Artificial Intelligence Molecular Screen (AIMS)


Awards program by Atomwise for academic researchers seeking novel compounds to treat disease.



10,000,000 molecules analyzed for your disease by artifical intelligence.
72 compounds delivered to your lab, ready for testing.
$0 cost.

Why did Atomwise create this award?

The goal of this program is to broaden the pool of scientists involved in the discovery of small molecules for the treatment and investigation of human diseases. To advance this goal, Atomwise seeks proposals from innovative university scientists to receive 72 potential medicines, generated specifically for their research by artificial intelligence. This Artificial Intelligence Molecular Screen (AIMS) program is designed to dramatically accelerate the race towards life-saving drugs by analyzing millions of compounds for each disease. Contributing AI technology and delivering physical molecules to up to 100 labs, the program is the first of its kind.

What will awardees receive?

AIMS awardees will receive the following:

  • Customized small molecule virtual screen using AtomNet™ technology
  • 72 small molecules predicted to bind to a specific target protein
  • Ordering of small molecules from suppliers, QC verification by mass spectrophotometry, resuspension and dilution to a convenient concentration, aliquoting into microtiter plates, and delivery to the researcher’s lab
  • Support from Atomwise medicinal chemists and computational biologists
  • Additional small molecules and support if criteria are met

What kind of projects are the best fit for an AIMS award?

Atomwise will consider an award for any project that can benefit from our expertise and technology. Project topics may be in any area, including those in agriculture, animal health, biotechnology, human biology, medicine, microbiology, plant biology, and virology. Highly suitable projects for the award will have both:

A target protein with:

  • An X-ray crystal structure or good homology model, AND
  • An identified site for the small molecule to bind

An established assay(s) that can:

  • Test at least 72 small molecules, AND
  • Directly measure protein function or activity, AND
  • Measure IC50 or equivalent.

Application Process

AIMS is a streamlined program. Short applications are submitted online, and recipients will be announced three months from the submission deadline. No preliminary data is required and projects showing success can receive further support.


  • Deadline for proposals:
    Extended to March 30, 2018
  • Announcement of recipients: May 2018


About Atomwise

Atomwise develops artificial intelligence systems for drug discovery. Its groundbreaking AtomNet technology reasons like a human medicinal chemist, using powerful Deep Learning algorithms and supercomputers to analyze millions of potential treatments each day. Atomwise has already launched 27 drug discovery projects with leading research institutions. These partnerships are advancing research on diseases as diverse as Ebola, multiple sclerosis, and leukemia. Molecules predicted by Atomwise have become lead medicinal chemistry candidates and successfully treated animals in trials.

Left: Ebola virus replicating in a human host cell.

Powered by AtomNet™


The first deep learning neural network for structure-based drug design and discovery.


AtomNet autonomously learning to identify sulfonyl groups.

AtomNet’s accuracy compared to previous technologies on the DUD-E benchmark developed at UCSF.