New search method improves protein motif scaffolding success rates
Evaluator-in-the-Loop Monte Carlo Tree Search via LLM Agents for Motif Scaffolding in Protein Design
Multiagent Systems
Summary
Designing proteins with specific parts called motifs is tricky because many attempts fail and only the successful ones are kept. The authors created a new method called ELMS that uses feedback from partially failed designs to guide better improvements instead of discarding them. This approach keeps track of past designs, identifies what went wrong, and chooses smarter ways to fix the proteins, resulting in much higher success rates than previous methods. Their system uses multiple specialized agents and a tree search to find better protein designs more efficiently.
What this means in practice
- •For protein engineers: Improve targeted protein designs with motifs by using evaluator feedback to guide iterative refinements within a fixed computational budget.
- •For biopharmaceutical developers: Accelerate the design of functional protein scaffolds that incorporate specific motifs for better drug or enzyme candidates.
Authors
Haotian Hu, Oguzhan Gungordo, Siheng Xiong, Faramarz Fekri
Abstract
Motif-scaffolding systems commonly follow a generate-then-filter paradigm, in which candidate proteins are generated independently and structural evaluation is used primarily for terminal screening or ranking. This paradigm underuses evaluation: failed predictions contain state-specific evidence about whether a design requires repair of motif geometry, global foldability, or other structural constraints. We introduce \textbf{ELMS} (Evidence-based LLM-guided Monte Carlo Search), an evaluator-in-the-loop search framework for motif scaffolding that turns such evaluator feedback into targeted design actions. Effective reuse of structural feedback is nontrivial because different scaffold states exhibit different failure modes, and repeatedly refining a single trajectory can prematurely commit computation to an unproductive region of sequence space. ELMS therefore retains evaluated scaffolds as persistent search states: a Critic Agent diagnoses state-local structural failures, a Policy Agent selects targeted operators with execution parameters, motif-locked operators realize legal sequence modifications, and MCTS determines which historical states should receive further design effort. Under the standard GeomMotif protocol (100 candidates per task), ELMS achieves Successful rates of 86.41\% on single-motif tasks and 84.57\% on paired-motif tasks, exceeding the strongest prior baseline by 19.3 and 21.9 percentage points, respectively. On MotifBench, under a matched 100-candidate search budget, it solves 26.7 of 30 tasks on average (88.89\% Task Success), compared with 16.0 tasks (53.33\%) for the strongest baseline. These results establish ELMS as an effective approach for converting structural evaluation from a terminal filter into actionable guidance for iterative motif scaffolding.