AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

CDBridge: A Cross-omics Post-training Bridge Strategy for Context-aware Biological Modeling

Chang Yu, Siyuan Li, Zicheng Liu, Jingbo Zhou, Xianglong Guo, Kai Yu, Yuqing Zhou, Ken Li, Zelin Zang, Zhen Lei, Stan Z. Li

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein fitness and variant effect prediction

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
add ToMe adaptive token merging (ablation)CDBridge stage 1 · GTEx segmentationAUC: 0.848 -> 0.882Improved
add ToMe adaptive token merging (ablation)CDBridge stage 1 · GTEx expressionR2: 0.021 -> 0.205Improved
add fixed protein cluster on top of ToMe (ablation)CDBridge stage 1 · GTEx segmentationAUC: 0.882 -> 0.990Improved
make protein cluster learned instead of fixed (ablation)CDBridge stage 1 · GTEx segmentationF1: 0.602 -> 0.635Improved
make protein cluster learned instead of fixed (ablation)CDBridge stage 1 · GTEx segmentationAUC: 0.990 -> 0.993No clear effect
add tissue conditioning (ablation)CDBridge stage 2 · GTEx expressionR2: 0.215 -> 0.387Improved
add tissue conditioning (ablation)CDBridge stage 2 · GTEx expressionSpearman: 0.483 -> 0.618Improved
tissue embedding alone without DNA features (ablation)CDBridge control · GTEx expressionR2: 0.387 -> 0.020Hurt
use CDBridge vs Evo2 backbone aloneDNA encoder · GTEx expression averageR2: 0.021 -> 0.387Improved
use CDBridge vs AlphaGenomeexpression prediction · GTEx expression averageSpearman: 0.438 -> 0.618Improved
use CDBridge vs Isoformer official (TSS aligned)expression prediction · GTEx expression averageR2: 0.530 -> 0.387Hurt
use CDBridge vs LucaOneisoform retrieval · Isoform RetrievalMRR: 0.354 -> 0.436Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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