Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Otun, Martins
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914579004522496
author Otun, Martins
author_facet Otun, Martins
contents Cold-chain storage limits access to insulin for hundreds of millions of people; a thermally protective patch polymer could help, but the design space is too large for exhaustive experiment. Starting from that problem, we narrow to an agentic workflow: a large language model (LLM) calls physics-based tools through the Model Context Protocol (MCP), searching the discrete PSMILES space under a budget of OpenMM Packmol-matrix evaluations. The LLM acts as an implicit acquisition function conditioned on a persistent "discovery world": hypotheses, literature claims, and simulation outcomes updated each iteration. Under matched oracle budgets, the best autonomous campaign reaches an insulin-polymer interaction energy of -2263 kJ/mol, outperforming reinforcement-learning baselines by 68% and Bayesian optimization by 19%. Three independent campaigns converge on one structural motif (dense hydrogen-bond donors and acceptors per repeat unit) while physics checks reject infeasible packings and name-structure mismatches before they steer the next step. The science stage is CPU-bound and runs on commodity hardware. More broadly, the same architecture and workflow designed here applies to other protein-stabilization tasks whenever a tractable screening oracle is available.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18831
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows
Otun, Martins
Quantitative Methods
Machine Learning
Cold-chain storage limits access to insulin for hundreds of millions of people; a thermally protective patch polymer could help, but the design space is too large for exhaustive experiment. Starting from that problem, we narrow to an agentic workflow: a large language model (LLM) calls physics-based tools through the Model Context Protocol (MCP), searching the discrete PSMILES space under a budget of OpenMM Packmol-matrix evaluations. The LLM acts as an implicit acquisition function conditioned on a persistent "discovery world": hypotheses, literature claims, and simulation outcomes updated each iteration. Under matched oracle budgets, the best autonomous campaign reaches an insulin-polymer interaction energy of -2263 kJ/mol, outperforming reinforcement-learning baselines by 68% and Bayesian optimization by 19%. Three independent campaigns converge on one structural motif (dense hydrogen-bond donors and acceptors per repeat unit) while physics checks reject infeasible packings and name-structure mismatches before they steer the next step. The science stage is CPU-bound and runs on commodity hardware. More broadly, the same architecture and workflow designed here applies to other protein-stabilization tasks whenever a tractable screening oracle is available.
title Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows
topic Quantitative Methods
Machine Learning
url https://arxiv.org/abs/2605.18831