Prediction of peptide binding to MHC using machine learning with sequence and structure-based feature sets.

Selecting peptides that bind strongly to the major histocompatibility complex (MHC) for inclusion in a vaccine has therapeutic potential for infections and tumors. Machine learning models trained on sequence data exist for peptide:MHC (p:MHC) binding predictions. Here, we train support vector machine classifier (SVMC) models on physicochemical sequence-based and structure-based descriptor sets to predict peptide binding to a well-studied model mouse MHC I allele, H-2Db. Recursive feature elimination and two-way forward feature selection were also performed. Although low on sensitivity compared to the current state-of-the-art algorithms, models based on physicochemical descriptor sets achieve specificity and precision comparable to the most popular sequence-based algorithms. The best-performing model is a hybrid descriptor set containing both sequence-based and structure-based descriptors. Interestingly, close to half of the physicochemical sequence-based descriptors remaining in the hybrid model were properties of the anchor positions, residues 5 and 9 in the peptide sequence. In contrast, residues flanking position 5 make little to no residue-specific contribution to the binding affinity prediction. The results suggest that machine-learned models incorporating both sequence-based descriptors and structural data may provide information on specific physicochemical properties determining binding affinities.

U.S. Army disease and nonbattle injury model, refined in Afghanistan and Iraq.

Previous analysis of Operation Desert Shield/Operation Desert Storm data yielded a disease and nonbattle injury (DNBI) model using distinct 95th percentile daily admission rates during the three phases of a war-fighting operation to predict medical requirements. This study refines the model with data from Operation Enduring Freedom (OEF) and Operation Iraqi Freedom (OIF). Inpatient health care records of U.S. Army soldiers deployed to OEF and OIF who were admitted with DNBI diagnoses were analyzed. DNBI admission rates for OEF and OIF were compared with rates for Operation Desert Shield/Operation Desert Storm. DNBI admission rates for OEF and OIF were lower than those for Operation Desert Shield/Operation Desert Storm. Rates among the phases of OIF were distinctly different. DNBI admission rates have been reduced during recent deployments. The concepts of the original model based on Operation Desert Shield/Operation Desert Storm data were validated by experiences during OEF and OIF. Continuous surveillance of DNBI admission rates is recommended.