Can artificial intelligence solve the problem of protein folding?

Text |

At present, the widespread application of artificial intelligence in the medical field has become a global consensus, and artificial intelligence is defending human health in a unique way.

The concept of artificial intelligence was proposed as early as the 1950s, and it was closely related to medical care at the beginning of its birth. In the early 1970s, the MYCIN system developed by Stanford University in the United States can assist doctors in diagnosing patients with blood infections, and has functions such as inferring pathogens and assisting patients with drug treatment.

Since the beginning of the 21st century, artificial intelligence has received more extensive attention and application in the medical field. Among them, a major breakthrough was the announcement by Google's artificial intelligence team DeepMind that its algorithm AlphaFold solved the protein folding problem.

Since the discovery of DNA in the 1950s, biologists have attempted to link the length of gene sequences to a range of cellular components and protein synthesis processes. Despite knowing the DNA-encoded lengths of the amino acids that make up each protein, solving the problem of protein folding is a huge undertaking. The emergence of AlphaFold undoubtedly solved this problem to a certain extent. AlphaFold also far outpaced its human competitors in the subsequent competition to guess the structure of a protein based solely on its genetic sequence.

In addition, artificial intelligence has also contributed an indispensable force in virus confirmation and medical research and development. The outbreak of COVID-19 has brought huge adjustments to social production and life, and it has also become a touchstone for artificial intelligence. One of the important means of confirming the COVID-19 virus is through nucleic acid detection. By extracting nucleic acid sequences in the blood of suspected cases and comparing them with the target virus, it is determined whether there is pathogen infection.

However, it is time-consuming and labor-intensive to perform whole-genome sequence analysis and comparison with virus samples from suspected cases, and artificial intelligence can replace human labor to complete the initial screening, greatly improving the detection efficiency. In the drug discovery stage, artificial intelligence can also play an effective role in the two scenarios of target screening and compound synthesis and screening.

Another upgrade of AI is in light field microscopy, which captures high-definition 3D motion images. Scientists typically take days to reconstruct video, but with AI, the time required to process these high-resolution data in motion is reduced to seconds, at extremely high resolution.

According to the relevant report of the China Research Institute Puhua Research Institute, in 2020, the market size of the medical AI industry will be 26.5 billion yuan. It is estimated that by 2027, the market size of China's medical artificial intelligence will reach 140 billion yuan. It can be said that artificial intelligence is leading a new medical revolution. As a partner, it will explore more endless scientific frontiers with scientists.