Researchers from Google DeepMind have presented the AlphaMissense tool that predicts whether genetic mutations can cause harm. This is called a breakthrough that can help in the research of rare diseases, writes IBT.

The tool focuses on missense mutations, which change a single letter of the genetic code. Such mutations can be harmless or cause diseases such as cystic fibrosis or cancer, or interfere with brain development.

Using AlphaMissense, scientists analyzed 71 million of these mutations. According to the results, 57% of them were classified as probably benign, 32% as probably pathogenic, and the rest as undetermined. The accuracy of the AI tool was up to 90%. The results of the study were published in the journal Science.

Google DeepMind believes that these predictions could potentially be useful for improving the diagnosis of rare diseases. They can also help in the search for new genes that cause diseases.

Earlier, scientists have developed an artificial intelligence application that promises to warn about dangerous variants of future pandemics. The application is called the Early Warning Anomaly Detection (EWAD) system, and when tested against actual SARS-CoV-2 spread data, it accurately predicted which new variants of concern (VOCs) would emerge as the virus mutated.