EMBER predicts TCR–pMHC binding without docked complexes, eliminating structure-prediction error propagation
NWULIST · hf · 2026-10-21
Northwestern University researchers propose EMBER, a structure-based framework for TCR–pMHC binding prediction that eliminates the need for a predicted docked complex:
- Traditional structure-based predictors interpret binding from the contact surface of the co-folded receptor–antigen complex, so any deviation introduced by the structure-prediction tool propagates into every downstream feature.
- EMBER folds the TCR and pMHC independently, encodes them as SE(3)-invariant residue graphs, and compares learned representations without constructing a shared coordinate frame—so placement error cannot propagate.
- The approach avoids docking errors, reduces computation, and improves accuracy across different folding tools.
More from Research
- TRACE framework from NeurIPS paper asks how to actually verify youth restrictions like TikTok's work — Stefania_druga · 2026-10-21
- After TikTok child-safety alarms, a NeurIPS paper proposes TRACE to evaluate youth restrictions — Stefania_druga · 2026-10-21
- Matrix-Game 4.0: real-time playable game worlds on a single RTX 5090 via engine-video split — Jihai Zhang · 2026-10-21
- Lafa scales continuous flow LMs to 8B, hitting 2.54x AR throughput via self-speculative decoding — Arnav Chavan · 2026-10-21
- SWIFT: Alibaba and UMich paper cuts diffusion training cost via weak-denoiser target extrapolation — alibabagroup · 2026-10-21
- Berkeley correction training cuts diffusion exposure bias, high-quality samples without guidance — UCBerkeley · 2026-10-21