Peptide Quantitative Structure-activity Relationship Research Articles

Comprehensive evaluation and systematic comparison of Gaussian process (GP) modelling applications in peptide quantitative structure-activity relationship

Peptide quantitative structure-activity relationship (pQSAR) is a specific extension of traditional QSARs from small-molecule drugs to bioactive peptides. Since peptides are linear biopolymers that are essentially different to small-molecule compounds in terms of their structural features such as ordering sequence, large size and intrinsic flexibility, the pQSAR methodology (including structural characterization and regression modelling) should be further exploited relative to traditional QSARs. Gaussian process (GP) serves as a pioneering Bayesian-based machine learning (ML) solution for tackling linear/nonlinear-hybrid regression issues in intricate domains. However, the applications of GP regression in QSAR and, particularly, the pQSAR still remain largely unexplored to date. In this work, we launched a comprehensive pQSAR study with GP regression modelling, aiming to the deep evaluation of GP performance based on different characterizations and also the systematic comparison of GP with other routine MLs. Here, we culled two distinct classes of peptide datasets, which separately comprise 12 panels of sophisticated benchmarks and 46 panels of extended samples, totally containing 8804 peptide samples and systematically resulting in 522 regression models. Our study indicated that the GP can generally provide an effective solution for many pQSAR problems with the potential to promote ML regression modelling in this area, which is comparable with or even better than those widely used methods on both the sophisticated benchmarks and extended samples. In addition, GP also has many advantages as compared to traditional MLs, such as hyperparameter self-consistency, overfitting resistance, interpretable output and estimable uncertainty.

Systematic Modeling, Prediction, and Comparison of Domain-Peptide Affinities: Does it Work Effectively With the Peptide QSAR Methodology?

The protein–protein association in cellular signaling networks (CSNs) often acts as weak, transient, and reversible domain–peptide interaction (DPI), in which a flexible peptide segment on the surface of one protein is recognized and bound by a rigid peptide-recognition domain from another. Reliable modeling and accurate prediction of DPI binding affinities would help to ascertain the diverse biological events involved in CSNs and benefit our understanding of various biological implications underlying DPIs. Traditionally, peptide quantitative structure-activity relationship (pQSAR) has been widely used to model and predict the biological activity of oligopeptides, which employs amino acid descriptors (AADs) to characterize peptide structures at sequence level and then statistically correlate the resulting descriptor vector with observed activity data via regression. However, the QSAR has not yet been widely applied to treat the direct binding behavior of large-scale peptide ligands to their protein receptors. In this work, we attempted to clarify whether the pQSAR methodology can work effectively for modeling and predicting DPI affinities in a high-throughput manner? Over twenty thousand short linear motif (SLiM)-containing peptide segments involved in SH3, PDZ and 14-3-3 domain-medicated CSNs were compiled to define a comprehensive sequence-based data set of DPI affinities, which were represented by the Boehringer light units (BLUs) derived from previous arbitrary light intensity assays following SPOT peptide synthesis. Four sophisticated MLMs (MLMs) were then utilized to perform pQSAR modeling on the set described with different AADs to systematically create a variety of linear and nonlinear predictors, and then verified by rigorous statistical test. It is revealed that the genome-wide DPI events can only be modeled qualitatively or semiquantitatively with traditional pQSAR strategy due to the intrinsic disorder of peptide conformation and the potential interplay between different peptide residues. In addition, the arbitrary BLUs used to characterize DPI affinity values were measured via an indirect approach, which may not very reliable and may involve strong noise, thus leading to a considerable bias in the modeling. The R prd 2 = 0.7 can be considered as the upper limit of external generalization ability of the pQSAR methodology working on large-scale DPI affinity data.

Systematic Comparison and Comprehensive Evaluation of 80 Amino Acid Descriptors in Peptide QSAR Modeling

The peptide quantitative structure-activity relationship (QSAR), also known as the quantitative sequence-activity model (QSAM), has attracted much attention in the bio- and chemoinformatics communities and is a well developed computational peptidology strategy to statistically correlate the sequence/structure and activity/property relationships of functional peptides. Amino acid descriptors (AADs) are one of the most widely used methods to characterize peptide structures by decomposing the peptide into its residue building blocks and sequentially parametrizing each building block with a vector of amino acid principal properties. Considering that various AADs have been proposed over the past decades and new AADs are still emerging today, we herein query the following: is it necessary to develop so many AADs and do we need to continuously develop more new AADs? In this study, we exhaustively collect 80 published AADs and comprehensively evaluate their modeling performance (including fitting ability, internal stability, and predictive power) on 8 QSAR-oriented peptide sample sets (QPSs) by employing 2 sophisticated machine learning methods (MLMs), totally building and systematically comparing 1280 (80 AADs × 8 QPSs × 2 MLMs) peptide QSAR models. The following is revealed: (i) None of the AADs can work best on all or most peptide sets; an AAD usually performs well for some peptides but badly for others. (ii) Modeling performance is primarily determined by the peptide samples and then the MLMs used, while AADs have only a moderate influence on the performance. (iii) There is no essential difference between the modeling performances of different AAD types (physiochemical, topological, 3D-structural, etc.). (iv) Two random descriptors, which are separately generated randomly in standard normal distribution N(0, 1) and uniform distribution U(-1, +1), do not perform significantly worse than these carefully developed AADs. (v) A secondary descriptor, which carries major information involved in the 80 (primary) AADs, does not perform significantly better than these AADs. Overall, we conclude that since there are various AADs available to date and they already cover numerous amino acid properties, further development of new AADs is not an essential choice to improve peptide QSAR modeling; the traditional AAD methodology is believed to have almost reached the theoretical limit nowadays. In addition, the AADs are more likely to be a vector symbol but not informative data; they are utilized to mark and distinguish the 20 amino acids but do not really bring much original property information to these amino acids.

In Silico Rational Design and Virtual Screening of Bioactive Peptides Based on QSAR Modeling.

Predicting the bioactivity of peptides is an important challenge in drug development and peptide research. In this study, numerical descriptive vectors (NDVs) for peptide sequences were calculated based on the physicochemical properties of amino acids (AAs) and principal component analysis (PCA). The resulted NDV had the same length as the peptide sequence, so that each entry of NDV corresponded to one AA in the sequence. They were then applied to quantitative structure–activity relationship (QSAR) analysis of angiotensin-converting enzyme (ACE) inhibitor dipeptides, bitter-tasting dipeptides, and nonameric binding peptides of the human leukocyte antigens (HLA-A*0201). Multiple linear regression was used to construct the QSAR models. For each peptide set, a proper subset of physicochemical properties was chosen by the ant colony optimization algorithm. The leave-one-out cross-validation (qloo2) values were 0.855, 0.936, and 0.642 and the root-mean-square errors (RMSEs) were 0.450, 0.149, and 0.461. Our results revealed that the new numerical descriptive vector can afford extensive characterization of peptide sequence so that it can be easily employed in peptide QSAR studies. Moreover, the proposed numerical descriptive vectors were able to determine hot spot residues in the peptides under study.

A New Descriptor of Amino Acids-SVGER and its Applications in Peptide QSAR.

In the study of peptide quantitative structure activity relationship (QSAR), a new descriptor of amino acids (SVGER) was calculated. It was applied in two peptides which are angiotensin converting enzyme inhibitors and bitter tasting threshold of di-peptide. QSAR models were built by stepwise multiple regression-multiple linear regression (SMR-MLR) and stepwise multiple regression-partial least square regression (SMR-PLS). In the SMR-MLR models for angiotensin converting enzyme inhibitors, the squared cross-validation correlation coefficient (QLOO2 ) was 0.907, squared correlation coefficient between predicted and observed activities (Rcum2 ) was 0.977 and external multiple correlation coefficient (Qext2 ) was 0.867. The corresponding data for the bitter tasting threshold of di-peptide were 0.802, 0.966, 0.719. While in the SMR-PLS model, QLOO2 , Rcum2 and Qext2 were 0.804, 0.915, 0.858 for angiotensin converting enzyme inhibitors and 0.782, 0.881, 0.747 for bitter tasting threshold of di-peptide. Our results showed that descriptor SVGER can afford good account of relationships between activity and structure of peptide drugs.

A Benchmark Dataset Comprising Partition and Distribution Coefficients of Linear Peptides

Peptides have a dominant role in biology; yet the study of their physical properties is at best sporadic. Peptide quantitative structure-activity relationship (QSAR) lags far behind the QSAR analysis of drug-like organic small molecules. Traditionally, QSAR has focussed on experimentally determined partition coefficients as the main descriptor of hydrophobicity. A partition coefficient () is the ratio between the concentrations of an uncharged chemical substance in two immiscible phases: most typically water and an organic solvent, usually 1-octanol. A distribution coefficient () is the equivalent ratio for charged molecules. We report here a compilation of partition and distribution coefficients for linear peptides compiled from literature reports, suitable for the development and benchmarking of peptide and prediction algorithms.

Feature Selection for High-Dimensional Data Based on Ridge Regression and SVM and Its Application in Peptide QSAR Modeling

Absolute weight values estimated from test data by ridge regression (RR) can reflect the significance of corresponding features.Based on RR and support vector machine (SVM),a new feature selection algorithm for high-dimensional data is proposed.Examples from bitter tasting thresholds (BTT) and cytotoxic T lymphocyte (CTL) epitopes are presented.All 531 physicochemical property parameters were employed to express each residue of one peptide,thus 1062 and 4779 descriptors were obtained for BTT and CTL,respectively.Each sample was divided into training and test sets,and weight estimates of all training set descriptors were generated by RR.According to the descending order of the weights,corresponding features were gradually selected until the mean square error (MSE) of leave-one-out cross validation (LOOCV) increased significantly.Based on smaller training datasets obtained from the previous step,the reserved features were available from multiple elimination rounds.7 and 18 descriptors were selected by the new method for BTT and CTL,respectively.A quantitative structure-activity relationship (QSAR) model based on support vector regression (SVR) was established on extracted data with the reserved descriptors,and was then used for test data prediction.The fitting,LOOCV,and external prediction accuracies were significantly improved with respect to reported literature values.Because of the calculation speed,clear physicochemical meaning,and ease of interpretation,the new method is widely applicable to regression forecasting of high-dimensional data such as QSAR modeling of peptide or proteins.

A descriptor of amino acids SVWG and its applications in peptide QSAR

A descriptor, SVWG (principal component scores vector of WHIM (weighted holistic invariant molecular index) descriptors and GETWAY (GEometry, Topology, and Atom‐Weights AssemblY) descriptors), was derived from a principal component analysis of a matrix of two structural variables of coded amino acid. SVWG scales were then applied in three panels of peptide quantitative structure activity relationship (QSAR) that were molded by partial least squares regression. The obtained models with the correlation coefficient () and cross‐validation correlation coefficient () were 0.893 and 0.830 for angiotensin‐converting enzyme inhibitors, 0.990 and 0.968 for antimicrobial peptides, and 0.955 and 0.908 for oxytocin, respectively. Satisfactory results showed that information related to biological activity can be systemically expressed by SVWG scales, which may be a useful structural expression methodology for study on peptide QSAR. Copyright © 2012 John Wiley & Sons, Ltd.

SVEEVA Descriptor Application to Peptide QSAR

A new descriptor, SVEEVA (principal component scores vector of electronic eigenvalue descriptors), was derived from principal component analysis (PCA) of a matrix of 220 electronic eigenvalue descriptors of coded amino acids. SVEEVA scales were then applied in three panels of peptide quantitative structure-activity relationship (QSAR) that were modeled by partial least squares regression (PLS). The obtained models with the correlation coefficient (R²(cum), cross-validation correlation coefficient (Q²(LOO) were 0.894 and 0.839 for 58 angiotensin-converting enzyme inhibitors, 0.995 and 0.949 for 12 antimicrobial polypeptides, and 0.995 and 0.976 for 20 thromboplastin inhibitors. Satisfactory results showed that information related to biological activity can be systemically expressed by SVEEVA scales, which may be a useful structural expression methodology for study on peptide QSAR.

Study of Peptides QSAR Based on Multidimensional Attributes (E) Using Multiple Linear Regression

A new amino acids descriptor E, which (E1~E5) has been introduced in bioactive peptides Quantitative Structure-Activity Relationship (QSAR) Study. It has been proved that correlate good with hydrophobicity, size, preference for amino acids to occur in -helices, composition and the net charge, respectively. They were then applied to construct characterization and QSAR analysis on 48 bitter tasting dipeptides and 30 bradykinin potentiating (BP) pentapeptides using multiple linear regression (MLR). The leave-one-out cross validation values (Q2(CV)) were 0.888 and 0.797, the multiple correlation coefficients (R2) were 0.940 and 0.891, respectively for bitter tasting dipeptides and BP pentapeptides. The results showed that, in comparison with the conventional descriptors, the descriptor (E) is a useful structure characterization method for peptide QSAR analysis. The importance of each property at each position in peptides is estimated by the regression coefficient value of the MLR model. The establishment of such methods will be a very meaningful work to peptide bioactive investigation in peptide drug design.

A descriptor of amino acids: SVRG and its application to peptide quantitative structure–activity relationship

In this work, a descriptor, SVRG (principal component scores vector of radial distribution function descriptors and geometrical descriptors), was derived from principal component analysis (PCA) of a matrix of two structural variables of coded amino acids, including radial distribution function index (RDF) and geometrical index. SVRG scales were then applied in three panels of peptide quantitative structure–activity relationships (QSARs) which were modelled by partial least squares regression (PLS). The obtained models with the correlation coefficient (), cross-validation correlation coefficient () were 0.910 and 0.863 for 48 bitter-tasting dipeptides; 0.968 and 0.931 for 21 oxytocin analogues; and 0.992 and 0.954 for 20 thromboplastin inhibitors. Satisfactory results showed that SVRG contained much chemical information relating to bioactivities. The approach may be a useful structural expression methodology for studies on peptide QSAR.

Descriptors for antimicrobial peptides

Introduction: A frightening increase in the number of isolated multidrug resistant bacterial strains linked to the decline in novel antimicrobial drugs entering the market is a great cause for concern. Cationic antimicrobial peptides (AMPs) have lately been introduced as a potential new class of antimicrobial drugs, and computational methods utilizing molecular descriptors can significantly accelerate the development of new peptide drug candidates.Areas covered: This paper gives a broad overview of peptide and amino-acid scale descriptors available for AMP modeling and highlights which of these are currently being used in quantitative structure–activity relationship (QSAR) studies for AMP optimization. Additionally, some key commercial computational tools are discussed, and both successful and less successful studies are referenced, illustrating some of the challenges facing AMP scientists. Through examples of different peptide QSAR studies, this review highlights some of the missing links and illuminates some of the questions that would be interesting to challenge in a more systematic fashion.Expert opinion: Computer-aided peptide QSAR using molecular descriptors may provide the necessary edge to peptide drug discovery, enabling successful design of a new generation anti-infective drug molecules. However, if this wonderful scenario is to play out, computational chemists and peptide microbiologists would need to start playing together and not just side by side.

QSAR modeling of peptide biological activity by coupling support vector machine with particle swarm optimization algorithm and genetic algorithm

A novel method coupling particle swarm optimization algorithm (PSO) and genetic algorithm (GA) was proposed to optimize simultaneously the kernel parameters of support vector machine (SVM) and determine the optimized features subset. By coupling GA with PSO, the particles produced in each generation in PSO algorithm were processed by crossover and mutation of GA, and then the particles could keep diversity to escape from local optima and find the global optima quickly and accurately. In order to evaluate the proposed method, four peptide datasets were employed for the investigation of quantitative structure–activity relationship (QSAR). The structural and physicochemical features of peptides from amino acid sequences were used to represent peptides for QSAR. The correlation coefficients ( R) of training set of the four datasets were 1.0000, 0.9508, 1.0000, 0.9995, the R of test set of the four datasets were 0.9922, 0.9687, 0.9022, 0.7404, respectively. The root-mean-square errors (RMSEs) of training set of the four datasets were 0.0000, 0.0986, 0.0000, 0.0203, the RMSEs of test set of the four datasets were 0.2522, 0.2782, 0.9625, 0.2928, respectively. A protein dataset, which consists of 277 proteins, was also employed to evaluate the current method for predicting protein structural class, and the good results of overall success rate were obtained. The results indicated that the proposed method might hold a high potential to become a useful tool in peptide QSAR and protein prediction research.

Studying Peptides Biological Activities Based on Multidimensional Descriptors (E) Using Support Vector Regression

A quantitative multidimensional amino acids descriptors E (E1–E5) has been introduced in bioactive peptides Quantitative Structure–Activity Relationship (QSAR) study. These descriptors correlate well with hydrophobicity, size, preferences for amino acids to occur in α-helices, composition and the net charge, respectively. They were then applied to construct characterization and QSAR analysis on 48 angiotensin-converting enzyme (ACE) inhibitors dipeptides, 55 ACE inhibitors tripeptides and 48 bitter tasting dipeptides by support vector regression (SVR). The leave one out cross validation Q(CV)2 were 0.886, 0.985 and 0.912, the root mean square error (RMSE) were 0.250, 0.021 and 0.123, respectively. The results showed that, in comparison with the conventional descriptors, the new descriptor (E) is a useful structure characterization method for peptide QSAR analysis. The importance of each parameter or property at each position in peptides is estimated by the value of the model RMSE obtained using leave-one-parameter-out (LOPO) approach in the SVR model. This will be provided with certain guidance meaning to design and exploit peptide analogues. The results also indicate that SVR can be used as an alternative powerful modeling tool for peptide QSAR studies, and give one advice (LOPO) about evaluating the importance of parameter in SVR model. Moreover, it also offered an idea about nonlinear relation between bioactive of peptides and their structural descriptors E. The establishment of such methods will be a very meaningful work to peptide bioactive investigation in peptide analogue drug design.

A novel vector of topological and structural information for amino acids and its QSAR applications for peptides and analogues

A new descriptor, called vector of topological and structural information for coded and noncoded amino acids (VTSA), was derived by principal component analysis (PCA) from a matrix of 66 topological and structural variables of 134 amino acids. The VTSA vector was then applied into two sets of peptide quantitative structure-activity relationships or quantitative sequence-activity modelings (QSARs/QSAMs). Molded by genetic partial least squares (GPLS), support vector machine (SVM), and immune neural network (INN), good results were obtained. For the datasets of 58 angiotensin converting enzyme inhibitors (ACEI) and 89 elastase substrate catalyzed kinetics (ESCK), the R2, cross-validation R2, and root mean square error of estimation (RMSEE) were as follows: ACEI, Rcu2⩾0.82, Qcu2⩾0.77, Ermse⩽0.44 (GPLS+SVM); ESCK, Rcu2⩾0.84, Qcu2⩾0.82, Ermse⩽0.20 (GPLS+INN), respectively.

A New 3D-Descriptor of Amino Acids and Its Application in Quantitative Structure Activity Relationship of Peptide Drugs

A new descriptor, vector of principal component scores for GETAWAY index, was derived from a principal components analysis of a matrix of 197 GETAWAY indexes of 20 natural amino acids. The scale was then applied to construct three panels of polypeptide quantitative structure activity relationship (QSAR) based on partial least squares (PLS) regression. The correlation coefficient (R2 cum) and cross-validation correlation coefficient (Q2 cum) of the obtained models were 0.887 and 0.753 for 48 bitter tasting dipeptides, 0.995 and 0.708 for 31 bradykinin-potentiating pentapeptides, 0.999 and 0.802 for 20 thromboplastin inhibitors, respectively. The satisfactory results showed that, as new amino acid scales, data of VSGETAWAY may be a useful structural expression methodology for study on peptide QSAR due to its many advantages such as easy manipulation, plentiful structural information and high characterization competence.

Modelling relationship between angiotensin-(I)-converting enzyme inhibition and the bitter taste of peptides

Relationships between angiotensin-(I)-converting enzyme inhibition and the bitter taste of peptides were studied. In cases where ACE inhibition or bitter taste had not been experimentally determined, their activity was estimated using several different peptide quantitative structure–activity relationship (QSAR) models. Significant correlations between increased ACE inhibition and bitterness were found for dipeptides using both observed and QSAR-predicted values. The relationship between ACE inhibition and bitter taste was attributed to the importance of hydrophobicity for both properties. Limited structural variations for dipeptides could make it difficult to have features that limit the effect of C-terminal hydrophobicity, necessary for ACE inhibition, on bitter taste. A similar modelling approach was also done on data from observed bitter oligopeptides derived from milk proteins. The relationship between QSAR-predicted ACE inhibition and observed bitter taste was not as strong as that found for dipeptides. Larger structural variation possibilities for oligopeptides than for dipeptides may thus make it, more feasible to find a highly efficient ACE inhibitory oligopeptide with a negligible bitter taste than a dipeptide.

Quantitative structure activity relationship modelling of peptides and proteins as a tool in food science

Abstract Peptides and proteins contribute to physical properties, biological activities and sensory characteristics of foods. Studies on the isolation and characterisation of peptides and proteins allow compilation of data sets on their structures and properties/activities. Quantitative structure activity relationship (QSAR) modelling provides methodology to find mathematical expressions for such relationships which may then be useful for estimating activities of any related compound and for predicting structures of high activity. Methodology for transforming peptide and protein structures into data sets are presented, and research relevant for food science and technology are discussed in this review. Peptide QSAR modelling has been especially useful for antimicrobial, ACE-inhibitory and bitter tasting peptides, but could easily be expanded to other areas within food research.

Some recent developments in PLS modeling

The original chemometrics partial least squares (PLS) model with two blocks of variables ( X and Y), linearly related to each other, has had several enhancements/extensions since the beginning of 1980. We here discuss multi-block and hierarchical PLS modeling for installing a priori knowledge of the data structure and simplifying the model interpretation, variable selection schemes for PLS with often similar objectives, nonlinear PLS, and prefiltered PLS, orthogonal signal correction (OSC). A very recent development, orthogonalized-PLS (O-PLS) is included as a way to accomplish both OSC, and a simpler interpretation of the PLS model. In this context, we also briefly mention time series, batch, and wavelets variants of PLS. These PLS extensions are illustrated by examples from peptide quantitative structure–activity relationships (QSAR) and multivariate characterization of pulp using NIR.

Optimising the signal peptide for glycosyl phosphatidylinositol modification of human acetylcholinesterase using mutational analysis and peptide-quantitative structure–activity relationships

Glycosyl phosphatidylinositol (GPI)-modified proteins have a C-terminal signal peptide (GPIsp) that mediates the addition of a GPI-anchor to an amino acid residue at the cleavage and modification site (ω-site). Within the GPIsp, a stretch of hydrophilic amino acid residues are found which constitutes the spacer region that separates the ω-site residue from a hydrophobic C-terminus. Deletions and insertions into the spacer region of human acetylcholinesterase (AChE) show that the length of this spacer region is very important for efficient GPI-modification. Surprisingly, the natural length of the spacer region in human AChE was not optimal for the highest degree of GPI modification. The importance of the two adjacent residues downstream of the ω-site, the ω+1 and ω+2 residues, was investigated by peptide-quantitative structure–activity relationships (Peptide-QSAR). A model was made that predicts the efficiency of the GPI modification when these residues are substituted with others, and suggests important features for these residues. The most preferred ω+1 and ω+2 residues, predicted by the model, in combination with an ideal spacer length resulted in an optimised GPIsp. This mutant protein is more efficiently GPI-modified than any mutant AChE tested thus far.