AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering

Jin Gao, Juntu Zhao, Zirui Zeng, Jiaqi Shen, Junhao Shi, Dukun Zhao, Yuming Lu, Dequan Wang

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative protein structure design · 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
evaluate on random 8:1:1 split instead of fixed future-round split (ablation)protein language models (ESM2, ESMC, ProtTrans) · TadA-Bench protein viewSpearman: 0.0509 -> 0.8079 (ESMC-600M test)Improved
full fine-tuning instead of frozen encoder (ablation)ESM2 and NT families · TadA-Bench future-round testbest test Spearman: 0.055 (ESM2), 0.063 (NT)No clear effect
prompt tuning instead of frozen encoder (ablation)NT-50M and ESMC-300M · TadA-Bench future-round testbest test Spearman: 0.075 (NT-50M), 0.027 (ESMC-300M)No clear effect
increase encoder size from ESM2-35M to ESM2-650M (ablation)ESM2 frozen probing · TadA-Bench future-round testSpearman: 0.0300 -> 0.0479No clear effect
select small candidate budget (96 or 384) with a protein model rankerESM2-35M, ESMC-300M · TadA-Bench future-round, top-5% hit ratehit rate: 3.1% and 4.9% at K=96 vs 5% randomNo clear effect
train on diversity-selected or whole-round subsets instead of random subsample of the same size (ablation)protein models on TadA-Bench · TadA-Bench future-round, Spearman vs training-set sizeSpearmanImproved
increase training-set size by random subsampling (ablation)protein models on TadA-Bench · TadA-Bench future-roundSpearmanImproved
rerun Seq2Graph with 50% of rounds subsampled (ablation)Seq2Graph · label robustnessSpearman of shared-sequence scores: rho = 0.90No clear effect
rerun Seq2Graph with 50% of sequences per round (ablation)Seq2Graph · label robustnessSpearman of shared-sequence scores: rho = 0.95No clear effect

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