Dataset Information

Machine learning-guided evolution of pyrrolysyl-tRNA synthetase for improved incorporation efficiency of diverse noncanonical amino acids

ABSTRACT: The pyrrolysyl-tRNA synthetase (PylRS) is widely used to incorporate noncanonical amino acids (ncAAs) into proteins. However, most of ncAA-containing protein yields remain low due to the limited activity of PylRS variants. Here, we apply machine learning (ML) to engineer the tRNA-binding domain of PylRS. The FFT-PLSR model is first applied to explore pairwise combinations of 12 single mutations, generating a variant Com1-IFRS with an 11-fold increase in stop codon suppression efficiency. Deep learning models ESM-1v, Mutcompute, and ProRefiner then identify new mutation sites. Applying FFT-PLSR on these sites yields a variant Com2-IFRS showing a 30.8-fold increase in stop codon suppression efficiency. Transplanting these mutations into 7 other PylRS-derived synthetases improved ncAA-containing protein yield by up to 1149.7-fold. Molecular dynamics simulations are used to explore the molecular change caused by the mutations. This paper presents improved PylRS variants and a machine learning framework for optimizing the enzyme activity.

INSTRUMENT(S): 6520A Quadrupole Time-of-Flight LC/MS

ORGANISM(S): Escherichia Coli

SUBMITTER: Haoran Yu

LAB HEAD: Haoran Yu

PROVIDER: PXD065336 | Pride | 2025-07-25

REPOSITORIES: Pride

ACCESS DATA

Dataset's files

Source:

Items per page:

1 - 5 of 10

Publications

Machine learning-guided evolution of pyrrolysyl-tRNA synthetase for improved incorporation efficiency of diverse noncanonical amino acids.

Zhang Qunfeng Q Jiang Ling L Niu Yadan Y Li Yujie Y Chen Wanyi W Cheng Jingxi J Ding Haote H Chen Binbin B Liu Ke K Cao Jiawen J Wang Junli J Ye Shilin S Yang Lirong L Wu Jianping J Xu Gang G Lin Jianping J Yu Haoran H

Nature communications 20250719 1

The pyrrolysyl-tRNA synthetase (PylRS) is widely used to incorporate noncanonical amino acids (ncAAs) into proteins. However, the yields of most ncAA-containing protein remain low due to the limited activity of PylRS variants. Here, we apply machine learning to engineer the tRNA-binding domain of PylRS. The FFT-PLSR model is first applied to explore pairwise combinations of 12 single mutations, generating a variant Com1-IFRS with an 11-fold increase in stop codon suppression (SCS) efficiency. D ...[more]

PMID: 40681550

Similar Datasets

Project description:Translation of mRNA into a polypeptide is terminated when the release factor eRF1 recognizes a UAA, UAG, or UGA stop codon in the ribosomal A site and stimulates nascent peptide release. However, stop codon readthrough can occur when a near-cognate tRNA outcompetes eRF1 in decoding the stop codon, resulting in the continuation of the elongation phase of protein synthesis. At the end of a conventional mRNA coding region readthrough allows translation into the mRNA 3’-UTR. Previous studies with reporter systems have shown that the efficiency of termination or readthrough is modulated by cis-acting elements other than stop codon identity, including two nucleotides 5’ of the stop codon, six nucleotides 3’ of the stop codon in the ribosomal mRNA channel, and stem-loop structures in the mRNA 3’-UTR. It is unknown whether these elements are important at a genome-wide level and whether other mRNA features proximal to the stop codon significantly affect termination and readthrough efficiencies in vivo. Accordingly, we carried out ribosome profiling analyses of yeast cells expressing wild-type or temperature-sensitive eRF1 and developed bioinformatics strategies to calculate readthrough efficiency, and to identify mRNA and peptide features which influence that efficiency. We found that the stop codon (nt +1 to +3), the nucleotide after it (nt +4), the codon in the P site (nt -3 to -1), and 3’-UTR length are the most influential features in the control of readthrough efficiency, while nts +5 to +9 and mRNA secondary structure in the 3’-UTR had milder effects. Additionally, we found low readthrough genes to have shorter 3’-UTRs compared to high readthrough genes in cells with thermally inactivated eRF1, while this trend was reversed in wild-type cells. Together, our results demonstrated the general roles of known regulatory elements in genome-wide regulation and identified several new mRNA or peptide features important for translation termination and readthrough.

			Action	DRS
	All_raw_data.zip	Other
	GFP-2ThiA.XML	Xml
	GFP-3BrF.XML	Xml
	GFP-3IY.XML	Xml
	GFP-3MeH.XML	Xml