AI isn’t close to curing cancer. This startup says it knows what it will take.
A biotech startup called Vivodyne says the AI drug-discovery industry has a data problem, and that it has built a machine to fix it. The company's autonomous biology labs can grow 20 kinds of human tissue, then autonomously dose and monitor them, generating the kind of ca…
Intelligence analysis by Llama
Vivodyne, a biotech startup, claims that the AI drug-discovery industry lacks data and has built a machine to generate causal biological data. The company's autonomous labs can grow human tissue and monitor its behavior, which could accelerate the development of new drugs.
Imagine you have a big box of LEGOs, and you want to build a specific castle. But instead of using the right instructions, you're just trying different combinations of LEGOs to see what works. That's basically what's happening in the AI drug-discovery industry right now. Vivodyne wants to change that by creating a machine that can grow human tissue and monitor its behavior, which will help create better instructions for building new drugs.
Analysis
Vivodyne's Challenge to AI Drug Discovery
Vivodyne, a biotech startup spun out of the University of Pennsylvania in 2021, claims that the AI drug-discovery industry has a data problem. The company's CEO and co-founder, Andrei Georgescu, says that existing models don't have the data to capture the complexity of human biology.
Georgescu believes that the space needs a 'sanity check' - that existing models don't have the data to capture the complexity of human biology. He points to studies like this one, published in Nature Methods last month, that find no clear data scaling laws when training generative AI models on existing cellular data.
The HIVE Machines
Vivodyne's plan is to accelerate the path of drug candidates by having a better idea of what will work before going through the expense of a clinical trial, which typically costs tens of millions of dollars. The company has built a machine called HIVE, which can grow 20 kinds of human tissue, then autonomously dose and monitor them, generating the kind of causal biological data that today’s AI models are missing.
The Future of Drug Discovery
Georgescu sees his autonomous biology labs as key to generating the kind of causal data that can be used to train new models on human biology. He believes that will be key not just for today’s medicine challenges, but also for a future where complex diseases require drugs that, unlike the majority of those available today, target multiple pathways.
The Road Ahead
Vivodyne's HIVE machines are tracking hundreds of thousands of ongoing experiments where diseased tissue is exposed to some stimulus, which Georgescu expects to provide the kind of reinforcement learning that will produce AI models that understand human biology enough to make more meaningful progress in healthcare.
Key points
- Vivodyne claims that the AI drug-discovery industry has a data problem and has built a machine to fix it.
- The company's autonomous biology labs can grow 20 kinds of human tissue and monitor its behavior.
- Vivodyne's technology could lead to the development of new and more effective treatments for diseases.
- The company is working with multiple major pharma companies to solve the problem of data in AI drug discovery.
If Vivodyne's technology is successful, it could lead to the development of new and more effective treatments for diseases. This could also lead to the creation of combination therapies that target multiple pathways, which could be a game-changer for complex diseases.
However, there are still many challenges to overcome before Vivodyne's technology can be widely adopted. For example, the company will need to demonstrate that its HIVE machines can produce consistent and reliable results. Additionally, the pharmaceutical industry will need to be willing to adopt new technologies and approaches, which can be a slow process.
