In the course of lectures, unique features of biological data are considered, leading to original statements of recognition and classification problems. It should be noted that for almost all the problems considered in the course, accurate and mathematically sound solutions have not yet been proposed. In this sense, the course represents an extensive field of activity for independent scientific work of students. A system of recognition tasks is formulated that reflects the structure of biological systems and provides a basis for the construction of problem-oriented theories. The fundamentals of the formalism developed to solve the problems of bioinformatics and other poorly formalized problems in the field of advanced biomedical research and sentiment analysis are considered. This formalism is based on the theory of universal and local constraints within the framework of an algebraic approach to recognition. Attention is paid to biomedical applications of the results of intelligent analysis of biological data.
- From cell biology to recognition tasks.
- iological data, objects and approaches to the formalization of tasks.
- Tasks 1D to 1D: comparison of character sequences.
- 1Ddna tasks. 1Ddna and 3Ddna tasks. Tasks of 1Drna, 2Drna, 3Drna.
- X-ray diffraction analysis and NMR of proteins, 3Db to 3Db and 3Db to 2Db tasks.
- Development of a problem-oriented theory on the example of the problem of recognition of a secondary structure.
- Tasks 1DB to 1Db.
- Tasks 1Db to F and 3D to F and genome annotation task.
- Analysis and synthesis of biological networks.
- Molecular pharmacology and chemoinformatics.
- Biomedical and genetic research.
- Text analysis, use of databases.
- Bio-logic and algorithms.
Practical tasks will be announced during the lectures. Students can formulate the topics of research tasks themselves. After selecting the task, the work requirements are discussed.
Before the start of the oral exam (report-presentation), it is necessary to submit a report on the research work (3-5 pages) carried out on the selected task.
Machine learning methods.