By treating atoms as letters and understanding molecules as words, IBM's artificial intelligence software is using the same methods as machine translation to predict the results of organic chemical reactions, thereby accelerating the development of new drugs.
Over the past 50 years, scientists have tried to teach the principles of computer chemistry to enable computers to predict the outcome of organic chemical reactions. However, organic chemicals can be very complex, so the simulation of their reaction processes can be very time consuming and inaccurate.
Instead, IBM researchers applied artificial intelligence (AI) programs commonly used for language translation to organic chemistry. On December 4th, at the Neuroinformatics Systems Conference in Long Beach, California, scientists detailed their findings. Teodoro Laino, a collaborator of related research papers at the IBM Research Institute in Zurich, said: "I don't translate English into German or Chinese, but use the same artificial intelligence technology to process hundreds of thousands or even millions of chemical reactions. Let them learn the basic structure of organic chemistry "language" and then try to predict the results of possible organic chemical reactions."
"We want to help chemists design new synthetic routes for organic compounds," Laino said. Synthetic drugs and other complex organic compounds are often a daunting task, “may take 30 or 40 steps,†he explained. “The business sector has been looking for shortcuts to skip a few steps, thus reducing time and increasing production.â€
The new AI program is an artificial neural network. In this network, components called neurons use existing data to solve a problem, such as translating sentences, and then the neural network repeatedly adjusts the connections between its neurons and see if these new connection patterns are better. Solve the problem. Over time, the neural network will find out which model can calculate the best solution, and the process is very similar to the learning process of the human brain. Laino said: "This way of reasoning and learning is very similar to that of organic chemists in real life."
A native-speaking child may not know the rules of the language, but know how to use it. Similarly, this new artificial intelligence software never learns how organic chemistry works, but still predicts the results of chemical reactions. If artificial intelligence believes that a chemical reaction may have more than one outcome, it will provide multiple solutions ranked by likelihood.
Philippe Schwaller, co-author of the research paper and IBM Research Institute in Zurich, said: "It can achieve 80% accuracy. Schwaller said: So far, the largest molecule processed by artificial intelligence contains 150 atoms. Co-author of the research report, Zurich Théophile Gaudin of the IBM Research Institute said: "We can use longer molecules if needed, which is theoretically feasible. â€
In the future, "We plan to offer this service to everyone through cloud services," Gaudin said. “We also want to achieve an accuracy of 90% or higher. One way to achieve this is to use a more specialized model that focuses on specific types of organic chemical reactions without using a generic organic chemical model.â€
In addition, future researchers may incorporate factors such as temperature, solvent and pH into the chemical reactions of AI learning, Laino said. However, this will require careful examination of the accuracy of all of this additional data. In addition, “we also want to conduct social experiments so that we can find organic chemistry experts and examine the competition between our models and their models,†Gaudin said. Because artificial intelligence is still not perfect, organic chemists still need to follow up. “We created this tool not to replace organic chemists, but to help them,†Laino said. 
ZGAR electronic cigarette uses high-tech R&D, food grade disposable pod device and high-quality raw material. All package designs are Original IP. Our designer team is from Hong Kong. We have very high requirements for product quality, flavors taste and packaging design. The E-liquid is imported, materials are food grade, and assembly plant is medical-grade dust-free workshops.
Our products include disposable e-cigarettes, rechargeable e-cigarettes, rechargreable disposable vape pen, and various of flavors of cigarette cartridges. From 600puffs to 5000puffs, ZGAR bar Disposable offer high-tech R&D, E-cigarette improves battery capacity, We offer various of flavors and support customization. And printing designs can be customized. We have our own professional team and competitive quotations for any OEM or ODM works.
We supply OEM rechargeable disposable vape pen,OEM disposable electronic cigarette,ODM disposable vape pen,ODM disposable electronic cigarette,OEM/ODM vape pen e-cigarette,OEM/ODM atomizer device.
ZGAR Disposable Vape 25 Disposable Vape, bar 3000puffs,ZGAR Disposable Vape 25, Disposable E-cigarette, ZGAR Disposable Vape 25 OEM/ODM disposable vape pen atomizer Device E-cig, ZGAR 25 Vape
Zgar International (M) SDN BHD , https://www.zgarvapor.com