Fingerprint-based in silico models for the prediction of P-glycoprotein substrates and inhibitors

P-Glycoprotein (P-gp, ABCB1) plays a significant role in determining the ADMET properties of drugs and drug candidates. Substrates of P-gp are not only subject to multidrug resistance (MDR) in tumor therapy, they are also associated with poor pharmacokinetic profiles. In contrast, inhibitors of P-gp have been advocated as modulators of MDR. However, due to the polyspecificity of P-gp, knowledge on the molecular basis of ligand-transporter interaction is still poor, which renders the prediction of whether a compound is a P-gp substrate/non-substrate or an inhibitor/non-inhibitor quite challenging. In the present investigation, we used a set of fingerprints representing the presence/absence of various functional groups for machine learning based classification of a set of 484 substrates/non-substrates and a set of 1935 inhibitors/non-inhibitors. Best models were obtained using a combination of a wrapper subset evaluator (WSE) with random forest (RF), kappa nearest neighbor (kNN) and support vector machine (SVM), showing accuracies >70%. Best P-gp substrate models were further validated with three sets of external P-gp substrate sources, which include Drug Bank (n=134), TP Search (n=90) and a set compiled from literature (n=76). Association rule analysis explores the various structural feature requirements for P-gp substrates and inhibitors.     

Evaluation of drug-human serum albumin binding interactions with support vector machine aided online automated docking

MOTIVATION: Human serum albumin (HSA), the most abundant plasma protein is well known for its extraordinary binding capacity for both endogenous and exogenous substances, including a wide range of drugs. Interaction with the two principal binding sites of HSA in subdomain IIA (site 1) and in subdomain IIIA (site 2) controls the free, active concentration of a drug, provides a reservoir for a long duration of action and ultimately affects the ADME (absorption, distribution, metabolism, and excretion) profile. Due to the continuous demand to investigate HSA binding properties of novel drugs, drug candidates and drug-like compounds, a support vector machine (SVM) model was developed that efficiently predicts albumin binding. Our SVM model was integrated to a free, web-based prediction platform (http://albumin.althotas.com). Automated molecular docking calculations for prediction of complex geometry are also integrated into the web service. The platform enables the users (i) to predict if albumin binds the query ligand, (ii) to determine the probable ligand binding site (site 1 or site 2), (iii) to select the albumin X-ray structure which is complexed with the most similar ligand and (iv) to calculate complex geometry using molecular docking calculations. Our SVM model and the potential offered by the combined use of in silico calculation methods and experimental binding data is illustrated.     

HingeProt: automated prediction of hinges in protein structures

Proteins are highly flexible molecules. Prediction of molecular flexibility aids in the comprehension and prediction of protein function and in providing details of functional mechanisms. The ability to predict the locations, directions, and extent of molecular movements can assist in fitting atomic resolution structures to low-resolution EM density maps and in predicting the complex structures of interacting molecules (docking). There are several types of molecular movements. In this work, we focus on the prediction of hinge movements. Given a single protein structure, the method automatically divides it into the rigid parts and the hinge regions connecting them. The method employs the Elastic Network Model, which is very efficient and was validated against a large data set of proteins. The output can be used in applications such as flexible protein-protein and protein-ligand docking, flexible docking of protein structures into cryo-EM maps, and refinement of low-resolution EM structures. The web server of HingeProt provides convenient visualization of the results and is available with two mirror sites at http://www.prc.boun.edu.tr/appserv/prc/HingeProt3 and http://bioinfo3d.cs.tau.ac.il/HingeProt/.     

Predicting binding to p-glycoprotein by flexible receptor docking

P-glycoprotein (P-gp) is an ATP-dependent transport protein that is selectively expressed at entry points of xenobiotics where, acting as an efflux pump, it prevents their entering sensitive organs. The protein also plays a key role in the absorption and blood-brain barrier penetration of many drugs, while its overexpression in cancer cells has been linked to multidrug resistance in tumors. The recent publication of the mouse P-gp crystal structure revealed a large and hydrophobic binding cavity with no clearly defined sub-sites that supports an "induced-fit" ligand binding model. We employed flexible receptor docking to develop a new prediction algorithm for P-gp binding specificity. We tested the ability of this method to differentiate between binders and nonbinders of P-gp using consistently measured experimental data from P-gp efflux and calcein-inhibition assays. We also subjected the model to a blind test on a series of peptidic cysteine protease inhibitors, confirming the ability to predict compounds more likely to be P-gp substrates. Finally, we used the method to predict cellular metabolites that may be P-gp substrates. Overall, our results suggest that many P-gp substrates bind deeper in the cavity than the cyclic peptide in the crystal structure and that specificity in P-gp is better understood in terms of physicochemical properties of the ligands (and the binding site), rather than being defined by specific sub-sites.     

PSLpred: prediction of subcellular localization of bacterial proteins

SUMMARY: We developed a web server PSLpred for predicting subcellular localization of gram-negative bacterial proteins with an overall accuracy of 91.2%. PSLpred is a hybrid approach-based method that integrates PSI-BLAST and three SVM modules based on compositions of residues, dipeptides and physico-chemical properties. The prediction accuracies of 90.7, 86.8, 90.3, 95.2 and 90.6% were attained for cytoplasmic, extracellular, inner-membrane, outer-membrane and periplasmic proteins, respectively. Furthermore, PSLpred was able to predict approximately 74% of sequences with an average prediction accuracy of 98% at RI = 5. AVAILABILITY: PSLpred is available at http://www.imtech.res.in/raghava/pslpred/     

Better prediction of the location of alpha-turns in proteins with support vector machine

We have developed a novel method named AlphaTurn to predict alpha-turns in proteins based on the support vector machine (SVM). The prediction was done on a data set of 469 nonhomologous proteins containing 967 alpha-turns. A great improvement in prediction performance was achieved by using multiple sequence alignment generated by PSI-BLAST as input instead of the single amino acid sequence. The introduction of secondary structure information predicted by PSIPRED also improved the prediction performance. Moreover, we handled the very uneven data set by combining the cost factor j with the "state-shifting" rule. This further promoted the prediction quality of our method. The final SVM model yielded a Matthews correlation coefficient (MCC) of 0.25 by a 10-fold cross-validation. To our knowledge, this MCC value is the highest obtained so far for predicting alpha-turns. An online Web server based on this method has been developed and can be freely accessed at http://bmc.hust.edu.cn/bioinformatics/ or http://210.42.106.80/.     

Cross‐docking benchmark for automated pose and ranking prediction of ligand binding

Significant efforts have been devoted in the last decade to improving molecular docking techniques to predict both accurate binding poses and ranking affinities. Some shortcomings in the field are the limited number of standard methods for measuring docking success and the availability of widely accepted standard data sets for use as benchmarks in comparing different docking algorithms throughout the field. In order to address these issues, we have created a Cross‐Docking Benchmark server. The server is a versatile cross‐docking data set containing 4,399 protein‐ligand complexes across 95 protein targets intended to serve as benchmark set and gold standard for state‐of‐the‐art pose and ranking prediction in easy, medium, hard, or very hard docking targets. The benchmark along with a customizable cross‐docking data set generation tool is available at http://disco.csb.pitt.edu . We further demonstrate the potential uses of the server in questions outside of basic benchmarking such as the selection of the ideal docking reference structure.     

Rigid substructure search

MOTIVATION: Identifying the location of binding sites on proteins is of fundamental importance for a wide range of applications, including molecular docking, de novo drug design, structure identification and comparison of functional sites. Here we present Erebus, a web server that searches the entire Protein Data Bank for a given substructure defined by a set of atoms of interest, such as the binding scaffolds for small molecules. The identified substructure contains atoms having the same names, belonging to same amino acids and separated by the same distances (within a given tolerance) as the atoms of the query structure. The accuracy of a match is measured by the root-mean-square deviation or by the normal weight with a given variance. Tests show that our approach can reliably locate rigid binding scaffolds of drugs and metal ions. Availability and Implementation: We provide this service through a web server at http://erebus.dokhlab.org.     

SVMyr: A Web Server Detecting Co- and Post-translational Myristoylation in Proteins

Myristoylation (MYR) is a protein modification where a myristoyl group is covalently attached to an exposed (N-terminal) glycine residue. Glycine myristoylation occurs during protein translation (co-translation) or after (post-translation). Myristoylated proteins have a role in signal transduction, apoptosis, and pathogen-mediated processes and their prediction can help in functionally annotating the fraction of proteins undergoing MYR in different proteomes.Here we present SVMyr, a web server allowing the detection of both co- and post-translational myristoylation sites, based on Support Vector Machines (SVM). The input encodes composition and physicochemical features of the octapeptides, known to act as substrates and to physically interact with N-myristoyltransferases (NMTs), the enzymes catalyzing the myristoylation reaction.The method, adopting a cross validation procedure, scores with values of Area Under the Curve (AUC) and Matthews Correlation Coefficient (MCC) of 0.92 and 0.61, respectively. When benchmarked on an independent dataset including experimentally detected 88 medium/high confidence co-translational myristoylation sites and 528 negative examples, SVMyr outperforms available methods, with AUC and MCC equal to 0.91 and 0.58, respectively.A unique feature of SVMyr is the ability to predict post-translational myristoylation sites by coupling the trained SVMs with the detection of caspase cleavage sites, identified by searching regular motifs matching upstream caspase cleavage sites, as reported in literature.Finally, SVMyr confirms 96% of the UniProt set of the electronically annotated myristoylated proteins (31,048) and identifies putative myristoylomes in eight different proteomes, highlighting also new putative NMT substrates.SVMyr is freely available through a user-friendly web server at https://busca.biocomp.unibo.it/lipipred.     

CASVM: web server for SVM-based prediction of caspase substrates cleavage sites

Caspases belong to a unique class of cysteine proteases which function as critical effectors of apoptosis, inflammation and other important cellular processes. Caspases cleave substrates at specific tetrapeptide sites after a highly conserved aspartic acid residue. Prediction of such cleavage sites will complement structural and functional studies on substrates cleavage as well as discovery of new substrates. We have recently developed a support vector machines (SVM) method to address this issue. Our algorithm achieved an accuracy ranging from 81.25 to 97.92%, making it one of the best methods currently available. CASVM is the web server implementation of our SVM algorithms, written in Perl and hosted on a Linux platform. The server can be used for predicting non-canonical caspase substrate cleavage sites. We have also included a relational database containing experimentally verified caspase substrates retrievable using accession IDs, keywords or sequence similarity. AVAILABILITY: http://www.casbase.org/casvm/index.html     

DPROT: prediction of disordered proteins using evolutionary information

The association of structurally disordered proteins with a number of diseases has engendered enormous interest and therefore demands a prediction method that would facilitate their expeditious study at molecular level. The present study describes the development of a computational method for predicting disordered proteins using sequence and profile compositions as input features for the training of SVM models. First, we developed the amino acid and dipeptide compositions based SVM modules which yielded sensitivities of 75.6 and 73.2% along with Matthew’s Correlation Coefficient (MCC) values of 0.75 and 0.60, respectively. In addition, the use of predicted secondary structure content (coil, sheet and helices) in the form of composition values attained a sensitivity of 76.8% and MCC value of 0.77. Finally, the training of SVM models using evolutionary information hidden in the multiple sequence alignment profile improved the prediction performance by achieving a sensitivity value of 78% and MCC of 0.78. Furthermore, when evaluated on an independent dataset of partially disordered proteins, the same SVM module provided a correct prediction rate of 86.6%. Based on the above study, a web server (“DPROT”) was developed for the prediction of disordered proteins, which is available at .     

Prediction of pi-turns in proteins using PSI-BLAST profiles and secondary structure information

Due to the structural and functional importance of tight turns, some methods have been proposed to predict gamma-turns, beta-turns, and alpha-turns in proteins. In the past, studies of pi-turns were made, but not a single prediction approach has been developed so far. It will be useful to develop a method for identifying pi-turns in a protein sequence. In this paper, the support vector machine (SVM) method has been introduced to predict pi-turns from the amino acid sequence. The training and testing of this approach is performed with a newly collected data set of 640 non-homologous protein chains containing 1931 pi-turns. Different sequence encoding schemes have been explored in order to investigate their effects on the prediction performance. With multiple sequence alignment and predicted secondary structure, the final SVM model yields a Matthews correlation coefficient (MCC) of 0.556 by a 7-fold cross-validation. A web server implementing the prediction method is available at the following URL: http://210.42.106.80/piturn/.     

BetaTPred: prediction of beta-TURNS in a protein using statistical algorithms

MOTIVATION: beta-turns play an important role from a structural and functional point of view. beta-turns are the most common type of non-repetitive structures in proteins and comprise on average, 25% of the residues. In the past numerous methods have been developed to predict beta-turns in a protein. Most of these prediction methods are based on statistical approaches. In order to utilize the full potential of these methods, there is a need to develop a web server. RESULTS: This paper describes a web server called BetaTPred, developed for predicting beta-TURNS in a protein from its amino acid sequence. BetaTPred allows the user to predict turns in a protein using existing statistical algorithms. It also allows to predict different types of beta-TURNS e.g. type I, I', II, II', VI, VIII and non-specific. This server assists the users in predicting the consensus beta-TURNS in a protein. AVAILABILITY: The server is accessible from http://imtech.res.in/raghava/betatpred/     

Using protein binding site prediction to improve protein docking

Predicting protein interaction interfaces and protein complexes are two important related problems. For interface prediction, there are a number of tools, such as PPI-Pred, PPISP, PINUP, Promate, and SPPIDER, which predict enzyme-inhibitor interfaces with success rates of 23% to 55% and other interfaces with 10% to 28% on a benchmark dataset of 62 complexes. Here, we develop, metaPPI, a meta server for interface prediction. It significantly improves prediction success rates to 70% for enzyme-inhibitor and 44% for other interfaces. As shown with Promate, predicted interfaces can be used to improve protein docking. Here, we follow this idea using the meta server instead of individual predictions. We confirm that filtering with predicted interfaces significantly improves candidate generation in rigid-body docking based on shape complementarity. Finally, we show that the initial ranking of candidate solutions in rigid-body docking can be further improved for the class of enzyme-inhibitor complexes by a geometrical scoring which rewards deep pockets. A web server of metaPPI is available at scoppi.tu-dresden.de/metappi. The source code of our docking algorithm BDOCK is also available at www.biotec.tu-dresden.de/~bhuang/bdock.     

pTARGET [corrected] a new method for predicting protein subcellular localization in eukaryotes

MOTIVATION: There is a scarcity of efficient computational methods for predicting protein subcellular localization in eukaryotes. Currently available methods are inadequate for genome-scale predictions with several limitations. Here, we present a new prediction method, pTARGET that can predict proteins targeted to nine different subcellular locations in the eukaryotic animal species. RESULTS: The nine subcellular locations predicted by pTARGET include cytoplasm, endoplasmic reticulum, extracellular/secretory, golgi, lysosomes, mitochondria, nucleus, plasma membrane and peroxisomes. Predictions are based on the location-specific protein functional domains and the amino acid compositional differences across different subcellular locations. Overall, this method can predict 68-87% of the true positives at accuracy rates of 96-99%. Comparison of the prediction performance against PSORT showed that pTARGET prediction rates are higher by 11-60% in 6 of the 8 locations tested. Besides, the pTARGET method is robust enough for genome-scale prediction of protein subcellular localizations since, it does not rely on the presence of signal or target peptides. AVAILABILITY: A public web server based on the pTARGET method is accessible at the URL http://bioinformatics.albany.edu/~ptarget. Datasets used for developing pTARGET can be downloaded from this web server. Source code will be available on request from the corresponding author.     

Position-specific residue preference features around the ends of helices and strands and a novel strategy for the prediction of secondary structures

It has been many years since position-specific residue preference around the ends of a helix was revealed. However, all the existing secondary structure prediction methods did not exploit this preference feature, resulting in low accuracy in predicting the ends of secondary structures. In this study, we collected a relatively large data set consisting of 1860 high-resolution, non-homology proteins from the PDB, and further analyzed the residue distributions around the ends of regular secondary structures. It was found that there exist position-specific residue preferences (PSRP) around the ends of not only helices but also strands. Based on the unique features, we proposed a novel strategy and developed a tool named E-SSpred that treats the secondary structure as a whole and builds models to predict entire secondary structure segments directly by integrating relevant features. In E-SSpred, the support vector machine (SVM) method is adopted to model and predict the ends of helices and strands according to the unique residue distributions around them. A simple linear discriminate analysis method is applied to model and predict entire secondary structure segments by integrating end-prediction results, tri-peptide composition, and length distribution features of secondary structures, as well as the prediction results of the most famous program PSIPRED. The results of fivefold cross-validation on a widely used data set demonstrate that the accuracy of E-SSpred in predicting ends of secondary structures is about 10% higher than PSIPRED, and the overall prediction accuracy (Q(3) value) of E-SSpred (82.2%) is also better than PSIPRED (80.3%). The E-SSpred web server is available at http://bioinfo.hust.edu.cn/bio/tools/E-SSpred/index.html.     

BIPSPI+: Mining Type-Specific Datasets of Protein Complexes to Improve Protein Binding Site Prediction

Computational approaches for predicting protein-protein interfaces are extremely useful for understanding and modelling the quaternary structure of protein assemblies. In particular, partner-specific binding site prediction methods allow delineating the specific residues that compose the interface of protein complexes. In recent years, new machine learning and other algorithmic approaches have been proposed to solve this problem. However, little effort has been made in finding better training datasets to improve the performance of these methods. With the aim of vindicating the importance of the training set compilation procedure, in this work we present BIPSPI+, a new version of our original server trained on carefully curated datasets that outperforms our original predictor. We show how prediction performance can be improved by selecting specific datasets that better describe particular types of protein interactions and interfaces (e.g. homo/hetero). In addition, our upgraded web server offers a new set of functionalities such as the sequence-structure prediction mode, hetero- or homo-complex specialization and the guided docking tool that allows to compute 3D quaternary structure poses using the predicted interfaces. BIPSPI+ is freely available at https://bipspi.cnb.csic.es.     

Computational prediction of heme-binding residues by exploiting residue interaction network

Computational identification of heme-binding residues is beneficial for predicting and designing novel heme proteins. Here we proposed a novel method for heme-binding residue prediction by exploiting topological properties of these residues in the residue interaction networks derived from three-dimensional structures. Comprehensive analysis showed that key residues located in heme-binding regions are generally associated with the nodes with higher degree, closeness and betweenness, but lower clustering coefficient in the network. HemeNet, a support vector machine (SVM) based predictor, was developed to identify heme-binding residues by combining topological features with existing sequence and structural features. The results showed that incorporation of network-based features significantly improved the prediction performance. We also compared the residue interaction networks of heme proteins before and after heme binding and found that the topological features can well characterize the heme-binding sites of apo structures as well as those of holo structures, which led to reliable performance improvement as we applied HemeNet to predicting the binding residues of proteins in the heme-free state. HemeNet web server is freely accessible at http://mleg.cse.sc.edu/hemeNet/.     

In silico platform for predicting and initiating β‐turns in a protein at desired locations

Numerous studies have been performed for analysis and prediction of β‐turns in a protein. This study focuses on analyzing, predicting, and designing of β‐turns to understand the preference of amino acids in β‐turn formation. We analyzed around 20,000 PDB chains to understand the preference of residues or pair of residues at different positions in β‐turns. Based on the results, a propensity‐based method has been developed for predicting β‐turns with an accuracy of 82%. We introduced a new approach entitled “Turn level prediction method,” which predicts the complete β‐turn rather than focusing on the residues in a β‐turn. Finally, we developed BetaTPred3, a Random forest based method for predicting β‐turns by utilizing various features of four residues present in β‐turns. The BetaTPred3 achieved an accuracy of 79% with 0.51 MCC that is comparable or better than existing methods on BT426 dataset. Additionally, models were developed to predict β‐turn types with better performance than other methods available in the literature. In order to improve the quality of prediction of turns, we developed prediction models on a large and latest dataset of 6376 nonredundant protein chains. Based on this study, a web server has been developed for prediction of β‐turns and their types in proteins. This web server also predicts minimum number of mutations required to initiate or break a β‐turn in a protein at specified location of a protein. Proteins 2015; 83:910–921. © 2015 Wiley Periodicals, Inc.