Machine learning methods applications for genome sequencing

The article is dedicated to the machine learning methods used to improve the analysis of sequenc-ing results. The subject of this study is the analysis of the existing approaches to the processing of molecular-biological (MB) data obtained with the help of various sequencing techniques, using ma-chine learning (ML). The purpose of the work is to generalize the current methods of obtaining "use-ful" information from " raw " MB data. Sequencing is used to establish the sequence of nucleotides in DNA and is one of the most important procedures within the framework of genomic research. In the process of conducting NGS (Next-Generation Sequencing), it is necessary to process huge amounts of data, often with various kinds of defects. Due to the existence of different variations of sequencing methods and the presence of three or more stages there, the range of the problems solved with the help of ML in this area is also extremely wide. The article provides a brief overview of some solutions based on machine learning and used to improve the quality of analysis and transform the results of individual stages of sequencing. The key groups of bioinformatics tasks in the framework of sequenc-ing are described, and the examples of the implemented algorithms using ML are given. In addition, the different approaches to solving the same problem have been developed and at the same time they have their own advantages and disadvantages.