Journal of Data Mining in Genomics & Proteomics provides rapid publication of articles in all areas of related to genomic data warehousing, genomic data mining, genomic and proteomics data services, data mining applications in genomics, data mining applications in proteomics, proteomics data warehousing, data warehousing, data mining in drug discovery, statistical data mining, data algorithms, data modelling and intellegence, data mining tools, comparative proteomics, proteogenomics, metagenomics, comparative genomics, molecular modeling, mapping of genomes, cluster analysis, computational drug design, genome annotation.

The phrase "genetic algorithms" (GA) refers to search algorithms that may adapt to the amount or kind of parameters you input. The algorithms sort the many solutions into several categories, and the design of each category is based on the design of the natural genetic solution. The survival of the fittest is one of the key tenants of genetic algorithms. The genetic makeup of the fittest humans is passed down naturally from one generation to the next. Similar to data mining, the genetic algorithm executes the selection, crossover, mutation, and encoding processes iteratively in order to create new models at each interaction. Even little input modifications or the presence of noise might cause malfunctions despite its greater robustness. When exploring huge multi-modal state spaces, large state spaces, or n-dimensional surfaces, a genetic algorithm can produce better and more meaningful results than other optimization techniques as praxis, linear programming, heuristic, first, or breadth-first.

Numerous industries, including robotics, automobile design, improved telecommunications routing, engineering design, and computer-aided molecular design, heavily rely on genetic algorithms. Data mining discovers patterns that are understandable by humans and makes predictions about the future based on the variables or features included in the database. The fundamental tenet of the linear multi regression model is that the characteristics do not interact. GA does a much better job of handling how the qualities interact with one another. Using GA, the non-linear multi regression model may extract specific data from the training set. In order to identify the ideal set of solutions, multiple objectives GA considers problems with multiple objective functions and constraints. The search space cannot contain any of the solutions from this set that can dominate another member of the set. Such algorithms are employed for rule mining in situations when there is a big search space and plenty of data to be found. Multi-objective GA conducts a global search with various objectives in order to get the best answers. Including a mix of elements including predictability, understand ability, and interest.