In the context of AI, drug R&D innovation is accelerating

The current pharmaceutical process mainly includes the development of candidate drugs-pre-clinical research-clinical trials (phase I~)-new drug application, approval for marketing, and post-marketing monitoring (phase IV clinical trials)
.
Among them, drug research and development is the top priority of the pharmaceutical industry
.
It is understood that the long R&D time period from drug R&D to registration takes an average of 10 years, the system is complex, and the total capital investment is at least US$1 billion
.
For the above reasons, the development of new drugs has always been a high-risk action
.
In this context, new drug design is difficult, costly, and time-consuming, and it has become a major problem that has been plagued by drug companies' drug R&D work
.
It is understood that once R&D fails, it is not uncommon for the huge investment to be lost in the industry
.
However, the research and development of AI drugs is bringing more and more hopes of cost reduction and efficiency enhancement to the research and development of new drugs
.
For example, in August, Deqi Pharmaceuticals, a biopharmaceutical company dedicated to the development and commercialization of innovative tumor therapies, announced a long-term strategic cooperation with AI drug research and development company De Rui Zhiyao to jointly promote the development of first-in-class small molecule anti-tumor drugs.
Research and development
.
It is reported that De Rui Zhiyao will use its unique one-stop AI drug development platform Molecule Pro and molecular dynamics platform Molecule Dance to assist Deqi Pharmaceuticals in designing and obtaining more first-in-class and best-in-class potentials.
Candidate drugs improve the current drug development efficiency and success rate of Deqi Pharmaceuticals, provide breakthrough treatment options for patients, and meet more unmet medical needs
.
At the same time, technology giants such as Baidu, Tencent, Huawei, ByteDance, etc.
in the field of non-medical origin are also deploying AI medicine
.
At the beginning of this year, Baitu Biosciences, led by Baidu founder Robin Li, launched the "One Million Leadership Program" and "One Million Youth Leadership Program", which will be supported by an annual salary of US$1 million, an annual salary of RMB 1 million, and other technical platforms, respectively.
Attracting biotechnology + AI technology cross-border integration talents
.
Some time ago, Huawei also released the "Huawei Cloud Pangu" drug molecular model, which is a new breakthrough for Huawei to enter the field of AI-assisted drug research and development
.
It is reported that the "Pangu Drug Molecule Model" has learned the chemical structure of 1.
7 billion drug molecules, which can help small molecule compounds calculate and match target proteins, predict the biochemical properties of new molecules, and efficiently generate new drugs; in addition, it can also Realize the targeted optimization of the lead drugs after screening
.
At present, the model has cooperated with the First Affiliated Hospital of Xi'an Jiaotong University to develop broad-spectrum antibacterial drugs.
The results show that the lead drug development cycle can be shortened from several years to one month, which means that the efficiency of new drug research and development has been greatly improved
.
From the above point of view, the industry is currently very optimistic about the development of AI pharmaceuticals
.
The industry predicts that as capital scrambles to enter the game, it will undoubtedly accelerate the development of the medical AI track, and it will also accelerate the speed of drug R&D and innovation in the pharmaceutical industry
.
In addition, in the future, it will further promote the appearance of innovations and benefit more patients
.
But while seeing the benefits of AI pharmacy, we also need to see that it also has certain limitations
.
The analysis believes that on the way of artificial intelligence participating in new drug research and development, related companies will also face many challenges, such as how to combine the data of various pharmaceutical companies and use more high-quality data to make molecular models; and When interdisciplinary cooperation, how to enable effective communication between different technical personnel will be difficulties that need to be resolved as soon as possible
.