As a mage, I just want to pursue the truth

Chapter 201 AI and Computational Biology
Currently, only the magicians in China have some understanding of the nature of magic.

They have taken the lead in the new generation of technological revolution.

Although this advantage is only an information advantage that can be broken through at any time, it is better to have an advantage than to have no advantage.

"We will first prepare a work report and submit it to the higher-ups for decision-making. The most important thing now is to hold Zheng Li back and prevent him from returning too early."

"Okay, I'll make arrangements."

The Chinese government has conducted multiple psychological profiles and character portraits of Zheng Li, and knows that although Zheng Li appears ruthless, he is actually very kind to his friends.

"Mr. Zheng, we are now mainly introducing the concept of world lattice parsing in the field of natural language processing into the research and development of innovative drugs."

"The protein small molecule sequences designed by algorithms are better than traditional methods in terms of stability, protein expression level and production cost."

"This method was first used two years ago when researchers from Sibico and Qiandu collaborated on an AI sequence optimization algorithm for mRNA vaccines."

"Mr. Cheng is a shareholder and external director of SiMicro. At that time, he was responsible for introducing this technology to researchers in Singapore. Over the past two years, we have expanded the application of AI sequence optimization algorithms to the research and development of innovative drugs."

“Iterative technologies for protein sequence design are still under development.”

Zheng Li was currently at the R&D center of Kechuang Biotechnology Jiangcheng, where the R&D director was reporting to Zheng Li.

Jiangcheng R&D Center is mainly responsible for the research and development of some innovative drugs.

Since the rise of Kechuang Biotechnology, the college entrance examination score line for the Biology Department of Jiangcheng University has increased by at least 20 points.

Originally, biology was considered Jiangcheng University's flagship major, but due to poor career prospects, the admission score was far lower than that of the School of Economics and Management.

A high ranking of a major does not mean a high score. The majors with the highest scores within Jiangnan University are financial engineering and mathematics. After graduation, you can obtain a double degree in finance and mathematics.

The research center of Kechuang Biotechnology in Jiangcheng mainly recruits students from Jiangcheng University and Jiangcheng University of Science and Technology.

We recruit a large number of masters and doctors who graduated in biology, and the salary and benefits are half a level higher than that of the Mi branch in Jiangcheng.

At the same time, Jiangcheng’s research center has also carried out many project collaborations with Jiangda’s School of Life Sciences.

During private discussions within Jiangnan University, everyone felt that as a graduate of the School of Mathematics, Zheng Li's biggest piece of the pie had been eaten up by the School of Life Sciences.

“So this is an application of AI and computational biology, right?”

In response to Zheng Li's question, Jiang Cheng's R&D director nodded and said, "Yes."

"We are currently mainly doing sequence alignment and protein structure prediction."

"Computational biology is not limited to these two fields, but also includes gene identification, evolutionary tree construction and other directions."

"Since AI technology came into people's view, machine learning technology has greatly developed computational biology."

“Advances in genomics and imaging technologies have led to an explosion of molecular and cellular profiling data from large numbers of samples.”

"The rapid growth in the dimensionality and acquisition rate of biological data has challenged traditional analysis strategies. Modern machine learning methods, such as deep learning, hold promise for leveraging very large datasets to find hidden structures within them and make accurate predictions."

"For example, we have a group that specializes in predicting the vitality of cancer cells under the action of drugs."

“The input features 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 the function.”

"Even though the function looks more like a black box to us, it's not easy to find the specific reasons behind its inner workings and why a particular combination of mutations affects cell growth."

"Both regression and classification can be viewed in this way."

“As a counterpart, unsupervised machine learning methods aim to discover patterns from the data samples x themselves, without requiring output labels y.”

"Similar methods such as clustering, principal component analysis and outlier detection are closer to black boxes, and we are currently mainly applying them to unsupervised models for biological data."

Zheng Li applauded and said, "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 lies not only in the fact that carbon-based computers have higher computing power and upper limits than silicon-based computers, but also in the fact that they can directly interfere with the material world through their will.

There will be more special samples and targeted induced samples for research.

Zheng Li continued to ask: "Actually, you are currently mainly using neural networks, right?"

“Convolutional neural networks, recurrent neural networks, autoencoders, etc.”

The R&D director was well aware of Zheng Li's scientific research capabilities and the wide range of fields he covered, so he was not surprised at all that Zheng Li had nailed down their key points in one sentence:

"Yes, it's mainly the application of neural networks in the field of computational biology."

When it comes to R&D, Zheng Li always speaks his mind:

"Deep learning has been used for a long time to compute biological levels."

"Bengio started using neural networks to study genomics and biological image analysis as early as 2012, linking sequence variation and molecular features."

"That is to say, the technology we use may seem very advanced to outsiders, such as deep learning and artificial intelligence, but in fact, it is something that others have been playing with for ten years."

"What breakthroughs have we made ourselves? Don't tell me we're just using other people's methods."

“If you only do this much”

Zheng Li didn't finish his words. He turned to look at Li Miaomiao and said, "Miaomiao, what is the annual budget of Jiangcheng R&D Center?"

Li Miaomiao said without hesitation: "The budget for them this year is 17.4 billion yuan."

Zheng Li nodded and said, "Okay, if you are only at this level, then cut the budget for this year."

Li Miaomiao asked, "Cut off 7.4 million yuan?" "Yes."

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 R&D targets this year.

The R&D director quickly said, "Director Zheng, we have a lot of independent R&D."

He knew that what he brought out must not be foolproof.

Zheng Li understood it too well. When your boss knows too much about your business, it becomes extremely difficult to slack off at work.

"We optimized the neural network algorithm to optimise molecular features from DNA sequences."

"Mr. Zheng, this is the molecular response variable of the individual's DNA sequence and genome."

"While traditional regulatory genomics approaches focus on differences between individuals, our optimized deep learning algorithm allows us to do this by flattening the genome into sequenced DNA windows centered on individual traits."

"Then we exploit the intra-individual variation to generate a large training dataset from a single sample."

“This is a one-dimensional convolutional neural network for predicting molecular features from raw DNA sequences.”

“The filters in the first convolutional layer scan for patterns in the input sequence. Subsequent pooling reduces the input dimensionality, and additional convolutional layers model the interactions of the DNA sequences in the previous layer.”

“Looking here again, the response variables for wild-type and mutant sequences predicted by the neural network shown in Figure (C) are used as input to another neural network that predicts variant scores and allows for the distinction between normal and deleterious variants.”

“D then visualized the convolutional filters by aligning the gene sequences that maximally activated the filters and creating sequence motifs.”

"This is a mutation map for a 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 letters at the top represent the wild-type sequence, and the height of each nucleotide indicates the maximum effect of the mutation."

After finishing the research on the Lion City R&D Center, Li Miaomiao asked, "What do you think?"

“I don’t understand what he said at all.”

"The internal resource support for Jiangcheng R&D Center has been increasing in the past two years."

"If their performance does not satisfy you, we can transfer some resources to other R&D centers with better performance."

Currently, Kechuang Bio has offices in Singapore, Jiangcheng, Suzhou, Jinling, Shenhai and London.

Among them, London and Shenhai are mainly engaged in the research and development of AI chips and brain-computer connection chips.

The only R&D centers in the biomedical field are Lion City, Jiangcheng, and Jinling.

A large part of the outside world's impression of Jiangcheng is that there are a lot of colleges and universities here, including two 985 universities and seven 7 universities, and it has strong educational resources.

However, Jinling's educational resources are no less than Jiangcheng's. Although they both have two 985 universities, Jinling has eight 8 universities.
Ke Chuang Bio's decision to set up a research and development center in Jinling is not only the hope of the Jinling government, but also a reflection of its appreciation for Jinling's high-quality educational resources and talents.

Zheng Li sighed: "Just barely pass."

"How should I put it? If it was a year ago when the Jiangcheng R&D Center had just been established for half a year, you would have shown me this achievement as a highlight of your work."

"I would give them an eight, but now that it's been a year and a half, I can only give them a six."

"What I made is just a modification of others' work. I haven't asked them about the underlying principles yet."

“The research is still at the application level.”

"We still have a huge gap with pharmaceutical giants like Pfizer and Bayer."

Li Miaomiao was thinking that according to Zheng Li's standards, the results of the Jiangcheng Research Center should be considered good in the country.

It’s just that Zheng Li’s own research has always been about breakthroughs, so he thinks that breakthrough results are natural.

But in fact, in the field of biomedicine, it is not so easy to break through the technological barriers of foreign giants.

Of course Li Miaomiao would not say this openly, she whispered:

"These few years should be used to train the team and cultivate talents."

"Giant companies like Pfizer and Bayer have a long history of cultivating talent and conducting research."

"Respecting objective laws, not all areas can achieve overtaking on curves."

"All we have to do is to move forward steadily."

While studying at the School of Economics and Management, Li Miaomiao heard a lot of pessimistic remarks, believing that China would never be able to achieve breakthroughs and surpass others in science and technology.

Let alone technological breakthroughs and transcendence, it is extremely difficult to achieve a breakthrough in the industrial chain.

When she was a student, Li Miaomiao heard mostly pessimistic voices from people around her.

After starting their own business with Zheng Li, they developed world-leading technology that was at least five years ahead of the world.

Three years have passed, and Musk's Neuralink has not yet come up with the brain-computer connection mobile phone technology that Ke Chuang Biotechnology did.

Because she has heard different voices, Li Miaomiao can make a more objective judgment.

It is inevitable for China's science and technology to break through, but the road is tortuous.

I drank until around 1:00 last night, slept all morning today, and started writing after I got up in the afternoon. I will post one chapter first and I will continue writing.

Hangover is really uncomfortable.



(End of this chapter)