Chemical stability is a major concern in the development of protein therapeutics due to its impact on both efficacy and safety. Protein “hotspots” are amino acid residues that are subject to various chemical modifications, including deamidation, isomerization, glycosylation, and phosphorylation etc. A more accurate prediction method for potential hotspot residues would allow their elimination or reduction as early as possible in the drug discovery process.<br/><br/>In this work, we focus on prediction models for asparagine (Asn) deamidation. Two approaches, namely, machine learning and molecular dynamics were applied. For the machine learning approach, the prediction models were built to mine available experimental and structural data of deamidated proteins. The training set contains 304 Asn residues from 31 proteins that all have available high resolution crystal structures. Experimentally measured deamidation half-life of Asn in penta-peptides as well as 3D structure based properties, such as solvent exposure, crystallographic B factors, local secondary structure and dihedral angles etc., were used to train prediction models with several machine learning algorithms. The prediction tools were cross-validated as well as tested with an external test dataset. The model correctly predicted the ranking for 6 out of 7 deamidated Asn residues in the test set. It is possible that such quantitative protein structure – function relationship tools can also be applied to other protein hotspot predictions.<br/><br/>For the molecular dynamics approach, we are interested in predicting whether deamination can happen in the NG motif, which is the most deamidation prone. We ran MD simulations to monitor the nucleophilic attacking distance between the Asn residue side chain amide carbon atom and its C terminus glycine residue main chain nitrogen atom. Increased time occupancy of the short C-N distance has been observed for deamidation cases.

Protein deamidation prediction with machine learning and molecular dynamics

251st National Meeting (2016)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.