1
|
Lu C, Lubin JH, Sarma VV, Stentz SZ, Wang G, Wang S, Khare SD. Prediction and design of protease enzyme specificity using a structure-aware graph convolutional network. Proc Natl Acad Sci U S A 2023; 120:e2303590120. [PMID: 37729196 PMCID: PMC10523478 DOI: 10.1073/pnas.2303590120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2023] [Accepted: 08/14/2023] [Indexed: 09/22/2023] Open
Abstract
Site-specific proteolysis by the enzymatic cleavage of small linear sequence motifs is a key posttranslational modification involved in physiology and disease. The ability to robustly and rapidly predict protease-substrate specificity would also enable targeted proteolytic cleavage by designed proteases. Current methods for predicting protease specificity are limited to sequence pattern recognition in experimentally derived cleavage data obtained for libraries of potential substrates and generated separately for each protease variant. We reasoned that a more semantically rich and robust model of protease specificity could be developed by incorporating the energetics of molecular interactions between protease and substrates into machine learning workflows. We present Protein Graph Convolutional Network (PGCN), which develops a physically grounded, structure-based molecular interaction graph representation that describes molecular topology and interaction energetics to predict enzyme specificity. We show that PGCN accurately predicts the specificity landscapes of several variants of two model proteases. Node and edge ablation tests identified key graph elements for specificity prediction, some of which are consistent with known biochemical constraints for protease:substrate recognition. We used a pretrained PGCN model to guide the design of protease libraries for cleaving two noncanonical substrates, and found good agreement with experimental cleavage results. Importantly, the model can accurately assess designs featuring diversity at positions not present in the training data. The described methodology should enable the structure-based prediction of specificity landscapes of a wide variety of proteases and the construction of tailor-made protease editors for site-selectively and irreversibly modifying chosen target proteins.
Collapse
Affiliation(s)
- Changpeng Lu
- Institute for Quantitative Biomedicine, Rutgers–The State University of New Jersey, Piscataway, NJ08854
| | - Joseph H. Lubin
- Department of Chemistry and Chemical Biology, Rutgers–The State University of New Jersey, Piscataway, NJ08854
| | - Vidur V. Sarma
- Institute for Quantitative Biomedicine, Rutgers–The State University of New Jersey, Piscataway, NJ08854
| | | | - Guanyang Wang
- Department of Statistics, Rutgers–The State University of New Jersey, Piscataway, NJ08854
| | - Sijian Wang
- Institute for Quantitative Biomedicine, Rutgers–The State University of New Jersey, Piscataway, NJ08854
- Department of Statistics, Rutgers–The State University of New Jersey, Piscataway, NJ08854
| | - Sagar D. Khare
- Institute for Quantitative Biomedicine, Rutgers–The State University of New Jersey, Piscataway, NJ08854
- Department of Chemistry and Chemical Biology, Rutgers–The State University of New Jersey, Piscataway, NJ08854
| |
Collapse
|
2
|
Lu C, Lubin JH, Sarma VV, Stentz SZ, Wang G, Wang S, Khare SD. Prediction and Design of Protease Enzyme Specificity Using a Structure-Aware Graph Convolutional Network. bioRxiv 2023:2023.02.16.528728. [PMID: 36824945 PMCID: PMC9949123 DOI: 10.1101/2023.02.16.528728] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 02/18/2023]
Abstract
Site-specific proteolysis by the enzymatic cleavage of small linear sequence motifs is a key post-translational modification involved in physiology and disease. The ability to robustly and rapidly predict protease substrate specificity would also enable targeted proteolytic cleavage - editing - of a target protein by designed proteases. Current methods for predicting protease specificity are limited to sequence pattern recognition in experimentally-derived cleavage data obtained for libraries of potential substrates and generated separately for each protease variant. We reasoned that a more semantically rich and robust model of protease specificity could be developed by incorporating the three-dimensional structure and energetics of molecular interactions between protease and substrates into machine learning workflows. We present Protein Graph Convolutional Network (PGCN), which develops a physically-grounded, structure-based molecular interaction graph representation that describes molecular topology and interaction energetics to predict enzyme specificity. We show that PGCN accurately predicts the specificity landscapes of several variants of two model proteases: the NS3/4 protease from the Hepatitis C virus (HCV) and the Tobacco Etch Virus (TEV) proteases. Node and edge ablation tests identified key graph elements for specificity prediction, some of which are consistent with known biochemical constraints for protease:substrate recognition. We used a pre-trained PGCN model to guide the design of TEV protease libraries for cleaving two non-canonical substrates, and found good agreement with experimental cleavage results. Importantly, the model can accurately assess designs featuring diversity at positions not present in the training data. The described methodology should enable the structure-based prediction of specificity landscapes of a wide variety of proteases and the construction of tailor-made protease editors for site-selectively and irreversibly modifying chosen target proteins.
Collapse
Affiliation(s)
- Changpeng Lu
- Institute for Quantitative Biomedicine, Rutgers - The State University of New Jersey, Piscataway, NJ
| | - Joseph H. Lubin
- Department of Chemistry & Chemical Biology, Rutgers - The State University of New Jersey, Piscataway, NJ
| | - Vidur V. Sarma
- Institute for Quantitative Biomedicine, Rutgers - The State University of New Jersey, Piscataway, NJ
| | | | - Guanyang Wang
- Department of Statistics, Rutgers - The State University of New Jersey, Piscataway, NJ
| | - Sijian Wang
- Institute for Quantitative Biomedicine, Rutgers - The State University of New Jersey, Piscataway, NJ
- Department of Statistics, Rutgers - The State University of New Jersey, Piscataway, NJ
| | - Sagar D. Khare
- Institute for Quantitative Biomedicine, Rutgers - The State University of New Jersey, Piscataway, NJ
- Department of Chemistry & Chemical Biology, Rutgers - The State University of New Jersey, Piscataway, NJ
| |
Collapse
|
3
|
Mac QD, Sivakumar A, Phuengkham H, Xu C, Bowen JR, Su FY, Stentz SZ, Sim H, Harris AM, Li TT, Qiu P, Kwong GA. Urinary detection of early responses to checkpoint blockade and of resistance to it via protease-cleaved antibody-conjugated sensors. Nat Biomed Eng 2022; 6:310-324. [PMID: 35241815 DOI: 10.1038/s41551-022-00852-y] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2021] [Accepted: 01/28/2022] [Indexed: 12/15/2022]
Abstract
Immune checkpoint blockade (ICB) therapy does not benefit the majority of treated patients, and those who respond to the therapy can become resistant to it. Here we report the design and performance of systemically administered protease activity sensors conjugated to anti-programmed cell death protein 1 (αPD1) antibodies for the monitoring of antitumour responses to ICB therapy. The sensors consist of a library of mass-barcoded protease substrates that, when cleaved by tumour proteases and immune proteases, are released into urine, where they can be detected by mass spectrometry. By using syngeneic mouse models of colorectal cancer, we show that random forest classifiers trained on mass spectrometry signatures from a library of αPD1-conjugated mass-barcoded activity sensors for differentially expressed tumour proteases and immune proteases can be used to detect early antitumour responses and discriminate resistance to ICB therapy driven by loss-of-function mutations in either the B2m or Jak1 genes. Biomarkers of protease activity may facilitate the assessment of early responses to ICB therapy and the classification of refractory tumours based on resistance mechanisms.
Collapse
Affiliation(s)
- Quoc D Mac
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Anirudh Sivakumar
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Hathaichanok Phuengkham
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Congmin Xu
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - James R Bowen
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Fang-Yi Su
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Samuel Z Stentz
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Hyoungjun Sim
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Adrian M Harris
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Tonia T Li
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA
| | - Peng Qiu
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA.,Parker H. Petit Institute for Bioengineering and Bioscience, Atlanta, GA, USA.,The Georgia Immunoengineering Consortium, Emory University and Georgia Tech, Atlanta, GA, USA.,Winship Cancer Institute, Emory University, Atlanta, GA, USA
| | - Gabriel A Kwong
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech College of Engineering and Emory School of Medicine, Atlanta, GA, USA. .,Parker H. Petit Institute for Bioengineering and Bioscience, Atlanta, GA, USA. .,The Georgia Immunoengineering Consortium, Emory University and Georgia Tech, Atlanta, GA, USA. .,Winship Cancer Institute, Emory University, Atlanta, GA, USA. .,Institute for Electronics and Nanotechnology, Georgia Tech, Atlanta, GA, USA. .,Integrated Cancer Research Center, Georgia Tech, Atlanta, GA, USA.
| |
Collapse
|