Go to ICLR 2026 Workshop Gen2 homepageMechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction
Track: Full / long paper (5-8 pages)
Keywords: Gene Perturbation Prediction, Gene Regulatory Networks, Mechanistic Grounding, LLM
TL;DR: MechPert shifts LLM-based perturbation modeling from symmetric functional similarity to directed regulatory logic, improving transcriptomic prediction by 10.5% and active experimental design efficiency by 46% in well-characterized cell lines.
Abstract: 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.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Submission Number: 77
Loading