The technological revolution has headed towards most of the industries. Even the chemical industry is untouched with this AI swift. According to the latest study, IBM, the biggest player in Artificial Intelligence has developed a program which predicts the outcomes of organic chemical reactions. This program is based on language translation software, where it thinks atoms as letter and molecules as words.
“Instead of translating English into German or Chinese, we had the same artificial intelligence technology look at hundreds of thousands or millions of chemical reactions and had it learn the basic structure of the ‘language’ of organic chemistry, and then had it try to predict the outcomes of possible organic chemical reactions,” says study co-author Teodoro Laino at IBM Research in Zurich.
“We want to help chemists design new synthesis routes for organic compounds,” Laino says. Synthesizing pharmaceuticals and other complex organic compounds is often a difficult task, “maybe requiring 30 or 40 steps,” he explains. “There’s a huge effort in the commercial sector to find shortcuts to skip a couple of steps, with the benefit of decreasing time and increasing yields.”
This Artificial Intelligence program is basically an artificial neural network where neurons are fed with data and cooperate to solve the problems. The network repeatedly adjusts the connections between its neurons to solve the problem. The task is done in a loop to find the best computing results.
This program is based on the principle where it doesn’t have to learn organic chemistry to predict the outcome reaction. It is as similar as a child who grows up speaking a native language can speak it efficiently but doesn’t know the rules of it. It also provides multiple solutions when it thinks the components can have more than two chemical reaction outcomes.
According to Philippe Schwaller, “This AI based IBM program achieves up to 80% accuracy.” The largest molecule, this program has processed has 150 atoms. However, it is just a number, there’s no theoretical reason IBM can’t work with larger molecules.
Predicting the future of this program, Mr. Gaudin of IBM Research, Zurich says that, “we plan to make this available to everyone through a cloud service, we also want to reach accuracies of 90 percent or even above. One way to do that is instead of having just a general organic chemistry model, we have more specialized models focused on specific classes of organic chemical reactions.”
Not only this, IBM plans to include factors like temperature, solvent, and pH in their AI learn. This program can thus speed up the formation of new drugs and could come out as a boon in the chemical industry. However, since the AI is not perfect, we can’t list the organic chemists in the list of jobs that AI will take over by 2030. We still need organic chemists to monitor the process and analyze the outcome reactions.