AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Greater than the Sum of Its Parts: Building Substructure into Protein Encoding Models

Robert Calef, Arthur Liang, Manolis Kellis, Marinka Zitnik

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 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
substructure-tuning (active+binding+conserved sites)SaProt (650M) · EC predictionFmax: 0.778 -> 0.839Improved
substructure-tuningESM-C 300M · EC predictionFmax: 0.688 -> 0.761Improved
substructure-tuningESM2-650M · EC predictionFmax: 0.755 -> 0.745Hurt
substructure-tuningProSST-2048 · GO:MF predictionFmax: 0.522 -> 0.567Improved
substructure-tuningESM-C 600M · Subcellular localizationaccuracy: 0.713 -> 0.635Hurt
substructure-tuningESM2-650M · Subcellular localizationaccuracy: 0.710 -> 0.749Improved
substructure-tuningProSST-2048 · zero-shot DMS variant effectSpearman's rho: 0.507 -> 0.356Hurt
substructure-tuningESM2-150M · thermostabilitySpearman's rho: 0.627 -> 0.582Hurt
substructure-tuningProSST-2048 · Human PPIAUROC: 0.925 -> 0.883Hurt
tune with secondary structure only (ablation)ESM-C 300M · EC predictionFmax: 0.688 -> 0.618Hurt
tune with homologous superfamily only (ablation)ESM-C 300M · EC predictionFmax: 0.688 -> 0.805Improved
tune with active sites only (ablation)ESM-C 300M · GO:MF predictionFmax: 0.429 -> 0.518Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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