EUVIMEDObjevte EUVIMED
ÜbersichtsarbeitOpen access · CC BY 4.0

Addressing Small Data Challenges in Biopharmaceutical Development and Manufacturing: A Mini Review of Multi‐Fidelity Techniques

Mohammad Golzarijalal, Uwe Aickelin, Ellen Otte

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.

AbstraktSubjectsBibliografické údajeCiteRelated studies

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)

Biological ProductsMachine LearningDrug DiscoveryDrug DevelopmentNeural Networks, ComputerData Analytics

Author keywords

Gaussian processesbiopharmaceutical processesgraph neural networksmodel interpretabilitymulti‐fidelity modelingneural networks

Substances

Biological Products

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}
}
Start for free →