Independent education resourceInformation here does not replace care from a qualified health professional.
Peptide Therapy GuideClear peptide education

Educational guide

Lilly Inks Up-to-$560M AI Drug Discovery Collaboration with Atomwise

Eli Lilly will support its drug discovery efforts through an up-to-$560 million partnership with Atomwise to develop up to ten drug targets selected by the pharma giant, using the San Francisco company’s artificial intelligence (AI) technology. The partnership

Written by Peptide Therapy Guide Editorial Team
For education only

This guide cannot diagnose a condition or recommend a personal treatment plan. Discuss medical questions with a qualified professional.

Eli Lilly will support its drug discovery efforts through an up-to-$560 million partnership with Atomwise to develop up to ten drug targets selected by the pharma giant, using the San Francisco company’s artificial intelligence (AI) technology.

The partnership, announced by Atomwise, aims to speed up target identification and drug development by tapping in to Lilly’s expertise in virtual library design, the large number of molecules enabled by automated synthesis that Lilly has in its robotic laboratory, and Atomwise’s analytical know-how, which will be applied to help Lilly molecules that hold potential as new therapeutics for specific diseases.

“Lilly has made it clear that they are focused on developing drugs for novel target proteins, which are often challenging and less well studied,” Atomwise CEO Abraham Heifets, PhD, said in a statement. “Our expertise and tools have been shown to succeed with these kinds of targets, and therefore could be a key to unlocking success for patients.”

Lilly has agreed to pay Atomwise up to $1 million per target in discovery milestones, as well as up to $550 million in payments tied to achieving potential development and commercialization milestones for all targets. As part of the agreement, Atomwise said, it will have the option to develop compounds from the collaboration that Lilly chooses not to advance into clinical testing.

Atomwise uses AI for its structure-based, drug design technology, which is designed to enable scientists to predict how well a small molecule will bind to a target protein of interest, as well as remove sole reliance on empirical screening. The company says its tech can screen billions of compounds, and has demonstrated success using homology-modeled proteins.

More than 60 partnerships

Lilly is not the first pharma to sign a collaboration agreement with Atomwise, which has partnerships established with more than 60 biopharmas and academic institutions. Atomwise said it now supports discovery projects in more than 100 universities and hospitals in 19 countries, across every major therapeutic area.

In January, for example, Atomwise signed a strategic alliance with Charles River Laboratories that could generate potentially more than $2.4 billion in royalties for the AI platform developer. Charles River agreed to use Atomwise’s technology in preclinical research, in return for paying Atomwise a technology access fee for each project; payments tied to milestones in hit discovery, hit-to-lead, and lead optimization; plus royalties from clients.

Other biopharma giants teaming up with Atomwise include AbbVie and Merck & Co. Also partnering with Atomwise is Pfizer, which has agreed to assess Atomwise’s platform for identifying potential drug candidates for up to three target proteins selected by Pfizer. In return for the access, Pfizer agreed to pay a technology access fee and additional milestone payments for each target protein of interest; the amounts were not disclosed at the time.

Established in 2012, Atomwise has raised over $50 million from venture capital firms to support the development and application of its AI technology. Most of that consists of a $45 million Series A financing completed in March 2018, led by Monsanto Growth Ventures, DCVC (Data Collective), and B Capital Group.

Connected reading

Helpful context for this guide

Source-derived material selected through this article’s indexed topics.

Related questions

01Undruggable or unscreenable?

Another obstacle to discovering new PPI inhibitors is the lack of libraries designed to hunt for them, points out Philippe Roche, PhD, senior scientist at the Integrative Structural and Chemical Biology team at the Cancer Research Center of Marseilles, France. “If you screen PPIs using libraries that were designed for kinases or GPCRs, that’s why you don’t get a lot of good results,” he says. To that end, his group began assembling a library focused on orthosteric inhibitors of PPIs. The result was 2P2Idb, a hand-curated, structural database cataloguing orthosteric inhibitors of PPIs for which the interface had been 3D characterized. From analyzing these known PPI inhibitors, and what structures they had in common, Roche and his colleagues developed a model to predict whether compounds would likely inhibit PPIs. Using this method, 2P2Idb creates an enriched screening library that dramatically increases the hit rate compared to standard libraries. Having proven their success with a small library of 1600 compounds, they are in the process of expanding the library to 10,000 compounds. Once that’s published, “the idea is to make this library available to labs around the world,” Roche says. “We will provide the library free of charge for people to be able to screen PPI targets.”

Source: www.genengnews.com ↗
02How stable is the antibody?

A crucial question often addressed during preclinical development focuses on the in vivo stability of therapeutic antibodies. Increasing the half-life of a therapeutic antibody has several benefits ranging from higher treatment efficacy to increased advantages for the patients who will have a fewer number of therapy sessions and a reduced cost. Given these compelling benefits, following the identification of therapeutic antibodies with the desired specificity, developers usually subject them to a refinement step to increase their stability. This process is often hindered by the lack of reliable experimental tools to predict the half-life of antibodies in patients. The major hurdle of using mouse models to predict antibody stability in the serum lies in the way immunoglobulin proteins are processed by the organism. In mammals, most proteins circulating in the serum undergo constant uptake by endothelial cells and are routed through the endosomes to the lysosomal compartment for degradation. In the endosomes, immunoglobulin G (IgG) proteins are recognized and bound by a transmembrane protein, called the neonatal Fc receptor (FcRn), which mediates their recycling to the plasma membrane and subsequent release back into the serum. As a result, the half-life of IgGs are significantly extended by this mechanism. Since most therapeutic antibodies belong to the IgG class, this recycling system is very relevant for their relative stability in the body. Remarkably, the relative affinity between IgGs and FcRn is extremely disparate between different species, with the mouse receptor showing a much higher affinity than its human counterpart.

Source: www.genengnews.com ↗
P

About the author

Peptide Therapy Guide Editorial Team

Editorial team for Peptide Therapy Guide.

View all articles →

Continue learning

Related guides