Unlearn.ai raises $12M to increase the efficiency of clinical trials by inducing digital technology to the proces
Fremont, CA: Unlearn.ai, a company that provides software tools for clinical research, has secured $12 million in equity financing. Unlearn’s “digital twin” approach to trials, in which digital models are used in place of real estate subjects, reducing the number of people required to run the trial without giving up the sacrificing standards of evidence.
Unlearn’s technology can help find a solution for systemic reproducibility issues in clinical research, which a pair of surveys by Bayer and Amgen recently brought into sharp relief. Bayer reported successfully replicating just 25 percent of published preclinical studies it analyzed, while Amgen confirmed findings in only 6 of 53 landmark cancer studies (11 percent).
The company was co-founded by physicists Charles Fisher, Aaron Smith, and Jon Walsh. They, in the beginning, built the company’s platform on top of an AI architecture known as restricted Boltzmann machines (RBMs). RBMS is inspired by statistical mechanics and can model a person’s characteristics while remaining robust in the missing data. But, they poorly model data from different groups, producing blended rather than distinct distributions of, for instance, patients.
To address the issues and such shortcomings, the team architected an open-source package, called Paysage, which is an implemented unsupervised learning algorithms (for use when data that hasn’t been classified or labeled exists) comprising a hybrid of an RBM and generative adversarial networks(GANs): a Boltzmann Encoded Adversarial Machine (BEAM). GANs are two-part AI models that consist of a generator that creates samples for testing and a discriminator that conducts sequences to differentiate between the generated samples and real-world samples. This unique arrangement allows them to achieve impressive feats of media synthesis.
“Patients who volunteer for clinical trials take some risk; they could receive a treatment that doesn’t work, or experience serious side-effects. Therefore, it’s really important that we run these trials as efficiently as possible while providing reliable evidence to further medical science,” Fisher told VentureBeat via email. “We believe that our [platform] will have a profound impact on this problem, and are excited to partner with 8VC to realize a shared vision to use technology to improve the lives of patients.”
The Series A financing round was led by 8VC with the participation from all of Unlearn’s existing investors, including DCVC, DCVC Bio, and Mubadala capital ventures. Through its investment, 8VC principal Francisco Gimenez joins the company’s board of directors.
See also: Top Artificial Intelligence Companies