1
|
Carou-Senra P, Ong JJ, Castro BM, Seoane-Viaño I, Rodríguez-Pombo L, Cabalar P, Alvarez-Lorenzo C, Basit AW, Pérez G, Goyanes A. Predicting pharmaceutical inkjet printing outcomes using machine learning. Int J Pharm X 2023; 5:100181. [PMID: 37143957 PMCID: PMC10151423 DOI: 10.1016/j.ijpx.2023.100181] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2023] [Revised: 04/13/2023] [Accepted: 04/15/2023] [Indexed: 05/06/2023] Open
Abstract
Inkjet printing has been extensively explored in recent years to produce personalised medicines due to its low cost and versatility. Pharmaceutical applications have ranged from orodispersible films to complex polydrug implants. However, the multi-factorial nature of the inkjet printing process makes formulation (e.g., composition, surface tension, and viscosity) and printing parameter optimization (e.g., nozzle diameter, peak voltage, and drop spacing) an empirical and time-consuming endeavour. Instead, given the wealth of publicly available data on pharmaceutical inkjet printing, there is potential for a predictive model for inkjet printing outcomes to be developed. In this study, machine learning (ML) models (random forest, multilayer perceptron, and support vector machine) to predict printability and drug dose were developed using a dataset of 687 formulations, consolidated from in-house and literature-mined data on inkjet-printed formulations. The optimized ML models predicted the printability of formulations with an accuracy of 97.22%, and predicted the quality of the prints with an accuracy of 97.14%. This study demonstrates that ML models can feasibly provide predictive insights to inkjet printing outcomes prior to formulation preparation, affording resource- and time-savings.
Collapse
Affiliation(s)
- Paola Carou-Senra
- Departamento de Farmacología, Farmacia y Tecnología Farmacéutica, I+D Farma (GI-1645), Facultad de Farmacia, Instituto de Materiales (iMATUS) and Health Research Institute of Santiago de Compostela (IDIS), Universidade de Santiago de Compostela, 15782, Spain
| | - Jun Jie Ong
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
| | - Brais Muñiz Castro
- IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain
| | - Iria Seoane-Viaño
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
| | - Lucía Rodríguez-Pombo
- Departamento de Farmacología, Farmacia y Tecnología Farmacéutica, I+D Farma (GI-1645), Facultad de Farmacia, Instituto de Materiales (iMATUS) and Health Research Institute of Santiago de Compostela (IDIS), Universidade de Santiago de Compostela, 15782, Spain
| | - Pedro Cabalar
- IRLab, Department of Computer Science, University of A Coruña, Spain
| | - Carmen Alvarez-Lorenzo
- Departamento de Farmacología, Farmacia y Tecnología Farmacéutica, I+D Farma (GI-1645), Facultad de Farmacia, Instituto de Materiales (iMATUS) and Health Research Institute of Santiago de Compostela (IDIS), Universidade de Santiago de Compostela, 15782, Spain
| | - Abdul W. Basit
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
- FabRx Ltd., Henwood House, Henwood, Ashford TN24 8DH, UK
- Corresponding authors at: Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK.
| | - Gilberto Pérez
- IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain
- Corresponding author at: IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain
| | - Alvaro Goyanes
- Departamento de Farmacología, Farmacia y Tecnología Farmacéutica, I+D Farma (GI-1645), Facultad de Farmacia, Instituto de Materiales (iMATUS) and Health Research Institute of Santiago de Compostela (IDIS), Universidade de Santiago de Compostela, 15782, Spain
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
- FabRx Ltd., Henwood House, Henwood, Ashford TN24 8DH, UK
- Fabrx Artificial Intelligence, Carretera de Escairón, 14, Currelos (O Saviñao) CP 27543, Spain
- Corresponding authors at: Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK.
| |
Collapse
|
2
|
Ong JJ, Castro BM, Gaisford S, Cabalar P, Basit AW, Pérez G, Goyanes A. Accelerating 3D printing of pharmaceutical products using machine learning. Int J Pharm X 2022; 4:100120. [PMID: 35755603 PMCID: PMC9218223 DOI: 10.1016/j.ijpx.2022.100120] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Revised: 05/26/2022] [Accepted: 05/29/2022] [Indexed: 12/11/2022] Open
Abstract
Three-dimensional printing (3DP) has seen growing interest within the healthcare industry for its ability to fabricate personalized medicines and medical devices. However, it may be burdened by the lengthy empirical process of formulation development. Active research in pharmaceutical 3DP has led to a wealth of data that machine learning could utilize to provide predictions of formulation outcomes. A balanced dataset is critical for optimal predictive performance of machine learning (ML) models, but data available from published literature often only include positive results. In this study, in-house and literature-mined data on hot melt extrusion (HME) and fused deposition modeling (FDM) 3DP formulations were combined to give a more balanced dataset of 1594 formulations. The optimized ML models predicted the printability and filament mechanical characteristics with an accuracy of 84%, and predicted HME and FDM processing temperatures with a mean absolute error of 5.5 °C and 8.4 °C, respectively. The performance of these ML models was better than previous iterations with a smaller and a more imbalanced dataset, highlighting the importance of providing a structured and heterogeneous dataset for optimal ML performance. The optimized models were integrated in an updated web-application, M3DISEEN, that provides predictions on filament characteristics, printability, HME and FDM processing temperatures, and drug release profiles (https://m3diseen.com/predictionsFDM/). By simulating the workflow of preparing FDM-printed pharmaceutical products, the web-application expedites the otherwise empirical process of formulation development, facilitating higher pharmaceutical 3DP research throughput.
Collapse
Affiliation(s)
- Jun Jie Ong
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
| | - Brais Muñiz Castro
- IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain
| | - Simon Gaisford
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK.,FabRx Ltd., Henwood House, Henwood, Ashford TN24 8DH, UK
| | - Pedro Cabalar
- IRLab, Department of Computer Science, University of A Coruña, Spain
| | - Abdul W Basit
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK.,FabRx Ltd., Henwood House, Henwood, Ashford TN24 8DH, UK
| | - Gilberto Pérez
- IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain
| | - Alvaro Goyanes
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK.,FabRx Ltd., Henwood House, Henwood, Ashford TN24 8DH, UK.,Departamento de Farmacología, Farmacia y Tecnología Farmacéutica, I+D Farma (GI-1645), Facultad de Farmacia, iMATUS and Health Research Institute of Santiago de Compostela (IDIS), Universidade de Santiago de Compostela, 15782, Spain
| |
Collapse
|
3
|
Aguado F, Cabalar P, Fandinno J, Pearce D, Pérez G, Vidal C. A Polynomial Reduction of Forks into Logic Programs. ARTIF INTELL 2022. [DOI: 10.1016/j.artint.2022.103712] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
4
|
Muñiz Castro B, Elbadawi M, Ong JJ, Pollard T, Song Z, Gaisford S, Pérez G, Basit AW, Cabalar P, Goyanes A. Machine learning predicts 3D printing performance of over 900 drug delivery systems. J Control Release 2021; 337:530-545. [PMID: 34339755 DOI: 10.1016/j.jconrel.2021.07.046] [Citation(s) in RCA: 51] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2021] [Revised: 07/22/2021] [Accepted: 07/29/2021] [Indexed: 12/16/2022]
Abstract
Three-dimensional printing (3DP) is a transformative technology that is advancing pharmaceutical research by producing personalized drug products. However, advances made via 3DP have been slow due to the lengthy trial-and-error approach in optimization. Artificial intelligence (AI) is a technology that could revolutionize pharmaceutical 3DP through analyzing large datasets. Herein, literature-mined data for developing AI machine learning (ML) models was used to predict key aspects of the 3DP formulation pipeline and in vitro dissolution properties. A total of 968 formulations were mined and assessed from 114 articles. The ML techniques explored were able to learn and provide accuracies as high as 93% for values in the filament hot melt extrusion process. In addition, ML algorithms were able to use data from the composition of the formulations with additional input features to predict the drug release of 3D printed medicines. The best prediction was obtained by an artificial neural network that was able to predict drug release times of a formulation with a mean error of ±24.29 min. In addition, the most important variables were revealed, which could be leveraged in formulation development. Thus, it was concluded that ML proved to be a suitable approach to modelling the 3D printing workflow.
Collapse
Affiliation(s)
- Brais Muñiz Castro
- IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain
| | - Moe Elbadawi
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
| | - Jun Jie Ong
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
| | - Thomas Pollard
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
| | - Zhe Song
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK
| | - Simon Gaisford
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK; FabRx Ltd., Henwood House, Henwood, Ashford, Kent, England TN24 8DH, UK
| | - Gilberto Pérez
- IRLab, CITIC Research Center, Department of Computer Science, University of A Coruña, Spain.
| | - Abdul W Basit
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK; FabRx Ltd., Henwood House, Henwood, Ashford, Kent, England TN24 8DH, UK.
| | - Pedro Cabalar
- IRLab, Department of Computer Science, University of A Coruña, Spain
| | - Alvaro Goyanes
- Department of Pharmaceutics, UCL School of Pharmacy, University College London, 29-39 Brunswick Square, London WC1N 1AX, UK; FabRx Ltd., Henwood House, Henwood, Ashford, Kent, England TN24 8DH, UK; Departamento de Farmacología, Farmacia y Tecnología Farmacéutica, I+D Farma (GI-1645), Facultad de Farmacia, Health Research Institute of Santiago de Compostela (IDIS), Universidade de Santiago de Compostela, 15782, Spain.
| |
Collapse
|
5
|
dos Santos TF, Santos PE, Ferreira LA, Bianchi RAC, Cabalar P. Heuristics, Answer Set Programming and Markov Decision Process for Solving a Set of Spatial Puzzles*. APPL INTELL 2021. [DOI: 10.1007/s10489-021-02423-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
6
|
Alonso-Betanzos A, Cabalar P, Dimuro GP, García M, Hernández-Orallo J, Hervás R, Manjarés Á, Martínez-Plumed F, Mora-Jiménez I, Sànchez-Marrè M. Editor's Note. IJIMAI 2021. [DOI: 10.9781/ijimai.2021.02.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
7
|
Santos PE, Cabalar P, Casati R. The knowledge of knots: an interdisciplinary literature review. Spatial Cognition & Computation 2019. [DOI: 10.1080/13875868.2019.1667998] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Affiliation(s)
- Paulo E. Santos
- Electrical Engineering Department, Centro Universitário da FEI, São Paulo, Brazil
- College of Science and Engineering, Flinders University, Adelaide, Australia
| | - Pedro Cabalar
- CITIC Research Center, University of A Coruña, A Coruña, Spain
| | - Roberto Casati
- Institut Jean Nicod, Ecole Normale Supérieure, Paris, France
- Ecole des Hautes Etudes en Sciences Sociales, Paris, France
| |
Collapse
|
8
|
|
9
|
Cabalar P, Fandinno J, Fariñas L, Pearce D, Valverde A. On the Properties of Atom Definability and Well-Supportedness in Logic Programming. Progress in Artificial Intelligence 2017. [DOI: 10.1007/978-3-319-65340-2_51] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
10
|
Santos PE, Cabalar P. Framing holes within a loop hierarchy. Spatial Cognition & Computation 2016. [DOI: 10.1080/13875868.2015.1091837] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
11
|
|
12
|
Santos PE, Cabalar P. The Space within Fisherman's Folly: Playing with a Puzzle in Mereotopology. Spatial Cognition & Computation 2008. [DOI: 10.1080/13875860801944804] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
13
|
Cabalar P, Pearce D, Valverde A. Reducing Propositional Theories in Equilibrium Logic to Logic Programs. Progress in Artificial Intelligence 2005. [DOI: 10.1007/11595014_2] [Citation(s) in RCA: 15] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
|