Integration of Machine Learning Improves The Prediction Accuracy of Molecular Modelling for M. jannaschii Tyrosyl-tRNA Synthetase Substrate Specificity

Design of enzyme binding pocket to accommodate substrates with different chemical structure is a great challenge. Traditionally, thousands even millions of mutants have to be screened in wet-lab experiments to find a ligand-specific mutant and large amount of time and resources are consumed. To accelerate the screening process, we propose a novel workflow through integration of molecular modeling and data-driven machine learning method to generate mutant libraries with high enrichment ratio for recognition of specific substrate. We collected all the M. janonschii tyrosyl-tRNA synthetase (Mj. TyrRS) mutants reported in the literature to compare and analyze the sequence and structural feature and difference between mutant and wild type Mj. TyrRS. Mj. TyrRS is used as an example since the sequences and structures of many unnatural amino acid specific Mj. TyrRS mutants have been reported. Based on the crystal structures of different Mj. TyrRS mutants and Rosetta modeling result, we found D158G/P is the critical residue which influences the backbone disruption of helix with residue 158-163. Our results showed that compared with random mutation, Rosetta modeling and score function calculation can elevate the enrichment ratio of desired mutants by 2-fold in a test library having 687 mutants, while after calibration by machine learning model trained using known data of Mj. TyrRS mutants and ligand, the enrichment ratio can be elevated by 11-fold. This molecular modeling and machine learning-integrated workflow is anticipated to significantly benefit to the Mj. tyrRS mutant screening and substantially reduce the time and cost of wet-lab experiments. Besides, this novel process will have broad application in the field of computational protein design.

Automated summary

Designing enzyme binding pockets to accommodate substrates with different chemical structures is a great challenge, traditionally requiring screening of thousands to millions of mutants. By integrating molecular modeling and data-driven machine learning, mutant libraries with high enrichment ratios can be generated to accelerate the screening process. This integrated workflow is expected to significantly benefit Mj. tyrRS mutant screening and reduce time and cost of wet-lab experiments.