EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Adaptive Machine Learning Framework for Optimizing the Affinity Purification of Adeno‐Associated Viral Vectors

Kelvin P Idanwekhai iD, Shriarjun Shastry, Morgan R Hurst iD, Arianna Minzoni, Eduardo Barbieri, Luke Remmler, Eugene N Muratov, Michael A Daniele iD, Stefano Menegatti iD, Alexander Tropsha

Biotechnology and Bioengineering · 2026-05 · 123 (5) · 1107-1122

DOI: 10.1002/bit.70159 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biotechnology and Bioengineering, online erschienen am 19.01.2026. Verfasst von Kelvin P Idanwekhai und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA. Hauptthemen laut MEDLINE: Dependovirus, Genetic Vectors, Machine Learning, Chromatography, Affinity. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 99 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: U.S. Food and Drug Administration, Novo Nordisk Fonden, Triangle Universities Center for Advanced Studies Inc. (TUCASI).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adeno‐associated viral (AAV) vectors for gene therapy are becoming integral to modern medicine, providing therapeutic options for diseases once deemed incurable. Currently, viral vector purification is a critical bottleneck in the gene therapy industry, impacting product efficacy and safety as well as accessibility and cost to patients. Traditional methods for improving viral vector purity are resource‐intensive and often fail to adjust the purification process parameters to maximize the resulting product yield and quality. To address this challenge, we developed a machine learning framework that leverages Bayesian optimization to systematically refine affinity chromatography parameters (sample load, flow rate, and the formulation of chromatographic media) to improve AAV purification. The efficiency of this closed‐loop workflow in iteratively optimizing the vector's yield, purity, and transduction efficiency was demonstrated by purifying clinically relevant serotypes AAV2, AAV5, AAV6, and AAV9 from HEK293 cell lysates using the affinity adsorbent AvXcel. We show that in three (or fewer) cycles of Bayesian optimization, we elevated yields from a baseline of 70% to a remarkable 97%–99%, while reducing host cell impurities by 230‐ to 400‐fold across all serotypes. Performing the purification process with optimized parameters consistently produced vectors with high purity and preserved high transduction activity, essential for therapeutic efficacy and safety, demonstrating the applicability of the framework across multiple serotypes—a key challenge in AAV manufacturing. This study represents the first reported application of closed‐loop, data‐driven Bayesian optimization for enhancing AAV productivity and quality at the affinity capture step, with demonstrated transferability of historical purification data and process knowledge. The proposed adaptive machine learning framework is efficient and applicable across serotypes, enabling rapid process development, reduced costs, and advancing the accessibility and clinical translation of AAV‐based gene therapies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DependovirusGenetic VectorsMachine LearningChromatography, AffinityHumansHEK293 CellsAdaptive AlgorithmsBayes Theorem

Stichwörter der Autor:innen

Bayesian optimizationGaussian processbioseparationsclosed‐loop process developmentgene therapy

Autor:innen und Institutionen

  • Department of Chemistry, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
  • Laboratory for Molecular Modeling, Division of Chemical Biology and Medicinal Chemistry, UNC Eshelman School of Pharmacy, University of North Carolina, Chapel Hill, North Carolina, USA.
  • Department of Chemical and Biomolecular Engineering, NC State University, Raleigh, North Carolina, USA.
  • North Carolina Viral Vector Initiative in Research and Learning (NC-VVIRAL), NC State University, Raleigh, North Carolina, USA.
  • Biomanufacturing Training and Education Center (BTEC), NC State University, Raleigh, North Carolina, USA.
  • ChromaGenix, Raleigh, North Carolina, USA.

ORCID-Profile: Kelvin P Idanwekhai, Morgan R Hurst, Michael A Daniele, Stefano Menegatti

Förderung

  • U.S. Food and Drug Administration
  • Novo Nordisk Fonden
  • Triangle Universities Center for Advanced Studies Inc. (TUCASI)
  • North Carolina Viral Vector Initiative in Research and Learning (NC-VVIRAL)

Zitieren

APA

Idanwekhai, K. P., Shastry, S., Hurst, M. R., Minzoni, A., Barbieri, E., Remmler, L., Muratov, E. N., Daniele, M. A., Menegatti, S., & Tropsha, A. (2026). Adaptive Machine Learning Framework for Optimizing the Affinity Purification of Adeno‐Associated Viral Vectors. Biotechnology and Bioengineering, 123(5), 1107-1122. https://doi.org/10.1002/bit.70159

Vancouver

Idanwekhai KP, Shastry S, Hurst MR, Minzoni A, Barbieri E, Remmler L, et al. Adaptive Machine Learning Framework for Optimizing the Affinity Purification of Adeno‐Associated Viral Vectors. Biotechnology and Bioengineering. 2026;123(5):1107-1122. doi:10.1002/bit.70159

BibTeX
@article{Idanwekhai2026,
  author = {Idanwekhai, Kelvin P and Shastry, Shriarjun and Hurst, Morgan R and Minzoni, Arianna and Barbieri, Eduardo and Remmler, Luke and Muratov, Eugene N and Daniele, Michael A and Menegatti, Stefano and Tropsha, Alexander},
  title = {Adaptive Machine Learning Framework for Optimizing the Affinity Purification of Adeno‐Associated Viral Vectors},
  journal = {Biotechnology and Bioengineering},
  year = {2026},
  volume = {123},
  number = {5},
  pages = {1107--1122},
  doi = {10.1002/bit.70159}
}
Kostenlos starten →