Currently, only the magicians of China have some slight understanding of the nature of magic.
They have taken the lead in the new generation of technological revolution.
Although this kind of first move is only an information advantage that can be broken through at any time, it is better to have an advantage than none.
"We will formulate a work report first and submit it to the superiors for decision-making. The most important thing now is to hold Zheng Li back so that he does not go back too early."
"Okay, I'll make arrangements."
Chinese officials have done many psychological profiles and portraits of Zheng Li, and they know that Zheng Li seems to be ruthless but is actually very interesting to his friends.
...
"Director Zheng, we are now mainly introducing the concept of world lattice parising in the field of natural language processing into the research and development of innovative drugs."
“The small protein molecule sequences designed through algorithms are better than traditional methods in terms of stability, protein expression level and production cost.”
"This method was developed as early as two years ago, when Si Microorganisms and Qiandu researchers collaborated on AI sequence optimization algorithms for mRNA vaccines."
"Mr. Cheng was a shareholder and outside director of Si Microorganisms. At that time, he was responsible for bringing this technology to Shicheng researchers. In the past two years, we have expanded the application field of AI sequence optimization algorithms to the research and development of innovative drugs."
“Currently, iterative technologies for guaranteed sequence design are still under development.”
Zheng Li is currently in the R&D center of Kechuang Biotechnology Jiangcheng, where the R&D director is reporting to Zheng Li.
Jiangcheng R&D Center is mainly responsible for the research and development of some innovative drugs.
Since the rise of science and innovation biology, Jiangcheng University's biology department's college entrance examination score has increased by at least 20 points.
Originally, biology at Jiangcheng University was regarded as the trump card major of Jiangcheng University, but due to poor prospects, the score was far lower than that of the School of Economics and Management.
The top ranking of majors does not mean high scores. The majors with the highest scores in Jiangsu University are financial engineering and mathematics. After graduation, you can get a double major in finance and mathematics.
Ke Chuang Bio's research center in Jiangcheng, the main targets for school recruitment are Jiang University and Jiangcheng University of Science and Technology.
A large number of graduates with master's and doctoral degrees in biology are recruited, and the salary package is half a grade higher than that of Dami's branch in Jiangcheng.
At the same time, Jiangcheng's research center has also cooperated with Jiangda's School of Biology on many projects.
Private discussions within Jiangnan University all felt that as a graduate of the School of Mathematics, Zheng Li’s biggest cake was eaten by the School of Biology.
“So this is an application of AI and computational biology, right?”
In response to Zheng Li's question, Jiangcheng's R&D director nodded and said, "Yes."
"What we are currently mainly doing is sequence alignment and protein structure prediction."
"Computational biology is not only these two fields, but also includes gene identification, evolutionary tree construction and other directions."
“Since AI technology entered people’s horizons, machine learning technology has greatly developed computational biology.”
"Advances in genomics and imaging technologies have led to an explosion of molecular and cellular analysis data from large numbers of samples."
"The rapid growth in the dimensionality and collection rate of biological data has challenged traditional analysis strategies. Modern machine learning methods, such as deep learning, promise to leverage very large data sets to find hidden structures within them and make accurate predictions."
"For example, we have a group that specializes in predicting the viability of cancer cells under the action of drugs."
“The input feature values will capture the somatic sequence variants of the cell line, the chemical composition of the drug, and its concentration summary, which together with the measured viability can be used to train a support vector machine, random forest classifier, or related methods.”
"Given a new cell line in the future, the learning function predicts its likely viability by computing a function."
"Even though the function looks more like a black box to us, its inner workings and why specific combinations of mutations affect cell growth are not easy to find."
"Both regression and classification to look at this way."
“As a counterpart, unsupervised machine learning methods aim to discover patterns from the data sample x itself, without requiring an output label y.”
“Methods like clustering, principal component analysis, and outlier detection are closer to black boxes, and we are currently mainly applying them to unsupervised models of biological data.”
Zheng Li applauded: "Very good."
In fact, the evolutionary path of computational biology has many similarities with the research of modern mages.
The mages use the high-frequency computing power of the biological cloud to conduct qualitative and quantitative analysis of genes, proteins and other basic elements that constitute life.
The advantage of mages is not only that the computing power and upper limit of carbon-based computers are higher than those of silicon-based computers, but also comes from the fact that they can directly interfere with the material world through their will.
There can be more special samples and targeted induction samples for research.
Zheng Li continued to ask: "Actually, you are mainly using neural networks now, right?"
"Convolutional neural networks, recurrent neural networks, automatic encoding machines, etc."
The R&D director is well aware of Zheng Li’s scientific research capabilities and the wide range of fields he covers, so it is not surprising that Zheng Li explained their key points in one sentence:
"Yes, it is mainly the application of neural networks in the field of computational biology."
When it comes to research and development, Zheng Li always speaks directly:
“The application of deep learning in computational biology began a long time ago.”
"Bengio began using neural networks to study genomics and biological image analysis as early as 2012, linking sequence variations and molecular features."
"In other words, the technology we use, if you listen to it to a layman, you will think it is very advanced, such as deep learning and artificial intelligence, but in fact this is what others were playing with ten years ago."
"What breakthroughs have we made ourselves? Don't tell me we are just using other people's methods."
"If only we could do this"
Before Zheng Li finished speaking, he turned to look at Li Miaomiao: "Miaomiao, what is the annual budget for Jiangcheng R&D Center?"
Li Miaomiao said without hesitation: "The budget for them this year is 1.74 billion yuan."
Zheng Li nodded and said: "Okay, if you are only at this level, then cut off a fraction of this year's budget."
Li Miaomiao asked: "Should we cut off 740 million yuan?"
"Um."
After Zheng Li finished speaking, he looked directly at the R&D director sitting opposite him.
The annual budget of each R&D center is not only money and resources, but also represents your importance within the company.
Zheng Li's budget cuts do not mean that they will lower their research and development goals for this year.
The R&D director quickly said: "Director Zheng, we have a lot of independent R&D."
He knew that what he took out must not be fooled.
Zheng Li understands very well that when your boss knows too much about your business, it becomes extremely difficult to fish at work.
"We optimized a neural network algorithm that optimizes molecular features from DNA sequences."
"Dr. Zheng, this is the molecular response variable of the individual's DNA sequence and genome."
"While traditional regulatory genomics approaches primarily account for differences between individuals, our optimized deep learning algorithm allows this by tiling the genome into sequential DNA windows centered on individual characteristics."
"The within-individual differences are then exploited to generate a large training data set from a single sample."
"This is a one-dimensional convolutional neural network used to predict molecular features from raw DNA sequences."
"The filters of the first convolutional layer scan the input sequence for patterns. Subsequent pooling reduces the input dimensionality, and additional convolutional layers can model the interactions of DNA sequences in the previous layer."
"Looking again here, Panel C. The response variables for wild-type and mutant sequences predicted by the neural network shown in Panel B are used as input to another neural network that predicts variant scores and allows to distinguish normal from deleterious variants. .”
"D then visualizes the convolutional filter by aligning the gene sequences that maximize the activation of the filter and creating sequence motifs."
"This is a mutation plot of the sequence window. The rows correspond to the four possible base pair substitutions, and the columns correspond to the sequence positions. The predicted impact of any sequence change is color-coded."
"The letter at the top indicates the wild-type sequence, and the height of each nucleotide indicates the maximum impact of the mutation..."
After finishing the investigation of the Lion City R&D Center, Li Miaomiao asked: "What do you think?"
"I don't understand what he means at all."
"Jiangcheng R&D Center has received increasing support from internal resources in the past two years."
"If their performance cannot satisfy you, we can transfer some resources to other R&D centers that perform better."
Currently, Science and Technology Biotechnology is located in Shicheng, Jiangcheng, Suzhou, Jinling, Shenhai and London.
Among them, London and Shenhai mainly develop AI chips and brain-computer connection chips.
The only R&D centers in the biomedical field are Shicheng, Jiangcheng and Jinling.
A large part of the outside world's impression of Jiangcheng is that there are many colleges and universities here, including two 985 schools and seven 211 schools, with abundant educational resources.
However, Jinling’s educational resources are no less than those of Jiangcheng. There are also two schools ranked 985, but Jinling has eight schools ranked 211.
The establishment of a research and development center in Jinling by Science and Technology Biotechnology is not only the hope of the Jinling government, but also the high-quality educational resources and talents of Jinling.
Zheng Li sighed: "Let's just get by."
"How should I put it? If it was just half a year ago when Jiangcheng R&D Center was established, this result would be shown to me as a highlight."
"I would give them an eight, but now a year and a half later I can only give them a six."
"The things we make are just modifications based on other people's work. I haven't even asked them about the real underlying principles."
"The research is still at the application layer."
"The gap between us and pharmaceutical giants such as Pfizer and Bayer is still too big."
Li Miaomiao was thinking that according to Zheng Li's standards, the results of Jiangcheng Research Center should be considered good in China.
It’s just that Zheng Li’s own research has always been a breakthrough, so he believes that breakthrough results are natural.
But in fact, in the field of biomedicine, it is not so easy to break through the technical barriers of foreign giants.
Of course Li Miaomiao would not say this openly, she whispered:
"The past few years have been spent training the team and cultivating talents."
"Giants such as Pfizer and Bayer have a long history of cultivating their talent teams and research teams."
"Respecting objective laws, overtaking in corners is not possible in all fields."
“As long as we can achieve steady progress, that’s it.”
While studying at the School of Economics and Management, Li Miaomiao heard many pessimistic remarks, believing that China would never be able to achieve breakthroughs and transcendence in science and technology.
Not to mention technological breakthroughs and transcendences, it is difficult to achieve a breakthrough in the industrial chain.
When Li Miaomiao was a student, she heard mostly pessimistic voices from around her.
After starting their own business with Zheng Li, they developed world-leading technology, and their technology led the world for at least five years.
Three years have passed, and Neuralink, owned by Musk, has not yet come up with the brain-computer connection technology used by Curriculum Biotechnology.
Because he has heard different voices, Li Miaomiao can make a more objective judgment.
It is inevitable for China's science and technology to achieve a breakthrough, but the road is tortuous.
