Enhancing the Taq polymerase via AI-driven rational design

The paper «Enhancing the reverse transcriptase function in Taq polymerase via AI-driven multiparametric rational» is published in the journal of Frontiers in Bioengineering and Biotechnology. The result is based on the AI models developed in NOVEL and Institute of Artificial Intelligence MSU.

We trained a Ridge regression model to predict multiple enzyme properties in the wild type and mutated Taq polymerase. The model is based on the embeddings of Taq polymerase primary structure generated by a protein language model. Using the regression model we conducted an in silico screen of over 18 million potential mutations, narrowing the field to 16 top candidates for comprehensive wet-lab evaluation.

This approach led to the identification of 18 enzyme variants that exhibited markedly improved reverse transcriptase activity while maintaining a favorable balance of other key properties. Several enzymes validated via this procedure were effective in single-enzyme real-time reverse-transcription PCR setups, implying their utility for the development of new tools for real-time reverse-transcription PCR technologies, such as pathogen RNA detection and gene expression analysis.

Our approach offers a robust framework for designing enzyme mutants tailored to specific biotechnological applications. The full text article is here https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2024.1495267/full.