Effective decoders for DNA codes

A number of applications use DNA as a storage mechanism. Because processes in these applications may cause errors in the data, the information must be encoded as one of a chosen set of words that are well separated from one another - a DNA error-correcting code. Typically, the types of errors that may occur include insertions, deletions and substitutions of symbols, making the edit metric the most suitable choice to measure the distance between strings. Decoding, the process of recovering the original word when errors occur, is complicated by biological restrictions combined with a high cost to calculate edit distance. Side effect machines (SEMs), an extension of finite state machines, can provide efficient decoding algorithms for such codes. Several codes of varying lengths are used to study the effectiveness of evolutionary programming (EP) as a general approach for finding SEMs for edit metric decoding. Two classification methods (direct and fuzzy classification) are compared, and different EP settings are examined to observe how decoding accuracy is affected. Regardless of code length, the best results are found using fuzzy classification. The best accuracy is seen for codes of length 10, for which a maximum accuracy of up to 99.4% is achieved for distance 1 and distance 2 and 3 achieve up to 97.1% and 85.9%, respectively. Additionally, the SEMs are examined for potential bloat by comparing the number of reachable states against the total number of states. Bloat is seen more in larger machines than in smaller machines. Furthermore, the results are analysed to find potential trends and relationships among the parameters, with the most consistent trend being that, when allowed, the longer codes generally show a propensity for larger machines.