# Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models

arXiv: https://arxiv.org/abs/2606.01461 · HTML: https://mlsanity.com/paper/2606.01461/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 31 May 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Geometric Latent Diffusion Models for 3D Molecule Generation](https://mlsanity.com/paper/2305.01140/) (2023)
- [Scientific Large Language Models: A Survey on Biological & Chemical Domains](https://mlsanity.com/paper/2401.14656/) (2024)
- [DrugLLM: Open Large Language Model for Few-shot Molecule Generation](https://mlsanity.com/paper/2405.06690/) (2024)
- [DrugGen: Advancing Drug Discovery with Large Language Models and Reinforcement Learning Feedback](https://mlsanity.com/paper/2411.14157/) (2024)
- [Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design](https://mlsanity.com/paper/2510.21153/) (2025)
- [A molecular generative model with genetic algorithm and tree search for cancer samples](https://mlsanity.com/paper/2112.08959/) (2021)

## Abstract (arXiv)

Developing effective anticancer therapeutics remains challenging due to tumor heterogeneity and the absence of well-defined molecular targets across cancer subtypes. Generative models conditioned on cancer genotypes offer a promising avenue for personalized drug discovery, yet existing approaches lack explicit optimization for simultaneous sensitivity, synthesizability, and mechanistic binding plausibility. We present a latent-space optimization approach for a pretrained genotype-to-drug diffusion model, introducing a learnable perturbation over the molecular latent space optimized via gradient ascent to maximize a composite reward combining predicted drug sensitivity (AUC), drug-likeness (QED), and synthetic accessibility (SAS). Critically, biological realism is enforced by grounding both reward design and evaluation in experimentally-derived cancer cell line data and validated pharmacologic signals, anchoring candidate generation in real-world clinical evidence. Mechanistic consistency plausibility is further assessed by a multi-agent LLM pipeline grounded in the diffusion model's attention mechanism. Experiments across 15 cancer cell lines from three held-out evaluation sets demonstrate consistent and noticeable improvements over competing baselines in sensitivity, drug-likeness, synthesizability, and chemical validity.