Cover Image

Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Kendiukhov, Ihor
Format:	Preprint
Published:	2026
Subjects:	Genomics Machine Learning Cell Behavior
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
by: Kendiukhov, Ihor
Published: (2026)

Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence
by: Kendiukhov, Ihor
Published: (2026)

Geometric coherence of single-cell CRISPR perturbations reveals regulatory architecture and predicts cellular stress
by: Raju, Prashant C.
Published: (2026)

scI2CL: Effectively Integrating Single-cell Multi-omics by Intra- and Inter-omics Contrastive Learning
by: Liu, Wuchao, et al.
Published: (2025)

Long-range gene expression prediction with token alignment of large language model
by: Honig, Edouardo, et al.
Published: (2024)

LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations
by: Bini, Lorenzo, et al.
Published: (2025)

HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data
by: Madhu, Hiren, et al.
Published: (2025)

STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations
by: Fu, Boyang, et al.
Published: (2026)

Season combinatorial intervention predictions with Salt & Peper
by: Gaudelet, Thomas, et al.
Published: (2024)

scRNA-seq of preeclamptic trophoblasts identifies EBI3, COL17A1, miR-27a-5p, and miR-193b-5p as hypoxia markers: validation of neuradapt as a superior mimetic to cobalt chloride
by: Knyazev, Evgeny, et al.
Published: (2025)

SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction
by: Phillips, Lawrence, et al.
Published: (2025)

From Syntax to Semantics: Geometric Stability as the Missing Axis of Perturbation Biology
by: Raju, Prashant C.
Published: (2026)

OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
by: Sypetkowski, Maciej, et al.
Published: (2026)

Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics
by: Kendiukhov, Ihor
Published: (2026)

Dimensional reduction of gradient-like stochastic systems with multiplicative noise via Fokker-Planck diffusion maps
by: Baumgartner, Andrew, et al.
Published: (2024)

What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses
by: Kendiukhov, Ihor
Published: (2026)

Multi-Dimensional Spectral Geometry of Biological Knowledge in Single-Cell Transformer Representations
by: Kendiukhov, Ihor
Published: (2026)

Complexity reduction by symmetry: uncovering the minimal regulatory network for logical computation in bacteria
by: Álvarez-García, Luis A., et al.
Published: (2023)

Towards generalizable single-cell perturbation modeling via the Conditional Monge Gap
by: Driessen, Alice, et al.
Published: (2025)

Systematic Evaluation of Single-Cell Foundation Model Interpretability Reveals Attention Captures Co-Expression Rather Than Unique Regulatory Signal
by: Kendiukhov, Ihor
Published: (2026)

scMamba: A Scalable Foundation Model for Single-Cell Multi-Omics Integration Beyond Highly Variable Feature Selection
by: Yuan, Zhen, et al.
Published: (2025)

Mix-Geneformer: Unified Representation Learning for Human and Mouse scRNA-seq Data
by: Nishio, Yuki, et al.
Published: (2025)

scMEDAL for the interpretable analysis of single-cell transcriptomics data with batch effect visualization using a deep mixed effects autoencoder
by: Andrade, Aixa X., et al.
Published: (2024)

Travelling waves in a minimal go-or-grow model of cell invasion
by: Falcó, Carles, et al.
Published: (2024)

Hierarchical cell identities emerge from animal gene regulatory mechanisms
by: Grishechkin, Anton, et al.
Published: (2024)

SpCAST: Decoding spatial transcriptomics at single-cell resolution with fast and interpretable analysis
by: Zhang, Yiyang, et al.
Published: (2026)

Engineering morphogenesis of cell clusters with differentiable programming
by: Deshpande, Ramya, et al.
Published: (2024)

Learning Model Parameter Dynamics in a Combination Therapy for Bladder Cancer from Sparse Biological Data
by: Olumoyin, Kayode, et al.
Published: (2025)

Spatial dynamic modelling to understand how dendritic cell clustering affects T cell activation
by: Germano, Domenic P. J., et al.
Published: (2026)

A computational scheme connecting gene regulatory network dynamics with heterogeneous stem cell regeneration
by: Li, Yakun, et al.
Published: (2024)

Benchmarking virtual cell models for in-the-wild perturbation response
by: Mao, Xinjie, et al.
Published: (2026)

Mapping, modeling, and reprogramming cell-fate decision making systems
by: Ham, Lucy, et al.
Published: (2024)

Modelling adhesion in stochastic and mean-field models of cell migration
by: Noureen, Shahzeb Raja, et al.
Published: (2024)

Nonthermal driving forces in cells revealed by nonequilibrium fluctuations
by: Ueda, Yuika, et al.
Published: (2024)

Single-cell genome and transcriptome sequencing without upfront whole-genome amplification reveals cell state plasticity of melanoma subclones.
by: Theunis, Koen, et al.
Published: (2025)

A mathematical model for smooth muscle cell phenotype switching in atherosclerotic plaque
by: Ndenda, Joseph P., et al.
Published: (2024)

Coarse-graining and stochastic oscillations in a phenomenological model of cell-size homeostasis
by: Levien, Ethan, et al.
Published: (2025)

Mathematical model of Nucleocytoplasmic Transport and Nuclear-to-Cell Ratio in a growing cell
by: Bai, Xuesong, et al.
Published: (2025)

The spontaneous emergence of leaders and followers in a mathematical model of cranial neural crest cell migration
by: Johnson, Samuel W. S., et al.
Published: (2026)

Using a probabilistic approach to derive a two-phase model of flow-induced cell migration
by: Ben-Ami, Yaron, et al.
Published: (2023)