AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models

Jiaxin Qi, Hang Li, Yan Cui, Yuhua Zheng, Jianqiang Huang

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse concepts and hypothesis testing · 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
map frozen scFM gene embeddings to links (Baseline-Emb) instead of attention (Origin-Attn)scBenchmark · UGRN trained on hESC (Str), scBenchmarkAUPRC: 0.630 -> 0.663Improved
add virtual value perturbation (VVP) over zero-out perturbationBaseline-Pert · UGRN trained on hESC (Str), scBenchmarkAUPRC: 0.596 -> 0.663Improved
add gradient trajectory (GDT) over VVPVVP · UGRN trained on hESC (Str), scBenchmarkAUPRC: 0.663 -> 0.738Improved
ensemble VVP, GDT and Emb features (Ens) over GDT alone (ablation)GDT · UGRN trained on hESC (Str), scBenchmarkAUPRC: 0.738 -> 0.768Improved
use GDT instead of Baseline-EmbBaseline-Emb · Spc network generalizationAUPRC: 0.540 -> 0.702Improved
ensemble features (Ens) over GDT alone on Spc network (ablation)GDT · Cross-network, SpcAUPRC: 0.702 -> 0.672Hurt
use Ens instead of Baseline-Emb when training on L/G mESCBaseline-Emb · L/G mESC training, scBenchmarkAUPRC: 0.515 -> 0.668Improved
use scGPT instead of scBenchmark as frozen scFM for Ens (ablation)Ens · UGRN trained on hESC (Str), scBenchmarkAUPRC: 0.768 -> 0.743Hurt
raise negative-to-positive ratio from 1 to 10 (ablation)Ens · Class imbalance, scBenchmarkAUPRC: 0.768 -> 0.413Hurt
raise negative-to-positive ratio from 1 to 10 (ablation)Ens · Class imbalance, scBenchmarkAUROC: 0.704 -> 0.706No clear effect
use Ens instead of Baseline-Emb at N/P=10Baseline-Emb · Class imbalance N/P=10AUPRC: 0.264 -> 0.413Improved
train on different species and test on the other (mouse-trained, tested on human)Ens · Cross-species, scBenchmarkAUPRC: 0.704 -> 0.936Improved

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