Structural prediction of peptides bound to MHC class I.

An ab initio structure prediction approach adapted to the peptide-major histocompatibility complex (MHC) class I system is presented. Based on structure comparisons of a large set of peptide-MHC class I complexes, a molecular dynamics protocol is proposed using simulated annealing (SA) cycles to sample the conformational space of the peptide in its fixed MHC environment. A set of 14 peptide-human leukocyte antigen (HLA) A0201 and 27 peptide-non-HLA A0201 complexes for which X-ray structures are available is used to test the accuracy of the prediction method. For each complex, 1000 peptide conformers are obtained from the SA sampling. A graph theory clustering algorithm based on heavy atom root-mean-square deviation (RMSD) values is applied to the sampled conformers. The clusters are ranked using cluster size, mean effective or conformational free energies, with solvation free energies computed using Generalized Born MV 2 (GB-MV2) and Poisson-Boltzmann (PB) continuum models. The final conformation is chosen as the center of the best-ranked cluster. With conformational free energies, the overall prediction success is 83% using a 1.00 Angstroms crystal RMSD criterion for main-chain atoms, and 76% using a 1.50 Angstroms RMSD criterion for heavy atoms. The prediction success is even higher for the set of 14 peptide-HLA A0201 complexes: 100% of the peptides have main-chain RMSD values < or =1.00 Angstroms and 93% of the peptides have heavy atom RMSD values < or =1.50 Angstroms. This structure prediction method can be applied to complexes of natural or modified antigenic peptides in their MHC environment with the aim to perform rational structure-based optimizations of tumor vaccines.

Experimental analysis and computer prediction of CTF/NFI transcription factor DNA binding sites.

Accurate prediction of transcription factor binding sites is needed to unravel the function and regulation of genes discovered in genome sequencing projects. To evaluate current computer prediction tools, we have begun a systematic study of the sequence-specific DNA-binding of a transcription factor belonging to the CTF/NFI family. Using a systematic collection of rationally designed oligonucleotides combined with an in vitro DNA binding assay, we found that the sequence specificity of this protein cannot be represented by a simple consensus sequence or weight matrix. For instance, CTF/NFI uses a flexible DNA binding mode that allows for variations of the binding site length. From the experimental data, we derived a novel prediction method using a generalised profile as a binding site predictor. Experimental evaluation of the generalised profile indicated that it accurately predicts the binding affinity of the transcription factor to natural or synthetic DNA sequences. Furthermore, the in vitro measured binding affinities of a subset of oligonucleotides were found to correlate with their transcriptional activities in transfected cells. The combined computational-experimental approach exemplified in this work thus resulted in an accurate prediction method for CTF/NFI binding sites potentially functioning as regulatory regions in vivo.

Improved predictive mapping of indoor radon concentrations using ensemble regression trees based on automatic clustering of geological units.

PURPOSE: According to estimations around 230 people die as a result of radon exposure in Switzerland. This public health concern makes reliable indoor radon prediction and mapping methods necessary in order to improve risk communication to the public. The aim of this study was to develop an automated method to classify lithological units according to their radon characteristics and to develop mapping and predictive tools in order to improve local radon prediction. METHOD: About 240 000 indoor radon concentration (IRC) measurements in about 150 000 buildings were available for our analysis. The automated classification of lithological units was based on k-medoids clustering via pair-wise Kolmogorov distances between IRC distributions of lithological units. For IRC mapping and prediction we used random forests and Bayesian additive regression trees (BART). RESULTS: The automated classification groups lithological units well in terms of their IRC characteristics. Especially the IRC differences in metamorphic rocks like gneiss are well revealed by this method. The maps produced by random forests soundly represent the regional difference of IRCs in Switzerland and improve the spatial detail compared to existing approaches. We could explain 33% of the variations in IRC data with random forests. Additionally, the influence of a variable evaluated by random forests shows that building characteristics are less important predictors for IRCs than spatial/geological influences. BART could explain 29% of IRC variability and produced maps that indicate the prediction uncertainty. CONCLUSION: Ensemble regression trees are a powerful tool to model and understand the multidimensional influences on IRCs. Automatic clustering of lithological units complements this method by facilitating the interpretation of radon properties of rock types. This study provides an important element for radon risk communication. Future approaches should consider taking into account further variables like soil gas radon measurements as well as more detailed geological information.

Psychoses a l'adolescence, les neurosciences ameliorent-elles la prediction? [Adolescent psychosis, can neuroscience improve prediction?]

Developments in the field of neuroscience have created a high level of interest in the subject of adolescent psychosis, particularly in relation to prediction and prevention. As the medical practice of adolescent psychosis and its treatment is characterised by a heterogeneity which is both symptomatic and evolutive, the somewhat poor prognosis of chronic development justifies the research performed: apparent indicators of schizophrenic disorders on the one hand and specific endophenotypes on the other are becoming increasingly important. The significant progresses made on the human genome show that the genetic predetermination in current psychiatric pathologies is complex and subject to moderating effects and there is therefore significant potential for nature-nurture interactions (between the environment and the genes). The road to be followed in researching the phenotypic expression of a psychosis gene is long and winding and is susceptible to many external influences at various levels with different effects. Neurobiological, neurophysiological, neuropsychological and neuroanatomical studies help to identify endophenotypes, which allow researchers to create identifying "markers" along this winding road. The endophenotypes could make it possible to redefine the nosological categories and enhance understanding of the physiopathology of schizophrenia. In a predictive approach, large-scale retrospective and prospective studies make it possible to identify risk factors, which are compatible with the neurodevelopmental hypothesis of schizophrenia. However, the predictive value of such markers or risk indicators is not yet sufficiently developed to offer a reliable early-detection method or possible schizophrenia prevention measures. Nonetheless, new developments show promise against the background of a possible future nosographic revolution, based on a paradigm shift. It is perhaps on the basis of homogeneous endophenotypes in particular that we will be able to understand what protects against, or indeed can trigger, psychosis irrespective of the clinical expression or attempts to isolate the common genetic and biological bases according to homogeneous clinical characteristics, which have to date, proved unsuccessful

Prediction and discrimination of osteoporotic hip fracture in postmenopausal women.

Osteoporotic hip fractures increase dramatically with age and are responsible for considerable morbidity and mortality. Several treatments to prevent the occurrence of hip fracture have been validated in large randomized trials and the current challenge is to improve the identification of individuals at high risk of fracture who would benefit from therapeutic or preventive intervention. We have performed an exhaustive literature review on hip fracture predictors, focusing primarily on clinical risk factors, dual X-ray absorptiometry (DXA), quantitative ultrasound, and bone markers. This review is based on original articles and meta-analyses. We have selected studies that aim both to predict the risk of hip fracture and to discriminate individuals with or without fracture. We have included only postmenopausal women in our review. For studies involving both men and women, only results concerning women have been considered. Regarding clinical factors, only prospective studies have been taken into account. Predictive factors have been used as stand-alone tools to predict hip fracture or sequentially through successive selection processes or by combination into risk scores. There is still much debate as to whether or not the combination of these various parameters, as risk scores or as sequential or concurrent combinations, could help to better predict hip fracture. There are conflicting results on whether or not such combinations provide improvement over each method alone. Sequential combination of bone mineral density and ultrasound parameters might be cost-effective compared with DXA alone, because of fewer bone mineral density measurements. However, use of multiple techniques may increase costs. One problem that precludes comparison of most published studies is that they use either relative risk, or absolute risk, or sensitivity and specificity. The absolute risk of individuals given their risk factors and bone assessment results would be a more appropriate model for decision-making than relative risk. Currently, a group appointed by the World Health Organization and lead by Professor John Kanis is working on such a model. It will therefore be possible to further assess the best choice of threshold to optimize the number of women needed to screen for each country and each treatment.

Improving generalized regression analysis for the spatial prediction of forest communities

Aim This study used data from temperate forest communities to assess: (1) five different stepwise selection methods with generalized additive models, (2) the effect of weighting absences to ensure a prevalence of 0.5, (3) the effect of limiting absences beyond the environmental envelope defined by presences, (4) four different methods for incorporating spatial autocorrelation, and (5) the effect of integrating an interaction factor defined by a regression tree on the residuals of an initial environmental model. Location State of Vaud, western Switzerland. Methods Generalized additive models (GAMs) were fitted using the grasp package (generalized regression analysis and spatial predictions, http://www.cscf.ch/grasp). Results Model selection based on cross-validation appeared to be the best compromise between model stability and performance (parsimony) among the five methods tested. Weighting absences returned models that perform better than models fitted with the original sample prevalence. This appeared to be mainly due to the impact of very low prevalence values on evaluation statistics. Removing zeroes beyond the range of presences on main environmental gradients changed the set of selected predictors, and potentially their response curve shape. Moreover, removing zeroes slightly improved model performance and stability when compared with the baseline model on the same data set. Incorporating a spatial trend predictor improved model performance and stability significantly. Even better models were obtained when including local spatial autocorrelation. A novel approach to include interactions proved to be an efficient way to account for interactions between all predictors at once. Main conclusions Models and spatial predictions of 18 forest communities were significantly improved by using either: (1) cross-validation as a model selection method, (2) weighted absences, (3) limited absences, (4) predictors accounting for spatial autocorrelation, or (5) a factor variable accounting for interactions between all predictors. The final choice of model strategy should depend on the nature of the available data and the specific study aims. Statistical evaluation is useful in searching for the best modelling practice. However, one should not neglect to consider the shapes and interpretability of response curves, as well as the resulting spatial predictions in the final assessment.

Prediction of difficult intubation with advanced face recognition techniques: a preliminary study

Introduction: Difficult tracheal intubation remains a constant and significant source of morbidity and mortality in anaesthetic practice. Insufficient airway assessment in the preoperative period continues to be a major cause of unanticipated difficult intubation. Although many risk factors have already been identified, preoperative airway evaluation is not always regarded as a standard procedure and the respective weight of each risk factor remains unclear. Moreover the predictive scores available are not sensitive, moderately specific and often operator-dependant. In order to improve the preoperative detection of patients at risk for difficult intubation, we developed a system for automated and objective evaluation of morphologic criteria of the face and neck using video recordings and advanced techniques borrowed from face recognition. Method and results: Frontal video sequences were recorded in 5 healthy volunteers. During the video recording, subjects were requested to perform maximal flexion-extension of the neck and to open wide the mouth with tongue pulled out. A robust and real-time face tracking system was then applied, allowing to automatically identify and map a grid of 55 control points on the face, which were tracked during head motion. These points located important features of the face, such as the eyebrows, the nose, the contours of the eyes and mouth, and the external contours, including the chin. Moreover, based on this face tracking, the orientation of the head could also be estimated at each frame of the video sequence. Thus, we could infer for each frame the pitch angle of the head pose (related to the vertical rotation of the head) and obtain the degree of head extension. Morphological criteria used in the most frequent cited predictive scores were also extracted, such as mouth opening, degree of visibility of the uvula or thyreo-mental distance. Discussion and conclusion: Preliminary results suggest the high feasibility of the technique. The next step will be the application of the same automated and objective evaluation to patients who will undergo tracheal intubation. The difficulties related to intubation will be then correlated to the biometric characteristics of the patients. The objective in mind is to analyze the biometrics data with artificial intelligence algorithms to build a highly sensitive and specific predictive test.

Prediction markets supporting technology assessment

In this thesis, we study the use of prediction markets for technology assessment. We particularly focus on their ability to assess complex issues, the design constraints required for such applications and their efficacy compared to traditional techniques. To achieve this, we followed a design science research paradigm, iteratively developing, instantiating, evaluating and refining the design of our artifacts. This allowed us to make multiple contributions, both practical and theoretical. We first showed that prediction markets are adequate for properly assessing complex issues. We also developed a typology of design factors and design propositions for using these markets in a technology assessment context. Then, we showed that they are able to solve some issues related to the R&D portfolio management process and we proposed a roadmap for their implementation. Finally, by comparing the instantiation and the results of a multi-criteria decision method and a prediction market, we showed that the latter are more efficient, while offering similar results. We also proposed a framework for comparing forecasting methods, to identify the constraints based on contingency factors. In conclusion, our research opens a new field of application of prediction markets and should help hasten their adoption by enterprises. Résumé français: Dans cette thèse, nous étudions l'utilisation de marchés de prédictions pour l'évaluation de nouvelles technologies. Nous nous intéressons plus particulièrement aux capacités des marchés de prédictions à évaluer des problématiques complexes, aux contraintes de conception pour une telle utilisation et à leur efficacité par rapport à des techniques traditionnelles. Pour ce faire, nous avons suivi une approche Design Science, développant itérativement plusieurs prototypes, les instanciant, puis les évaluant avant d'en raffiner la conception. Ceci nous a permis de faire de multiples contributions tant pratiques que théoriques. Nous avons tout d'abord montré que les marchés de prédictions étaient adaptés pour correctement apprécier des problématiques complexes. Nous avons également développé une typologie de facteurs de conception ainsi que des propositions de conception pour l'utilisation de ces marchés dans des contextes d'évaluation technologique. Ensuite, nous avons montré que ces marchés pouvaient résoudre une partie des problèmes liés à la gestion des portes-feuille de projets de recherche et développement et proposons une feuille de route pour leur mise en oeuvre. Finalement, en comparant la mise en oeuvre et les résultats d'une méthode de décision multi-critère et d'un marché de prédiction, nous avons montré que ces derniers étaient plus efficaces, tout en offrant des résultats semblables. Nous proposons également un cadre de comparaison des méthodes d'évaluation technologiques, permettant de cerner au mieux les besoins en fonction de facteurs de contingence. En conclusion, notre recherche ouvre un nouveau champ d'application des marchés de prédiction et devrait permettre d'accélérer leur adoption par les entreprises.

A new accelerometric method to assess the daily walking practice.

OBJECTIVE: To describe a method to obtain a profile of the duration and intensity (speed) of walking periods over 24 hours in women under free-living conditions. DESIGN: A new method based on accelerometry was designed for analyzing walking activity. In order to take into account inter-individual variability of acceleration, an individual calibration process was used. Different experiments were performed to highlight the variability of acceleration vs walking speed relationship, to analyze the speed prediction accuracy of the method, and to test the assessment of walking distance and duration over 24-h. SUBJECTS: Twenty-eight women were studied (mean+/-s.d.) age: 39.3+/-8.9 y; body mass: 79.7+/-11.1 kg; body height: 162.9+/-5.4 cm; and body mass index (BMI) 30.0+/-3.8 kg/m(2). RESULTS: Accelerometer output was significantly correlated with speed during treadmill walking (r=0.95, P<0.01), and short unconstrained walks (r=0.86, P<0.01), although with a large inter-individual variation of the regression parameters. By using individual calibration, it was possible to predict walking speed on a standard urban circuit (predicted vs measured r=0.93, P<0.01, s.e.e.=0.51 km/h). In the free-living experiment, women spent on average 79.9+/-36.0 (range: 31.7-168.2) min/day in displacement activities, from which discontinuous short walking activities represented about 2/3 and continuous ones 1/3. Total walking distance averaged 2.1+/-1.2 (range: 0.4-4.7) km/day. It was performed at an average speed of 5.0+/-0.5 (range: 4.1-6.0) km/h. CONCLUSION: An accelerometer measuring the anteroposterior acceleration of the body can estimate walking speed together with the pattern, intensity and duration of daily walking activity.

Outcome Prediction after Cardiac Arrest Treated with Hypothermia

Rationale: Clinical and electrophysiological prognostic markers of brain anoxia have been mostly evaluated in comatose survivors of out hospital cardiac arrest (OHCA) after standard resuscitation, but their predictive value in patients treated with mild induced hypothermia (IH) is unknown. The objective of this study was to identify a predictive score of independent clinical and electrophysiological variables in comatose OHCA survivors treated with IH, aiming at a maximal positive predictive value (PPV) and a high negative predictive value (NPV) for mortality. Methods: We prospectively studied consecutive adult comatose OHCA survivors from April 2006 to May 2009, treated with mild IH to 33-34_C for 24h at the intensive care unit of the Lausanne University Hospital, Switzerland. IH was applied using an external cooling method. As soon as subjects passively rewarmed (body temperature >35_C) they underwent EEG and SSEP recordings (off sedation), and were examined by experienced neurologists at least twice. Patients with status epilepticus were treated with AED for at least 24h. A multivariable logistic regression was performed to identify independent predictors of mortality at hospital discharge. These were used to formulate a predictive score. Results: 100 patients were studied; 61 died. Age, gender and OHCA etiology (cardiac vs. non-cardiac) did not differ among survivors and nonsurvivors. Cardiac arrest type (non-ventricular fibrillation vs. ventricular fibrillation), time to return of spontaneous circulation (ROSC) >25min, failure to recover all brainstem reflexes, extensor or no motor response to pain, myoclonus, presence of epileptiform discharges on EEG, EEG background unreactive to pain, and bilaterally absent N20 on SSEP, were all significantly associated with mortality. Absent N20 was the only variable showing no false positive results. Multivariable logistic regression identified four independent predictors (Table). These were used to construct the score, and its predictive values were calculated after a cut-off of 0-1 vs. 2-4 predictors. We found a PPV of 1.00 (95% CI: 0.93-1.00), a NPV of 0.81 (95% CI: 0.67-0.91) and an accuracy of 0.93 for mortality. Among 9 patients who were predicted to survive by the score but eventually died, only 1 had absent N20. Conclusions: Pending validation in a larger cohort, this simple score represents a promising tool to identify patients who will survive, and most subjects who will not, after OHCA and IH. Furthermore, while SSEP are 100% predictive of poor outcome but not available in most hospitals, this study identifies EEG background reactivity as an important predictor after OHCA. The score appears robust even without SSEP, suggesting that SSEP and other investigations (e.g., mismatch negativity, serum NSE) might be principally needed to enhance prognostication in the small subgroup of patients failing to improve despite a favorable score.

Ruling out coronary heart disease in primary care: external validation of a clinical prediction rule.

BACKGROUND: The Marburg Heart Score (MHS) aims to assist GPs in safely ruling out coronary heart disease (CHD) in patients presenting with chest pain, and to guide management decisions. AIM: To investigate the diagnostic accuracy of the MHS in an independent sample and to evaluate the generalisability to new patients. DESIGN AND SETTING: Cross-sectional diagnostic study with delayed-type reference standard in general practice in Hesse, Germany. METHOD: Fifty-six German GPs recruited 844 males and females aged ≥ 35 years, presenting between July 2009 and February 2010 with chest pain. Baseline data included the items of the MHS. Data on the subsequent course of chest pain, investigations, hospitalisations, and medication were collected over 6 months and were reviewed by an independent expert panel. CHD was the reference condition. Measures of diagnostic accuracy included the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, likelihood ratios, and predictive values. RESULTS: The AUC was 0.84 (95% confidence interval [CI] = 0.80 to 0.88). For a cut-off value of 3, the MHS showed a sensitivity of 89.1% (95% CI = 81.1% to 94.0%), a specificity of 63.5% (95% CI = 60.0% to 66.9%), a positive predictive value of 23.3% (95% CI = 19.2% to 28.0%), and a negative predictive value of 97.9% (95% CI = 96.2% to 98.9%). CONCLUSION: Considering the diagnostic accuracy of the MHS, its generalisability, and ease of application, its use in clinical practice is recommended.

Individual prediction of cognitive decline in mild cognitive impairment using support vector machine-based analysis of diffusion tensor imaging data.

Although cross-sectional diffusion tensor imaging (DTI) studies revealed significant white matter changes in mild cognitive impairment (MCI), the utility of this technique in predicting further cognitive decline is debated. Thirty-five healthy controls (HC) and 67 MCI subjects with DTI baseline data were neuropsychologically assessed at one year. Among them, there were 40 stable (sMCI; 9 single domain amnestic, 7 single domain frontal, 24 multiple domain) and 27 were progressive (pMCI; 7 single domain amnestic, 4 single domain frontal, 16 multiple domain). Fractional anisotropy (FA) and longitudinal, radial, and mean diffusivity were measured using Tract-Based Spatial Statistics. Statistics included group comparisons and individual classification of MCI cases using support vector machines (SVM). FA was significantly higher in HC compared to MCI in a distributed network including the ventral part of the corpus callosum, right temporal and frontal pathways. There were no significant group-level differences between sMCI versus pMCI or between MCI subtypes after correction for multiple comparisons. However, SVM analysis allowed for an individual classification with accuracies up to 91.4% (HC versus MCI) and 98.4% (sMCI versus pMCI). When considering the MCI subgroups separately, the minimum SVM classification accuracy for stable versus progressive cognitive decline was 97.5% in the multiple domain MCI group. SVM analysis of DTI data provided highly accurate individual classification of stable versus progressive MCI regardless of MCI subtype, indicating that this method may become an easily applicable tool for early individual detection of MCI subjects evolving to dementia.

Prediction of Recanalization Trumps Prediction of Tissue Fate: The Penumbra: A Dual-edged Sword.

BACKGROUND AND PURPOSE: To determine whether infarct core or penumbra is the more significant predictor of outcome in acute ischemic stroke, and whether the results are affected by the statistical method used. METHODS: Clinical and imaging data were collected in 165 patients with acute ischemic stroke. We reviewed the noncontrast head computed tomography (CT) to determine the Alberta Score Program Early CT score and assess for hyperdense middle cerebral artery. We reviewed CT-angiogram for site of occlusion and collateral flow score. From perfusion-CT, we calculated the volumes of infarct core and ischemic penumbra. Recanalization status was assessed on early follow-up imaging. Clinical data included age, several time points, National Institutes of Health Stroke Scale at admission, treatment type, and modified Rankin score at 90 days. Two multivariate regression analyses were conducted to determine which variables predicted outcome best. In the first analysis, we did not include recanalization status among the potential predicting variables. In the second, we included recanalization status and its interaction between perfusion-CT variables. RESULTS: Among the 165 study patients, 76 had a good outcome (modified Rankin score ≤2) and 89 had a poor outcome (modified Rankin score >2). In our first analysis, the most important predictors were age (P<0.001) and National Institutes of Health Stroke Scale at admission (P=0.001). The imaging variables were not important predictors of outcome (P>0.05). In the second analysis, when the recanalization status and its interaction with perfusion-CT variables were included, recanalization status and perfusion-CT penumbra volume became the significant predictors (P<0.001). CONCLUSIONS: Imaging prediction of tissue fate, more specifically imaging of the ischemic penumbra, matters only if recanalization can also be predicted.

Improvement of therapeutic drug monitoring of imatinib by Bayesian prediction of trough levels. Personalized drug dosage

Aims: Plasma concentrations of imatinib differ largely between patients despite same dosage, owing to large inter-individual variability in pharmacokinetic (PK) parameters. As the drug concentration at the end of the dosage interval (Cmin) correlates with treatment response and tolerability, monitoring of Cmin is suggested for therapeutic drug monitoring (TDM) of imatinib. Due to logistic difficulties, random sampling during the dosage interval is however often performed in clinical practice, thus rendering the respective results not informative regarding Cmin values.Objectives: (I) To extrapolate randomly measured imatinib concentrations to more informative Cmin using classical Bayesian forecasting. (II) To extend the classical Bayesian method to account for correlation between PK parameters. (III) To evaluate the predictive performance of both methods.Methods: 31 paired blood samples (random and trough levels) were obtained from 19 cancer patients under imatinib. Two Bayesian maximum a posteriori (MAP) methods were implemented: (A) a classical method ignoring correlation between PK parameters, and (B) an extended one accounting for correlation. Both methods were applied to estimate individual PK parameters, conditional on random observations and covariate-adjusted priors from a population PK model. The PK parameter estimates were used to calculate trough levels. Relative prediction errors (PE) were analyzed to evaluate accuracy (one-sample t-test) and to compare precision between the methods (F-test to compare variances).Results: Both Bayesian MAP methods allowed non-biased predictions of individual Cmin compared to observations: (A) - 7% mean PE (CI95% - 18 to 4 %, p = 0.15) and (B) - 4% mean PE (CI95% - 18 to 10 %, p = 0.69). Relative standard deviations of actual observations from predictions were 22% (A) and 30% (B), i.e. comparable to the intraindividual variability reported. Precision was not improved by taking into account correlation between PK parameters (p = 0.22).Conclusion: Clinical interpretation of randomly measured imatinib concentrations can be assisted by Bayesian extrapolation to maximum likelihood Cmin. Classical Bayesian estimation can be applied for TDM without the need to include correlation between PK parameters. Both methods could be adapted in the future to evaluate other individual pharmacokinetic measures correlated to clinical outcomes, such as area under the curve(AUC).

Prediction of cross-recognition of peptide-HLA A2 by Melan-A-specific cytotoxic T lymphocytes using three-dimensional quantitative structure-activity relationships.

The cross-recognition of peptides by cytotoxic T lymphocytes is a key element in immunology and in particular in peptide based immunotherapy. Here we develop three-dimensional (3D) quantitative structure-activity relationships (QSARs) to predict cross-recognition by Melan-A-specific cytotoxic T lymphocytes of peptides bound to HLA A*0201 (hereafter referred to as HLA A2). First, we predict the structure of a set of self- and pathogen-derived peptides bound to HLA A2 using a previously developed ab initio structure prediction approach [Fagerberg et al., J. Mol. Biol., 521-46 (2006)]. Second, shape and electrostatic energy calculations are performed on a 3D grid to produce similarity matrices which are combined with a genetic neural network method [So et al., J. Med. Chem., 4347-59 (1997)] to generate 3D-QSAR models. The models are extensively validated using several different approaches. During the model generation, the leave-one-out cross-validated correlation coefficient (q (2)) is used as the fitness criterion and all obtained models are evaluated based on their q (2) values. Moreover, the best model obtained for a partitioned data set is evaluated by its correlation coefficient (r = 0.92 for the external test set). The physical relevance of all models is tested using a functional dependence analysis and the robustness of the models obtained for the entire data set is confirmed using y-randomization. Finally, the validated models are tested for their utility in the setting of rational peptide design: their ability to discriminate between peptides that only contain side chain substitutions in a single secondary anchor position is evaluated. In addition, the predicted cross-recognition of the mono-substituted peptides is confirmed experimentally in chromium-release assays. These results underline the utility of 3D-QSARs in peptide mimetic design and suggest that the properties of the unbound epitope are sufficient to capture most of the information to determine the cross-recognition.