1. نقش هوش مصنوعی در ژنومیکس.
- Author
-
محمدرضا محمدآبادی, حمید خیرالدین, ولودیمیر آفاناسنکو, اولنا بابنکو, ناتالیا کلوپنکو, الکساندر کلاشنیک, یولیا ایوستافیوا, and ویتا بوچکوفسکا
- Abstract
Objective: Data generation in biology and biotechnology has greatly increased in recent years due to the very rapid development of high-performance technologies. These data are obtained from studying biological molecules, such as metabolites, proteins, RNA, and DNA, to understand the role of these molecules in determining the structure, function, and dynamics of living systems. Functional genomics is a field of research that aims to characterize the function and interaction of all the major components (DNA, RNA, proteins, and metabolites, along with their modifications) that contribute to the set of observable characteristics of a cell or individual (i.e., phenotype). Furthermore, in a breeding program, genetic improvement can be maximized through accurate identification of superior animals that are selected as parents of the next generation, thereby achieving breeding goals. Artificial neural networks have been proposed to alleviate this limitation of traditional regression methods and can be used to handle nonlinear and complex data, even when the data is imprecise and noisy. Omics data can be too large and complex to handle through visual analysis or statistical correlations. This has encouraged the use of machine intelligence or artificial intelligence. The objectives of this study was to review the main applications of artificial intelligence methods in functional genomics, cancer, agriculture, domestic animals and its intertwined fields, i.e. epigenomics, transcriptomics, epitranscriptomics, proteomics, and metabolomics, discuss important aspects of data management, such as data integration, cleaning, noise removal, balancing and ratio of missing data, functional genomicssystem modeling, artificial intelligence and systems biology, addressing legal, ethical and economic issues related to the application of artificial intelligence methods in the field of genomics and presenting a view of possible scenarios in the future. Materials and methods: In this review, all researches conducted in the field of artificial intelligence application in functional genomics, cancer, agriculture, domestic animals, and its intertwined fields, i.e. epigenomics, transcriptomics, epitranscriptomics, proteomics, and metabolomics, were tried, focusing on the applications of recent years after Increase production of big data to be studied and used. Results: The studies showed that the application of artificial intelligence in all fields, including functional genomics, cancer, agriculture, domestic animals, and its intertwined fields, i.e., epigenomics, transcriptomics, epitranscriptomics, proteomics, and metabolomics, is increasing rapidly and has many benefits. Conclusions: Considering the vital applications that are often addressed by biology and especially functional genomics, it is better to deal with artificial intelligence tools that are able to help mechanistic understanding of biological processes. In other words, enabling systems biology is important to reap the benefits of AI results in genomics. Interpretability can certainly help AI to be more easily adopted in practical applications such as medicine. In our opinion, increasing the volume and diversity of reliable big data and integrating it with theoretical modeling will help increase human trust in AI-based predictions and decisions in the future. On the one hand, model-based approaches can provide knowledge-based constraints. On the other hand, the results of artificial intelligence can help to create the parameters of models of biological systems. Functional genomics, as well as all fields of medicine, biology, agriculture, animal science, and other sciences that involve both individual and collective rights, is a complex field of research. Those who want to use AI in this field will find it difficult to navigate, as the field is sensitive to legal, ethical, and spiritual aspects. Artificial intelligence opens many opportunities that we should not refuse for fear of not understanding all the steps. The path that artificial intelligence will follow is just beginning to unfold. It has many promises and many potential dangers ahead. This path will probably be long and irreversible. Artificial intelligence will change our lives and we need to change our minds as soon as possible to adapt, accept, and manage the resulting changes in the best possible way, to ensure that they will bring as many benefits as possible and will cause the least possible negative consequences for us. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF