# SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction

arXiv: https://arxiv.org/abs/2509.25346 · HTML: https://mlsanity.com/paper/2509.25346/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [LoRA+: Efficient Low Rank Adaptation of Large Models](https://mlsanity.com/paper/2402.12354/) (2024)
- [4+3 Phases of Compute-Optimal Neural Scaling Laws](https://mlsanity.com/paper/2405.15074/) (2024)
- [VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary](https://mlsanity.com/paper/2407.19524/) (2024)
- [Blind Beamforming for Coverage Enhancement with Intelligent Reflecting Surface](https://mlsanity.com/paper/2407.12648/) (2024)

## Built on by (most cited first, 6 of 6)

- [Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering](https://mlsanity.com/paper/2510.05871/) (2025)
- [MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction](https://mlsanity.com/paper/2602.13791/) (2026)
- [Towards Autonomous Mechanistic Reasoning in Virtual Cells](https://mlsanity.com/paper/2604.11661/) (2026)
- [AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling](https://mlsanity.com/paper/2604.20263/) (2026)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)
- [PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects](https://mlsanity.com/paper/2607.18777/) (2026)

## Abstract (arXiv)

Predicting cellular responses to genetic perturbations represents a fundamental challenge in systems biology, critical for advancing therapeutic discovery and virtual cell modeling. While large language models (LLMs) show promise for biological reasoning, their application to perturbation prediction remains underexplored due to challenges in adapting them to structured experimental data. We present SynthPert, a novel method that enhances LLM performance through supervised fine-tuning on synthetic reasoning traces generated by frontier models. Using the PerturbQA benchmark, we demonstrate that our approach not only achieves state-of-the-art performance but surpasses the capabilities of the frontier model that generated the training data. Our results reveal three key insights: (1) Synthetic reasoning traces effectively distill biological knowledge even when partially inaccurate, (2) This approach enables cross-cell-type generalization with 87% accuracy on unseen RPE1 cells, and (3) Performance gains persist despite using only 2% of quality-filtered training data. This work shows the effectiveness of synthetic reasoning distillation for enhancing domain-specific reasoning in LLMs.