AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

scCBGM: Single-Cell Editing via Concept Bottlenecks

Alma Andersson, Aya Abdelsalam Ismail, Edward De Brouwer, Doron Haviv, Tommaso Biancalani, Kyunghyun Cho, Gabriele Scalia, Aicha BenTaieb, Hector Corrada Bravo

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative latent models for single-cell data

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use scCBGM (concept bottleneck with skip connections and cross-covariance loss) instead of standard CBGMscCBGM · Kang PBMC IFN-b, B cellsrMMD: 0.902 -> 0.112Improved
condition flow matching on scCBGM embeddings instead of observed concepts only (Vanilla-FM)Flow matching · Kang, Cui, Nault datasets (14 cell groups)rMMD: improved or matched in 12/14 cell groupsImproved
use encode-edit counterfactual procedure instead of decode-only sampling (ablation)scCBGM-FM · Kang, Cui, Nault datasetsrMMD: Kang B cells 0.106 -> 0.093Improved
use concept bottleneck head instead of concept embedding head (ablation)scCBGM · synthetic data, counterfactual MSEMSEImproved
add cross-covariance loss in place of cosine orthogonality loss (ablation)scCBGM (CBM family) · synthetic data, counterfactual MSEMSEImproved
add decoder concept skip connections (ablation)scCBGM · synthetic data, counterfactual MSEMSEMixed
use scCBGM under noisy concept annotationsscCBGM · synthetic data, four noise typesMSEImproved
use scCBGM instead of baselines on Monocytes (CD14) in Kang datascCBGM · Kang PBMC IFN-b, Monocytes (CD14)rMMD: Vanilla-FM (edit) 0.394 vs scCBGM-FM (edit) 1.171Hurt
edit pathway-activity concepts of control stellate cells jointly with simulated TCDD treatmentscCBGM · Nault dataset stellate cells case studyrMMD / expression changeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy