AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

AbDiffuser: full-atom generation of in-vitro functioning antibodies

Karolis Martinkus, Jan Ludwiczak, WEI-CHING LIANG, Julien Lafrance-Vanasse, Isidro Hotzel, Arvind Rajpal, Yan Wu, Kyunghyun Cho, Richard Bonneau, Vladimir Gligorijevic, Andreas Loukas

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Diffusion for protein and antibody 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
use AHo numbering and position-specific residue-frequency priors (ablation)antibody generation models · Paired OASW1(Nat.): 0.2837 -> 0.1979Improved
use learned conditional atom covariance (ablation)AbDiffuser · Paired OASRMSD: 0.6302 -> 0.5230Improved
remove the physics-based projection layer (ablation)AbDiffuser · Paired OASRMSD: 0.5230 -> 11.1431Hurt
generate side chains alongside the backbone (ablation)AbDiffuser · Paired OASW1(Nat.): 0.1979 -> 0.0916Improved
generate side chains alongside the backbone (ablation)AbDiffuser · HER2 binder generationp_bind: 0.5761 -> 0.6848Improved
generate side chains alongside the backbone (ablation)AbDiffuser · HER2 binder generationW1(Sta.): 0.0028 -> 0.0062Hurt
reduce sampling temperature to τ = 0.75 (ablation)AbDiffuser · HER2 binder generationp_bind: 0.5761 -> 0.6382Improved
reduce sampling temperature to τ = 0.01 (ablation)AbDiffuser · HER2 binder generationUniq.: 100% -> 99.7%Hurt
reduce sampling temperature to τ = 0.01 (ablation)AbDiffuser (side chains) · HER2 binder generationUniq.: 100% -> 91.4%Hurt
filter generated designs by in-silico metrics and classifier confidenceAbDiffuser HER2 designs · HER2 in-vitro designsbinding rate: 22. 2% -> 57. 1%Improved

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