analiza aiqbench
This research addresses the critical data scarcity in biomanufacturing by systematically integrating established biokinetic ODE models into neural networks, offering a viable path forward where experimental datasets are too small for standard deep learning. The study demonstrates that pre-training on simulated biological curves is functionally equivalent to embedding physical laws directly into network architecture, providing an efficient strategy for accelerating industrial-scale process modeling without requiring massive public data repositories.
Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling
arXiv:2607.20539v1 Announce Type: cross Abstract: While deep learning has accelerated drug discovery, its impact on biomanufacturing has been considerably more limited. The reason is data scarcity. Bioreactor experiments are high-cost, take days to weeks, and are rarely shared in public form, leaving each research work with only a handful of experiments. The domain itself, however, is rich in prior knowledge. Biokinetic ordinary differential equation (ODE) models have described microbial growth for decades, yet how to inject this knowledge into a neural network has not been studied systematically. We present the first systematic study of how to inject this ODE knowledge into a neural network, comparing a data-level prior that pre-trains a generic decoder on simulated ODE curves against an architecture-level prior that embeds the ODE inside the decoder. Both consistently outperform no-prior baselines across 11 datasets and 7 microbial species. Our central finding is that the two are substitutable. A generic decoder pre-trained on simulation matches a fully bio-structured decoder trained on real data. Simulation pre-training therefore offers a simple, data-efficient recipe for deep learning under bioprocess data scarcity.
Abstract:While deep learning has accelerated drug discovery, its impact on biomanufacturing has been considerably more limited. The reason is data scarcity. Bioreactor experiments are high-cost, take days to weeks, and are rarely shared in public form, leaving each research work with only a handful of experiments. The domain itself, however, is rich in prior knowledge. Biokinetic ordinary differential equation (ODE) models have described microbial growth for decades, yet how to inject this knowledge into a neural network has not been studied systematically. We present the first systematic study of how to inject this ODE knowledge into a neural network, comparing a data-level prior that pre-trains a generic decoder on simulated ODE curves against an architecture-level prior that embeds the ODE inside the decoder. Both consistently outperform no-prior baselines across 11 datasets and 7 microbial species. Our central finding is that the two are substitutable. A generic decoder pre-trained on simulation matches a fully bio-structured decoder trained on real data. Simulation pre-training therefore offers a simple, data-efficient recipe for deep learning under bioprocess data scarcity.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2607.20539 [cs.LG]
(or arXiv:2607.20539v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.20539 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 271 cuvinte
Subiecte conexe
Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems
arXiv · 29 iul. 2026
ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset
arXiv · 24 sept. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
Learning Reliable GUI Agents under Imperfect Priors
arXiv · 1 oct. 2026