bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2022.07.25.501428

Preparing for the next Pandemic: Simulation-based Deep Reinforcement Learning to discover and test multimodal control of systemic inflammation using repurposed immunomodulatory agents

Cockrell, C.·Larie, D.·An, G.
View original source ↗Export metadata ↓

Abstract

BackgroundPreparation to address the critical gap in a future pandemic between non-pharmacological measures and the deployment of new drugs/vaccines requires addressing two factors: 1) finding virus/pathogen-agnostic pathophysiological targets to mitigate disease severity and 2) finding a more rational approach to repurposing existing drugs. It is increasingly recognized that acute viral disease severity is heavily driven by the immune response to the infection ("cytokine storm"). There exist numerous clinically available biologics that suppress various pro-inflammatory cytokines/mediators, but it is extremely difficult to identify clinically effective treatment regimens with these agents. We propose that this is a complex control problem that resists standard methods of developing treatment regimens and accomplishing this goal requires the application of simulation-based, model-free deep reinforcement learning (DRL) in a fashion akin to training successful game-playing artificial intelligences (AIs). This proof-of-concept study determines if simulated sepsis (e.g. infection-driven cytokine storm) can be controlled in the absence of effective antimicrobial agents by targeting cytokines for which FDA-approved biologics currently exist. MethodsWe use a previously validated agent-based model, the Innate Immune Response Agent-based Model (IIRABM), for control discovery using DRL. DRL training used a Deep Deterministic Policy Gradient (DDPG) approach with a clinically plausible control interval of 6 hours with manipulation of six cytokines for which there are existing drugs: Tumor Necrosis Factor (TNF), Interleukin-1 (IL-1), Interleukin-4 (IL-4), Interleukin-8 (IL-8), Interleukin-12 (IL-12) and Interferon-{gamma} (IFNg). ResultsDRL trained an AI policy that could improve outcomes from a baseline mortality rate of 41% (= recovery rate of 59%) to one with a recovery rate of 82.3% over 42 days simulated time. DiscussionThe current proof-of-concept study demonstrates that significant disease severity mitigation can potentially be accomplished with existing anti-mediator drugs, but only through a multi-modal, adaptive treatment policy requiring implementation with an AI. While the actual clinical implementation of this approach is a projection for the future, the current goal of this work is to inspire the development of a research ecosystem that marries what is needed to improve the simulation models with the development of the sensing/assay technologies to collect the data needed to iteratively refine those models.

Source connections

Explore related subjects

systems biologyPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Cockrell, C., Larie, D., An, G.. 2022-07-27. Preparing for the next Pandemic: Simulation-based Deep Reinforcement Learning to discover and test multimodal control of systemic inflammation using repurposed immunomodulatory agents. https://doi.org/10.1101/2022.07.25.501428

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Low-fidelity simulator selection for multi-fidelity inference of epithelial vertex models

Vertex models link cell division, neighbour exchange, and intercellular forces to epithelial tissue form through parameters such as junctional line tension and perimeter contractility. Bayesian inference of these parameters from data quantifies their uncertainty, but for stochastic models of proliferating tissues it requires many costly simulations. Multi-fidelity simulation-based inference reduces this cost by training on many runs of a cheaper, less accurate ('low-fidelity') simulator before refining with a few full ('high-fidelity') runs. Low-fidelity versions can be constructed in several ways, for example by stopping simulations early, coarsening the timestep, or averaging fewer replicates, but it is unclear which to choose before committing to costly training. To address this, we introduce PRISM (Paired Ranking Index for Simulator Matching), a screen that compares each candidate with the full simulator on paired runs, scoring agreement in cell-packing statistics against cost. For a vertex model of a proliferating tissue, PRISM flags stopping early as unreliable before training; once trained, this choice can produce confidently wrong parameter estimates. By contrast, a coarser timestep, within the range tested, is cheap and accurate; while fewer replicates are accurate but too costly. Using a screened low-fidelity simulator, multi-fidelity inference outperforms approximate Bayesian computation and neural-network inference trained on full simulations alone, at matched cost and with well-calibrated uncertainty. The same pattern recurs for a second vertex model fitted to published Drosophila pupal-wing imaging data, although there stopping halfway proves safe. Together, our findings suggest that which approximations are safe depends on the model, and that screening them before training makes multi-fidelity inference of tissue mechanics practical.

systems biology↗
bioRxiv2026

Calibrating developmental dynamics from single-cell atlases: lineage paths outrun least-action routes

Single-cell atlases infer developmental dynamics from destructive snapshots, yet how far realized lineage paths depart from such inferred dynamics has never been measured with controls. We introduce LADD (Least-Action Developmental Dynamics), a measurement framework that learns a stochastic developmental vector field from time-series single-cell RNA-seq and computes minimum-action and minimum-time paths, together with a three-layer calibration protocol that separates genuine path deviation from the generic cost of centroid measurement, and we compare its forecasting component with optimal-transport and flow-matching methods. In the lineage-resolved Caenorhabditis elegans atlas, the raw action ratio of observed lineage-centroid trajectories to optimal paths is 3.79, yet forward-simulated ensembles of the learned model itself score 2.07, leaving a genuine excess of about two-fold. In zebrafish (Danio rerio), the observed ratio sits entirely at the model's floor. Three mechanisms that could explain the residual deviation (detours, flow-opposition, and fate-map complexity) are each excluded; what remains is speed, with lineages moving 30-43% faster along the learned flow. We report validity boundaries for temporal resolution, cross-species comparison, and energetic interpretation, delimiting where action-based trajectory comparisons are meaningful.

systems biology↗
bioRxiv2026

Choice of annotation data significantly impacts automated reconstruction of genome-scale metabolic networks

Genome-scale metabolic models are valuable tools for studying metabolism in many applications, such as metabolic engineering or understanding human disease. However, curated models are available for only a limited number of organisms, and generating high-quality models for additional organisms remains a challenge. To help address this challenge, several software tools have been developed that can produce draft models in an automated fashion, but the quality of these draft models lags behind manually curated ones. Thus, there is still a need to improve these tools. Previous work has focused primarily on developing better methods for each step in the reconstruction process, such as gene annotation and gap-filling. Here, we focus on the data that underlies these methods, such as known connections between protein sequence and function. We find that changing the source of reconstruction data has a substantial impact on the contents and predictions of generated models. In fact, the source of data can have a bigger impact than the choice of reconstruction method. Additionally, we show that the reconstruction process is sensitive to the accuracy of gene annotations in the reconstruction data. Finally, we demonstrate the importance of having functional annotation data from an organism that is closely related to the one for which a model is being built. These observations highlight the importance of reconstruction data and identify principles that should be considered when selecting data for reconstruction tools.

systems biology↗