AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design

Fang Wu, Stan Z. Li

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein representation learning · 3 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
add single-protein sequence level (ESM-2) training (ablation)HTP baseline · SAbDab CDR-H3 co-designAAR (%): 22.95 -> 33.87Improved
add single-protein sequence level (ESM-2) training (ablation)HTP baseline · SAbDab CDR-H3 co-designRMSD: 3.55 -> 2.77Improved
add antibody sequence level training (ablation)HTP with SPS · SAbDab CDR-H3 co-designAAR (%): 33.87 -> 38.42Improved
add protein-protein complex structure level training (ablation)HTP with SPS and AS · SAbDab CDR-H3 co-designRMSD: 2.49 -> 2.06Improved
add protein-protein complex structure level training (ablation)HTP with SPS and AS · SAbDab CDR-H3 co-designAAR (%): 38.42 -> 40.98Improved
replace pretrained PLM features with learnable embeddings (ablation)HTP · SAbDab CDR-H3 co-designAAR (%): 40.98 -> 25.31Hurt
replace pretrained PLM features with learnable embeddings (ablation)HTP · SAbDab CDR-H3 co-designRMSD: 2.06 -> 2.65Hurt
use external AbLang instead of HTP's first two pretraining levels (ablation)HTP · SAbDab CDR-H3 co-designAAR (%): 28.46 vs 40.98Hurt
use external AntiBERTa instead of HTP's first two pretraining levels (ablation)HTP · SAbDab CDR-H3 co-designAAR (%): 34.52 vs 40.98Hurt
add AntiBERTa features to GNN without any PLM (ablation)GNN baseline · SAbDab CDR-H3 co-designAAR (%): 25.31 -> 34.52Improved
add AbLang features to GNN without any PLM (ablation)GNN baseline · SAbDab CDR-H3 co-designAAR (%): 25.31 -> 28.46Improved
use sequence-only ESM-2 with MLP for CDR-H3 recovery (ablation)ESM-2 only · SAbDab CDR-H3 co-designAAR (%): 14.63 vs 40.98Hurt

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