mlsanityData to 14 Oct 2026

scCBGM: Interpretable Single-Cell Counterfactual Editing

arXiv 2606.07760 ↗First posted 5 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 61 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

15 of 61 references.

References · 15

  1. 2022Flow Matching for Generative Modelingcited by 5,702
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  3. 2020Concept Bottleneck Modelscited by 1,032
  4. 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 385
  5. 2024Flow Matching Guide and Codecited by 301
  6. 2023Label-Free Concept Bottleneck Modelscited by 285
  7. 2024Taming Rectified Flow for Inversion and Editingcited by 204
  8. 2024Semantic Image Inversion and Editing using Rectified Stochastic Differential Equationscited by 165
  9. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  10. 2019Robust Learning with the Hilbert-Schmidt Independence Criterioncited by 36
  11. 2022Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modelingcited by 34
  12. 2024scDiffusion: conditional generation of high-quality single-cell data using diffusion modelcited by 24
3 more
  1. 2024Concept Bottleneck Language Models For protein designcited by 15
  2. 2024Multi-Modal and Multi-Attribute Generation of Single Cells with CFGencited by 12
  3. 2021Gene regulatory network in single cells based on the Poisson log-normal modelcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery
  2. 2026scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction
  3. 2026Generalizable single-cell perturbation response prediction using energy-guided flow matching
  4. 2026SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention
  5. 2026From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching
  6. 2025Cell2Text: Multimodal LLM for Generating Single-Cell Descriptions from RNA-Seq Data
  7. 2026SCTA: An Agentic Framework for Stable and Interpretable Target Gene Discovery from Single-Cell RNA Sequencing
  8. 2026Systematic Evaluation of Single-Cell Foundation Model Interpretability Reveals Attention Captures Co-Expression Rather Than Unique Regulatory Signal