Addressing Small Data Challenges in Biopharmaceutical Development and Manufacturing: A Mini Review of Multi‐Fidelity Techniques
Biotechnology and Bioengineering · 2026
DOI: 10.1002/bit.70213 ↗At a glance
Übersichtsarbeit in Biotechnology and Bioengineering, 2026. Written by Mohammad Golzarijalal and 2 co-authors. Institution: School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, Australia. Major MEDLINE topics: Biological Products, Machine Learning, Drug Discovery, Drug Development. Cited 2 times so far (Crossref); 93 references. The full text is freely available (open access, CC BY 4.0). Funded by: Australian Research Council.
Abstract (original language)
The growing demand for biopharmaceutical products reflects their effectiveness in medical treatments. However, developing new biopharmaceuticals remains a major bottleneck, often taking up to a decade before market approval. Machine learning (ML) models have the potential to accelerate this process, but their success depends on access to large and diverse data sets for training. Multi‐fidelity ML techniques offer a promising solution by integrating abundant, low‐cost, and less accurate low‐fidelity (LF) data with limited, expensive, and more accurate high‐fidelity (HF) data. In this framework, LF data capture global system trends, while HF data refine and align model predictions with the available ground truth. Such integration can substantially reduce development costs and timelines by minimizing the need to acquire HF data, for example, through extensive experimental campaigns. This work reviews developments in surrogate modeling within the biopharmaceutical context, including Gaussian processes, neural networks, and physics‐informed approaches. It also provides practical recommendations for identifying appropriate LF and HF data. Existing research has primarily focused on upstream processing and drug discovery, highlighting opportunities to extend these methods to other stages, like downstream processing. While Gaussian processes and neural networks remain the most frequently used models, emerging architectures such as Transformer and diffusion models present promising directions for future research.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- School of Computing and Information Systems, The University of Melbourne, Melbourne, Victoria, Australia.
- The ARC Digital Bioprocess Development Hub, The University of Melbourne, Melbourne, Victoria, Australia.
- CSL Innovation, Melbourne, Victoria, Australia.
Funding
- Australian Research Council
Cite
APA
Golzarijalal, M., Aickelin, U., & Otte, E. (2026). Addressing Small Data Challenges in Biopharmaceutical Development and Manufacturing: A Mini Review of Multi‐Fidelity Techniques. Biotechnology and Bioengineering. https://doi.org/10.1002/bit.70213
Vancouver
Golzarijalal M, Aickelin U, Otte E. Addressing Small Data Challenges in Biopharmaceutical Development and Manufacturing: A Mini Review of Multi‐Fidelity Techniques. Biotechnology and Bioengineering. 2026. doi:10.1002/bit.70213
BibTeX
@article{Golzarijalal2026,
author = {Golzarijalal, Mohammad and Aickelin, Uwe and Otte, Ellen},
title = {Addressing Small Data Challenges in Biopharmaceutical Development and Manufacturing: A Mini Review of Multi‐Fidelity Techniques},
journal = {Biotechnology and Bioengineering},
year = {2026},
doi = {10.1002/bit.70213}
}
EUVIMED