Generative AI to transform Laboratory Testing

Dr. Tong

About the author



Share This Post

In recent years, hyperreal media has gained widespread attention for its ability to transform the entertainment industry, pop culture and visual effects. A new area of transformation is within laboratory testing, and Metaphysic is honored to have inspired advancements in science by Dr. Weida Tong, a lead researcher at the FDA’s National Center for Toxicological Research and Director of its Bioinformatics and Biostatistics division. 

Generative AI can transform Laboratory Testing

Dr. Tong has dedicated his career to finding alternatives to animal testing and found that AI can learn from past animal data to generate new data. He was inspired by our America’s Got Talent performance and seeing the power of AI technology in action. In his work, he created a virtual lab rat using the same deep generative adversarial network (GAN)-based framework to do synthetic animal testing. Dr. Tong and his team were able to generate new data results from existing animal studies and found that there was an 87% agreement between the results from the virtual lab rat compared to real data. 

Weida Tong
Credits: Arkansas Money & Politics

‘Elvis’ to help transform Laboratory Testing

At Metaphysic, we are always inspired and honored to be a part of all technological advancements to better the world and help people find new ways to own and control their biometric data. Our recent appearance on America’s Got Talent, the very one that inspired Dr. Tong in his research, showcased how hyperreal media can potentially change the entertainment industry. It can bring stars back to the stage, such as our work to bring back Elvis, or allow actors to transform their appearance to age or de-age. Metaphysic’s proprietary technology incorporates machine learning, algorithms, and software to create hyperreal media at scale. 

We advocate for people to know about the capabilities of hyperreal media and find ways for it to be a part of everyday life. To propel this mission, we launched Every Anyone, a platform that allows anyone to upload their image and create a hyperreal avatar that is securely backed by their biometric data. Metaphysic also formed Synthetic Futures, a community of individuals dedicated to educating people on ethics of synthetic media.

As we continue to build AI generation tools and infrastructure, we hope more people, such as Dr. Tong, will be inspired by the limitless possibilities in the industries of science, technology, entertainment and more. 

Full article from Dr. Weida Tong PHD here.

More To Explore


Solving the ‘Profile View Famine’ With Generative Adversarial Networks

It’s hard to guess what people look like from the side if you only have frontal views of their face; and the chronic lack of profile views in popular datasets makes this a stubborn data problem that’s standing in the way of 360-degree facial synthesis. Now, researchers from Korea are offering a method that might alleviate this traditional roadblock.


Repairing Demographic Imbalance in Face Datasets With StyleGAN3

New research from France and Switzerland uses Generative Adversarial Networks (GANs) to create extra examples of races and genders that are under-represented in historical face datasets, in an effort to offset controversies such as the tendency for facial recognition systems to fail to recognize (or to over-recognize) particular types of people.

It is the mark of an educated mind to be able to entertain a thought without accepting it.