Cell and Structural Biology

Data Mining in Structural Biology

Data mining, in simple terms, is the extraction of usable data from large volumes of raw data. It deals with analyzing hidden patterns of data for categorization into useful information. This information is collected and assembled for analysis and data mining algorithms. Data mining combines tools from machine learning and artificial intelligence, statistics (e.g. neural networks), and database management systems. This interdisciplinary sub-discipline of computer science aims to extract information from a raw data set and alter it into a comprehensible structure for further analysis. Apart from the initial raw analysis step, data mining also involves database and data management aspects, data pre-processing, model and inference considerations, interestingness metrics, complexity considerations, post-processing of discovered structures, visualization, and online updating. Data mining (also sometimes called knowledge discovery in databases) is the analytic step of the "knowledge discovery in databases" process, or KDD. Further, the large quantities of data are analyzed automatically or semi-automatically to extract previously unknown patterns such as groups of data records, unusual records, and reliance. Multi-relational data mining tools have been used for a variety of biological studies including proteomic and genomic research. The science of data mining within the realm of bioinformatics is a good addition due to the ever growing and developing biological data. These research areas are extensive and attributes of biological databases put forward great challenges ahead. Improving the accuracy of conclusions drawn from data mining is ever more imperative due to these challenges. Consequently, it is imperative for future directions of research to adapt to the integration of biological databases to provide better methods of research.