EPS Dashboard

Authors: Jiaxin Qi, Hang Li, Yan Cui et al.

Summary

The authors tackle gene regulatory network (GRN) inference—figuring out which genes regulate which other genes—using single-cell foundation models (scFMs). They find that standard scFMs underperform because their pretraining (reconstruction-based objectives) doesn't explicitly learn regulatory signals. They introduce two new methods, Virtual Value Perturbation and Gradient Trajectory, to extract implicit regulatory knowledge from scFMs and build a zero-shot benchmark that tests whether models can predict regulation for genes and datasets they've never seen.

Main takeaways:

Single-cell foundation models don't naturally capture gene regulation—their reconstruction pretraining misses latent regulatory signals.
The new benchmark tests zero-shot generalization: can a model predict regulatory relationships on completely unseen genes and datasets?
Virtual Value Perturbation and Gradient Trajectory distill regulatory knowledge from scFMs into transferable inter-gene features.
The approach significantly outperforms existing GRN inference methods, especially on out-of-distribution data.
This creates a new paradigm for using foundation models in biology: extracting implicit structure rather than using embeddings directly.

Relevance

Not directly related to my LLM persona work—this is entirely about gene regulation in biology. Included because the theme of extracting implicit knowledge from foundation models (distilling latent structure that pretraining didn't explicitly optimize for) loosely parallels what I'm doing when probing for persona structure in language models.

Threat model

Potential threat/caveat for clean result "Fine-tuning one persona on a two-marker chunk and another on the start marker plants the end marker at every donor answer's end, not chained to the start (LOW confidence)": this item discusses benchmark.

Abstract

arXiv:2605.08128v1 Announce Type: new Abstract: Gene Regulatory Network (GRN) inference is essential for understanding complex cellular mechanisms, rendered tractable through single-cell transcriptomic data. With the emergence of single-cell Foundation Models (scFMs), enhanced transcriptomic encoding is widely expected to revolutionize GRN inference. However, we observe that their performance remains far from satisfactory. The primary reason is that the standard reconstruction-based pre-training objectives often fail to explicitly capture latent regulatory signals. To bridge this gap, we first introduce a GRN generalization benchmark designed to evaluate regulatory predictions on unseen genes and datasets, which relies on the zero-shot capabilities of scFMs and is inherently challenging for traditional methods. Furthermore, to unlock the regulatory knowledge within the foundation models, we propose two novel methods, Virtual Value Perturbation and Gradient Trajectory, to distill implicit regulatory information from scFMs into highly generalizable inter-gene features. Extensive experiments demonstrate that our approach significantly outperforms existing methods, establishing a new paradigm for leveraging the potential of scFMs in universal GRN inference.