Machine Learning Combined with Restriction Enzyme Mining Assists in the Design of Multi-Point Mutagenic Primers

The polymerase chain reaction–restriction fragment length polymorphism (PCR-RFLP) experiment has the characteristics of low-cost, rapidity, simplicity, convenience, high sensitivity and specificity; thus, many small medium laboratories use it to perform all kinds single nucleotide polymorphisms (SNPs) genotyping works, as a molecular biotechnology for disease-related analysis. However, lack available restriction enzymes distinguish specific genotypes on target SNP, that causes PCR-RFLP assay which is unavailable be called mismatch PCR-RFLP. In order completely solve problem PCR-RFLP, we have created teaching–learning-based optimization (TLBO) multi-point mutagenic primer design algorithm which, combined with REHUNT, provides complete enzyme mining solution. proposed method not only introduces several search strategies suitable mutagenesis primers, but also enhances reliability design. addition, this study designed more complex SNP structures (with multiple dNTPs insertion deletion) provide solutions diversity. We tested against fifteen SNPs in human SLC6A4 gene NCBI dbSNP database experimental templates. results indicate helpful providing primers meet constrain conditions PCR experiments.