- Reverie Labs uses AI to develop new medicines.
- The drug research firm raised $25 million in Series A funding.
- Reverie Labs regularly screens drug discovery optimization libraries.
Reverie Labs is a startup that uses AI to develop new medicines. The company today announced the closure of its $25 million Series A round. The capital will be used to advance its internal and partnered drug discovery program. They developed the platform further and expanded its team of scientists and engineers.
Fewer than 12 percent of all drugs entering clinical trials end up in pharmacies. The journey from discovery to the marketplace takes at least 10 years for medicines to complete. According to the Pharmaceutical Research and Manufacturers of America, clinical trials alone take six to seven years, on average, putting the cost of R&D at about $ 2.6 billion. Such challenges are especially acute in oncology, where patient outcomes for many subtypes of cancer remain poor. Off-target toxicities, other than desired adverse effects on tissue, limit the effectiveness of many drugs.
Reverie Labs’ AI Modeling
It can predict important molecular properties for the discovery and optimization of drugs. The company develops special-purpose models that train on in-house datasets for things like bioactivity. It leverages large-scale distributed training and transfers learning. A model stores knowledge gained while solving one issue and applies it to a related issue.
To generate new ideas for molecules, we use computational techniques, from genetic algorithms to continuous latent models. Reverie explains on its website that we place a strong emphasis on generating molecules that are synthesizable, stable, and optimized against multiple criteria. Our data scientists can quickly train models on thousands of machines, and millions of compounds can be enumerated, searched, and prioritized every week by our medical chemists, allowing us to iterate incredibly quickly.
Reverie’s Response to Drug Optimization
Reverie says it regularly screens drug discovery optimization libraries of millions to billions of compounds. In addition, the company says it has invested for its data in building representations, including interpretable charts intended to help inform decision-making.
To date, for undisclosed oncology targets, Reverie has discovered selective, brain-penetrant kinase inhibitors. A kinase inhibitor is a type of enzyme inhibitor that blocks the action of one or more protein kinases that add and modulate the function of a phosphate group to a protein. In July, Reverie announced a collaboration with Roche and Genentech, a subsidiary of Roche, to assist with the discovery of several kinase inhibitor programs. Reverie received an upfront payment and is entitled to receive payments for preclinical, clinical and regulatory milestones, as well as royalties on Roche’s sales of the partnership’s drug candidates.
Reverie’s latest funding round was led by Ridgeback Capital Investments. That brings the total raised by the Cambridge, Massachusetts-based company to over $32 million.