# Improving Molecular Design by Stochastic Iterative Target Augmentation

arXiv: https://arxiv.org/abs/2002.04720 · HTML: https://mlsanity.com/paper/2002.04720/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

## Built on by (most cited first, 18 of 18)

- [Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design](https://mlsanity.com/paper/2110.04624/) (2021)
- [Conditional Antibody Design as 3D Equivariant Graph Translation](https://mlsanity.com/paper/2208.06073/) (2022)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [De Novo Molecular Generation via Connection-aware Motif Mining](https://mlsanity.com/paper/2302.01129/) (2023)
- [Reprogramming Pretrained Language Models for Antibody Sequence Infilling](https://mlsanity.com/paper/2210.07144/) (2022)
- [CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph](https://mlsanity.com/paper/2406.10840/) (2024)
- [C5T5: Controllable Generation of Organic Molecules with Transformers](https://mlsanity.com/paper/2108.10307/) (2021)
- [Multi-Objective Latent Space Optimization of Generative Molecular Design Models](https://mlsanity.com/paper/2203.00526/) (2022)
- [Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer](https://mlsanity.com/paper/2305.09480/) (2023)
- [Relation-Aware Equivariant Graph Networks for Epitope-Unknown Antibody Design and Specificity Optimization](https://mlsanity.com/paper/2501.00013/) (2024)
- [Riemannian MeanFlow](https://mlsanity.com/paper/2602.07744/) (2026)
- [Learning Space Partitions for Path Planning](https://mlsanity.com/paper/2106.10544/) (2021)
- [Enhancing Generative Molecular Design via Uncertainty-guided Fine-tuning of Variational Autoencoders](https://mlsanity.com/paper/2405.20573/) (2024)
- [MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization](https://mlsanity.com/paper/2512.20135/) (2025)
- [An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design](https://mlsanity.com/paper/2110.05478/) (2021)
- [Decoupled Sequence and Structure Generation for Realistic Antibody Design](https://mlsanity.com/paper/2402.05982/) (2024)
- [Multi-objective generative AI for designing novel brain-targeting small molecules](https://mlsanity.com/paper/2407.00004/) (2024)
- [A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer](https://mlsanity.com/paper/2502.06913/) (2025)

## Abstract (arXiv)

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training approach for iteratively creating additional molecular targets. We first pre-train the generative model together with a simple property predictor. The property predictor is then used as a likelihood model for filtering candidate structures from the generative model. Additional targets are iteratively produced and used in the course of stochastic EM iterations to maximize the log-likelihood that the candidate structures are accepted. A simple rejection (re-weighting) sampler suffices to draw posterior samples since the generative model is already reasonable after pre-training. We demonstrate significant gains over strong baselines for both unconditional and conditional molecular design. In particular, our approach outperforms the previous state-of-the-art in conditional molecular design by over 10% in absolute gain. Finally, we show that our approach is useful in other domains as well, such as program synthesis.