Using Artificial Intelligence to Build a Better Organoid
New technology will allow 3D printing of structures that mimic functions of human organs
The next breakthrough for artificial intelligence may help scientists design and print smarter cell structures that mimic human organs - thereby reducing trial-and-error and costs while contributing to new methods to fight disease and improve human health.
These three-dimensional cell structures are called organoids - they can be designed to exhibit unique organ function and are used to conduct complex research on human tissue physiology, genetic diseases, organ-specific infectious diseases and cancer. Organoids can replicate development of native tissue in the architecture, function, cellular composition and transcriptional profile of almost any organ.
But, there are limitations. Current methods of manufacturing organoids have yet to demonstrate consistent and robust extraction of mature organoids from renewable cells. This is where AI comes into the picture - designing and testing organoids utilizing computers rather than traditional lab methods.
Ipsita Banerjee at the University of Pittsburgh Swanson School of Engineering, together with a multi-disciplinary team of several co-principal investigators, recently received a $500,000 award from the National Science Foundation to realize their vision of scalable production of high-quality organoids.
“Our vision is to enable organoid technology to finally realize its potential in clinical research and drug development,” said Banerjee, professor of chemical and petroleum engineering. “This breakthrough research will benefit society and the healthcare system at large by creating a more efficient, effective and sustainable way to design these structures.”
Most organoid production relies on chemical experiments, but Banerjee’s approach involves engaging mechano-transduction pathways, or the process in which cells respond to mechanical stimuli, to regulate manufacturing while also exploiting cytoskeletal rearrangements that are part of the organoid phenotype. The mechano-transduction will be controlled by bioprinting the organoid phenotype, while machine learning models will identify signature cytoskeletal states associated with the phenotype.
The team predicts using artificial intelligence models will also enhance accuracy in predictions of organoid behavior for further research.
“Central to our goal of organoid manufacturing is the integration of bioprinting and artificial intelligence to enable automated and non-invasive learning of different types of organoids,” Banerjee explained. “Bioprinting also will enable us to scale up the production of these structures in quantity and quality over time, without the restrictions we currently face using traditional methods.”
This will be the first attempt to create a roadmap to producing high quality organoids, as well as integrate quality control in the manufacturing pipeline.
“This will be a novel application of artificial intelligence techniques in the organoid research field,” said Shandong Wu, a co-principal investigator for the project and artificial intelligence expert in the Department of Radiology at the University of Pittsburgh. “In recent years, artificial intelligence, especially machine learning, has shown transformative power in analyzing medical imaging data. The adoption of machine learning into biological image processing will create an innovative avenue for robust organoid function assessment.”
Banerjee will be joined by a multi-disciplinary collaborator team:
- Prashant Kumta, the Edward R. Weidlan Chair Professor of Bioengineering at Pitt
- Shandong Wu, associate professor in radiology, biomedical informatics, bioengineering, intelligent systems and clinical and translational science at the Center for Artificial Intelligence Innovation in Medical Imaging
- Yong Fan, associate professor at Allegheny Health Network
- Kimberly Forsten Williams, associate professor at Rangos School of Health Sciences Engineering at Duquesne University
- Bin Yang, assistant professor Rangos School of Health Sciences Engineering at Duquesne University