Related Experiment Video
Updated: Dec 24, 2025
08:34
Bioprinting Cellularized Constructs Using a Tissue-specific Hydrogel Bioink
Published on: April 21, 2016
17.2K
Machine learning-based design strategy for 3D printable bioink: elastic modulus and yield stress determine
Jooyoung Lee1, Seung Ja Oh1, Sang Hyun An2
1Center for Biomaterials, Biomedical Research Institute, Korea Institute of Science and Technology, Seoul 02792, Republic of Korea.
Biofabrication
|April 7, 2020
Summary
Machine learning aids in designing 3D-printable bioinks from natural materials. This method optimizes bioink properties for high shape fidelity in 3D constructs, ensuring cell viability and proliferation.
Area of Science:
- Biomaterials Science
- Biotechnology
- Regenerative Medicine
Background:
- Designing 3D-printable bioinks with desired properties is challenging.
- Naturally derived biomaterials offer potential but require careful formulation.
- Existing methods lack predictive power for optimizing bioink printability.
Purpose of the Study:
- To develop a machine learning-based strategy for designing 3D-printable bioinks.
- To identify key mechanical properties governing bioink printability and shape fidelity.
- To create high-fidelity, cell-laden 3D constructs using optimized bioinks.
Main Methods:
- Comparative analysis of native collagen (NC) and atelocollagen (AC) for printability.
- Machine learning model development to correlate mechanical properties with printability.
- Multiple regression analysis to derive optimal bioink formulations.
- Fabrication of cell-laden 3D hydrogel constructs.
Main Results:
- Atelocollagen (AC) exhibits superior printability over native collagen (NC) due to its rheological properties.
- A universal relationship between mechanical properties (elastic modulus, yield stress) and printability was established using machine learning.
- Optimized bioink formulations achieved high shape fidelity in 3D printed constructs.
- Encapsulated cells demonstrated high viability and proliferative capacity within the 3D constructs.
Conclusions:
- Machine learning provides an effective approach to design advanced 3D-printable bioinks.
- Optimized bioinks based on naturally derived materials can achieve high shape fidelity for complex 3D tissue engineering.
- This strategy supports the development of functional 3D cell-laden constructs for regenerative medicine applications.
