Researchers at Collaborations Pharmaceuticals were in for a surprise when they tweaked their AI model for drug discovery to look for biochemical weapons. The machine learning algorithm found 40,000 options in just six hours.

Collaborations Pharmaceuticals recently published computational machine learning models for toxicity prediction in different areas. The company explored how AI could be used to design toxic molecules and it evolved into a computational proof of concept for making biochemical weapons. 

The model generated 40,000 molecules that scored within the desired threshold. In the process, the AI designed not only VX but also many other known chemical warfare agents. Many new molecules were also designed that looked equally plausible. These new molecules were predicted to be more toxic, based on the predicted LD50 values, than publicly known chemical warfare agents. Interestingly, the datasets used for training the AI did not include these nerve agents. 
The paper, Dual use of artificial-intelligence-powered drug discovery, is a wake-up call for the companies in the ‘AI in drug discovery’ community. Though some domain expertise in chemistry or toxicology is still required to generate toxic substances or biological agents that can cause significant harm, when these fields intersect with machine learning models, all you need is the ability to code and to understand the output of the models.