AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Towards All-Atom Foundation Models for Biomolecular Binding Affinity Prediction

Liang Shi, Zuobai Zhang, Huiyu Cai, Santiago Miret, Zhi Yang, Jian Tang

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein interface and docking 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 denoising pre-training (ablation)ADiT-M · SKEMPIv2Pearson: 0.649 -> 0.683Improved
add denoising pre-training (ablation)ADiT-M · SKEMPIv2RMSE: 1.624 -> 1.559Improved
use all-atom instead of backbone-only structures (ablation)ADiT-M · SKEMPIv2Pearson: 0.658 -> 0.683Improved
use all-atom instead of backbone-only structures (ablation)ADiT-M · SKEMPIv2RMSE: 1.606 -> 1.559Improved
scale model from 35M to 253M parameters (ablation)ADiT · SKEMPIv2Pearson: 0.683 -> 0.691Improved
scale model from 12M to 35M parameters (ablation)ADiT · SKEMPIv2Pearson: 0.660 -> 0.683Improved
scale model from 12M to 253M parametersADiT · DavisMSE: 0.252 -> 0.198Improved
use ADiT instead of fine-tuned ProtenixADiT-L · LBA-60RMSE: 1.781 -> 1.246Improved
use ADiT instead of fine-tuned ProtenixADiT-L · LBA-30RMSE: 1.354 -> 1.308Improved
scale model size from S to LADiT · HER2 bindersPearson: 0.527 -> 0.507 -> 0.567Mixed
use ADiT-L instead of GearBind + PADiT-L · HER2 bindersPearson: 0.515 -> 0.567Improved
use ADiT-S instead of GEARNET-EDGEADiT-S · EC annotationFmax: 0.744 -> 0.751 (30%), 0.848 -> 0.843 (70%)Mixed

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