Artificial intelligence, injecting intelligent kinetic energy for scientific research (Reprinted from CCTV)
Recently, the Ministry of Science and Technology and six other departments issued a document, focusing on creating a number of major scenarios to expand the application of artificial intelligence, high-level scientific research activities is one of them. Today, China's rapid development of artificial intelligence technology, in data acquisition, experimental prediction, results analysis and other aspects of advantage, life sciences, mathematics, chemistry, space science and other disciplines of research have embraced artificial intelligence. Rich application scenarios also feed the development of technology and promote industrial intelligence upgrading.
From daily life to scientific research, today, China's rapid development of artificial intelligence technology, data and computing power resources are increasingly abundant. Application demand is an important driving force for technological progress, new technology is often in the "use" of continuous improvement, maturity. In order to promote artificial intelligence on the ground, recently, the Ministry of Science and Technology and other six departments jointly issued a "guidance on accelerating scene innovation to promote the high level of application of artificial intelligence for high-quality economic development," focusing on creating a number of major scenes to expand the application of artificial intelligence, high-level scientific research activities is one of them.
As a means of empowerment, how does AI bring new research methods, and how does it inject "intelligent kinetic energy" into economic development?
Closer integration to help research become more efficient and accurate
Among many disciplines, life science research is more closely integrated with artificial intelligence, and one of the popular directions is to predict protein structure.
Protein has a three-dimensional structure, and its primary structure (sequence) consists of multiple amino acids in series. The three-dimensional structure determines the function of the protein in the cell, and many diseases are caused by abnormalities in the structure of important proteins in the body. Therefore, it is important to map the "three-dimensional map" of important proteins in the human body in order to find the targets of drug action in the human body, so as to develop precise and effective new drugs.
Traditionally, scientists have used cryoelectron microscopy, X-rays and nuclear magnetic resonance to observe the three-dimensional structure of proteins, but this process is time-consuming and costly. "In cryo-electron microscopy, for example, it costs tens of millions of dollars to set up an observation platform, and it takes a long time for researchers to map out the protein structure." Baidu flying propeller propeller biocomputing platform in charge of the He Trail Zhou said.
Due to the high difficulty, long experimental period and high cost, the number of protein three-dimensional structures observed through traditional methods has been very limited so far. In contrast, amino acid sequencing is much easier. Why can't we predict the structure of proteins based on amino acid sequences? Back in 1972, American biochemist Christian Anfinson had proposed this idea in his Nobel Prize acceptance speech.
Accurately predicting the three-dimensional structure of a protein from its primary structure is exactly what artificial intelligence is good at. However, human attempts to parse the proteome have been slow. It is explained that this is partly because of the small amount and low quality of available biological data and the lack of sufficient samples for deep learning; on the other hand, because the maturation of AI algorithms also requires a process.
In recent years, with the dramatic increase in biological data and the optimization of artificial intelligence technology, scientists have built more accurate prediction models. 2020 December, in a competition, the artificial intelligence program "Alpha Fold" shine, it predicted the results with most of the experimental data. This proves that AI is already quite accurate in predicting protein structure.
Today, with AI, work that once could have taken years can now be done in minutes, and some protein structures that could not be observed by traditional methods can be resolved.
Using artificial intelligence, researchers are known to have predicted the structures of more than 200 million proteins from about 1 million species, covering almost every protein that has been cataloged by the scientific community. This will have a major impact on the field of structural biology, potentially triggering a paradigm shift in life science research and enhancing human understanding of life.
Broad prospects, useful in multiple fields such as life sciences
Artificial intelligence has entered the life sciences research landscape, with the needs of the biopharmaceutical industry as a key driver. According to reports, in the biopharmaceutical industry, every $1 billion invested in the kinds of drugs that can be developed has been declining. New drug research and development is becoming increasingly difficult, the cycle is getting longer and longer, the urgent need for new methods to break through, artificial intelligence is highly expected.
Not only to accelerate new drug development, artificial intelligence is playing an important role in more and more areas of life sciences.
Earlier this year, a protein prediction model run by the National Supercomputing Center in Chengdu helped a team from the Wheat Research Institute of the College of Agriculture at Sichuan Agricultural University successfully resolve the molecular mechanism by which PGS1 regulates seed development and affects yield, providing a theoretical basis for breeding high-yielding, high-quality wheat materials. The researchers said it would have been difficult to make this breakthrough efficiently without artificial intelligence.
Researchers have also tried to introduce AI techniques into vaccine design. For example, compared with protein vaccines and DNA vaccines, mRNA (messenger ribonucleic acid) vaccines have advantages such as fast mass production and good anti-infection properties, but relatively poor stability and immunogenicity. To make up for these shortcomings, researchers have been hoping to optimize mRNA vaccine sequence design to make it more stable and immunogenic. More efficient and less costly, the intervention of artificial intelligence is expected to provide new ideas for vaccine development.
Precision therapy is also an arena for AI applications. Through machine learning methods, AI can theoretically decode the human immune system and explore the complex immune laws of some diseases more precisely, thus helping people to understand diseases and develop therapeutic drugs and methods in a more efficient and targeted manner.
With the increase in human data from genomics research, knowledge accumulated from new drug development, and the continuous iteration of machine learning algorithms, industry experts believe that artificial intelligence has a bright future in the life sciences. Some researchers even envision relying on powerful biocomputing engines to build a unified knowledge graph using large amounts of biological data as a way to advance the understanding of life and health.
*** Translated with www.DeepL.com/Translator (free version) ***
Rich scenarios to drive the application to a higher level
Into life science research, artificial intelligence is expected to open a new era of biopharmaceutical industry while bringing new methods.
Industry experts say that seizing the new opportunity of intelligent drug design and strengthening the layout in AI + biopharma will help us to be one step ahead on the new track of new drug development.
Although artificial intelligence + biopharmaceuticals is developing rapidly, but overall it has just started. HeJiaoZhou believes that the biopharmaceutical industry has hundreds of years of history, there is a mature and perfect research process, industrial chain and division of labor, artificial intelligence to improve only some of the links, "biopharmaceuticals are about life and health, the development of the industry to steadily promote, maintain rationality and reverence." Up to now, there is no new drug discovered worldwide that relies entirely on artificial intelligence. Some of the products developed with the help of AI are still a long way from being truly marketable.
Seeing the advantages of AI technology in data acquisition, experimental prediction and result analysis, disciplines such as mathematics, chemistry, materials science and space science have also embraced AI.
Lithium battery performance varies depending on material composition. Responding to the demand for lithium batteries in rich and diverse scenarios, researchers hope to design a suitable lithium battery system by optimizing material combinations.
"Previously, the design of material systems mainly relied on manual experiments, which were very inefficient." Zhang Qiang, a professor of chemical engineering at Tsinghua University, said that right now, he is leading a team to use artificial intelligence to predict molecular properties so as to find energy materials more efficiently and precisely and design a more valuable and safer battery system.
It is estimated that the size of China's AI core industry exceeds 400 billion yuan and the number of enterprises exceeds 3,000. Thanks to the exuberant demand brought by massive data processing and the test soil provided by rich application scenarios, China is at the forefront of the world in areas such as computer vision and speech recognition.
Industry experts suggest that to promote the application of artificial intelligence to a higher level, it is necessary to play the advantages of China's rich application scenarios. Around the high level of scientific research activities to create a major scene, will promote the application of artificial intelligence in China to go deeper and deeper, for the high quality development of the economy to inject "intelligent kinetic energy".
Original article reprinted: artificial intelligence, for scientific research to inject wisdom kinetic energy (science and technology self-reliance and self-improvement)
Recently, the Ministry of Science and Technology and six other departments issued a document, focusing on creating a number of major scenarios to expand the application of artificial intelligence, high-level scientific research activities is one of them. Today, China's rapid development of artificial intelligence technology, in data acquisition, experimental prediction, results analysis and other aspects of advantage, life sciences, mathematics, chemistry, space science and other disciplines of research have embraced artificial intelligence. Rich application scenarios also feed the development of technology and promote industrial intelligence upgrading.
From daily life to scientific research, today, China's rapid development of artificial intelligence technology, data and computing power resources are increasingly abundant. Application demand is an important driving force for technological progress, new technology is often in the "use" of continuous improvement, maturity. In order to promote artificial intelligence on the ground, recently, the Ministry of Science and Technology and other six departments jointly issued a "guidance on accelerating scene innovation to promote the high level of application of artificial intelligence for high-quality economic development," focusing on creating a number of major scenes to expand the application of artificial intelligence, high-level scientific research activities is one of them.
As a means of empowerment, how does AI bring new research methods, and how does it inject "intelligent kinetic energy" into economic development?
Closer integration to help research become more efficient and accurate
Among many disciplines, life science research is more closely integrated with artificial intelligence, and one of the popular directions is to predict protein structure.
Protein has a three-dimensional structure, and its primary structure (sequence) consists of multiple amino acids in series. The three-dimensional structure determines the function of the protein in the cell, and many diseases are caused by abnormalities in the structure of important proteins in the body. Therefore, it is important to map the "three-dimensional map" of important proteins in the human body in order to find the targets of drug action in the human body, so as to develop precise and effective new drugs.
Traditionally, scientists have used cryoelectron microscopy, X-rays and nuclear magnetic resonance to observe the three-dimensional structure of proteins, but this process is time-consuming and costly. "In cryo-electron microscopy, for example, it costs tens of millions of dollars to set up an observation platform, and it takes a long time for researchers to map out the protein structure." Baidu flying propeller propeller biocomputing platform in charge of the He Trail Zhou said.
Due to the high difficulty, long experimental period and high cost, the number of protein three-dimensional structures observed through traditional methods has been very limited so far. In contrast, amino acid sequencing is much easier. Why can't we predict the structure of proteins based on amino acid sequences? Back in 1972, American biochemist Christian Anfinson had proposed this idea in his Nobel Prize acceptance speech.
Accurately predicting the three-dimensional structure of a protein from its primary structure is exactly what artificial intelligence is good at. However, human attempts to parse the proteome have been slow. It is explained that this is partly because of the small amount and low quality of available biological data and the lack of sufficient samples for deep learning; on the other hand, because the maturation of AI algorithms also requires a process.
In recent years, with the dramatic increase in biological data and the optimization of artificial intelligence technology, scientists have built more accurate prediction models. 2020 December, in a competition, the artificial intelligence program "Alpha Fold" shine, it predicted the results with most of the experimental data. This proves that AI is already quite accurate in predicting protein structure.
Today, with AI, work that once could have taken years can now be done in minutes, and some protein structures that could not be observed by traditional methods can be resolved.
Using artificial intelligence, researchers are known to have predicted the structures of more than 200 million proteins from about 1 million species, covering almost every protein that has been cataloged by the scientific community. This will have a major impact on the field of structural biology, potentially triggering a paradigm shift in life science research and enhancing human understanding of life.
Broad prospects, useful in multiple fields such as life sciences
Artificial intelligence has entered the life sciences research landscape, with the needs of the biopharmaceutical industry as a key driver. According to reports, in the biopharmaceutical industry, every $1 billion invested in the kinds of drugs that can be developed has been declining. New drug research and development is becoming increasingly difficult, the cycle is getting longer and longer, the urgent need for new methods to break through, artificial intelligence is highly expected.
Not only to accelerate new drug development, artificial intelligence is playing an important role in more and more areas of life sciences.
Earlier this year, a protein prediction model run by the National Supercomputing Center in Chengdu helped a team from the Wheat Research Institute of the College of Agriculture at Sichuan Agricultural University successfully resolve the molecular mechanism by which PGS1 regulates seed development and affects yield, providing a theoretical basis for breeding high-yielding, high-quality wheat materials. The researchers said it would have been difficult to make this breakthrough efficiently without artificial intelligence.
Researchers have also tried to introduce AI techniques into vaccine design. For example, compared with protein vaccines and DNA vaccines, mRNA (messenger ribonucleic acid) vaccines have advantages such as fast mass production and good anti-infection properties, but relatively poor stability and immunogenicity. To make up for these shortcomings, researchers have been hoping to optimize mRNA vaccine sequence design to make it more stable and immunogenic. More efficient and less costly, the intervention of artificial intelligence is expected to provide new ideas for vaccine development.
Precision therapy is also an arena for AI applications. Through machine learning methods, AI can theoretically decode the human immune system and explore the complex immune laws of some diseases more precisely, thus helping people to understand diseases and develop therapeutic drugs and methods in a more efficient and targeted manner.
With the increase in human data from genomics research, knowledge accumulated from new drug development, and the continuous iteration of machine learning algorithms, industry experts believe that artificial intelligence has a bright future in the life sciences. Some researchers even envision relying on powerful biocomputing engines to build a unified knowledge graph using large amounts of biological data as a way to advance the understanding of life and health.
*** Translated with www.DeepL.com/Translator (free version) ***
Rich scenarios to drive the application to a higher level
Into life science research, artificial intelligence is expected to open a new era of biopharmaceutical industry while bringing new methods.
Industry experts say that seizing the new opportunity of intelligent drug design and strengthening the layout in AI + biopharma will help us to be one step ahead on the new track of new drug development.
Although artificial intelligence + biopharmaceuticals is developing rapidly, but overall it has just started. HeJiaoZhou believes that the biopharmaceutical industry has hundreds of years of history, there is a mature and perfect research process, industrial chain and division of labor, artificial intelligence to improve only some of the links, "biopharmaceuticals are about life and health, the development of the industry to steadily promote, maintain rationality and reverence." Up to now, there is no new drug discovered worldwide that relies entirely on artificial intelligence. Some of the products developed with the help of AI are still a long way from being truly marketable.
Seeing the advantages of AI technology in data acquisition, experimental prediction and result analysis, disciplines such as mathematics, chemistry, materials science and space science have also embraced AI.
Lithium battery performance varies depending on material composition. Responding to the demand for lithium batteries in rich and diverse scenarios, researchers hope to design a suitable lithium battery system by optimizing material combinations.
"Previously, the design of material systems mainly relied on manual experiments, which were very inefficient." Zhang Qiang, a professor of chemical engineering at Tsinghua University, said that right now, he is leading a team to use artificial intelligence to predict molecular properties so as to find energy materials more efficiently and precisely and design a more valuable and safer battery system.
It is estimated that the size of China's AI core industry exceeds 400 billion yuan and the number of enterprises exceeds 3,000. Thanks to the exuberant demand brought by massive data processing and the test soil provided by rich application scenarios, China is at the forefront of the world in areas such as computer vision and speech recognition.
Industry experts suggest that to promote the application of artificial intelligence to a higher level, it is necessary to play the advantages of China's rich application scenarios. Around the high level of scientific research activities to create a major scene, will promote the application of artificial intelligence in China to go deeper and deeper, for the high quality development of the economy to inject "intelligent kinetic energy".
Original article reprinted: artificial intelligence, for scientific research to inject wisdom kinetic energy (science and technology self-reliance and self-improvement)
