This article is produced by NetEase Smart Studio (public number smartman 163). Focus on AI and read the next big era!
[NetEase smart news December 10 news] If you have seen crime scenes such as "crime scene", you may think of a scene: Forensics through the computer to search for thousands of DNA fragments to match the crime scene and crime suspects. Although this process is not really like TV shows in real life, the main idea is the same. Genetics is essentially a comparative science. Whether you want to confirm a suspect, a genetic disease, or a long-lost relative, you need to compare one genome to another to find similarities and differences in billions of DNA.
Although the process of identifying missing persons or suspects usually involves only a few genetic fragments of a person, problems such as identifying gene mutations in a disease often require large amounts of data processing. Although many cutting-edge researches are currently being conducted to help scientists do this, the full definition of all these data faces enormous challenges. This is exactly the problem that artificial intelligence needs to solve.
This week, Google launched a program called DeepVariant that can use deep learning to piece together a person's genome and more accurately identify mutations in DNA sequences.
This technique was used in Google to identify whether a picture was a cat or a dog. DeepVarient used the same technology to solve an important issue in the area of ​​DNA analysis. Modern DNA sequencers can perform high-throughput sequencing, reading not complete DNA sequences but overlapping short fragments. These fragments are then compared with another genome so that they are patched together for mutation recognition. However, this technique is easy to make mistakes, and it is very difficult for scientists to detect these errors and small mutations. These small mutations are very important. They can provide important insights, such as the root causes of the disease. It is called "variable calls" to distinguish which base pairs are wrong and which are correct.
In fact, there are already some tools that can help scientists do this. The most widely used is GATK, an artificially designed algorithm that can apply statistical data to the sequencing machine's most common mistakes. However, DeepVariant uses neural network technology to build more accurate programs than any previous technology. Last year, this technology won the first place in the FDA competition.
Neural networks are so named because they work a bit like neurons in the brain. Each layer of network handles more complex tasks step by step. In order to use image recognition technology to establish a precise DNA sequence, the Google team transformed DNA sequencing data into an image. For example, As, Ts, c, and Gs that make up the genetic code appear in red. The researchers then conducted research on millions of genome sequencing and high-throughput reading techniques, and taught the program which things are more important and which can be ignored.
The resulting algorithm can more accurately troubleshoot errors than any previous system. Initially, these images consist of only three colors, or three layers of data. However, the latest version released this week contains seven types, allowing it to be expressed more accurately. This program is currently released as open source software, and external researchers can use and continue to implement program enhancements.
DeepVariant is by no means 100% accurate. But its success represented the influence of machine learning on genetics. The size and complexity of genomic data is enormous. The machine may be exactly what we need to figure out.
(Selected from: gizmodo compilation: NetEase See Compilation Robot Review: Qin Hao)
Pay attention to NetEase smart public number (smartman163), obtain the latest report of artificial intelligence industry.
The 7-inch tablet can be used as the golden size of a tablet computer. It is small and portable. It can be used at home and outdoors. You can browse the web, watch videos and play games. It is a household artifact. Although the size of the 7-inch tablet is inclined to the tablet, the function is more inclined to the mobile phone, so it can also be used as a substitute for the mobile phone. Compared with other sized tablets, the 7-inch tablet has obvious advantages in appearance and weight. Both the body size and the body weight have reached a very reasonable amount.
1.In appearance, the 7 inch tablet computer looks like a large-screen mobile phone, or more like a separate LCD screen.
2.In terms of hardware configuration, the 7 inch tablet computer has all the hardware devices of a traditional computer, and has its own unique operating system, compatible with a variety of applications, and has a complete set of computer functions.
3.The 7 inch tablet computer is a miniaturized computer. Compared with traditional desktop computers, tablet computers are mobile and flexible. Compared with Laptops, tablets are smaller and more portable
4.The 7 inch tablet is a digital notebook with digital ink function. In daily use, you can use the tablet computer like an ordinary notebook, take notes anytime and anywhere, and leave your own notes in electronic texts and documents.
7 Inches Tablet Pc,Quad Core Tablet 7 Inch,7 Inch Gaming Tablet,Supersonic Tablet 7 Inch
Jingjiang Gisen Technology Co.,Ltd , https://www.jsgisentec.com