Unique strategy, novel technology.
radically expand the range of treatable cancers.
Most mutations are infrequent, understudied, and unaddressed — even on well-known oncogenes. As such, existing drugs target only the most common cancer-triggering mutations.
Our high-throughput, high-precision functional genomics approach opens up new therapeutic options for patients whose cancers are defined by the multitude of rarer cancer-triggering mutations that remain largely untreatable today.
The better we understand understudied mutations, the more patients we can reach. Here’s how.
We identify new mutation targets through functional genomics.
By monitoring the signaling pathway effects induced by hundreds of untested mutations through our Foresight platform, we screen for driver mutations and thus identify new hyper-specific targets.
We match hundreds of targets to candidate compounds.
Newly identified driver mutations are retested through Foresight for their response to different compounds. Compounds that reduce oncogenic signaling pathway activity are flagged as potential drug candidates, thus generating a range of potential new therapeutic applications.
We build new patient subpopulations.
Matching rare oncogenic mutations to experimentally effective drug candidates allows us to pinpoint the diverse patients who are expected to respond to the drug. We can therefore aggregate otherwise underserved rare cancer patients into significant new populations, optimize the clinical trial process and accelerate drug development.
We put partnerships at the heart of our strategy.
We focus on clinic-ready compounds and can accommodate a wide range of partnering structures. Our approach allows us to determine the best drug candidates without any inherent internal biases, thus circumventing the potential challenges and low probabilities of success associated with early research efforts.
Contact us at email@example.com to discuss a potential collaboration.
Our unique strategy is supported by novel technologies that merge experimental biology and machine learning at scale.
Our cell models are grounded in human data. We start by identifying addictive targets by using machine learning on population scale data, then use gene editing to synthesize all the mutations reported on our targets.
The synthesized mutations are transfected into live cells with and without candidate drug compounds and expressed using a patented method.
Following an incubation period, we deploy high content cellular microscopy to observe the mutations in action, with multiple channels capturing different tagged proteins.
We use machine learning to analyze the images and quantify each mutation’s functional effect and its response to candidate compounds. We aggregate this information for many mutations and use it to guide our clinical development programs.