# SAFE setup for generative molecular design

arXiv: https://arxiv.org/abs/2410.20232 · HTML: https://mlsanity.com/paper/2410.20232/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 26 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [SELFIES and the future of molecular string representations](https://mlsanity.com/paper/2204.00056/) (2022)
- [SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules](https://mlsanity.com/paper/1703.07076/) (2017)
- [Gotta be SAFE: A New Framework for Molecular Design](https://mlsanity.com/paper/2310.10773/) (2023)
- [Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning](https://mlsanity.com/paper/2004.14308/) (2020)
- [Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery](https://mlsanity.com/paper/2002.06053/) (2020)
- [Scaffold-constrained molecular generation](https://mlsanity.com/paper/2009.07778/) (2020)

## Built on by (most cited first, 2 of 2)

- [Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discovery](https://mlsanity.com/paper/2509.26405/) (2025)
- [Conditional Chemical Language Models are Versatile Tools in Drug Discovery](https://mlsanity.com/paper/2507.10273/) (2025)

## Abstract (arXiv)

SMILES-based molecular generative models have been pivotal in drug design but face challenges in fragment-constrained tasks. To address this, the Sequential Attachment-based Fragment Embedding (SAFE) representation was recently introduced as an alternative that streamlines those tasks. In this study, we investigate the optimal setups for training SAFE generative models, focusing on dataset size, data augmentation through randomization, model architecture, and bond disconnection algorithms. We found that larger, more diverse datasets improve performance, with the LLaMA architecture using Rotary Positional Embedding proving most robust. SAFE-based models also consistently outperform SMILES-based approaches in scaffold decoration and linker design, particularly with BRICS decomposition yielding the best results. These insights highlight key factors that significantly impact the efficacy of SAFE-based generative models.