Bayesian classification with Gaussian processes

We consider the problem of assigning an input vector class='mathrm'>bfx to one of class='mathrm'>m classes by predicting class='mathrm'>P(c|bfx) for class='mathrm'>c = 1, ldots, m. For a two-class problem, the probability of class 1 given class='mathrm'>bfx is estimated by class='mathrm'>s(y(bfx)), where class='mathrm'>s(y) = 1/(1 + e^-y). A Gaussian process prior is placed on class='mathrm'>y(bfx), and is combined with the training data to obtain predictions for new class='mathrm'>bfx points. We provide a Bayesian treatment, integrating over uncertainty in class='mathrm'>y and in the parameters that control the Gaussian process prior; the necessary integration over class='mathrm'>y is carried out using Laplace's approximation. The method is generalized to multi-class problems class='mathrm'>(m >2) using the softmax function. We demonstrate the effectiveness of the method on a number of datasets.

The clinical significance of medicines reconciliation in children admitted to hospital

Aims and Objectives: The NICE/NPSA guidance on Medicines Reconciliation in adults upon hospital admission excludes children under the age of 16.1 Hence the primary aim and objective of this study was to use medicines reconciliation to primarily identify if discrepancies occur upon hospital admission. Secondary objectives were to clinically assess for harm discrepancies that were identified in paediatric patients on long term medications at four hospitals across the UK. Method: Medicines reconciliation is a procedure where the current medication history of a patient prior to hospital admission would be taken and verifying the medication orders made at hospital admission against this history, addressing any discrepancies identified. Medicines reconciliation was carried out prospectively for 244 paediatric patients on chronic medication across four UK hospitals (Birmingham, London, Leeds and North Staffordshire) between January – May 2011. Medicines reconciliation was conducted by a clinical pharmacist using the following sources of information: 1) the patient's Pre-Admission Medication (PAM) from the patient's general practitioner 2) examination of the Patient's Own Medications brought into hospital, 3) a semi-structured interview with the parent-carers and 4) identification of admission medication orders written on the drug chart prior to clinical pharmacy input (Drug Chart). Discrepancies between the PAM and Drug Chart were documented and classified as intentional or unintentional. Intentional discrepancies were defined as changes that were made knowingly by the prescriber and confirmed. Unintentional discrepancies were assessed for clinical significance by an expert panel and assigned a significance score based on the likelihood of causing potential discomfort or clinical deterioration: class 1 unlikely, class 2 moderate and class 3 severe.2 Results: 1004 medication regimens were included from the 244 patients across the four sites. 588 of the 1004 (59%) medicines, had discrepancies between the PAM and Drug Chart; of these 36% (n = 209) were unintentional and included for clinically assessment. 189 drug discrepancies 30% were classified as class 1, 47% were class 2 and 23% were class 3 discrepancies. The remaining 20 discrepancies were cases where deviating from the PAM would have been the right thing to do, which might suggest that an intentional but undocumented discrepancy by the prescriber writing up the admission order may have occurred. Conclusion: The results suggest that medication discrepancies in paediatric patients do occur upon hospital admission, which do have a potential to cause harm and that medicines reconciliation is a potential solution to preventing such discrepancies. References: 1. National Institute for Health and Clinical Excellence. National Patient Safety Agency. PSG001. Technical patient safety solutions for medicines reconciliation on admission of adults to hospital. London: NICE; 2007. 2. Cornish, P. L., Knowles, S. R., Marchesano, et al. Unintended Medication Discrepancies at the Time of Hospital Admission. Archives of Internal Medicine 2005; 165:424–429

Peptide binding prediction for the human class II MHC allele HLA-DP2:a molecular docking approach

MHC class II proteins bind oligopeptide fragments derived from proteolysis of pathogen antigens, presenting them at the cell surface for recognition by CD4+ T cells. Human MHC class II alleles are grouped into three loci: HLA-DP, HLA-DQ and HLA-DR. In contrast to HLA-DR and HLA-DQ, HLA-DP proteins have not been studied extensively, as they have been viewed as less important in immune responses than DRs and DQs. However, it is now known that HLA-DP alleles are associated with many autoimmune diseases. Quite recently, the X-ray structure of the HLA-DP2 molecule (DPA*0103, DPB1*0201) in complex with a self-peptide derived from the HLA-DR a-chain has been determined. In the present study, we applied a validated molecular docking protocol to a library of 247 modelled peptide-DP2 complexes, seeking to assess the contribution made by each of the 20 naturally occurred amino acids at each of the nine binding core peptide positions and the four flanking residues (two on both sides).

HLA-DP2 binding prediction by molecular dynamics simulations

Major histocompatibility complex (MHC) II proteins bind peptide fragments derived from pathogen antigens and present them at the cell surface for recognition by T cells. MHC proteins are divided into Class I and Class II. Human MHC Class II alleles are grouped into three loci: HLA-DP, HLA-DQ, and HLA-DR. They are involved in many autoimmune diseases. In contrast to HLA-DR and HLA-DQ proteins, the X-ray structure of the HLA-DP2 protein has been solved quite recently. In this study, we have used structure-based molecular dynamics simulation to derive a tool for rapid and accurate virtual screening for the prediction of HLA-DP2-peptide binding. A combinatorial library of 247 peptides was built using the "single amino acid substitution" approach and docked into the HLA-DP2 binding site. The complexes were simulated for 1 ns and the short range interaction energies (Lennard-Jones and Coulumb) were used as binding scores after normalization. The normalized values were collected into quantitative matrices (QMs) and their predictive abilities were validated on a large external test set. The validation shows that the best performing QM consisted of Lennard-Jones energies normalized over all positions for anchor residues only plus cross terms between anchor-residues.

Integrating in silico and in vitro analysis of peptide binding affinity to HLA-Cw*0102:a bioinformatic approach to the prediction of new epitopes

Predictive models of peptide-Major Histocompatibility Complex (MHC) binding affinity are important components of modern computational immunovaccinology. Here, we describe the development and deployment of a reliable peptide-binding prediction method for a previously poorly-characterized human MHC class I allele, HLA-Cw*0102.

EpiTOP—a proteochemometric tool for MHC class II binding prediction

Motivation: T-cell epitope identification is a critical immunoinformatic problem within vaccine design. To be an epitope, a peptide must bind an MHC protein. Results: Here, we present EpiTOP, the first server predicting MHC class II binding based on proteochemometrics, a QSAR approach for ligands binding to several related proteins. EpiTOP uses a quantitative matrix to predict binding to 12 HLA-DRB1 alleles. It identifies 89% of known epitopes within the top 20% of predicted binders, reducing laboratory labour, materials and time by 80%. EpiTOP is easy to use, gives comprehensive quantitative predictions and will be expanded and updated with new quantitative matrices over time.

Identification of the HLA-DM/HLA-DR interface

Human leukocyte antigen (HLA)-DM is a critical participant in antigen presentation that catalyzes the dissociation of the Class II-associated Invariant chain-derived Peptide (CLIP) from the major histocompatibility complex (MHC) Class II molecules. There is competition amongst peptides for access to an MHC Class II groove and it has been hypothesised that DM functions as a 'peptide editor' that catalyzes the replacement of one peptide for another within the groove. It is established that the DM catalyst interacts directly with the MHC Class II but the precise location of the interface is unknown. Here, we combine previously described mutational data with molecular docking and energy minimisation simulations to identify a putative interaction site of >4000A2 which agrees with known point mutational data for both the DR and DM molecule. The docked structure is validated by comparison with experimental data and previously determined properties of protein-protein interfaces. A possible dissociation mechanism is suggested by the presence of an acidic cluster near the N terminus of the bound peptide.

Predicting class I major histocompatibility complex (MHC) binders using multivariate statistics:comparison of discriminant analysis and multiple linear regression

The accurate in silico identification of T-cell epitopes is a critical step in the development of peptide-based vaccines, reagents, and diagnostics. It has a direct impact on the success of subsequent experimental work. Epitopes arise as a consequence of complex proteolytic processing within the cell. Prior to being recognized by T cells, an epitope is presented on the cell surface as a complex with a major histocompatibility complex (MHC) protein. A prerequisite therefore for T-cell recognition is that an epitope is also a good MHC binder. Thus, T-cell epitope prediction overlaps strongly with the prediction of MHC binding. In the present study, we compare discriminant analysis and multiple linear regression as algorithmic engines for the definition of quantitative matrices for binding affinity prediction. We apply these methods to peptides which bind the well-studied human MHC allele HLA-A*0201. A matrix which results from combining results of the two methods proved powerfully predictive under cross-validation. The new matrix was also tested on an external set of 160 binders to HLA-A*0201; it was able to recognize 135 (84%) of them.

Large-scale molecular dynamics simulations of HLA-A*0201 complexed with a tumor-specific antigenic peptide:can the α3 and β2m domains be neglected?

Large-scale massively parallel molecular dynamics (MD) simulations of the human class I major histo-compatibility complex (MHC) protein HLA-A*0201 bound to a decameric tumor-specific antigenic peptide GVY-DGREHTV were performed using a scalable MD code on high-performance computing platforms. Such computational capabilities put us in reach of simulations of various scales and complexities. The supercomputing resources available Large-scale massively parallel molecular dynamics (MD) simulations of the human class I major histocompatibility complex (MHC) protein HLA-A*0201 bound to a decameric tumor-specific antigenic peptide GVYDGREHTV were performed using a scalable MD code on high-performance computing platforms. Such computational capabilities put us in reach of simulations of various scales and complexities. The supercomputing resources available for this study allow us to compare directly differences in the behavior of very large molecular models; in this case, the entire extracellular portion of the peptide–MHC complex vs. the isolated peptide binding domain. Comparison of the results from the partial and the whole system simulations indicates that the peptide is less tightly bound in the partial system than in the whole system. From a detailed study of conformations, solvent-accessible surface area, the nature of the water network structure, and the binding energies, we conclude that, when considering the conformation of the α1–α2 domain, the α3 and β2m domains cannot be neglected. © 2004 Wiley Periodicals, Inc. J Comput Chem 25: 1803–1813, 2004

Peptide binding to HLA-DP proteins at pH 5.0 and pH 7.0:a quantitative molecular docking study

Background: HLA-DPs are class II MHC proteins mediating immune responses to many diseases. Peptides bind MHC class II proteins in the acidic environment within endosomes. Acidic pH markedly elevates association rate constants but dissociation rates are almost unchanged in the pH range 5.0 - 7.0. This pH-driven effect can be explained by the protonation/deprotonation states of Histidine, whose imidazole has a pKa of 6.0. At pH 5.0, imidazole ring is protonated, making Histidine positively charged and very hydrophilic, while at pH 7.0 imidazole is unprotonated, making Histidine less hydrophilic. We develop here a method to predict peptide binding to the four most frequent HLA-DP proteins: DP1, DP41, DP42 and DP5, using a molecular docking protocol. Dockings to virtual combinatorial peptide libraries were performed at pH 5.0 and pH 7.0. Results: The X-ray structure of the peptide - HLA-DP2 protein complex was used as a starting template to model by homology the structure of the four DP proteins. The resulting models were used to produce virtual combinatorial peptide libraries constructed using the single amino acid substitution (SAAS) principle. Peptides were docked into the DP binding site using AutoDock at pH 5.0 and pH 7.0. The resulting scores were normalized and used to generate Docking Score-based Quantitative Matrices (DS-QMs). The predictive ability of these QMs was tested using an external test set of 484 known DP binders. They were also compared to existing servers for DP binding prediction. The models derived at pH 5.0 predict better than those derived at pH 7.0 and showed significantly improved predictions for three of the four DP proteins, when compared to the existing servers. They are able to recognize 50% of the known binders in the top 5% of predicted peptides. Conclusions: The higher predictive ability of DS-QMs derived at pH 5.0 may be rationalised by the additional hydrogen bond formed between the backbone carbonyl oxygen belonging to the peptide position before p1 (p-1) and the protonated ε-nitrogen of His 79β. Additionally, protonated His residues are well accepted at most of the peptide binding core positions which is in a good agreement with the overall negatively charged peptide binding site of most MHC proteins. © 2012 Patronov et al.; licensee BioMed Central Ltd.

A hydrogen-bonded polar network in the core of the glucagon-like peptide-1 receptor is a fulcrum for biased agonism:lessons from class B crystal structuress

The glucagon-like peptide 1 (GLP-1) receptor is a class B G protein-coupled receptor (GPCR) that is a key target for treatments for type II diabetes and obesity. This receptor, like other class B GPCRs, displays biased agonism, though the physiologic significance of this is yet to be elucidated. Previous work has implicated R2.60190 , N3.43240 , Q7.49394 , and H6.52363 as key residues involved in peptide-mediated biased agonism, with R2.60190 , N3.43240 , and Q7.49394 predicted to form a polar interaction network. In this study, we used novel insight gained from recent crystal structures of the transmembrane domains of the glucagon and corticotropin releasing factor 1 (CRF1) receptors to develop improved models of the GLP-1 receptor that predict additional key molecular interactions with these amino acids. We have introduced E6.53364 A, N3.43240 Q, Q7.49493N, and N3.43240 Q/Q7.49 Q/Q7.49493N mutations to probe the role of predicted H-bonding and charge-charge interactions in driving cAMP, calcium, or extracellular signal-regulated kinase (ERK) signaling. A polar interaction between E6.53364 and R2.60190 was predicted to be important for GLP-1- and exendin-4-, but not oxyntomodulin-mediated cAMP formation and also ERK1/2 phosphorylation. In contrast, Q7.49394 , but not R2.60190 /E6.53364 was critical for calcium mobilization for all three peptides. Mutation of N3.43240 and Q7.49394 had differential effects on individual peptides, providing evidence for molecular differences in activation transition. Collectively, this work expands our understanding of peptide-mediated signaling from the GLP-1 receptor and the key role that the central polar network plays in these events.