Volkan Uslan

Quantitative prediction of peptide binding affinity by using hybrid fuzzy support vector regression

Graphical abstractDisplay Omitted HighlightsHigh-dimensional biological data sets are modelled with a regression based fuzzy system.An SVR based fuzzy model is proposed to find degree of peptide binding to MHC molecules.SVR is enhanced by adding the fuzziness concept.TSK fuzzy system is benefited from SVR-based training.The proposed models suggest that the predictive ability and performance are increased. Support vector machines have a wide use for the prediction problems in life sciences. It has been shown to offer more generalisation ability in input-output mapping. However, the performance of predictive models is often negatively influenced due to the complex, high-dimensional, and non-linear nature of the post-genome data. Soft computing methods can be used to model such non-linear systems. Fuzzy systems are one of the widely used methods of soft computing that model uncertainties. It is formed of interpretable rules aiding one to gain insight into applied model. This study is therefore concerned to provide more interpretable and efficient biological model with the development of a hybrid method that integrates the fuzzy system and support vector regression. In order to demonstrate the robustness of this new hybrid method, it is applied to the prediction of peptide binding affinity being one of the most challenging problems in the post-genomic era due to diversity in peptide families and complexity and high-dimensionality in the characteristic features of the peptides. Having used four different case studies, this hybrid predictive model has yielded the highest predictive power in all the four cases and achieved an improvement of as much as 34% compared to the results presented in the literature. Availability: Matlab scripts are available at https://github.com/sekerbigdatalab/tsksvr.

Support vector-based Takagi-Sugeno fuzzy system for the prediction of binding affinity of peptides

High dimensional, complex and non-linear nature of the post-genome data often adversely affects the performance of predictive models. There are two methods that have been widely used to model such non-linear systems, namely Fuzzy System (FS) and Support Vector Machine (SVM). FS is good at modelling uncertainty and yielding a set of interpretable IF-THEN rules, but suffers from the curse of dimensionality whereas SVM is a method that has been shown to effectively deal with large number of dimensions leading to better generalization ability. In this paper, a hybrid system is therefore proposed to improve FS with the aid of SVM-based regression method and successfully applied to the prediction of binding affinity of peptides, which is regarded as one of the most complex modelling problems in the post-genome era due to the diversity of peptides discovered. The proposed hybrid method yields comparatively better results than what has been presented in the recently published papers, therefore can also be considered for other bioinformatics applications.

Support vector-based fuzzy system for the prediction of mouse class I MHC peptide binding affinity

The performance of predictive models is crucial in order to accurately determine peptide binding affinity for major histocompatibility complex (MHC) alleles. Data sets extracted to model the relationship between the peptides and their binding affinities are often high-dimensional, complex and non-linear, which require highly sophisticated computational predictive models. Support Vector Machine (SVM)-based predictive methods have been used for such problems and have been shown to deal with such high dimensional data, however failed to take into account of uncertainty that naturally exists in this type of data. In order to address to the uncertainty issue, Fuzzy System (FS) has generally been utilised in various applications. Therefore, a hybrid method that combines FS and SVM is proposed in this study for the prediction of binding affinity of peptides in mouse class I MHC alleles. The hybrid system is successfully applied to two benchmark data sets of class I MHC peptides, each of which contains over 5000 peptide features. The assessments yield as much as 17% improvement over the previous studies that also include SVM-based experiments. The results also suggest positive impact of the concept of fuzziness on SVM-based predictive methods when combined and that the hybrid model can be generalised for similar non-linear system modelling problems.

Optimized parametric skin modelling for diagnosis of skin abnormalities by combining light back-scatter and laser speckle imaging

Optical and parametric skin imaging methods which can efficiently identify invisible sub‐skin features or subtle changes in skin layers are very important for accurate optical skin modelling. In this study, a hybrid method is introduced that helps develop a parametric optical skin model by utilizing interdisciplinary techniques including light back‐scatter analysis, laser speckle imaging, image‐texture analysis and Bayesian inference methods. The model aims to detect subtle skin changes and hence very early signs of skin abnormalities/diseases.

Comparison of unsupervised feature selection methods for high-dimensional regression problems in prediction of peptide binding affinity

Identification of robust set of predictive features is one of the most important steps in the construction of clustering, classification and regression models from many thousands of features. Although there have been various attempts to select predictive feature sets from high-dimensional data sets in classification and clustering, there is a limited attempt to study it in regression problems. As semi-supervised and supervised feature selection methods tend to identify noisy features in addition to discriminative variables, unsupervised feature selection methods (USFSMs) are generally regarded as more unbiased approach. Therefore, in this study, along with the entire feature set, four different USFSMs are considered for the quantitative prediction of peptide binding affinities being one of the most challenging post-genome regression problems of very high-dimension comparted to extremely small size of samples. As USFSMs are independent of any predictive method, support vector regression was then utilised to assess the quality of prediction. Given three different peptide binding affinity data sets, the results suggest that the regression performance of USFMs depends generally on the datasets. There is no particular method that yields the best performance compared to their performances in the classification problems. However, a closer investigation of the results appears to suggest that the spectral regression-based approach yields slightly better performance. To the best of our knowledge, this is the first study that presents comprehensive comparison of USFSMs in such high-dimensional regression problems, particularly in biological domain with an application in the prediction of peptide binding affinity, and provides a number of practical suggestions for future practitioners.

A supervised feature selection framework in relation to prediction of antibody feature-function activity relationships in RV144 vaccines

Identification of functional characteristics of the virus-antibody interplay in individuals can provide insight to the development of effective vaccines against HIV virus. In order to reveal the functional interactions between human immune system and HIV virus, computational methods such as clustering, classification, feature selection and regression methods can be utilised to construct predictive models. The purpose of this study is to predict the associations between antibody features and effector function activities on RV144 vaccine recipients. The RV144 vaccine dataset contains 100 data samples in which 20 of them are the placebo samples and 80 of them are the vaccine injected samples. Each data sample has twenty antibody features that consist of features related to IgG subclass and antigen specificity. In this study, we proposed a novel supervised feature selection framework to identify the discriminating antibody features from RV144 vaccine dataset. Then, the Support Vector Regression is utilised to quantitatively predict the association between antibody features (IgGs) and effector function activities. Three different cell-mediated assays are utilised in this study to characterise effector function activities: antibody dependent cellular phagocytosis (ADCP), antibody dependent cellular cytotoxicity (ADCC), and natural killer cell cytokine release. Promising experimental results on these three cell-based assays have validated the effectiveness of our proposed framework. The prediction performance of proposed feature selection framework is compared to the previous studies which utilised the RV144 dataset for the same purpose.

The quantitative prediction of HLA-B*2705 peptide binding affinities using Support Vector Regression to gain insights into its role for the Spondyloarthropathies

Computational methods are increasingly utilised in many immunoinformatics problems such as the prediction of binding affinity of peptides. The peptides could provide valuable insight into the drug design and development such as vaccines. Moreover, they can be used to diagnose diseases. The presence of human class I MHC allele HLA-B*2705 is one of the strong hypothesis that would lead spondyloarthropathies. In this paper, Support Vector Regression is used in order to predict binding affinity of peptides with the aid of experimentally determined peptide-MHC binding affinities of 222 peptides to HLA-B*2705 to get more insight into this problematic disease. The results yield a high correlation coefficient as much as 0.65 and the SVR-based predictive models can be considered as a useful tool in order to predict the binding affinities for newly discovered peptides.

Exploration of unsupervised feature selection methods in relation to the prediction of cytokine release effect correlated to antibody features in RV144 vaccines

Computational methods such as clustering, classification and regression methods can be applied in immunoin-formatics to construct predictive models to reveal relationships between antibody features and their functional outcomes. This paper studies the effect of antibody features and the functional outcome obtained on RV144 vaccine recipients. The RV144 vaccine data set contains 100 data samples in which 20 of them are the placebo samples and 80 of them are the vaccine injected samples. Each data sample has twenty antibody features that consist of features related to IgG subclass and antigen specificity. Unlike semi-supervised and supervised feature selection methods, unsupervised feature selection methods provide unbiased approach as they are not dependent to response variable. In this paper, four different unsupervised feature selection methods are used in order to reveal the discriminating antibody features. Then, the support vector based methods are used in order to predict natural killer (NK) cell cytokine release effect. The results yield a high correlation coefficient as much as 0.59 and 0.72 for the support vector based regression (SVR) and classification (SVM) predictive models, respectively.

A support vector-based interval Type-2 fuzzy system.

In this paper, a new fuzzy regression model that is supported by support vector regression is presented. Type-2 fuzzy systems are able to tackle applications that have significant uncertainty. However general type-2 fuzzy systems are more complex than type-1 fuzzy systems. Support vector machines are similar to fuzzy systems in that they can also model systems that are non-linear in nature. In the proposed model the consequent parameters of type-2 fuzzy rules are learnt using support vector regression and an efficient closed-form type reduction strategy is used to simplify the computations. Support vector regression improved the generalisation performance of the fuzzy rule-based system in which the fuzzy rules were a set of interpretable IF-THEN rules. The performance of the proposed model was demonstrated by conducting case studies for the non-linear system approximation and prediction of chaotic time series. The model yielded promising results and the simulation results are compared to the results published in the area.

An improvement of skin aging assessment by non-invasive laser speckle effect: A comparative texture analysis

Skin aging is a complex biological process that is yet to be successfully modelled as it depends on various internal and external factors. This work therefore investigates novel low-cost skin aging assessment technique and equipment by using robust analysis of textural features unified with a laser-speckle imaging method, which is found to be quite capable of detecting multi-layer cellular textural changes exhibited by the biological skin aging process. This study and low-cost product seem to be the first of its kind, which is expected to bring great benefit to both healthcare and cosmetic sectors.