# MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction

arXiv: https://arxiv.org/abs/2602.13791 · HTML: https://mlsanity.com/paper/2602.13791/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning](https://mlsanity.com/paper/2509.02401/) (2025)
- [TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction](https://mlsanity.com/paper/2505.14919/) (2025)
- [LLM4GRN: Discovering Causal Gene Regulatory Networks with LLMs -- Evaluation through Synthetic Data Generation](https://mlsanity.com/paper/2410.15828/) (2024)
- [SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction](https://mlsanity.com/paper/2509.25346/) (2025)
- [Large Language Models for Bioinformatics](https://mlsanity.com/paper/2501.06271/) (2025)
- [Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering](https://mlsanity.com/paper/2510.05871/) (2025)
- [GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models](https://mlsanity.com/paper/2503.01682/) (2025)

## Built on by (most cited first, 1 of 1)

- [Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization](https://mlsanity.com/paper/2605.06308/) (2026)

## Abstract (arXiv)

Predicting transcriptional responses to unseen genetic perturbations is essential for understanding gene regulation and prioritizing large-scale perturbation experiments. Existing approaches either rely on static, potentially incomplete knowledge graphs, or prompt language models for functionally similar genes, retrieving associations shaped by symmetric co-occurrence in scientific text rather than directed regulatory logic. We introduce MechPert, a lightweight framework that encourages LLM agents to generate directed regulatory hypotheses rather than relying solely on functional similarity. Multiple agents independently propose candidate regulators with associated confidence scores; these are aggregated through a consensus mechanism that filters spurious associations, producing weighted neighborhoods for downstream prediction. We evaluate MechPert on Perturb-seq benchmarks across four human cell lines. For perturbation prediction in low-data regimes (N=50 observed perturbations), MechPert improves Pearson correlation by up to 10.5% over similarity-based baselines. For experimental design, MechPert-selected anchor genes outperform standard network centrality heuristics by up to 46% in well-characterized cell lines.