Skip to content

Overcoming Challenges Faced by AI Drug Discovery Startups: An Analysis of Turbine's Success Strategy

Biotech company in Budapest creates the first globally accessible, interpretable cell simulation platform, modeled as a "digital counterpart" of cellular systems, enabling countless virtual experiments.

Challenges faced by most AI drug discovery businesses - along with Turbine's approach to overcoming...
Challenges faced by most AI drug discovery businesses - along with Turbine's approach to overcoming these difficulties

Overcoming Challenges Faced by AI Drug Discovery Startups: An Analysis of Turbine's Success Strategy

Turbine, a groundbreaking biotech company, has developed the Simulated Cell platform - a biology-first, AI-powered virtual lab and the world's first interpretable cell simulation platform. This innovative technology is designed to revolutionise the pharmaceutical industry, potentially reducing reliance on animal experiments, accelerating discovery, and changing the economics of pharmaceuticals.

The Simulated Cell platform creates virtual cells that mimic molecular-level behaviour, modeled on real patient biology. It was developed over the first four to five years to make it scalable for use in drug discovery and development. The platform is trained on data from real biological systems, including lab-based experiments, animal studies, and human samples.

Initially, Turbine started out as a network science company, representing a cell as a network of proteins connected by interactions. However, the company later turned to machine learning to improve predictivity and flexibility. While this enhanced the platform's capabilities, it posed challenges in interpretability as it became more of a "black box". To address this, Turbine's model infers the wiring that led from A to B, across millions of experiments, making it interpretable and easier to understand.

The model used by Turbine's Simulated Cell platform is trained on the data primarily consisting of genomic information and protein-level measurements, most often transcriptomics. It learns fundamental rules of biology, such as how proteins interact with each other and how molecules can alter their function.

Turbine's technology has been applied to almost 30 programs, from target identification to indication expansion. Notable pharma companies such as AstraZeneca, Ono Pharmaceutical, Cancer Research Horizons, and Bayer are using Turbine's platform to guide their pipelines.

In August, Turbine entered into a one-year research partnership with MSD (Merck & Co.) to simulate hard-to-study cancer patient populations. The collaboration aims to uncover new therapeutic dependencies, insights that can help MSD prioritise drug targets, biomarkers, and combination strategies for validation in wet-lab experiments.

The Simulated Cell platform enables in silico experimentation to accelerate drug discovery and development across oncology and beyond. By using simulations before actual experiments, the likelihood of success is increased by two to three times. The platform was launched in April, allowing scientists to use Turbine's cellular simulation technology to tackle R&D challenges, including predicting a potential drug's performance in humans before a clinical trial.

If platforms like Turbine's succeed, they could potentially revolutionise the pharmaceutical industry, making it more efficient, ethical, and cost-effective. The future of drug discovery and development is undoubtedly virtual.

Read also: