AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Shrinking Proteins with Diffusion

Ethan Baron, Alan Nawzad Amin, Ruben Weitzman, Simon d'Oelsnitz, Debora Susan Marks, Andrew Gordon Wilson

ICLR 2026 · 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
scale SCISOR from small to largeSCISOR · ProteinGym single deletionsSpearman correlation: 0.332 -> 0.573Improved
scale SCISOR from small to mediumSCISOR · ProteinGym multiple deletionsSpearman correlation: 0.268 -> 0.520Improved
scale SCISOR from medium to largeSCISOR · ProteinGym multiple deletionsSpearman correlation: 0.520 -> 0.492Hurt
use SCISOR L instead of PoET with family informationPoET (200M) · ProteinGym single deletionsSpearman correlation: 0.551 -> 0.573Improved
use SCISOR M instead of PoETPoET (200M) · ProteinGym multiple deletionsSpearman correlation: 0.488 -> 0.520Improved
use SCISOR L instead of PoET on activity assaysPoET (200M) · ProteinGym single deletions (activity assays)Spearman correlation: 0.664 -> 0.604Hurt
shrink with SCISOR instead of Raygun at 20% deletionRaygun · RalA shrinking, 20% deleteddesigns with TM above 0.5 (out of 5): 1 -> 5Improved
shrink with SCISOR instead of ProGen2 at 20% deletionProGen2 · RalA shrinking, 20% deleteddesigns with TM above 0.5 (out of 5): 0 -> 5Improved
shrink with SCISOR instead of ProGen2 at 20% deletionProGen2 · RalA-Sec5 binding, 20% deletedAlphaFold ipTM: 0.36 -> 0.58Improved
shrink with SCISOR instead of ProGen2 by 50% on functional site enrichmentProGen2 · UniProt shrinking, 50% deletedfunctional site enrichmentHurt
replace independent-effect ProGen2 baseline with costlier O(L*M) ProGen2 (ablation)ProGen2 · UniProt shrinkingpLDDT, TM, RMSD, functional enrichmentNo clear effect
use SCISOR deterministic greedy shrinking vs ProGen2ProGen2 · UniProt shrinking (greedy)pLDDT, TM, RMSD, functional enrichmentMixed

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