# Knowledge Graphs and Reasoning LLMs for Finding Simple Yet Effective Transcriptomic Perturbation Predictors

arXiv: https://arxiv.org/abs/2606.08816 · HTML: https://mlsanity.com/paper/2606.08816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [RL with KL penalties is better viewed as Bayesian inference](https://mlsanity.com/paper/2205.11275/) (2022)
- [How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities](https://mlsanity.com/paper/2409.11654/) (2024)
- [BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model](https://mlsanity.com/paper/2505.23579/) (2025)
- [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://mlsanity.com/paper/2408.10609/) (2024)
- [Benchmarking Transcriptomics Foundation Models for Perturbation Analysis : one PCA still rules them all](https://mlsanity.com/paper/2410.13956/) (2024)
- [CellForge: Agentic Design of Virtual Cell Models](https://mlsanity.com/paper/2508.02276/) (2025)
- [Season combinatorial intervention predictions with Salt & Peper](https://mlsanity.com/paper/2404.16907/) (2024)
- [Contextualizing biological perturbation experiments through language](https://mlsanity.com/paper/2502.21290/) (2025)
- [TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction](https://mlsanity.com/paper/2505.14919/) (2025)
- [Automated Discovery of Pairwise Interactions from Unstructured Data](https://mlsanity.com/paper/2409.07594/) (2024)
- [Virtual Cells: Predict, Explain, Discover](https://mlsanity.com/paper/2505.14613/) (2025)

## Abstract (arXiv)

Predicting the effect of an unseen gene knockout perturbation on transcriptomic gene expression remains a highly challenging problem for virtual cell models. Recent progress has been made by leveraging biological knowledge graphs to provide a notion of similar perturbation, allowing for improved extrapolation beyond the set of training perturbations. In this work, we demonstrate that the simplest model to leverage these assumptions - a K-nearest neighbour from the knowledge graph - achieves highly competitive performance on this task, and that this can be improved further using LLMs optimised via reinforcement learning (RL) for predictive performance. Specifically, we find that the K-nearest neighbour approach beats almost all methods on out-of-distribution perturbation prediction, and when a reasoning LLM is trained via RL to make changes to the neighbourhood, it obtains equivalent performance to current state of the art methods on the cell lines from Replogle et al. (2022). We also demonstrate that the RL training improves the LLM's performance on the downstream task of differential expression prediction, despite not being trained on this directly. Overall, these findings demonstrate the efficacy of knowledge graphs as model priors, and show early signs that RL can refine LLMs into generalizable tools for predicting complex biological responses.