Publications

@article{Yatipanthalawa2026,

title = {Amino acid metabolism, demand and supply in Chinese Hamster ovary cell culture – A comprehensive literature review},

author = {Bhagya S. Yatipanthalawa and Yih Yean Lee and Sally L. Gras and Gregory J.O. Martin},

doi = {10.1016/j.biotechadv.2026.108866},

issn = {0734-9750},

year  = {2026},

date = {2026-07-00},

journal = {Biotechnology Advances},

volume = {89},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Discepola2026,

title = {Transmembrane pressure evolution during constant flux SPTFF – a comparison of two proteins},

author = {Michele Discepola and Bastian Oetomo and Buddy Heydon and James Atherton and Ben Hunt and Ling Luo and Sally L. Gras and Sandra E. Kentish},

doi = {10.1016/j.memsci.2026.125541},

issn = {0376-7388},

year  = {2026},

date = {2026-06-00},

journal = {Journal of Membrane Science},

volume = {751},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Golzarijalal2026,

title = {Addressing Small Data Challenges in Biopharmaceutical Development and Manufacturing: A Mini Review of Multi‐Fidelity Techniques},

author = {Mohammad Golzarijalal and Uwe Aickelin and Ellen Otte},

doi = {10.1002/bit.70213},

issn = {1097-0290},

year  = {2026},

date = {2026-04-19},

journal = {Biotech & Bioengineering},

publisher = {Wiley},

abstract = {ABSTRACT

                  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.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hermanto2026,

title = {Hybrid machine learning models for predictions of mammalian cell culture: a comparison of model structures and training approaches},

author = {Timothy Hermanto and Kenny W.L. Lam and Bhagya S. Yatipanthalawa and Gregory J.O. Martin and Yih Yean Lee and Sally L. Gras},

doi = {10.1016/j.compchemeng.2026.109657},

issn = {0098-1354},

year  = {2026},

date = {2026-04-00},

journal = {Computers & Chemical Engineering},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ou2026,

title = {Comparative study of Bayesian Network-based root cause analysis methods for chemical and bioprocess systems},

author = {Paul Ou and Abel Armas Cervantes and Mansoureh Maadi and Kym Baker and Armando Camillo and Sally L. Gras and Michael Kirley},

doi = {10.1016/j.jprocont.2026.103674},

issn = {0959-1524},

year  = {2026},

date = {2026-04-00},

journal = {Journal of Process Control},

volume = {160},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Peng2026,

title = {Machine learning methods for small data and upstream bioprocessing applications: A comprehensive review},

author = {Johnny Peng and Thanh Tung Khuat and Katarzyna Musial and Bogdan Gabrys},

doi = {10.1016/j.biotechadv.2025.108749},

issn = {0734-9750},

year  = {2026},

date = {2026-03-00},

journal = {Biotechnology Advances},

volume = {87},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Softmax is not Enough (for Adaptive Conformal Classification)},

author = {Navid Akhavan Attar, Hesam Asadollahzadeh, Ling Luo, Uwe Aickelin},

url = {

https://doi.org/10.48550/arXiv.2602.19498

},

doi = { https://doi.org/10.48550/arXiv.2602.19498},

year  = {2026},

date = {2026-02-23},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pham2025b,

title = {Single-objective robust optimisation in bioprocessing with conformalised quantile regression as interval-based surrogate models},

author = {Tien Dung Pham and Robert Bassett and Uwe Aickelin},

doi = {10.1007/s11590-025-02239-9},

issn = {1862-4480},

year  = {2025},

date = {2025-09-24},

journal = {Optim Lett},

publisher = {Springer Science and Business Media LLC},

abstract = {Abstract

          We present a Monte Carlo-based robust optimisation framework that employs Conformalised Quantile Regression (CQR) as a surrogate model to identify robust operating conditions in various bioprocess single-objective optimisation problems. By generating adaptive and reliable prediction intervals, CQR enables the discovery of solutions that remain near-optimal under worst-case conditions. Through three case studies (upstream glucose feed optimisation, univariate downstream affinity chromatography, and multivariate cation exchange chromatography), we show that CQR-based solutions outperform those obtained with the traditionally used surrogate Gaussian Process Regression (GPR) in both maximin and minimax regret scenarios, particularly when process uncertainty is high. We further validate these robust solutions against mechanistic models, confirming their optimality and underscoring how effective uncertainty estimation leads to robustness. Our results establish this framework as a practical, data-driven decision-support tool for minimising yield losses and mitigating economic risks in biomanufacturing processes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pham2025,

title = {Capturing uncertainty in black-box chromatography modelling using conformal prediction and Gaussian processes},

author = {Tien Dung Pham and Robert Bassett and Uwe Aickelin},

doi = {10.1016/j.compchemeng.2025.109136},

issn = {0098-1354},

year  = {2025},

date = {2025-08-00},

journal = {Computers & Chemical Engineering},

volume = {199},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Khuat2025c,

title = {Uncertainty Quantification Using Ensemble Learning and Monte Carlo Sampling for Performance Prediction and Monitoring in Cell Culture Processes},

author = {Thanh Tung Khuat and Robert Bassett and Ellen Otte and Bogdan Gabrys},

doi = {10.1002/jrs.6808},

issn = {1097-4555},

year  = {2025},

date = {2025-07-00},

journal = {J Raman Spectroscopy},

volume = {56},

number = {7},

pages = {623--636},

publisher = {Wiley},

abstract = {ABSTRACTBiopharmaceutical products, particularly monoclonal antibodies (mAbs), have gained prominence in the pharmaceutical market due to their high specificity and efficacy. As these products are projected to constitute a substantial portion of global pharmaceutical sales, the application of machine learning models in mAb development and manufacturing is gaining momentum. This paper addresses the critical need for uncertainty quantification in machine learning predictions, particularly in scenarios with limited training data. Leveraging ensemble learning and Monte Carlo simulations, our proposed method generates additional input samples to enhance the robustness of the model in small training datasets. We evaluate the efficacy of our approach through two case studies: predicting antibody concentrations in advance and real‐time monitoring of glucose concentrations during bioreactor runs using Raman spectra data. Our findings demonstrate the effectiveness of the proposed method in estimating the uncertainty levels associated with process performance predictions and facilitating real‐time decision‐making in biopharmaceutical manufacturing. This contribution not only introduces a novel approach for uncertainty quantification but also provides insights into overcoming challenges posed by small training datasets in bioprocess development. The evaluation demonstrates the effectiveness of our method in addressing key challenges related to uncertainty estimation within upstream cell cultivation, illustrating its potential impact on enhancing process control and product quality in the dynamic field of biopharmaceuticals.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Khuat2025,

title = {Uncertainty Quantification Using Ensemble Learning and Monte Carlo Sampling for Performance Prediction and Monitoring in Cell Culture Processes},

author = {Thanh Tung Khuat and Robert Bassett and Ellen Otte and Bogdan Gabrys},

doi = {10.1002/jrs.6808},

issn = {1097-4555},

year  = {2025},

date = {2025-04-04},

journal = {J Raman Spectroscopy},

publisher = {Wiley},

abstract = {ABSTRACTBiopharmaceutical products, particularly monoclonal antibodies (mAbs), have gained prominence in the pharmaceutical market due to their high specificity and efficacy. As these products are projected to constitute a substantial portion of global pharmaceutical sales, the application of machine learning models in mAb development and manufacturing is gaining momentum. This paper addresses the critical need for uncertainty quantification in machine learning predictions, particularly in scenarios with limited training data. Leveraging ensemble learning and Monte Carlo simulations, our proposed method generates additional input samples to enhance the robustness of the model in small training datasets. We evaluate the efficacy of our approach through two case studies: predicting antibody concentrations in advance and real‐time monitoring of glucose concentrations during bioreactor runs using Raman spectra data. Our findings demonstrate the effectiveness of the proposed method in estimating the uncertainty levels associated with process performance predictions and facilitating real‐time decision‐making in biopharmaceutical manufacturing. This contribution not only introduces a novel approach for uncertainty quantification but also provides insights into overcoming challenges posed by small training datasets in bioprocess development. The evaluation demonstrates the effectiveness of our method in addressing key challenges related to uncertainty estimation within upstream cell cultivation, illustrating its potential impact on enhancing process control and product quality in the dynamic field of biopharmaceuticals.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Discepola2025,

title = {The effect of shear stress on bovine lactoferrin},

author = {Michele Discepola and Yiran Qu and Sally L. Gras and Sandra E. Kentish},

doi = {10.1016/j.idairyj.2025.106253},

issn = {0958-6946},

year  = {2025},

date = {2025-03-00},

journal = {International Dairy Journal},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Oetomo2025,

title = {Controlling tangential flow filtration in biomanufacturing processes via machine learning: A literature review},

author = {Bastian Oetomo and Ling Luo and Yiran Qu and Michele Discepola and Sandra E. Kentish and Sally L. Gras},

doi = {10.1016/j.dche.2024.100211},

issn = {2772-5081},

year  = {2025},

date = {2025-03-00},

journal = {Digital Chemical Engineering},

volume = {14},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Nik-Khorasani2025,

title = {Hyperbox Mixture Regression for process performance prediction in antibody production},

author = {Ali Nik-Khorasani and Thanh Tung Khuat and Bogdan Gabrys},

doi = {10.1016/j.dche.2025.100221},

issn = {2772-5081},

year  = {2025},

date = {2025-02-00},

journal = {Digital Chemical Engineering},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}