They have developed a novel method to predict the success of PCR amplification for a specific primer set and DNA template based on the relationship between the primer sequence and the template. To perform the prediction using a recurrent neural network, the usual double-stranded formation between the primer and template nucleotide sequences was herein expressed as a five-lettered word. The set of words (pseudo-sentences) was placed to indicate the success or failure of PCR targeted to learn recurrent neural network (RNN). After learning pseudo-sentences, RNN predicted PCR results from pseudo-sentences which were created by primer and template sequences with 70% accuracy.
Fig: PCR process diagram of primers with incomplete homology with the template. Schematic diagram of the reaction assumed by PCR from partially matched primers. DNA elongation may start from primers on which partially 3′-end matches (B). On the end of second cycle, the 3′-end of the elongated DNA completely match with a primer (C). On the end of third cycle, synthesized DNA are completely matched on both ends of synthesized DNA (D).
These results suggest that PCR results could be predicted using learned RNN and the trained RNN could be used as a replacement for preliminary PCR experimentation. This is the first report which utilized the application of neural network for primer design and prediction of PCR results.
Kayama, K., Kanno, M., Chisaki, N. et al. Prediction of PCR amplification from primer and template sequences using recurrent neural network. Sci Rep 11, 7493 (2021). https://doi.org/10.1038/s41598-021-86357-1