scCBGM: Interpretable Single-Cell Counterfactual Editing
- URL: http://arxiv.org/abs/2606.07760v1
- Date: Fri, 05 Jun 2026 18:17:37 GMT
- Title: scCBGM: Interpretable Single-Cell Counterfactual Editing
- Abstract summary: We introduce single-cell Concept Bottleneck Generative Models (scCBGM)<n>scCBGM is a framework for interpretable and precise counterfactual editing of individual cells.<n>We extend the framework to flow matching models, enabling concept-guided editing in both encoding-decoding and generation regimes.
- Score: 39.96631162986181
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Understanding cellular phenotypes and how they respond to perturbations is critical for disease biology and therapeutic design. Single-cell RNA sequencing enables characterization at cellular resolution, yet the combinatorial space of conditions makes exhaustive experimental mapping infeasible. We introduce single-cell Concept Bottleneck Generative Models (scCBGM), a framework for interpretable and precise counterfactual editing of individual cells. scCBGM adapts concept bottleneck architectures for single-cell data through decoder skip connections and a cross-covariance penalty that promotes disentanglement without dimensional constraints. We extend the framework to flow matching models, enabling concept-guided editing in both encoding-decoding and generation regimes. To enable rigorous evaluation, we develop a synthetic benchmark with ground-truth counterfactuals. Across multiple real datasets, scCBGM demonstrates superior performance in combinatorial generalization and counterfactual prediction, supported by cell-level validation on synthetic data and population-level benchmarks on real datasets.
Related papers
- OCOO-T : A Simple and Scalable Virtual Cell Model for Transcriptional Perturbation Response Prediction [0.8574682463936006]
This paper introduces OCOO-T, a flow-matching-based AIVC model for perturbation response prediction.<n>OCOO-T formulates perturbation response prediction as a continuous-time denoising process.<n>It achieves state-of-the-art performance across diverse perturbations and cell types.
arXiv Detail & Related papers (2026-06-11T03:04:38Z) - SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention [10.404186274295222]
SAVE is a unified generative framework based on conditional Transformers for single-cell modeling.<n>We evaluate SAVE on a range of benchmarks including conditional generation, batch effect correction, and perturbation prediction.<n>Save offers a scalable and generalizable solution for modeling complex single-cell data.
arXiv Detail & Related papers (2026-04-18T01:45:16Z) - MAT-Cell: A Multi-Agent Tree-Structured Reasoning Framework for Batch-Level Single-Cell Annotation [81.82645086402366]
We propose MAT-Cell, a neuro-symbolic reasoning framework that reframes single-cell analysis into constructive, verifiable proof generation.<n> MAT-Cell injects symbolic constraints through adaptive Retrieval-Augmented Generation (RAG) to ground neural reasoning in biological axioms and reduce transcriptomic noise.<n>It significantly outperforms state-of-the-art (SOTA) models and maintains robust per-formance in challenging scenarios.
arXiv Detail & Related papers (2026-04-07T04:56:06Z) - scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction [12.48933770510505]
We present scDFM, a generative framework based on conditional flow matching.<n> scDFM aligns perturbed and control populations beyond cell-level correspondences.
arXiv Detail & Related papers (2026-02-06T17:00:21Z) - scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration [53.683726781791385]
We introduce a scalable and flexible generative framework called single-cell Multi-omics Regularized Disentangled Representations (scMRDR) for unpaired multi-omics integration.<n>Our method achieves excellent performance on benchmark datasets in terms of batch correction, modality alignment, and biological signal preservation.
arXiv Detail & Related papers (2025-10-28T21:28:39Z) - Linearized Optimal Transport for Analysis of High-Dimensional Point-Cloud and Single-Cell Data [45.87606039212519]
Single-cell technologies generate high-dimensional point clouds of cells.<n>Each patient is represented by an irregular point cloud rather than a simple vector.<n>We adapt the Linear Optimal Transport framework to embed irregular point clouds into a fixed-dimensional Euclidean space.
arXiv Detail & Related papers (2025-10-24T21:33:12Z) - CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis [51.56484100374058]
We introduce CellPainTR, a Transformer-based architecture designed to learn foundational representations of cellular morphology.<n>Our work represents a significant step towards creating truly foundational models for image-based profiling, enabling more reliable and scalable cross-study biological analysis.
arXiv Detail & Related papers (2025-09-02T03:30:07Z) - Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen [76.02070962797794]
This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data.<n>CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics.
arXiv Detail & Related papers (2024-07-16T14:05:03Z) - Scalable Amortized GPLVMs for Single Cell Transcriptomics Data [9.010523724015398]
Dimensionality reduction is crucial for analyzing large-scale single-cell RNA-seq data.
We introduce an improved model, the amortized variational model (BGPLVM)
BGPLVM is tailored for single-cell RNA-seq with specialized encoder, kernel, and likelihood designs.
arXiv Detail & Related papers (2024-05-06T21:54:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.