AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Beyond Independent Genes: Learning Module-Inductive Representations for Single-Cell Gene Perturbation Prediction

Jiafa Ruan, Ruijie Quan, Xu Liyang, Zongxin Yang, Yi Yang

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 0 citations (OpenAlex)

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 scBIG module-inductive model instead of CellFlowscBIG · Norman additive splitrho-delta: 0.7892 -> 0.8496Improved
use scBIG instead of CellFlow on unseen single genesscBIG · Norman holdout, unseen single generho-delta D: 0.4736 -> 0.6537Improved
use scBIG instead of Linear-scGPT on unseen double genesscBIG · Norman holdout, unseen double generho-delta D: 0.7230 -> 0.8719Improved
use scBIG instead of CellFlow on drug perturbationscBIG · ComboSciPlex drug perturbationrho-delta: 0.8276 -> 0.8671Improved
add GRC clustering instead of balanced K-means (ablation)scBIG (GCAE fixed) · Norman additive splitrho-delta: 0.8358 -> 0.8496Improved
add GCAE encoder instead of standard Transformer (ablation)scBIG (GRC fixed) · Norman additive splitrho-delta: 0.8348 -> 0.8496Improved
use balanced OT clustering instead of unbalanced K-means (ablation)scBIG · Norman additive splitrho-delta D: 0.7765 -> 0.8230Improved
keep stable GRC modules instead of updating clusters by perturbation (ablation)scBIG · Norman additive splitrho-delta D: 0.8065 -> 0.8230Improved
add PPI structure prior (ablation)scBIG · Norman additive splitrho-delta D: 0.7988 -> 0.8230Improved
add GeneCompass embeddings to clustering (ablation)scBIG · Norman additive splitrho-delta: 0.8326 -> 0.8496Improved
add both L_corr and L_pathway losses (ablation)scBIG · Norman additive splitrho-delta: 0.8242 -> 0.8496Improved
add L_corr alone (ablation)scBIG · Norman additive splitrho-delta: 0.8242 -> 0.8306Improved

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