AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

DecoderTCR: Compositional Pretraining and Entropy-Guided Decoding for TCR-pMHC Interactions

Boqiao Lai, Melissa Englund, Ramit Bharanikumar, Isabel Nocedal, Ali Davariashtiyani, Jason Perera, Aly A Khan

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 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
add Stage 1 domain-specific continual pretraining on pMHC and TCR dataESM-2 (3B) · Zero-shot pMHC binding, Class IAUROC: 0.45 -> 0.93Improved
add Stage 1 domain-specific pretraining to ESM-2 embeddingsESM-2 (3B) · ESCAPE-seq oncogene pMHCAUROC: 0.63 -> 0.77Improved
scale DecoderTCR from 650M to 3BDecoderTCR Stage 1 · Zero-shot pMHC Class IAUROC: .96±.04 -> .93±.08No clear effect
add Stage 2 paired pretraining after Stage 1 (ablation)DecoderTCR (3B) · YLQ TCR recognitionAUROC: 0.18 -> 0.76Improved
add Stage 1 unpaired pretraining before Stage 2 (ablation)DecoderTCR (3B) · YLQ TCR recognitionAUROC: 0.56 -> 0.76Improved
add Stage 2 paired training on top of Stage 1 (knowledge retention)DecoderTCR · Held-out TCR sequencesinverse perplexity: 0.72 -> 0.79Improved
continue Stage 2 training for 3500 stepsDecoderTCR · Zero-shot pMHC held-out allelesAUROC: 0.925-0.93No clear effect
use IEGR entropy-guided decoding instead of Greedy (ablation)DecoderTCR designs · YLQ in silico designsalt-bridge enrichment: 17.2% -> 34.2%Improved
use IEGR entropy-guided decoding instead of OneShot (ablation)DecoderTCR designs · YLQ in silico designsalt-bridge enrichment: 21.9% -> 34.2%Improved
use IEGR instead of single-pass decoding (ablation)DecoderTCR designs · YLQ AlphaFold3 ipTMipTM significance: p < 0.001Improved
add classifier filtering on DecoderTCR embeddings (lab-in-the-loop round 2)IEGR designs · YLQ wet-lab hit ratehit rate: 3% -> 12%Improved
use zero-shot DecoderTCR vs supervised NetTCR-2.2DecoderTCR (3B) · YLQ TCR recognitionAUROC: 0.88 -> 0.76Hurt

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