Machine Learning Enables Accurate Prediction of Asparagine Deamidation Probability and Rate
Autor: | Jason A. Martins, Jared A. Delmar, Seo Woo Choi, John P. Mikhail, Jihong Wang |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
mab
0301 basic medicine lcsh:QH426-470 IgG Computer science medicine.drug_class Stability (learning theory) Vectors in gene therapy Protein degradation Machine learning computer.software_genre Monoclonal antibody Article 03 medical and health sciences 0302 clinical medicine antibody developability Aspartic acid medicine Genetics therapeutic protein Asparagine lcsh:QH573-671 Deamidation Molecular Biology business.industry lcsh:Cytology Correction prediction stability drug development deamidation lcsh:Genetics machine learning 030104 developmental biology Biopharmaceutical 030220 oncology & carcinogenesis Molecular Medicine Artificial intelligence business computer |
Zdroj: | Molecular Therapy: Methods & Clinical Development, Vol 19, Iss, Pp 374-(2020) Molecular Therapy. Methods & Clinical Development Molecular Therapy: Methods & Clinical Development, Vol 15, Iss, Pp 264-274 (2019) |
ISSN: | 2329-0501 |
Popis: | The spontaneous conversion of asparagine residues to aspartic acid or iso-aspartic acid, via deamidation, is a major pathway of protein degradation and is often seriously disruptive to biological systems. Deamidation has been shown to negatively affect both in vitro stability and in vivo biological function of diverse classes of proteins. During protein therapeutics development, deamidation liabilities that are overlooked necessitate expensive and time-consuming remediation strategies, sometimes leading to termination of the project. In this paper, we apply machine learning to a large (n = 776) liquid chromatography-tandem mass spectrometry (LC-MS/MS) dataset of monoclonal antibody peptides to create computational models for the post-translational modification asparagine deamidation, using the random decision forest method. We show that our categorical model predicts antibody deamidation with nearly 5% increased accuracy and 0.2 MCC over the best currently available models. Surprisingly, our model also paces or outperforms advanced and conventional models on an independent non-antibody dataset. In addition to deamidation probability, we are able to accurately predict deamidation rate (R2 = 0.963 and Q2 = 0.822), a capability with no peer in current models. This method should enable significant improvement in protein candidate selection, especially in biopharmaceutical development, and can be applied with similar accuracy to enzymes, monoclonal antibodies, next-generation formats, vaccine component antigens, and gene therapy vectors such as adeno-associated virus. Keywords: deamidation, machine learning, prediction, developability, stability, drug development, therapeutic protein, antibody, mab, IgG |
Databáze: | OpenAIRE |
Externí odkaz: |