Article

Do Single-Cell Models Learn Real Biology? An Empirical Analysis of Physical Interaction Signal in Pretrained scGPT Gene Embeddings

2026-07-24

Abstract excerpt

<title>Abstract</title> <p>Single-cell foundation models are trained on millions of transcriptomes, but it remains unclear whether their internal representations contain biological relationships that were not supplied as labels. We test one narrow claim: genes whose proteins physically interact should be closer in the pretrained gene-token space of scGPT than carefully matched gene pairs without a recorded intera...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 1195b18d-0084-5d30-a29e-df73580bb470
DOI: 10.21203/rs.3.rs-10461095/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Do Single-Cell Models Learn Real Biology? An Empirical Analysis of Physical Interaction Signal in Pretrained scGPT Gene EmbeddingsDOI 10.21203/rs.3.rs-10461095/v1Read

Mechanistic Interpretability of Biological Foundation Models: An Empirical Analysis of scGPT Gene-Embedding GeometrySemantic proximity Read

Reading Mechanism off Biological Foundation Models: An Empirical Analysis of Genomic Neighborhood Structure in scGPT Gene EmbeddingsSemantic proximity Read

Building Foundation Models to Characterize Cellular Interactions via Geometric Self-Supervised Learning on Spatial GenomicsSemantic proximity Read

Transformers Enhance the Predictive Power of Network MedicineSemantic proximity Read

scRepresenter: a workflow for computing, integrating and benchmarking cellular representations in single-cell transcriptomicsSemantic proximity Read

CLOP-DiT: Structured-Metadata-Conditioned Single-Cell Latent Generation via Contrastive Language-Omics Pretraining and Diffusion TransformersSemantic proximity Read

Protein-protein interaction priors shape biologically coherent latent spaces for causally concordant cross-omic translationSemantic proximity Read

scGenePT: Is language all you need for modeling single-cell perturbations?Semantic proximity Read

Geometric Representations of Knowledge Inside Biological Large Language Models: an Empirical AnalysisSemantic proximity Read

Benchmarking single-cell foundation models in a zero-shot settingSemantic proximity Read

Scalable Non-negative Matrix Factorization of the Human Cell Census Reveals Interpretable Transcriptional ProgramsSemantic proximity Read

RegFormer: A Single-Cell Foundation Model Powered by Gene Regulatory HierarchiesSemantic proximity Read