AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

FlexProtein: Joint Sequence and Structure Pretraining for Protein Modeling

Jianwei Zhu, Yu Shi, Ran Bi, Peiran Jin, Chang Liu, Zhe Zhang, Haitao Huang, Zekun Guo, Pipi Hu, Fusong Ju, Lin Huang, Xinwei Tai and 11 more

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative protein structure design

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
joint sequence-structure pretraining (MLM plus diffusion) instead of MSA-based or sequence-only modelsFlexRibbon · SAb-23H2 antibody structure predictionsuccess rate: 0.4667 -> 0.6133 vs IgGMImproved
joint sequence-structure pretrainingFlexRibbon · FoldBench protein-peptidesuccess rate: 0.8431 -> 0.9137 vs AlphaFold 3Improved
joint sequence-structure pretraining for nanobody CDR designFlexRibbon · Nanobody CDR designDockQ: 0.267 -> 0.244 DockQ; 0.183 -> 0.218 AARMixed
add ligand context when predicting conformational ensembles (ablation)FlexRibbon · Apo/Holo conformational changeTM-ens: +0.012 (0.889 baseline mode)Improved
joint structure pretraining versus sequence-only encoders for function predictionFlexRibbon · GO-BP, GO-MF, GO-CC F1F1: +0.051, +0.013, +0.096 over ESM-GearNetImproved
joint pretraining versus ESM-GearNet on ECFlexRibbon · ECF1: 0.890 -> 0.891No clear effect
joint pretraining for protein-ligand docking versus single-sequence baselinesFlexRibbon · PoseBusters V1success rate: 71.82% random-1, 78.70% oracleImproved
joint pretraining for binding affinityFlexRibbon · CASF-2016RMSE: 1.258 -> 1.150Improved
remove alignment-based loss (use plain denoising with random rotation augmentation) (ablation)FlexRibbon diffusion · pretrainingtraining stabilityNo clear effect
defer MLM loss to stage B (ablation)FlexRibbon pretraining · pretrainingstabilityImproved

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