Advancing algorithmic drug product development - Recommendations for machine learning approaches in drug formulation

Aug 3, 2026

Artificial intelligence has strong potential to reshape pharmaceutical workflows, from discovery through clinical translation. Machine learning enables streamlined in silico modelling and supports more efficient formulation development, yet practical modelling guidance remains limited for drug product work. This review analyzes data-driven modelling practices, highlights risks of unreliable predictions from suboptimal approaches, and addresses the dominance of benchtop experimental targets. Recommendations are provided to improve model trustworthiness, transparency, reliability, and to guide future directions toward robust tools for formulators.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Data-driven modelling in drug product development

Challenges in model reliability and interpretability

Recommendations for trustworthy machine learning

Future directions for robust guidance

University of Southern Denmark Advancing algorithmic drug product development Recommendations for machine learning approaches in drug formulation Murray, Jack D. ; Lange, Justus J. ; Bennett-Lenane, Harriet; Holm, René; Kuentz, Martin; O'Dwyer, Patrick J. ; Griffin, Brendan T. Published in: European Journal of Pharmaceutical Sciences DOI: 10.1016/j.ejps.2023.106562 Publication date: 2023 Document version: Final published version Document license: CC BY Citation for pulished version (APA): Murray, J. D. , Lange, J. J. , Bennett-Lenane, H. , Holm, R. , Kuentz, M. , O'Dwyer, P. J. , & Griffin, B. T. (2023) . Advancing algorithmic drug product development: Recommendations for machine learning approaches in drug formulation. European Journal of Pharmaceutical Sciences, 191, Article 106562. [https://doi.org/10.1016/j.ejps.2023.106562](https://doi.org/10.1016/j.ejps.2023.106562) Go to publication entry in University of Southern Denmark's Research Portal Terms of use This work is brought to you by the University of Southern Denmark. Unless otherwise specified it has been shared according to the terms for self-archiving. If no other license is stated, these terms apply: • You may download this work for personal use only. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying this open access version If you believe that this document breaches copyright please contact us providing details and we will investigate your claim. Please direct all enquiries to [puresupport@bib.sdu.dk](puresupport@bib.sdu.dk) Download date: 02. Aug. 2026 European Journal of Pharmaceutical Sciences 191 (2023) 106562 Contents lists available at ScienceDirect European Journal of Pharmaceutical Sciences journal [homepage: www.elsevier.com/locate/ejps](homepage: www.elsevier.com/locate/ejps) | Advancing algorithmic drug product development: Recommendations for machine learning approaches in drug formulation
Jack D. Murray a, Justus J. Lange a, b, Harriet Bennett-Lenanea, Ren´e Holm c, Martin Kuentz d, Patrick J. O’Dwyer a, Brendan T. Griffin a, *
a School of Pharmacy, University College Cork, Cork, Ireland
b Roche Pharmaceutical Research & Early Development, Pre-Clinical CMC, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd, Grenzacherstrasse 124, Basel, Switzerland
c Department of Physics, Chemistry and Pharmacy, University of Southern Denmark, Campusvej 55, Odense 5230, Denmark d School of Life Sciences, University of Applied Sciences and Arts Northwestern Switzerland, Muttenz CH 4132, Switzerland | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Keywords:
Machine learning
Artificial intelligence Computational pharmaceutics Drug formulation
Data-driven modelling Property prediction | | Artificial intelligence is a rapidly expanding area of research, with the disruptive potential to transform traditional approaches in the pharmaceutical industry, from drug discovery and development to clinical practice. Machine learning, a subfield of artificial intelligence, has fundamentally transformed in silico modelling and has the capacity to streamline clinical translation. This paper reviews data-driven modelling methodologies with a focus on drug formulation development. Despite recent advances, there is limited modelling guidance specific to drug product development and a trend towards suboptimal modelling practices, resulting in models that may not give reliable predictions in practice. There is an overwhelming focus on benchtop experimental outcomes obtained for a specific modelling aim, leaving the capabilities of data scraping or the use of combined modelling approaches yet to be fully explored. Moreover, the preference for high accuracy can lead to a reliance on blackbox methods over interpretable models. This further limits the widespread adoption of machin

FAQs

Why is machine learning important for drug product development?

Machine learning improves in silico modelling and can streamline clinical translation by enabling data-driven approaches for formulation development.

What limitations in current drug product ML modelling does the review highlight?

It notes limited formulation-specific guidance, a tendency toward suboptimal practices, and models that may not produce reliable predictions in real-world use.

How does the review suggest improving trustworthiness of ML models?

It presents recommendations aimed at ensuring trustworthiness, transparency, and reliability, reducing dependence on black-box methods and improving interpretability for formulators.

Aug 3, 2026

Upload by Theodore