11 Genetic Algorithms
Cases arise in which abundant data is generated but the optimal function that could simulate the data is not known. For example, protein sequences as well as protein folding structures are known, but the missing part is the function that converts a protein sequence into a folded structure. This is a very difficult problem with no easy solution. However, it illustrates the idea that plenty of data can be available without knowing the exact function that associates them.
An approach to problems of this nature is to optimize a function through the use of an artificial genetic algorithm (GA). The idea of this system is that the GA contains several genes, each one encoding a solution to the problem. Some solutions are better ...
Get Python for Bioinformatics now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
