AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Multi-Scale Representation Learning on Proteins

Vignesh Ram Somnath, Charlotte Bunne, Andreas Krause

NeurIPS 2021 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein representation learning · 22 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 surface layer to structure layer (multi-scale) (ablation)HoloProt · PDBbind identity 30%RMSE: 1.476 -> 1.464Improved
add structure layer to surface layer (ablation)HoloProt · PDBbind identity 30%RMSE: 1.482 -> 1.464Improved
add surface layer to structure layer (ablation)HoloProt · Enzyme reaction classaccuracy: 74.2 -> 77.8Improved
add structure to surface-only model (ablation)HoloProt · Enzyme reaction classaccuracy: 28.6 -> 77.8Improved
add surface layer to structure layer (ablation)HoloProt · PDBbind identity 60%RMSE: 1.378 -> 1.365Improved
add surface layer to structure layer (ablation)HoloProt · PDBbind scaffoldRMSE: 1.521 -> 1.523No clear effect
replace full surface with molecular superpixelsHoloProt · PDBbind identity 30%RMSE: 1.464 -> 1.491No clear effect
replace full surface with molecular superpixelsHoloProt · Enzyme reaction classaccuracy: 77.8 -> 78.9Improved
replace full surface with molecular superpixelsHoloProt · PDBbind scaffoldRMSE: 1.523 -> 1.516Improved
learn superpixel patch features with MPN instead of summary statistics (ablation)HoloProt superpixels · PDBbind identity 30%RMSE: 1.491 -> 1.491No clear effect
learn superpixel patch features with MPN instead of summary statistics (ablation)HoloProt superpixels · Enzyme reaction classaccuracy: 78.9 -> 75.7Hurt

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