The hottest AI chemical AI is liberating the hands

  • Detail

Ai+ chemical AI is freeing the hands of chemists

ai+ chemical AI is freeing the hands of chemists

may 13, 2019

recently, the Xiangshan Science conference focused on green ecology and chemical engineering. In addition to various cutting-edge chemical technologies, the application of AI in this field has become a new topic of concern

"there are too many variables in the synthetic chemistry process, which indeed makes it more difficult to prepare flux and screen flux reaction conditions. However, in the era of big data and artificial intelligence, this situation will greatly change the coating." Madawei, deputy director of Shanghai Institute of organic chemistry, Chinese Academy of Sciences, introduced at the meeting that artificial intelligence is expected to help synthetic chemistry research to a new level

"labor intensive" will be a thing of the past

"in the field of organic synthesis, synthetic chemists claimed to give sufficient students and financial support in the last century, which can perform the" Three Kingdoms kill "of any complex organic small molecule in the cathode material of the main battlefield of synthetic power battery technology. But until now, no matter new drug development or new material development, people have found that the decisive step in the process is often the synthesis of compounds. " Madawei introduced

Ma Dawei explained that this is because although most of the evaluation of compound properties has entered the flux screening stage, the chemical synthesis is still in the manual operation stage

in the field of chemical synthesis, due to the infinite changes under different chemical reaction conditions, researchers still rely on manual work to design chemical synthesis routes, especially in the field of drug molecular synthesis. This makes chemical synthesis more like a "labor-intensive" job

however, in the era of artificial intelligence, this situation will gradually become a thing of the past. Computer programs based on big data and artificial intelligence are becoming more and more mature and practical in assisting researchers to design chemical synthesis routes

last April, a German research team published a paper in the journal Nature, saying that they can conduct chemical synthesis analysis at an unprecedented rate with the help of artificial intelligence system, which will greatly improve the efficiency of researchers in developing new drugs and other compounds

according to the content of this paper, researchers use artificial intelligence system to design a molecular synthesis route, which takes only 5 seconds. Ma Dawei lamented that if you design manually, you won't be able to see the molecular structure clearly in five seconds, and you won't be able to design the molecules in five minutes

lichenghui, an associate professor of the school of chemistry and chemical engineering of Nanjing University, learned that artificial intelligence algorithm can push the synthesis route of molecules with the help of the gravity of the sample itself, and gained a lot of inspiration. He is also considering how to use artificial intelligence to help him do chemical research

lichenghui discovered a new intramolecular cyclization reaction not long ago. He hopes to know whether this reaction also exists in other molecules. According to the previous research method, his workload will be very large. Because to test whether this reaction is universal, a lot of experiments need to be done with different molecules. "With the help of artificial intelligence, we can do it in a targeted way." Lichenghui said

began to act as a right-hand man

"small flux reaction condition screening equipment has become a conventional weapon in some companies and universities, and large-scale reaction matrix robots with large flux have been born." Ma Dawei believes that the popularization of these devices may bring great changes to the research of synthetic chemistry in the future, which largely liberates the hands of synthetic chemists and allows researchers to spend more time on data analysis and top-level design of reactions

Ma Dawei introduced in a science and technology interview that the artificial intelligence program used to predict the general chemical small molecule synthesis route has become mature. Even for some complex small organic molecules, such as drug molecules, there are not many synthetic reactions due to the relatively single structural units. Artificial intelligence programs can directly assist in the design of synthetic routes. This will be of great help to junior researchers

"if we know the structure of a drug molecule, the artificial intelligence system can analyze many synthetic routes according to its structure and recommend an optimal route." Lichenghui said that in the past, such research could only be achieved by very experienced organic chemistry experts, but in the future, with the help of artificial intelligence, researchers engaged in inorganic chemistry can also do so

when synthesizing target molecules with complex structures, such as complex molecules in the natural world that require more than 20 steps to be synthesized, artificial intelligence programs can predict many different routes

"researchers may only think of more than 20 synthetic routes, and these programs may provide hundreds of possible synthetic routes, which is very helpful for researchers, because some routes may never be thought of." Madawei said

Ma Dawei told Science and technology that according to the prediction route provided by the artificial intelligence program, experienced researchers can judge which routes are good and which are meaningful, so as to help researchers think about some problems. This can provide more opportunities for chemical synthesis. Because according to the tips of the artificial intelligence program and the further deep thinking of the human brain, a better chemical synthesis route may be designed

in the future, it is only necessary to "prescribe according to the medicine"

Ma Dawei believes that the above changes are of great significance to chemical synthesis. Because the artificial intelligence program may be like a "fool machine" in the future, researchers only need to "prescribe the medicine" according to its recommendations when conducting chemical synthesis

in the past, understanding whether a chemical reaction condition was feasible was a process of trial and error. It needs to be tested manually one by one, which involves a lot of repetitive work. Nowadays, artificial intelligence can be used to quickly detect chemical reaction data, and then test the reaction conditions of flux on the machine. The whole system can test thousands of reaction conditions a day. It would be very good to do 20 chemical reaction tests in a laboratory every day

Ma Dawei told Science and technology that some large pharmaceutical companies have used artificial intelligence to assist in the design of chemical synthesis routes, becoming the first users of such technologies. In addition to drug research and development, new material research and development and other fields including compound synthesis can use artificial intelligence to recommend chemical synthesis routes

"in the future, the synthesis of molecules that did not exist in the past will be like building a house. Let artificial intelligence draw the blueprint first, and researchers only need to build according to the blueprint." Madawei said

lichenghui also believes that artificial intelligence will have great potential in the field of chemistry. In his opinion, the future application of artificial intelligence in the field of chemistry will be like an artificial intelligence doctor. It can master and digest a large number of synthesis methods, synthesis routes, material structures and properties. When scientific researchers do chemical synthesis research, it can help to analyze and solve many problems

however, generally speaking, the role of artificial intelligence is still auxiliary. It can liberate chemical researchers from the heavy manual labor, and provide some references for their research. However, the recommended results also require researchers to use professional knowledge and experience to judge which are really feasible

in addition, the chemical synthesis route recommended by artificial intelligence is still in the model machine stage. Ma Dawei believes that chemical researchers need to constantly provide some innovative strategies for artificial intelligence to promote the continuous optimization of artificial intelligence systems, which in turn promotes chemical researchers to conduct more in-depth research

related links

AI robots help to quickly discover new molecules

as early as last year, chemists at the University of Glasgow in the United Kingdom had discussed how to train an AI organic chemical synthesis robot to automatically explore a large number of chemical reactions

this "self driven" system is based on machine learning algorithm. Ruag space has contacted Altair to discover new reactions and molecules, allowing the use of digital chemistry data-driven methods to locate new molecules of interest, rather than being limited to a known database and conventional organic synthesis rules. The result may reduce the cost of discovering new drug molecules, new chemical products (including materials), polymers and molecules for high-tech applications (such as imaging)

the research team demonstrated the potential of this system by using a combination of 18 different starting chemicals to simulate about 1000 reactions. After exploring about 100 possible reactions, the robot can predict with more than 80% accuracy which initial chemical combinations should be explored to produce new reactions and molecules. By exploring these reactions, they discovered a series of previously unknown new molecules and reactions. The researchers found four new reactions, one of which was classified as the top 1% of the most unique reactions known

researchers say that this method is a key step in chemical digitalization. It will allow real-time retrieval of chemical space, so as to help find new drugs, reduce costs, save time, improve safety, reduce waste, and help chemistry enter a new digital era

Copyright © 2011 JIN SHI