Scalable Agentic Reasoning for Designing Biologics Targeting Intrinsically Disordered Proteins

2025-12-17

AI Summary

Intrinsically disordered proteins (IDPs) pose significant challenges for drug discovery due to their conformational heterogeneity and lack of stable binding pockets, rendering them historically “undruggable.” Method: We present StructBioReasoner—the first tournament-style, multi-agent autonomous reasoning system tailored for IDP-targeted biologics design. It integrates domain knowledge with a heterogeneous computational toolkit—including AlphaFold3/ESMFold, molecular dynamics simulations, and binding free energy calculations—orchestrated via the federated agent middleware Academy on high-performance computing infrastructure, enabling end-to-end closed-loop optimization of binding site identification, binder generation, and stability assessment. Results: On Der f 21, >50% of top candidates outperformed published human-designed binders; on NMNAT-2, the system identified three distinct binding modes among 97,000 candidates—including recognition of the known p53 interaction interface—demonstrating its capability to target functionally critical regions of IDPs.

Technology Category

• Multiagent Systems: Mechanism Design
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Bio-inspired Learning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Intrinsically disordered proteins (IDPs) represent crucial therapeutic targets due to their significant role in disease -- approximately 80% of cancer-related proteins contain long disordered regions -- but their lack of stable secondary/tertiary structures makes them "undruggable". While recent computational advances, such as diffusion models, can design high-affinity IDP binders, translating these to practical drug discovery requires autonomous systems capable of reasoning across complex conformational ensembles and orchestrating diverse computational tools at scale.To address this challenge, we designed and implemented StructBioReasoner, a scalable multi-agent system for designing biologics that can be used to target IDPs. StructBioReasoner employs a novel tournament-based reasoning framework where specialized agents compete to generate and refine therapeutic hypotheses, naturally distributing computational load for efficient exploration of the vast design space. Agents integrate domain knowledge with access to literature synthesis, AI-structure prediction, molecular simulations, and stability analysis, coordinating their execution on HPC infrastructure via an extensible federated agentic middleware, Academy. We benchmark StructBioReasoner across Der f 21 and NMNAT-2 and demonstrate that over 50% of 787 designed and validated candidates for Der f 21 outperformed the human-designed reference binders from literature, in terms of improved binding free energy. For the more challenging NMNAT-2 protein, we identified three binding modes from 97,066 binders, including the well-studied NMNAT2:p53 interface. Thus, StructBioReasoner lays the groundwork for agentic reasoning systems for IDP therapeutic discovery on Exascale platforms.

Problem

• Designs biologics targeting intrinsically disordered proteins using scalable agentic reasoning
• Addresses undruggable nature of IDPs lacking stable structures via multi-agent system
• Enables autonomous exploration of vast design space with diverse computational tools

Innovation

• Multi-agent system with tournament-based reasoning for biologics design
• Integrates domain knowledge with AI prediction and molecular simulations
• Extensible federated middleware coordinates execution on HPC infrastructure