://doi.org/10.1021/acs.jmedchem.3c01009) | [code](https://github.com/JenniferKim09/FFLOM)
* **Domain-Agnostic Molecular Generation with Self-feedback** [2023]
Yin Fang, Ningyu Zhang, Zhuo Chen, Xiaohui Fan, Huajun Chen
[arXiv:2301.11259v3](https://arxiv.org/abs/2301.11259) | [code](https://github.com/zjunlp/MolGen)
* **GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation** [2020]
Shi, C., Xu, M., Zhu, Z., Zhang, W., Zhang, M., & Tang, J.
[ICLR (2020)](https://openreview.net/forum?id=S1esMkHYPr) |[arXiv:2001.09382](https://arxiv.org/abs/2001.09382) | [code](https://github.com/DeepGraphLearning/GraphAF)
### Transformer-based
* **Accelerating discovery of bioactive ligands with pharmacophore-informed generative models** [2025]
Xie, W., Zhang, J., Xie, Q. et al.
[Nat Commun 16, 2391 (2025)](https://doi.org/10.1038/s41467-025-56349-0) | [code](https://github.com/iipharma/transpharmer-repo)
* **3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery** [2025]
Xiuyuan Hu, Guoqing Liu, Can Chen, Yang Zhao, Hao Zhang, Xue Liu.
[arXiv:2502.05107 (2025)](https://arxiv.org/abs/2502.05107) | [code](https://github.com/HXYfighter/3DMolFormer)
* **Molecular optimization using a conditional transformer for reaction-aware compound exploration with reinforcement learning** [2025]
Nakamura, S., Yasuo, N. & Sekijima, M.
[Commun Chem 8, 40 (2025)](https://doi.org/10.1038/s42004-025-01437-x) | [code](https://github.com/sekijima-lab/TRACER)
* **Expanding Chemical Space: Developing a Compound Generative Pre-trained Transformer for De Novo Drug Design** [2025]
Dai Z, Zhang J, Zhong S, Fu J, Deng Y, Zhang D, et al.
[bioRxiv. (2025)](https://doi.org/10.1101/2025.01.24.634665) | [code](https://github.com/Charliefff/CompoundGPT)
* **A Zero-Shot Single-point Molecule Optimization Model: Mimicking Medicinal Chemists’ Expertise** [2025]
Dai Z, Zhang J, Zhong S, Fu J, Deng Y, Zhang D, et al.
[chemrxiv-2025-m82r5 (2025)](https://doi.org/10.26434/chemrxiv-2025-m82r5) | [code](https://github.com/DonaldDai/new_paper_code)
* **Molecular Generation with State Space Sequence Models** [2024]
Anri Lombard, Shane Acton, Ulrich Armel Mbou Sob, Jan Buys.
[NeurIPS 2024 Workshop on AI for New Drug Modalities (2024)](https://openreview.net/forum?id=1ib5oyTQIb) | [code](https://github.com/Anri-Lombard/Mamba-SAFE)
* **3DSMILES-GPT: 3D Molecular Pocket-based Generation with Token-only Large Language Model** [2024]
Wang, Jike, Hao Luo, Rui Qin, Mingyang Wang, Meijing Fang, Odin Zhang, Qiaolin Gou et al.
[Chemical Science (2024)](https://doi.org/10.1039/D4SC06864E) | [code](https://github.com/ashipiling/GPT_3DSMILES)
* **Generative Artificial Intelligence for Navigating Synthesizable Chemical Space** [2024]
Wenhao Gao, Shitong Luo, Connor W. Coley.
[arXiv:2410.03494 (2024)](https://arxiv.org/abs/2410.03494) | [code](https://github.com/wenhao-gao/synformer)
* **Diffusion-based generative drug-like molecular editing with chemical natural language** [2024]
Jianmin Wang, Peng Zhou, Zixu Wang, Wei Long, Yangyang Chen, Kyoung Tai No, Dongsheng Ouyang*，Jiashun Mao* and Xiangxiang Zeng*.
[J. Pharm. Anal. (2024)](https://doi.org/10.1016/j.jpha.2024.101137) | [code](https://github.com/AspirinCode/DiffIUPAC)
* **Leveraging Tree-Transformer VAE with fragment tokenization for high-performance large chemical generative model** [2024]
Inukai T, Yamato A, Akiyama M, Sakakibara Y.
[ChemRxiv. (2024)](https://doi.org/10.26434/chemrxiv-2024-77vhr-v3) | [code](https://github.com/slab-it/FRATTVAE)
* **A deep learning approach for rational ligand generation with toxicity control via reactive building blocks** [2024]
Li, P., Zhang, K., Liu, T. et al.
[Nat Comput Sci (2024)](https://doi.org/10.1038/s43588-024-00718-0) | [code](https://github.com/BioChemAI/DeepBlock)
* **A Foundation Model for Chemical Design and Property Prediction** [2024]
Cai, F., Zhu, T., Tzeng, T.R., Duan, Y., Liu, L., Pilla, S., Li, G. and Luo, F.
[arXiv:2410.21422 (2024)](https://arxiv.org/abs/2410.21422) | [code](https://github.com/TheLuoFengLab/ChemFM)
* **SE(3) Equivariant Topologies for Structure-based Drug Discovery** [2024]
Prat A, Abdel Aty H, Pabrinkis A, Bastas O, Paquet T, Kamuntavičius G, et al.
[ChemRxiv. (2024)](https://doi.org/10.26434/chemrxiv-2024-5q7ts)
* **Graph Diffusion Transformers for Multi-Conditional Molecular Generation** [2024]
Liu, Gang, Jiaxin Xu, Te Luo and Meng Jiang.
[NeurIPS 2024 (Oral). (2024)](https://arxiv.org/abs/2401.13858) | [code](https://github.com/liugangcode/Graph-DiT)
* **Exhaustive local chemical space exploration using a transformer model** [2024]
Tibo, A., He, J., Janet, J.P. et al.
[Nat Commun 15, 7315 (2024)](https://doi.org/10.1038/s41467-024-51672-4) | [code](https://github.com/MolecularAI/exahustive_search_mol2mol)
* **Transformer Graph Variational Autoencoder for Generative Molecular Design** [2024]
Nguyen, Trieu, and Aleksandra Karolak.
[bioRxiv (2024)](https://doi.org/10.1101/2024.07.22.604603)
* **BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning** [2024]
Zholus, Artem, Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Daniil Polykovskiy, Sarath Chandar, and Alex Zhavoronkov.
[arXiv:2406.03686 (2024)](https://arxiv.org/abs/2406.03686)
* **Exploring Novel Fentanyl Analogues Using a Graph-Based Transformer Model** [2024]
Zhang, Guangle, Yuan Zhang, Ling Li, Jiaying Zhou, Honglin Chen, Jinwen Ji, Yanru Li, Yue Cao, Zhihui Xu, and Cong Pian.
[Interdisciplinary Sciences: Computational Life Sciences (2024)](https://doi.org/10.1007/s12539-024-00623-0) | [code](https://github.com/xueyuanyuan0410/fentanyl_data)
* **TenGAN: Pure Transformer Encoders Make an Efficient Discrete GAN for De Novo Molecular Generation** [2024]
Li, Chen, and Yoshihiro Yamanishi.
[ International Conference on Artificial Intelligence and Statistics. PMLR (2024)](https://proceedings.mlr.press/v238/li24d.html)
* **DockingGA: enhancing targeted molecule generation using transformer neural network and genetic algorithm with docking simulation** [2024]
Changnan Gao, Wenjie Bao, Shuang Wang, Jianyang Zheng, Lulu Wang, Yongqi Ren, Linfang Jiao, Jianmin Wang, Xun Wang.
[Briefings in Functional Genomics (2024)](https://doi.org/10.1093/bfgp/elae011) | [code](https://github.com/Chinafor/DockingGA)
* **Gotta be SAFE: A New Framework for Molecular Design** [2024]
Noutahi, Emmanuel, Cristian Gabellini, Michael Craig, Jonathan SC Lim, and Prudencio Tossou.
[Digital Discovery (2024)](https://doi.org/10.1039/D4DD00019F) | [arXiv:2310.10773 (2023)](https://arxiv.org/abs/2310.10773) | [code](https://github.com/datamol-io/safe)
* **Enhancing molecular design efficiency: Uniting language models and generative networks with genetic algorithms** [2024]
Bhowmik, Debsindhu, Pei Zhang, Zachary Fox, Stephan Irle, and John Gounley.
[Patterns (2024)](https://doi.org/10.1016/j.patter.2024.100947) | [code](https://zenodo.org/records/8387351)
* **ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation** [2024]
Kyro, Gregory W., Anton Morgunov, Rafael I. Brent, and Victor S. Batista.
[J. Chem. Inf. Model. (2024)](https://doi.org/10.1021/acs.jcim.3c01456) | [code](https://github.com/batistagroup/ChemSpaceAL)
* **Evaluation of Reinforcement Learning in Transformer-based Molecular Design** [2024]
He J, Tibo A, Janet JP, Nittinger E, Tyrchan C, Czechtizky W, et al.
[chemrxiv-2024-r9ljm (2024)](https://doi.org/10.26434/chemrxiv-2024-r9ljm) | [code](https://github.com/MolecularAI/transformer_rl)
* **Dual-Space Optimization: Improved Molecule Sequence Design by Latent Prompt Transformer** [2024]
Deqian Kong and Yuhao Huang and Jianwen Xie and Edouardo Honig and Ming Xu and Shuanghong Xue and Pei Lin and Sanping Zhou and Sheng Zhong and Nanning Zheng and Ying Nian Wu.
[ arXiv:2402.17179 (2024)](https://arxiv.org/abs/2402.17179)
* **A novel molecule generative model of VAE combined with Transformer** [2024]
Yasuhiro Yoshikai and Tadahaya Mizuno and Shumpei Nemoto and Hiroyuki Kusuhara.
[ arXiv:2402.11950 (2024)](https://arxiv.org/abs/2402.11950) | [code](https://github.com/mizuno-group/TransformerVAE)
* **GexMolGen: Cross-modal Generation of Hit-like Molecules via Large Language Model Encoding of Gene Expression Signatures** [2024]
Cheng, Jia-Bei, Xiaoyong Pan, Kaiyuan Yang, Shenghao Cao, Bin Liu, Qingran Yan, and Ye Yuan.
[bioRxiv (2024)](https://www.biorxiv.org/content/10.1101/2023.11.11.566725v4) | [code](https://github.com/Bunnybeibei/GexMolGen)
* **Local Scaffold Diversity-Contributed Generator for Discovering Potential NLRP3 Inhibitors** [2024]
Weichen Bo, Yangqin Duan, Yurong Zou, Ziyan Ma, Tao Yang, Peng Wang, Tao Guo, Zhiyuan Fu, Jianmin Wang, Linchuan Fan, Jie liu, Taijin Wang, and Lijuan Chen.
[J. Chem. Inf. Model. (2024)](https://doi.org/10.1021/acs.jcim.3c01818) | [code](https://github.com/wichen-2022/LSDC)
* **Target-aware Molecule Generation for Drug Design Using a Chemical Language Model** [2024]
Xia, Yingce, Kehan Wu, Pan Deng, Renhe Liu, Yuan Zhang, Han Guo, Yumeng Cui et al.
[bioRxiv (2024)](https://doi.org/10.1101/2024.01.08.574635)
* **Accelerating Discovery of Novel and Bioactive Ligands With Pharmacophore-Informed Generative Models** [2024]
Xie, Weixin, Jianhang Zhang, Qin Xie, Chaojun Gong, Youjun Xu, Luhua Lai, and Jianfeng Pei.
[arXiv:2401.01059 (2024)](https://arxiv.org/abs/2401.01059) | [code](http://gitlab.iipharma.cn/zhangjh/transpharmer-repo)
* **A self-improvable Polymer Discovery Framework Based on Conditional Generative Model** [2023]
Xiangyun Lei and Weike Ye and Zhenze Yang and Daniel Schweigert and Ha-Kyung Kwon and Arash Khajeh.
[ arXiv:2312.04013. (2023)](https://arxiv.org/abs/2312.04013)
* **LLamol: A Dynamic Multi-Conditional Generative Transformer for De Novo Molecular Design** [2023]
Dobberstein, Niklas, Astrid Maass, and Jan Hamaekers.
[arXiv:2311.14407. (2023)](https://arxiv.org/abs/2311.14407) | [code](https://github.com/Fraunhofer-SCAI/llamol)
* **GraphGPT: A Graph Enhanced Generative Pretrained Transformer for Conditioned Molecular Generation** [2023]
Lu, Hao, Zhiqiang Wei, Xuze Wang, Kun Zhang, and Hao Liu.
[International Journal of Molecular Sciences 24.23 (2023)](https://doi.org/10.3390/ijms242316761) | [code](https://github.com/luhao27/GraphGPT)
* **PROTACable is an Integrative Computational Pipeline of 3-D Modeling and Deep Learning to Automate the De Novo Design of PROTACs** [2023]
Hazem Mslati, Francesco Gentile, Mohit Pandey, Fuqiang Ban, Artem Cherkasov.
[bioRxiv 2023.11.20.567951. (2023)](https://doi.org/10.1101/2023.11.20.567951) | [code](https://github.com/giaguaro/PROTACable)
* **Molecular generation strategy and optimization based on A2C reinforcement learning in de novo drug design** [2023]
Wang, Qian, Zhiqiang Wei, Xiaotong Hu, Zhuoya Wang, Yujie Dong, and Hao Liu.
[Bioinformatics: btad693. (2023)](https://doi.org/10.1093/bioinformatics/btad693) | [code](https://github.com/wq-sunshine/MomdTDSRL)
* **Cross-modal Generation of Hit-like Molecules via Foundation Model Encoding of Gene Expression Signatures** [2023]
Jiabei Cheng, Xiaoyong Pan, Kaiyuan Yang, Shenghao Cao, Bin Liu, Ye Yuan.
[bioRxiv 2023.11.11.566725. (2023)](https://doi.org/10.1101/2023.11.11.566725) | [code](https://github.com/Bunnybeibei/GexMolGen)
* **REINVENT4: Modern AI–Driven Generative Molecule Design** [2023]
Loeffler H, He J, Tibo A, Janet JP, Voronov A, Mervin L, et al.
[chemrxiv-2023-xt65x (2023)](https://doi.org/10.26434/chemrxiv-2023-xt65x) | [code](https://github.com/MolecularAI/REINVENT4)
* **Optimization of binding affinities in chemical space with transformer and deep reinforcement learning** [2023]
Xu, Xiaopeng, Juexiao Zhou, Chen Zhu, Qing Zhan, Zhongxiao Li, Ruochi Zhang, Yu Wang, Xingyu Liao, and Xin Gao.
[chemrxiv-2023-7v4sw (2023)](https://doi.org/10.26434/chemrxiv-2023-7v4sw) | [code](https://github.com/charlesxu90/sgpt)
* **Searching for High-Value Molecules Using Reinforcement Learning and Transformers** [2023]
Raj Ghugare and Santiago Miret and Adriana Hugessen and Mariano Phielipp and Glen Berseth.
[arXiv:2310.02902 (2023)](https://arxiv.org/abs/2310.02902)
* **Molecular De Novo Design through Transformer-based Reinforcement Learning** [2023]
Feng, Tao, Pengcheng Xu, Tianfan Fu, Siddhartha Laghuvarapu, and Jimeng Sun.
[arXiv:2310.05365 (2023)](https://arxiv.org/abs/2310.05365)
* **Probabilistic generative transformer language models for generative design of molecules** [2023]
Wei, L., Fu, N., Song, Y. et al.
[J Cheminform 15, 88 (2023)](https://doi.org/10.1186/s13321-023-00759-z) | [code](https://github.com/usccolumbia/GMTransformer)
* **De Novo Drug Design with Joint Transformers** [2023]
Adam Izdebski and Ewelina Węglarz-Tomczak and Ewa Szczurek and Jakub M. Tomczak
[ arXiv:2310.02066. (2023)](https://arxiv.org/abs/2310.02066)
* **Structured State-Space Sequence Models for De Novo Drug Design** [2023]
Özçelik R, de Ruiter S, Grisoni F.
[chemrxiv-2023-jwmf3. (2023)](https://doi.org/10.26434/chemrxiv-2023-jwmf3) | [code](https://github.com/molML/s4-for-de-novo-drug-design)
* **De Novo Generation of Chemical Structures of Inhibitor and Activator Candidates for Therapeutic Target Proteins by a Transformer-Based Variational Autoencoder and Bayesian Optimization** [2023]
Yuki Matsukiyo, Chikashige Yamanaka, and Yoshihiro Yamanishi.
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.3c00824) | [code](https://yamanishi.cs.i.nagoya-u.ac.jp/triompheboa/)
* **A Reverse-Transformer GAN Generates Scaffold-Constrained Molecules with Property Optimization.** [2023]
Li, C., Yamanishi, Y.
[ECML PKDD (2023)](https://doi.org/10.1007/978-3-031-43412-9_19) | [code](https://github.com/naruto7283/SpotGAN)
* **ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation** [2023]
Kyro, Gregory W., Anton Morgunov, Rafael I. Brent, and Victor S. Batista.
[arXiv:2309.05853 (2023)](https://arxiv.org/abs/2309.05853) | [code](https://github.com/batistagroup/ChemSpaceAL/)
* **Efficient 3D Molecular Design with an E(3) Invariant Transformer VAE** [2023]
Dollar, Orion, Nisarg Joshi, Jim Pfaendtner, and David AC Beck.
[The Journal of Physical Chemistry A (2023)](https://doi.org/10.1021/acs.jpca.3c04188) | [code](https://github.com/oriondollar/vagrant_en)
* **Lingo3DMol: Generation of a Pocket-based 3D Molecule using a Language Model** [2023]
Wang, Lvwei, Zaiyun Lin, Yanhao Zhu, Rong Bai, Wei Feng, Huting Wang, Jielong Zhou, Wei Peng, Bo Huang, and Wenbiao Zhou.
[arXiv:2305.10133 (2023)](https://arxiv.org/abs/2305.10133) | [code](https://github.com/stonewiseAIDrugDesign/Lingo3DMol)
* **FSM-DDTR: End-to-end feedback strategy for multi-objective De Novo drug design using transformers** [2023]
Monteiro, Nelson RC, Tiago O. Pereira, Ana Catarina D. Machado, José L. Oliveira, Maryam Abbasi, and Joel P. Arrais.
[Computers in Biology and Medicine (2023)](https://doi.org/10.1016/j.compbiomed.2023.107285) | [code](https://github.com/larngroup/FSM-DDTR)
* **Macrocyclization of linear molecules by deep learning to facilitate macrocyclic drug candidates discovery** [2023]
Diao, Y., Liu, D., Ge, H. et al.
[Nat Commun 14, 4552 (2023)](https://doi.org/10.1038/s41467-023-40219-8) | [code](https://github.com/yydiao1025/Macformer)
* **De novo drug design based on patient gene expression profiles via deep learning** [2023]
Yamanaka, Chikashige, Shunya Uki, Kazuma Kaitoh, Michio Iwata, and Yoshihiro Yamanishi.
[Molecular Informatics (2023)](https://doi.org/10.1002/minf.202300064) | [code](https://www.dropbox.com/s/vg3nxcio799h4ex/software.zip?dl=0)
* **Transformer-based deep learning method for optimizing ADMET properties of lead compounds** [2023]
Yang, Lijuan, Chao Jin, Guanghui Yang, Zhitong Bing, Liang Huang, Yuzhen Niu, and Lei Yang.
[Physical Chemistry Chemical Physics 25.3 (2023)](https://doi.org/10.1039/D2CP05332B)
* **Sequence-based drug design as a concept in computational drug design** [2023]
Chen, L., Fan, Z., Chang, J. et al.
[Nat Commun 14, 4217 (2023)]( https://doi.org/10.1038/s41467-023-39856-w) | [code](https://github.com/lifanchen-simm/transformerCPI2.0/)
* **DrugGPT: A GPT-based Strategy for Designing Potential Ligands Targeting Specific Proteins** [2023]
Yuesen Li, Chengyi Gao, Xin Song, Xiangyu Wang, View ORCID ProfileYungang Xu, Suxia Han
[bioRxiv (2023)](https://doi.org/10.1101/2023.06.29.543848) | [code](https://github.com/LIYUESEN/druggpt)
* **PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding** [2023]
Gao, Zhangyang, Yuqi Hu, Cheng Tan, and Stan Z. Li.
[arXiv:2302.07120 (2023)](https://arxiv.org/abs/2302.07120) | [code](https://github.com/A4Bio/PrefixMolf)
* **Adaptive language model training for molecular designs** [2023]
Andrew E. Blanchard, Debsindhu Bhowmik, Zachary Fox, John Gounley, Jens Glaser, Belinda S. Akpa & Stephan Irle.
[ J Cheminform 15, 59 (2023)](https://doi.org/10.1186/s13321-023-00719-7) | [code](https://code.ornl.gov/candle/mlmol%20in%20the%20adaptive-lm%20directory)
* **CMGN: a conditional molecular generation net to design target-specific molecules with desired properties** [2023]
Yang, Minjian, Hanyu Sun, Xue Liu, Xi Xue, Yafeng Deng, and Xiaojian Wang.
[Briefings in Bioinformatics, 2023;, bbad185](https://doi.org/10.1093/bib/bbad185) | [code](https://github.com/WJmodels/CMGN)
* **cMolGPT: A Conditional Generative Pre-Trained Transformer for Target-Specific De Novo Molecular Generation** [2023]
Wang, Ye, Honggang Zhao, Simone Sciabola, and Wenlu Wang.
[Molecules 2023, 28(11), 4430](https://doi.org/10.3390/molecules28114430) | [code](https://github.com/VV123/cMolGPT)
* **Molecule generation using transformers and policy gradient reinforcement learning** [2023]
Mazuz, E., Shtar, G., Shapira, B. et al.
[Sci Rep 13, 8799 (2023)](https://doi.org/10.1038/s41598-023-35648-w) | [code](https://github.com/eyalmazuz/MolGen)
* **iupacGPT: IUPAC-based large-scale molecular pre-trained model for property prediction and molecule generation** [2023]
Jiashun Mao,, Jianmin Wang, Kwang-Hwi Cho, Kyoung Tai No
[chemrxiv-2023-5kjvh](https://doi.org/10.26434/chemrxiv-2023-5kjvh) | [code](https://github.com/AspirinCode/iupacGPT)
* **Molecular Generation with Reduced Labeling through Constraint Architecture** [2023]
Wang, Jike, Yundian Zeng, Huiyong Sun, Junmei Wang, Xiaorui Wang, Ruofan Jin, Mingyang Wang et al.
[J. Chem. Inf. Model. (2023)](https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00579) | [code](https://github.com/jkwang93/Frag-G_M)
* **Generative Discovery of Novel Chemical Designs using Diffusion Modeling and Transformer Deep Neural Networks with Application to Deep Eutectic Solvents** [2023]
Luu, Rachel K., Marcin Wysokowski, and Markus J. Buehler.
[arXiv:2304.12400v1](https://arxiv.org/abs/2304.12400) | [code](https://github.com/lamm-mit/MoleculeDiffusionTransformer)
* **Regression Transformer enables concurrent sequence regression and generation for molecular language modelling** [2023]
Born, J., Manica, M.
[Nat Mach Intell 5, 432–444 (2023)](https://doi.org/10.1038/s42256-023-00639-z) | [code](https://github.com/GT4SD/gt4sd-core/tree/main/examples/regression_transformer)
* **Transformer-based molecular generative model for antiviral drug design** [2023]
mao, jiashun; wang, jianming; zeb, amir; Cho, Kwang-Hwi; jin, haiyan; Kim, Jongwan; Lee, Onju; Wang, Yunyun; No, Kyoung Tai.
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.3c00536) | [code](https://github.com/AspirinCode/TransAntivirus)
* **Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks** [2023]
Ünlü, Atabey, Elif Çevrim, Ahmet Sarıgün, Hayriye Çelikbilek, Heval Ataş Güvenilir, Altay Koyaş, Deniz Cansen Kahraman, Ahmet Rifaioğlu, and Abdurrahman Olğaç.
[arXiv:2302.07868v5](https://arxiv.org/abs/2302.07868)
* **DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning** [2023]
Liu, X., Ye, K., van Vlijmen, H.W.T. et al.
[J Cheminform 15, 24 (2023)](https://doi.org/10.1186/s13321-023-00694-z) | [code](https://github.com/CDDLeiden/DrugEx)
* **Explore drug-like space with deep generative models** [2023]
Wang, Jianmin, et al.
[Methods (2023)](https://doi.org/10.1016/j.ymeth.2023.01.004) | [code](https://github.com/AspirinCode/drug-likeness_space)
* **Large-scale chemical language representations capture molecular structure and properties** [2022]
Ross, J., Belgodere, B., Chenthamarakshan, V., Padhi, I., Mroueh, Y., & Das, P.
[Nat Mach Intell 4, 1256–1264 (2022)](https://www.nature.com/articles/s42256-022-00580-7) | [code](https://github.com/IBM/molformer)
* **AlphaDrug: protein target specific de novo molecular generation** [2022]
Qian, Hao, Cheng Lin, Dengwei Zhao, Shikui Tu, and Lei Xu.
[ PNAS Nexus (2022)](https://academic.oup.com/pnasnexus/article/1/4/pgac227/6751929) | [code](https://github.com/CMACH508/AlphaDrug)
* **Can We Quickly Learn to “Translate” Bioactive Molecules with Transformer Models?** [2022]
Bagal, V., Aggarwal, R., Vinod, P. K., & Priyakumar, U. D.
[chemrxiv-2022-gln27](https://doi.org/10.26434/chemrxiv-2022-gln27)
* **MolGPT: Molecular Generation Using a Transformer-Decoder Model** [2022]
Bagal, V., Aggarwal, R., Vinod, P. K., & Priyakumar, U. D.
[J. Chem. Inf. Model. 2022, 62, 9, 2064–2076](https://pubs.acs.org/doi/10.1021/acs.jcim.1c00600) | [code](https://github.com/devalab/molgpt)
* **Tailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design** [2022]
Wu, K., Xia, Y., Fan, Y., Deng, P., Liu, H., Wu, L., ... & Liu, T. Y.
[arXiv.2209.06158](https://arxiv.org/abs/2209.06158) | [code](https://github.com/HankerWu/TamGent)
* **Exploiting pretrained biochemical language models for targeted drug design** [2022]
Uludoğan, Gökçe, Elif Ozkirimli, Kutlu O. Ulgen, Nilgün Karalı, and Arzucan Özgür.
[Bioinformatics (2022)](https://doi.org/10.1093/bioinformatics/btac482) | [code](https://github.com/boun-tabi/biochemical-lms-for-drug-design)
* **A Transformer-based Generative Model for De Novo Molecular Design** [2022]
Wang, Wenlu, et al.
[arXiv:2210.08749v2](https://arxiv.org/abs/2210.08749)
* **Translation between Molecules and Natural Language** [2022]
Edwards, C., Lai, T., Ros, K., Honke, G., & Ji, H.
[arXiv:2204.11817v3](https://arxiv.org/abs/2204.11817) | [code](https://github.com/blender-nlp/MolT5)
* **Regression Transformer enables concurrent sequence regression and generation for molecular language modeling** [2022]
Born, Jannis and Manica, Matteo
[arXiv:2202.01338v3](https://arxiv.org/abs/2202.01338) | [code](https://github.com/IBM/regression-transformer)
* **Generative Pre-Training from Molecules** [2021]
Adilov, Sanjar.
[J. Chem. Inf. Model. 2022, 62, 9, 2064–2076](https://pubs.acs.org/doi/10.1021/acs.jcim.1c00600) | [code](https://github.com/sanjaradylov/smiles-gpt)
* **Transformers for Molecular Graph Generation** [2021]
Cofala, Tim, and Oliver Kramer.
[ESANN 2021 ](https://www.esann.org/sites/default/files/proceedings/2021/ES2021-112.pdf) | [code](https://gitlab.uni-oldenburg.de/gies6280/molegent)
* **Spatial Generation of Molecules with Transformers** [2021]
Cofala, Tim, and Oliver Kramer.
[IJCNN52387.2021.9533439 (2021)](https://ieeexplore.ieee.org/abstract/document/9533439) | [code](https://gitlab.uni-oldenburg.de/gies6280/molegent)
* **Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attentio** [2021]
Hyunseung Kim, Jonggeol Na*, and Won Bo Lee*.
[J. Chem. Inf. Model. 2021, 61, 12, 5804–5814](https://pubs.acs.org/doi/abs/10.1021/acs.jcim.1c01289) | [code](https://github.com/Hyunseung-Kim/molGCT)
* **C5T5: Controllable Generation of Organic Molecules with Transformer** [2021]
Rothchild, D., Tamkin, A., Yu, J., Misra, U., & Gonzalez, J.
[arXiv:2108.10307v1](https://arxiv.org/abs/2108.10307) | [code](https://github.com/dhroth/c5t5)
* **Molecular optimization by capturing chemist’s intuition using deep neural networks** [2021]
He, J., You, H., Sandström, E. et al.
[J Cheminform 13, 26 (2021)](https://doi.org/10.1186/s13321-021-00497-0) | [code](https://github.com/MolecularAI/deep-molecular-optimization)
* **Transformer neural network for protein-specific de novo drug generation as a machine translation problem** [2021]
Grechishnikova, Daria.
[Sci Rep 11, 321 (2021)](https://www.nature.com/articles/s41598-020-79682-4) | [code](https://github.com/dariagrechishnikova/molecule_structure_generation)
* **Transmol: repurposing a language model for molecular generation** [2021]
Grechishnikova, Daria.
[RSC advances. 2021;11(42):25921-32.](https://pubs.rsc.org/en/content/articlelanding/2021/ra/d1ra03086h) | [code](https://gitlab.com/cheml.io/public/transmol)
* **Attention-based generative models for de novo molecular design** [2021]
Dollar, O., Joshi, N., Beck, D.A. and Pfaendtner, J.,
[Chemical Science 12.24 (2021)](https://pubs.rsc.org/en/content/articlelanding/2021/sc/d1sc01050f) | [code](https://github.com/oriondollar/TransVAE)
### VAE-based
* **MolGene-E: Inverse Molecular Design to Modulate Single Cell Transcriptomics** [2025]
Rahul Ohlan, Raswanth Murugan, Li Xie, Mohammedsadeq Mottaqi, Shuo Zhang, Lei Xie.
[bioRxiv. (2025)](https://doi.org/10.1101/2025.02.19.638723) | [code](https://zenodo.org/records/7041849)
* **Leveraging Tree-Transformer VAE with fragment tokenization for high-performance large chemical generative model** [2024]
Inukai T, Yamato A, Akiyama M, Sakakibara Y.
[ChemRxiv. (2024)](https://doi.org/10.26434/chemrxiv-2024-77vhr-v3) | [code](https://github.com/slab-it/FRATTVAE)
* **Transformer Graph Variational Autoencoder for Generative Molecular Design** [2024]
Nguyen, Trieu, and Aleksandra Karolak.
[bioRxiv (2024)](https://doi.org/10.1101/2024.07.22.604603)
* **Structure-Based Drug Design with a Deep Hierarchical Generative Model** [2024]
Weller, Jesse A., and Remo Rohs.
[J. Chem. Inf. Model. (2024)](https://pubs.acs.org/doi/full/10.1021/acs.jcim.4c01193) | [code](https://github.com/jssweller/DrugHIVE)
* **Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design** [2024]
Abeer, A. N. M., Sanket Jantre, Nathan M. Urban, and Byung-Jun Yoon.
[arXiv:2405.00202 (2024)](https://arxiv.org/abs/2405.00202)
* **GxVAEs: Two Joint VAEs Generate Hit Molecules from Gene Expression Profiles** [2024]
Li, Chen, and Yoshihiro Yamanishi.
[Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 12. (2024)](https://doi.org/10.1609/aaai.v38i12.29248) | [code](https://github.com/naruto7283/GxVAEs)
* **3D molecular generative framework for interaction-guided drug design** [2024]
Zhung, W., Kim, H. & Kim, W.Y.
[Nat Commun 15, 2688 (2024)](https://doi.org/10.1038/s41467-024-47011-2) | [code](https://github.com/ACE-KAIST/DeepICL)
* **Attention Based Molecule Generation via Hierarchical Variational Autoencoder** [2024]
Divahar Sivanesan.
[ arXiv:2402.16854. (2024)](https://arxiv.org/abs/2402.16854)
* **A novel molecule generative model of VAE combined with Transformer** [2024]
Yasuhiro Yoshikai and Tadahaya Mizuno and Shumpei Nemoto and Hiroyuki Kusuhara.
[ arXiv:2402.11950 (2024)](https://arxiv.org/abs/2402.11950) | [code](https://github.com/mizuno-group/TransformerVAE)
* **De Novo Generation and Identification of Novel Compounds with Drug Efficacy Based on Machine Learning** [2024]
He, Dakuo, Qing Liu, Yan Mi, Qingqi Meng, Libin Xu, Chunyu Hou, Jinpeng Wang et al.
[Advanced Science (2024)](https://doi.org/10.1002/advs.202307245)
* **Computational Drug Discovery on HIV Virus with a Customized LSTM Variational Autoencoder Deep Learning Architecture** [2023]
Kutsal, Mucahit, Ferhat Ucar, and Nida Kati.
[CPT: Pharmacometrics & Systems Pharmacology. (2023)](https://doi.org/10.1002/psp4.13085) | [code](https://github.com/McahitKutsal/lstm-drug-discovery)
* **NRC-VABS: Normalized Reparameterized Conditional Variational Autoencoder with applied beam search in latent space for drug molecule design** [2023]
Bhadwal, Arun Singh, Kamal Kumar, and Neeraj Kumar.
[Expert Systems with Applications. (2023)](https://doi.org/10.1016/j.eswa.2023.122396)
* **Target-Aware Variational Auto-Encoders for Ligand Generation with Multi-Modal Protein Modeling** [2023]
Ngo, Khang, and Truong Son Hy.
[NeurIPS 2023 Generative AI and Biology (GenBio) Workshop. (2023)](https://openreview.net/forum?id=4k926QVVM4) | [code](https://github.com/HySonLab/Ligand_Generation)
* **Interaction-aware 3D Molecular Generative Framework for Generalizable Structure-based Drug Design** [2023]
Woo Youn Kim, Wonho Zhung, and Hyeongwoo Kim.
[Research Square. (2023)](https://www.researchsquare.com/article/rs-3388359/v1) | [code](https://github.com/ACE-KAIST/DeepICL)
* **Application of variational graph encoders as an effective generalist algorithm in computer-aided drug design** [2023]
Lam, H.Y.I., Pincket, R., Han, H. et al.
[Nat Mach Intell 5, 754–764 (2023)](https://doi.org/10.1038/s42256-023-00683-9) | [code](https://github.com/Chokyotager/NotYetAnotherNightshade)
* **De Novo Generation of Chemical Structures of Inhibitor and Activator Candidates for Therapeutic Target Proteins by a Transformer-Based Variational Autoencoder and Bayesian Optimization** [2023]
Yuki Matsukiyo, Chikashige Yamanaka, and Yoshihiro Yamanishi.
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.3c00824) | [code](https://yamanishi.cs.i.nagoya-u.ac.jp/triompheboa/)
* **ReBADD-SE: Multi-objective molecular optimisation using SELFIES fragment and off-policy self-critical sequence training** [2023]
Choi, Jonghwan, Sangmin Seo, Seungyeon Choi, Shengmin Piao, Chihyun Park, Sung Jin Ryu, Byung Ju Kim, and Sanghyun Park.
[Computers in Biology and Medicine 157 (2023)](https://doi.org/10.1016/j.compbiomed.2023.106721) | [code](https://github.com/mathcom/ReBADD-SE)
* **Efficient 3D Molecular Design with an E(3) Invariant Transformer VAE** [2023]
Dollar, Orion, Nisarg Joshi, Jim Pfaendtner, and David AC Beck.
[The Journal of Physical Chemistry A (2023)](https://doi.org/10.1021/acs.jpca.3c04188) | [code](https://github.com/oriondollar/vagrant_en)
* **Multi-constraint molecular generation using sparsely labelled training data for localized high-concentration electrolyte diluent screening** [2023]
Mailoa, Jonathan P., Xin Li, Jiezhong Qiu, and Shengyu Zhang.
[Digital Discovery (2023)](https://doi.org/10.1039/D3DD00064H) | [code](https://github.com/jpmailoa/ConGen) | [Dataset](https://github.com/jpmailoa/ConGen_Dataset)
* **Multi-objective Molecular Optimization for Opioid Use Disorder Treatment Using Generative Network Complex** [2023]
Feng, Hongsong, Rui Wang, Chang-Guo Zhan, and Guo-Wei Wei.
[J. Med. Chem. (2023)](https://doi.org/10.1021/acs.jmedchem.3c01053) | [code](https://weilab.math.msu.edu/DataLibrary/2D/)
* **ScaffoldGVAE: Scaffold Generation and Hopping of Drug Molecules via a Variational Autoencoder Based on Multi-View Graph Neural Networks** [2023]
Hu, Chao, Song Li, Chenxing Yang, Jun Chen, Yi Xiong, Guisheng Fan, Hao Liu, and Liang Hong.
[J Cheminform 15, 91 (2023)](https://doi.org/10.1186/s13321-023-00766-0) | [Research Square. (2023)](https://www.researchsquare.com/article/rs-3254116/v1) | [code](https://github.com/ecust-hc/ScaffoldGVAE)
* **Deep Generative Design of Porous Organic Cages via a Variational Autoencoder** [2023]
Jiajun Zhou, Austin Mroz, Kim Jelfs*.
[chemrxiv (2023)](https://doi.org/10.26434/chemrxiv-2023-ggnz0) | [code](https://github.com/JiajunZhou96/Cage-VAE)
* **Target-aware Variational Auto-encoders for Ligand Generation with Multimodal Protein Representation Learning** [2023]
Nhat Khang Ngo, Truong Son Hy.
[bioRxiv. (2023)](https://doi.org/10.1101/2023.08.10.552868) | [code](https://github.com/HySonLab/Ligand_Generation)
* **De Novo Design of κ-Opioid Receptor Antagonists Using a Generative Deep-Learning Framework** [2023]
Salas-Estrada, Leslie, Davide Provasi, Xing Qiu, H. Umit Kaniskan, Xi-Ping Huang, Jeffrey DiBerto, Joao Marcelo Lamim Ribeiro, Jian Jin, Bryan L. Roth, and Marta Filizola.
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.3c00651) | [code](https://github.com/insilicomedicine/GENTRL)
* **Deep generative model of constructing chemical latent space for large molecular structures with 3D complexity** [2023]
Ochiai, Toshiki, Tensei Inukai, Manato Akiyama, Kairi Furui, Masahito Ohue, Nobuaki Matsumori, Shinsuke Inuki et al.
[Commun Chem 6, 249 (2023)](https://doi.org/10.1038/s42004-023-01054-6) | [chemrxiv (2023)](https://doi.org/10.26434/chemrxiv-2023-pjl0w-v2) | [code](https://github.com/toshikiochiai/NPVAE)
* **De novo drug design based on patient gene expression profiles via deep learning** [2023]
Yamanaka, Chikashige, Shunya Uki, Kazuma Kaitoh, Michio Iwata, and Yoshihiro Yamanishi.
[Molecular Informatics (2023)](https://doi.org/10.1002/minf.202300064) | [code](https://www.dropbox.com/s/vg3nxcio799h4ex/software.zip?dl=0)
* **Construction of order-independent molecular fragments space with vector quantised graph autoencoder** [2023]
Akhmetshin, Timur and Lin, Albert and Madzhidov, Timur and Varnek, Alexandre
[chemrxiv-2023-5zmvw](https://doi.org/10.26434/chemrxiv-2023-5zmvw) | [code](https://github.com/Laboratoire-de-Chemoinformatique/VQGAE)
* **De Novo Design of κ-Opioid Receptor Antagonists Using a Generative Deep Learning Framework** [2023]
Salas-Estrada, Leslie, Davide Provasi, Xing Qiu, H. Umit Kaniskan, Xi-Ping Huang, Jeffrey DiBerto, Joao Marcelo Lamim Ribeiro, Jian Jin, Bryan L. Roth, and Marta Filizola.
[bioRxiv (2023)](https://doi.org/10.1101/2023.04.25.537995) | [code](https://github.com/insilicomedicine/GENTRL)
* **De Novo Design of Molecules with Multiaction Potential from Differential Gene Expression using Variational Autoencoder** [2023]
Salas-Estrada, Leslie, Davide Provasi, Xing Qiu, H. Umit Kaniskan, Xi-Ping Huang, Jeffrey DiBerto, Joao Marcelo Lamim Ribeiro, Jian Jin, Bryan L. Roth, and Marta Filizola.
[bioRxiv (2023)](https://doi.org/10.1101/2023.04.25.537995) | [code](https://github.com/insilicomedicine/GENTRL)
* **De Novo Design of Molecules with Multiaction Potential from Differential Gene Expression using Variational Autoencoder** [2023]
Pravalphruekul, Nutaya, Maytus Piriyajitakonkij, Phond Phunchongharn, and Supanida Piyayotai.
[J. Chem. Inf. Model. (2023)](https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00355) | [code](https://github.com/ChemEXL/BiCEV)
* **Chemical Design with GPU-based Ising Machine** [2023]
Mao, Zetian, Yoshiki Matsuda, Ryo Tamura, and Koji Tsuda.
[Digital Discovery (2023)](https://doi.org/10.1039/D3DD00047H) | [code](https://github.com/tsudalab/bVAE-IM)
* **Accelerating drug target inhibitor discovery with a deep generative foundation model** [2023]
Vijil Chenthamarakshan et al.
[Sci. Adv.9,eadg7865(2023)](https://www.science.org/doi/10.1126/sciadv.adg7865) | [code](https://zenodo.org/record/7863805)
* **De Novo Design of Molecules with Multiaction Potential from Differential Gene Expression using Variational Autoencoder** [2023]
Nutaya Pravalphruekul, Maytus Piriyajitakonkij, Phond Phunchongharn, and Supanida Piyayotai.
[J. Chem. Inf. Model. 2023](https://doi.org/10.1021/acs.jcim.3c00355) | [code](https://github.com/ChemEXL/BiCEV)
* **A Protein-Ligand Interaction-focused 3D Molecular Generative Framework for Generalizable Structure-based Drug Design** [2023]
Zhung W, Kim H, Kim WY.
[chemrxiv-2023-jsjwx](https://doi.org/10.26434/chemrxiv-2023-jsjwx) | [code](https://github.com/ACE-KAIST/DeepICL)
* **VGAE-MCTS: a New Molecular Generative Model combining Variational Graph Auto-Encoder and Monte Carlo Tree Search** [2023]
Iwata, Hiroaki, Taichi Nakai, Takuto Koyama, Shigeyuki Matsumoto, Ryosuke Kojima, and Yasushi Okuno.
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.3c01220) | [chemrxiv-2023-q8419-v2](https://doi.org/10.26434/chemrxiv-2023-q8419-v2) | [code](https://github.com/clinfo/VGAE-MCTS)
* **Deep Generation Model Guided by the Docking Score for Active Molecular Design** [2023]
Yang, Yuwei, Chang-Yu Hsieh, Yu Kang, Tingjun Hou, Huanxiang Liu, and Xiaojun Yao.
[J. Chem. Inf. Model. 2023, 63, 10, 2983–2991](https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00572) | [code](https://github.com/jaechanglim/CVAE)
* **Direct De Novo Molecule Generation Using Probabilistic Diverse Variational Autoencoder** [2023]
Singh Bhadwal, Arun, and Kamal Kumar.
[Computer Vision and Machine Intelligence. Lecture Notes in Networks and Systems, vol 586. Springer (2023)](https://link.springer.com/chapter/10.1007/978-981-19-7867-8_2)
* **MoVAE: A Variational AutoEncoder for Molecular Graph Generation** [2023]
Lin, Zerun, Yuhan Zhang, Lixin Duan, Le Ou-Yang, and Peilin Zhao.
[Society for Industrial and Applied Mathematics, 2023.](https://doi.org/10.1137/1.9781611977653.ch58)
* **Gex2SGen: Designing Drug-like Molecules from Desired Gene Expression Signatures** [2023]
Das, Dibyajyoti, Broto Chakrabarty, Rajgopal Srinivasan, and Arijit Roy.
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.2c01301)
* **COMA: efficient structure-constrained molecular generation using contractive and margin losses** [2023]
Choi, J., Seo, S. & Park, S.
[J Cheminform 15, 8 (2023)](https://doi.org/10.1186/s13321-023-00679-y) | [code](https://github.com/mathcom/COMA)
* **Design of potent antimalarials with generative chemistry** [2022]
Godinez, W.J., Ma, E.J., Chao, A.T. et al.
[Nat Mach Intell 4, 180–186 (2022)](https://doi.org/10.1038/s42256-022-00448-w) | [code](https://github.com/Novartis/JAEGER)
* **Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders** [2022]
Stanton, S., Maddox, W., Gruver, N., Maffettone, P., Delaney, E., Greenside, P., & Wilson, A. G.
[PMLR 162:20459-20478, 2022](https://arxiv.org/abs/2203.12742)
* **Conditional β-VAE for De Novo Molecular Generation** [2022]
Richards, Ryan J., and Austen M. Groener.
[arXiv:2205.01592v1 ](https://arxiv.org/abs/2205.01592)
* **MGCVAE: Multi-Objective Inverse Design via Molecular Graph Conditional Variational Autoencoder** [2022]
Lee, Myeonghun, and Kyoungmin Min.
[J. Chem. Inf. Model. 2022, 62, 12, 2943–2950](https://pubs.acs.org/doi/10.1021/acs.jcim.2c00487) | [code](https://github.com/mhlee216/MGCVAE)
* **RELATION: A Deep Generative Model for Structure-Based De Novo Drug Design** [2022]
Wang, M., Hsieh, C.Y., Wang, J., Wang, D., Weng, G., Shen, C., Yao, X., Bing, Z., Li, H., Cao, D. and Hou, T.,
[J. Med. Chem. 2022, 65, 13, 9478–9492](https://pubs.acs.org/doi/10.1021/acs.jmedchem.2c00732) | [code](https://github.com/micahwang/RELATION)
* **3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design** [2022]
Huang, Yinan, Xingang Peng, Jianzhu Ma, and Muhan Zhang.
[Paper]https://arxiv.org/abs/2205.07309) | [code](https://github.com/GraphPKU/3DLinker)
* **Molecule Generation by Principal Subgraph Mining and Assembling** [2022]
Kong, X., Huang, W., Tan, Z., & Liu, Y.
[NeurIPS 2022](https://openreview.net/forum?id=ATfARCRmM-a) |[arXiv:2106.15098v4](https://arxiv.org/abs/2106.15098) | [code](https://github.com/THUNLP-MT/PS-VAE)
* **LIMO: Latent Inceptionism for Targeted Molecule Generation** [2022]
Eckmann, Peter, Kunyang Sun, Bo Zhao, Mudong Feng, Michael K. Gilson, and Rose Yu.
[ICML (2022)](https://proceedings.mlr.press/v162/eckmann22a/eckmann22a.pdf) | [arXiv:2206.09010v1](https://arxiv.org/abs/2206.09010) | [code](https://github.com/rose-stl-lab/limo)
* **Predicting chemical structure using reinforcement learning with a stack-augmented conditional variational autoencoder** [2022]
Kim, H., Ko, S., Kim, B.J. *et al.*
[J Cheminform 14, 83 (2022)](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-022-00666-9) | [code](https://github.com/HwanheeKim813/stack_CVAE)
* **Geometry-Based Molecular Generation With Deep Constrained Variational Autoencoder** [2022]
Li, Chunyan, Junfeng Yao, Wei Wei, Zhangming Niu, Xiangxiang Zeng, Jin Li, and Jianmin Wang.
[IEEE Transactions on Neural Networks and Learning Systems (2022)](https://ieeexplore.ieee.org/abstract/document/9714718) | [code](https://github.com/anny0316/GEOM-CVAE)
* **High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning** [2021]
Grosnit, A., Tutunov, R., Maraval, A.M., Griffiths, R-R., Cowen-Rivers, A.I. et al.
[arXiv:2106.03609v3](https://arxiv.org/abs/2106.03609) | [code](https://github.com/huawei-noah/HEBO/tree/master/T-LBO)
* **Inverse design of nanoporous crystalline reticular materials with deep generative models.** [2021]
Yao, Z., Sánchez-Lengeling, B., Bobbitt, N.S. et al.
[Nat Mach Intell 3, 76–86 (2021)](https://doi.org/10.1038/s42256-020-00271-1) | [code](https://github.com/zhenpengyao/Supramolecular_VAE)
* **Attention-based generative models for de novo molecular design** [2021]
Dollar, O., Joshi, N., Beck, D.A. and Pfaendtner, J.,
[Chemical Science 12.24 (2021)](https://pubs.rsc.org/en/content/articlelanding/2021/sc/d1sc01050f) | [code](https://github.com/oriondollar/TransVAE)
* **Toward efficient generation, correction, and properties control of unique drug-like structures** [2021]
Druchok, Maksym, Dzvenymyra Yarish, Oleksandr Gurbych, and Mykola Maksymenko.
[Journal of Computational Chemistry 42.11 (2021)](https://onlinelibrary.wiley.com/doi/10.1002/jcc.26494) | [code](https://github.com/SoftServeInc/novel-molecule-generation)
* **Compressed graph representation for scalable molecular graph generation** [2020]
Kwon, Youngchun, Dongseon Lee, Youn-Suk Choi, Kyoham Shin, and Seokho Kang.
[J Cheminform 12, 58 (2020)](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-020-00463-2) | [code](https://github.com/seokhokang/graphvae_compress)
* **Deep learning enables rapid identification of potent DDR1 kinase inhibitors** [2019]
Zhavoronkov, A., Ivanenkov, Y.A., Aliper, A. et al.
[Nat Biotechnol 37, 1038–1040 (2019)](https://doi.org/10.1038/s41587-019-0224-x) | [code](https://github.com/insilicomedicine/gentrl)
* **Fragment Graphical Variational AutoEncoding for Screening Molecules with Small Data** [2019]
Armitage, John, Leszek J. Spalek, Malgorzata Nguyen, Mark Nikolka, Ian E. Jacobs, Lorena Marañón, Iyad Nasrallah et al.
[arXiv:1910.13325v2](https://arxiv.org/abs/1910.13325) | [code](https://github.com/OE-FET/FraGVAE)
* **Molecular generative model based on conditional variational autoencoder for de novo molecular design** [2018]
Lim, J., Ryu, S., Kim, J. W., & Kim, W. Y.
[J Cheminform 10, 31 (2018)](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-018-0286-7) | [code](https://github.com/jaechanglim/CVAE)
* **Constrained Bayesian optimization for automatic chemical design using variational autoencoders** [2017]
Griffiths, R-R., Hernández-Lobato, J. M.
[Chemical Science 11, 2 (2020)](https://pubs.rsc.org/en/content/articlehtml/2019/sc/c9sc04026a) | [arXiv:1709.05501v6](https://arxiv.org/abs/1709.05501) | [code](https://github.com/Ryan-Rhys/Constrained-Bayesian-Optimisation-for-Automatic-Chemical-Design)
* **Automatic chemical design using a data-driven continuous representation of molecules** [2017]
Gómez-Bombarelli, R., Wei, J. N., Duvenaud, D., Hernández-Lobato, J. M., Sánchez-Lengeling, B., Sheberla, D., ... & Aspuru-Guzik, A.
[ACS Cent. Sci. 2018](https://pubs.acs.org/doi/10.1021/acscentsci.7b00572) | [arXiv:1610.02415v3](https://arxiv.org/abs/1610.02415) | [code](https://github.com/tuantla80/VAE-Molecular-Generation)
### GAN-based
* **Interface-aware molecular generative framework for protein-protein interaction modulators** [2024]
Jianmin Wang, Jiashun Mao, Chunyan Li, Hongxin Xiang, Xun Wang, Shuang Wang, Zixu Wang, Yangyang Chen, Yuquan Li, Heqi Sun, Kyoung Tai No, Tao Song, Xiangxiang Zeng
[J. Cheminform. (2024)](https://doi.org/10.1186/s13321-024-00930-0) | [bioRxiv (2023)](https://doi.org/10.1101/2023.10.10.557742) | [code](https://github.com/AspirinCode/GENiPPI)
* **TenGAN: Pure Transformer Encoders Make an Efficient Discrete GAN for De Novo Molecular Generation** [2024]
Li, Chen, and Yoshihiro Yamanishi.
[ International Conference on Artificial Intelligence and Statistics. PMLR (2024)](https://proceedings.mlr.press/v238/li24d.html)
* **Enhancing molecular design efficiency: Uniting language models and generative networks with genetic algorithms** [2024]
Bhowmik, Debsindhu, Pei Zhang, Zachary Fox, Stephan Irle, and John Gounley.
[Patterns (2024)](https://doi.org/10.1016/j.patter.2024.100947) | [code](https://zenodo.org/records/8387351)
* **Automated Generation and Analysis of Molecular Images Using Generative Artificial Intelligence Models** [2024]
Zhiwen Zhu, Jiayi Lu, Shaoxuan Yuan, Yu He, Fengru Zheng, Hao Jiang, Yuyi Yan, Qiang Sun.
[J. Phys. Chem. Lett. (2024)](https://doi.org/10.1021/acs.jpclett.3c03504)
* **De Novo Molecule Design Towards Biased Properties via a Deep Generative Framework and Iterative Transfer Learning** [2024]
Sattari, Kianoosh, Dawei Li, Bhupalee Kalita, Yunchao Xie, Fatemeh Barmaleki Lighvan, Olexandr Isayev, and Jian Lin.
[Digital Discovery (2024)](https://pubs.rsc.org/en/content/articlehtml/2024/dd/d3dd00210a) | [code](https://github.com/linresearchgroup/RRCGAN_Molecules_Ehl)
* **STAGAN: An approach for improve the stability of molecular graph generation based on generative adversarial networks** [2023]
Zou, Jinping, Jialin Yu, Pengwei Hu, Long Zhao, and Shaoping Shi.
[Computers in Biology and Medicine (2023)](https://doi.org/10.1016/j.compbiomed.2023.107691) | [code](https://github.com/JinPing1025/STAGAN)
* **A Reverse-Transformer GAN Generates Scaffold-Constrained Molecules with Property Optimization.** [2023]
Li, C., Yamanishi, Y.
[ECML PKDD (2023)](https://doi.org/10.1007/978-3-031-43412-9_19) | [code](https://github.com/naruto7283/SpotGAN)
* **Mol-Zero-GAN: Zero-Shot Adaptation of Molecular Generative Adversarial Network for Specific Protein Targets** [2023]
Ravipas Aphikulvanich*， Natapol Pornputtapong， Duangdao Wichadakul
[Paper](https://doi.org/10.26434/chemrxiv-2023-lv2m1) | [code](https://github.com/cucpbioinfo/Mol-Zero-GAN)
* **De Novo Design of Molecules Towards Biased Properties via a Deep Generative Framework and Iterative Transfer Learning** [2023]
Sattari, Kianoosh, Dawei Li, Yunchao Xie, Olexandr Isayev, and Jian Lin.
[Paper](https://doi.org/10.26434/chemrxiv-2023-0zv2f-v2) | [code](https://github.com/linresearchgroup/RRCGAN_Molecules)
* **MolFilterGAN: a progressively augmented generative adversarial network for triaging AI-designed molecules** [2023]
Liu, X., Zhang, W., Tong, X. et al.
[J Cheminform 15, 42 (2023)](https://doi.org/10.1186/s13321-023-00711-1) | [code](https://github.com/MolFilterGAN/MolFilterGAN)
* **Deep generative model for drug design from protein target sequence** [2023]
Yangyang Chen, Zixu Wang, Lei Wang, Jianmin Wang, Pengyong Li, Dongsheng Cao, Xiangxiang Zeng, Xiucai Ye & Tetsuya Sakurai.
[J Cheminform 15, 38 (2023)](https://doi.org/10.1186/s13321-023-00702-2) | [code](https://github.com/viko-3/TargetGAN)
* **Cell morphology-guided de novo hit design by conditioning GANs on phenotypic image features** [2022]
Zapata, Paula A. Marin, Oscar Méndez-Lucio, Tuan Le, Carsten Jörn Beese, Jörg Wichard, David Rouquié, and Djork-Arné Clevert.
[Digital Discovery (2023)](https://doi.org/10.1039/D2DD00081D) | [code](https://github.com/Bayer-Group/CPMolGAN)
* **Generating 3D molecules conditional on receptor binding sites with deep generative models** [2022]
Ragoza, Matthew, Tomohide Masuda, and David Ryan Koes.
[Chemical science. 2022;13(9):2701-13.](https://pubs.rsc.org/en/content/articlelanding/2022/sc/d1sc05976a) | [code](https://github.com/mattragoza/liGAN)
* **Designing optimized drug candidates with Generative Adversarial Network** [2022]
Abbasi, M., Santos, B.P., Pereira, T.C. et al.
[J Cheminform 14, 40 (2022)](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-022-00623-6) | [code](https://github.com/larngroup/GAN-Drug-Generator)
* **De novo molecular design with deep molecular generative models for PPI inhibitors** [2022]
Jianmin Wang, Yanyi Chu, Jiashun Mao, Hyeon-Nae Jeon, Haiyan Jin, Amir Zeb, Yuil Jang, Kwang-Hwi Cho, Tao Song, Kyoung Tai No.
[Briefings in Bioinformatics,July 2022, bbac285,](https://doi.org/10.1093/bib/bbac285) | [code](https://github.com/AspirinCode/iPPIGAN)
* **Improvement on Generative Adversarial Network for Targeted Drug Design** [2021]
Santos, B. P., Abbasi, M., Pereira, T., Ribeiro, B., & Arrais, J.
[ESANN.(2021)](https://www.cisuc.uc.pt/download-file/16987/IR5glkL7JLe3EZrI59BI)
* **Generative Adversarial Networks for De Novo Molecular Design** [2021]
Lee, Y.J., Kahng, H. and Kim, S.B.,
[Molecular Informatics 40.10 (2021)](https://doi.org/10.1002/minf.202100045) | [code](https://github.com/dudwojae/SMILES-MaskGAN)
* **De-novo generation of novel phenotypically active molecules for Chagas disease from biological signatures using AI-driven generative chemistry** [2021]
Pikusa, Michal, Olivier René, Sarah Williams, Yen-Liang Chen, Eric Martin, William J. Godinez, Srinivasa PS Rao, W. Armand Guiguemde, and Florian Nigsch.
[bioRxiv (2021)](https://www.biorxiv.org/content/10.1101/2021.12.10.472084v1) | [code](https://github.com/Novartis/pqsar2cpd)
* **Mol-CycleGAN: a generative model for molecular optimization** [2020]
Maziarka, Łukasz, Agnieszka Pocha, Jan Kaczmarczyk, Krzysztof Rataj, Tomasz Danel, and Michał Warchoł
[J Cheminform 12, 2 (2020)](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-019-0404-1) | [code](https://github.com/ardigen/mol-cycle-gan)
* **MolGAN: An implicit generative model for small molecular graph** [2018]
De Cao, N. and Kipf, T.,
[arXiv:1805.11973 (2018)](https://arxiv.org/abs/1805.11973) | [code](https://github.com/yongqyu/MolGAN-pytorch)
* **Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models** [2017]
Guimaraes, G.L., Sanchez-Lengeling, B., Outeiral, C., Farias, P.L.C. and Aspuru-Guzik, A.,
[ arXiv:1705.10843 (2017)](https://arxiv.org/abs/1705.10843) | [code](https://github.com/gablg1/ORGAN)
### Flow-based
* **Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows** [2025]
Xiangxin Zhou, Yi Xiao, Haowei Lin, Xinheng He, Jiaqi Guan, Yang Wang, Qiang Liu, Feng Zhou, Liang Wang, Jianzhu Ma.
[ICLR (2025)](https://arxiv.org/abs/2503.03989)
* **SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching** [2025]
Ross Irwin, Alessandro Tibo, Jon Paul Janet, Simon Olsson.
[arXiv:2406.07266 (2025)](https://arxiv.org/abs/2406.07266)
* **FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling** [2024]
Zaixi Zhang, Mengdi Wang, Qi Liu.
[arXiv:2409.19645 (2024)](https://arxiv.org/abs/2409.19645)
* **Cell Morphology-Guided Small Molecule Generation with GFlowNets** [2024]
Lu, Stephen Zhewen, Ziqing Lu, Ehsan Hajiramezanali, Tommaso Biancalani, Yoshua Bengio, Gabriele Scalia, and Michał Koziarski.
[ ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling (2024)](https://openreview.net/forum?id=KmSlN13Xk3)
* **Efficient 3D Molecular Generation with Flow Matching and Scale Optimal Transport** [2024]
Irwin, Ross, Alessandro Tibo, Jon-Paul Janet, and Simon Olsson.
[ arXiv:2406.07266 (2024)](https://arxiv.org/abs/2406.07266)
* **RGFN: Synthesizable Molecular Generation Using GFlowNets** [2024]
Koziarski, Michal, Andrei Rekesh, Dmytro Shevchuk, Almer van der Sloot, Piotr Gai'nski, Yoshua Bengio, Cheng-Hao Liu, Mike Tyers and Robert A. Batey.
[ arXiv:2406.08506 (2024)](https://arxiv.org/abs/2406.08506)
* **Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generation** [2024]
Dunn, Ian, and David Ryan Koes.
[arXiv:2404.19739 (2024)](https://arxiv.org/abs/2404.19739) | [code](https://github.com/dunni3/FlowMol)
* **PocketFlow is a data-and-knowledge-driven structure-based molecular generative model** [2024]
Shengyong Yang, Yuanyuan Jiang, Guo Zhang et al.
[Nat Mach Intell (2024)](https://doi.org/10.1038/s42256-024-00808-8) | [Research Square. PREPRINT. (2023)](https://www.researchsquare.com/article/rs-3077992/v1) | [code](https://github.com/Saoge123/PocketFlow)
* **High-Temperature Polymer Dielectrics Designed Using an Invertible Molecular Graph Generative Model** [2023]
Di-Fan Liu, Yong-Xin Zhang, Wen-Zhuo Dong, Qi-Kun Feng, Shao-Long Zhong, and Zhi-Min Dang.
[J. Chem. Inf. Model. (2023)](https://doi.org/10.1021/acs.jcim.3c01572) | [code](https://github.com/pfnet-research/graph-nvp)
* **TacoGFN: Target Conditioned GFlowNet for Structure-Based Drug Design** [2023]
Tony Shen, Mohit Pandey, Martin Ester.
[arXiv:2310.03223. (2023)](https://arxiv.org/abs/2310.03223v1)
* **PocketFlow: an autoregressive flow model incorporated with chemical knowledge for generating drug-like molecules inside protein pockets** [2023]
Shengyong Yang, Yuanyuan Jiang, Guo Zhang et al.
[Research Square. PREPRINT. (2023)](https://www.researchsquare.com/article/rs-3077992/v1) | [code](https://github.com/Saoge123/PocketFlow)
* **FFLOM: A Flow-Based Autoregressive Model for Fragment-to-Lead Optimization** [2023]
Jieyu Jin, Dong Wang, Guqin Shi, Jingxiao Bao, Jike Wang, Haotian Zhang, Peichen Pan, Dan Li, Xiaojun Yao, Huanxiang Liu, Tingjun Hou, and Yu Kang
[J. Med. Chem. (2023)](https://doi.org/10.1021/acs.jmedchem.3c01009) | [code](https://github.com/JenniferKim09/FFLOM)
* **Semi-Equivariant conditional normalizing flows, with applications to target-aware molecule generation** [2023]
Rozenberg, Eyal, and Daniel Freedman.
[Machine Learning: Science and Technology (2023)](https://iopscience.iop.org/article/10.1088/2632-2153/ace58c/meta) | [arXiv:2304.06779 (2023)](https://arxiv.org/abs/2304.06779)
* **Multi-view deep learning based molecule design and structural optimization accelerates the SARS-CoV-2 inhibitor discovery** [2022]
Chao Pang , Yu Wang , Yi Jiang , Ruheng Wang , Ran Su , and Leyi Wei.
[arXiv:2212.01575 (2022)](https://arxiv.org/abs/2212.01575) | [code](https://github.com/Pang-chao/MEDICO)
* **Biological Sequen