Donate to Science & Enterprise

S&E on Mastodon

S&E on LinkedIn

S&E on Flipboard

Please share Science & Enterprise

A.I. Discovery Company Raises $123M in Venture Funds

Synthetic biology

(Gerd Altmann, Pixabay)

11 Aug. 2020. A company using image analysis and deep learning to discover therapies for diseases often considered difficult to treat is raising $123 million in new venture funds. The funding is Atomwise Inc.’s second venture round, bringing its total capital raised to nearly $175 million, according to the company.

Atomwise in San Francisco uses artificial intelligence to discover new drugs, with a variation of machine learning known as convolutional neural networks. A convolutional neural network combines image analysis and machine learning to dissect an image by layers for understanding features in the image. Different aspects of each layer discovered and analyzed by the algorithm are translated into data that the algorithm then uses to train its understanding of the problem being solved, with that understanding enhanced and refined as more images and data are encountered.

The Atomwise technology, called AtomNet, adapts statistical processing techniques of image analysis to parse the hierarchical structure of chemical compounds that number in the billions. These analytical processes identify the optimum mix of binding with protein targets and biological activities in the body, including interactions with other functions that affect the safety of therapy candidates.

The company says its technology makes possible highly sophisticated chemical analyses, without the repeated trial-and-error required in most drug discovery projects. AtomNet is based on research by company co-founder and current chief technology officer Izhar Wallach while at University of Toronto.

The company largely operates in partnerships with drug makers and biotechnology enterprises, but also academic researchers. In May, Atomwise said it’s undertaking 15 research collaborations with academic labs to find broad-spectrum therapies for SARS-CoV-2 viruses responsible for Covid-19 and other coronaviruses. The goal is to find long-term treatments for current Covid-19 infections, but also possible mutations in the SARS-CoV-2 virus as well as future coronaviruses that threaten global pandemics. The company says its technology screens up to billions of small molecule candidates to identify much smaller hit collections that Atomwise farms out to partnering labs for potency and selectivity testing.

In March, Science & Enterprise reported on a partnership between Atomwise and Bridge Biotherapeutics in Seongnam, Korea to discover new drugs addressing a set of proteins that regulate immune-related functions, including inflammation. The agreement that could bring Atomwise up to $1 billion, calls for the company to discover new drugs addressing Pellino E3 ubiquitin ligases, a collection of enzymes affecting immune system functions. Atomwise is expected to begin with Pellino enzymes regulating inflammation, although the deal covers discovery of up to 13 new drugs addressing these and other targets.

The new $123 million financing is led by B Capital Group and Sanabil Investments, with current investors DCVC, BV, Tencent, Y Combinator, Dolby Family Ventures, and AME Cloud Ventures. Joining the funding round, says the company, are two unnamed global insurance companies. Atomwise raised $45 million in its first venture round in March 2018.

The company expects to apply the funds to scaling up its AtomNet technology platform and expand its staff, with the goal of developing its own therapeutics pipeline. Abraham Heifets, CEO and co-founder of Atomwise, says in a company statement, “With support from our new and existing investment partners, we will be able to leverage this to develop our own pipeline of small molecule drug programs, further grow our portfolio of joint-venture investments, and realize our vision to create better medicines that can improve the lives of billions of people.”

More from Science & Enterprise:

*     *     *

Comments are closed.