Residues In Protein Sequences Research Articles

SERT-StructNet: Protein secondary structure prediction method based on multi-factor hybrid deep model

Protein secondary structure prediction (PSSP) is a pivotal research endeavour that plays a crucial role in the comprehensive elucidation of protein functions and properties. Current prediction methodologies are focused on deep-learning techniques, particularly focusing on multi-factor features. Diverging from existing approaches, in this study, we placed special emphasis on the effects of amino acid properties and protein secondary structure propensity scores (SSPs) on secondary structure during the meticulous selection of multi-factor features. This differential feature-selection strategy results in a distinctive and effective amalgamation of the sequence and property features. To harness these multi-factor features optimally, we introduced a hybrid deep feature extraction model. The model initially employs mechanisms such as dilated convolution (D-Conv) and a channel attention network (SENet) for local feature extraction and targeted channel enhancement. Subsequently, a combination of recurrent neural network variants (BiGRU and BiLSTM), along with a transformer module, was employed to achieve global bidirectional information consideration and feature enhancement. This approach to multi-factor feature input and multi-level feature processing enabled a comprehensive exploration of intricate associations among amino acid residues in protein sequences, yielding a Q3 accuracy of 84.9% and an Sov score of 85.1%. The overall performance surpasses that of the comparable methods. This study introduces a novel and efficient method for determining the PSSP domain, which is poised to deepen our understanding of the practical applications of protein molecular structures.

Prot2GO: Predicting GO Annotations From Protein Sequences and Interactions.

Protein is the main material basis of living organisms and plays crucial role in life activities. Understanding the function of protein is of great significance for new drug discovery, disease treatment and vaccine development. In recent years, with the widespread application of deep learning in bioinformatics, researchers have proposed many deep learning models to predict protein functions. However, the existing deep learning methods usually only consider protein sequences, and thus cannot effectively integrate multi-source data to annotate protein functions. In this article, we propose the Prot2GO model, which can integrate protein sequence and PPI network data to predict protein functions. We utilize an improved biased random walk algorithm to extract the features of PPI network. For sequence data, we use a convolutional neural network to obtain the local features of the sequence and a recurrent neural network to capture the long-range associations between amino acid residues in protein sequence. Moreover, Prot2GO adopts the attention mechanism to identify protein motifs and structural domains. Experiments show that Prot2GO model achieves the state-of-the-art performance on multiple metrics.

PFresGO: an attention mechanism-based deep-learning approach for protein annotation by integrating gene ontology inter-relationships.

The rapid accumulation of high-throughput sequence data demands the development of effective and efficient data-driven computational methods to functionally annotate proteins. However, most current approaches used for functional annotation simply focus on the use of protein-level information but ignore inter-relationships among annotations. Here, we established PFresGO, an attention-based deep-learning approach that incorporates hierarchical structures in Gene Ontology (GO) graphs and advances in natural language processing algorithms for the functional annotation of proteins. PFresGO employs a self-attention operation to capture the inter-relationships of GO terms, updates its embedding accordingly and uses a cross-attention operation to project protein representations and GO embedding into a common latent space to identify global protein sequence patterns and local functional residues. We demonstrate that PFresGO consistently achieves superior performance across GO categories when compared with 'state-of-the-art' methods. Importantly, we show that PFresGO can identify functionally important residues in protein sequences by assessing the distribution of attention weightings. PFresGO should serve as an effective tool for the accurate functional annotation of proteins and functional domains within proteins. PFresGO is available for academic purposes at https://github.com/BioColLab/PFresGO. Supplementary data are available at Bioinformatics online.

IDRNA-ITF: identifying DNA- and RNA-binding residues in proteins based on induction and transfer framework.

Protein-DNA and protein-RNA interactions are involved in many biological activities. In the post-genome era, accurate identification of DNA- and RNA-binding residues in protein sequences is of great significance for studying protein functions and promoting new drug design and development. Therefore, some sequence-based computational methods have been proposed for identifying DNA- and RNA-binding residues. However, they failed to fully utilize the functional properties of residues, leading to limited prediction performance. In this paper, a sequence-based method iDRNA-ITF was proposed to incorporate the functional properties in residue representation by using an induction and transfer framework. The properties of nucleic acid-binding residues were induced by the nucleic acid-binding residue feature extraction network, and then transferred into the feature integration modules of the DNA-binding residue prediction network and the RNA-binding residue prediction network for the final prediction. Experimental results on four test sets demonstrate that iDRNA-ITF achieves the state-of-the-art performance, outperforming the other existing sequence-based methods. The webserver of iDRNA-ITF is freely available at http://bliulab.net/iDRNA-ITF.

DisoLipPred: accurate prediction of disordered lipid-binding residues in protein sequences with deep recurrent networks and transfer learning.

Intrinsically disordered protein regions interact with proteins, nucleic acids and lipids. Regions that bind lipids are implicated in a wide spectrum of cellular functions and several human diseases. Motivated by the growing amount of experimental data for these interactions and lack of tools that can predict them from the protein sequence, we develop DisoLipPred, the first predictor of the disordered lipid-binding residues (DLBRs). DisoLipPred relies on a deep bidirectional recurrent network that implements three innovative features: transfer learning, bypass module that sidesteps predictions for putative structured residues, and expanded inputs that cover physiochemical properties associated with the protein-lipid interactions. Ablation analysis shows that these features drive predictive quality of DisoLipPred. Tests on an independent test dataset and the yeast proteome reveal that DisoLipPred generates accurate results and that none of the related existing tools can be used to indirectly identify DLBR. We also show that DisoLipPred's predictions complement the results generated by predictors of the transmembrane regions. Altogether, we conclude that DisoLipPred provides high-quality predictions of DLBRs that complement the currently available methods. DisoLipPred's webserver is available at http://biomine.cs.vcu.edu/servers/DisoLipPred/. Supplementary data are available at Bioinformatics online.

DNAgenie: accurate prediction of DNA-type-specific binding residues in protein sequences.

Efforts to elucidate protein-DNA interactions at the molecular level rely in part on accurate predictions of DNA-binding residues in protein sequences. While there are over a dozen computational predictors of the DNA-binding residues, they are DNA-type agnostic and significantly cross-predict residues that interact with other ligands as DNA binding. We leverage a custom-designed machine learning architecture to introduce DNAgenie, first-of-its-kind predictor of residues that interact with A-DNA, B-DNA and single-stranded DNA. DNAgenie uses a comprehensive physiochemical profile extracted from an input protein sequence and implements a two-step refinement process to provide accurate predictions and to minimize the cross-predictions. Comparative tests on an independent test dataset demonstrate that DNAgenie outperforms the current methods that we adapt to predict residue-level interactions with the three DNA types. Further analysis finds that the use of the second (refinement) step leads to a substantial reduction in the cross predictions. Empirical tests show that DNAgenie's outputs that are converted to coarse-grained protein-level predictions compare favorably against recent tools that predict which DNA-binding proteins interact with double-stranded versus single-stranded DNAs. Moreover, predictions from the sequences of the whole human proteome reveal that the results produced by DNAgenie substantially overlap with the known DNA-binding proteins while also including promising leads for several hundred previously unknown putative DNA binders. These results suggest that DNAgenie is a valuable tool for the sequence-based characterization of protein functions. The DNAgenie's webserver is available at http://biomine.cs.vcu.edu/servers/DNAgenie/.

A Haloalkane Dehalogenase from Saccharomonospora viridis Strain DSM 43017, a Compost Bacterium with Unusual Catalytic Residues, Unique (S)-Enantiopreference, and High Thermostability.

Haloalkane dehalogenases can cleave a carbon-halogen bond in a broad range of halogenated aliphatic compounds. However, a highly conserved catalytic pentad composed of a nucleophile, a catalytic base, a catalytic acid, and two halide-stabilizing residues is required for their catalytic activity. Only a few family members, e.g., DsaA, DmxA, or DmrB, remain catalytically active while employing a single halide-stabilizing residue. Here, we describe a novel haloalkane dehalogenase, DsvA, from a mildly thermophilic bacterium, Saccharomonospora viridis strain DSM 43017, possessing one canonical halide-stabilizing tryptophan (W125). At the position of the second halide-stabilizing residue, DsvA contains the phenylalanine F165, which cannot stabilize the halogen anion released during the enzymatic reaction by a hydrogen bond. Based on the sequence and structural alignments, we identified a putative second halide-stabilizing tryptophan (W162) located on the same α-helix as F165, but on the opposite side of the active site. The potential involvement of this residue in DsvA catalysis was investigated by the construction and biochemical characterization of the three variants, DsvA01 (F165W), DsvA02 (W162F), and DsvA03 (W162F and F165W). Interestingly, DsvA exhibits a preference for the (S)- over the (R)-enantiomers of β-bromoalkanes, which has not been reported before for any characterized haloalkane dehalogenase. Moreover, DsvA shows remarkable operational stability at elevated temperatures. The present study illustrates that protein sequences possessing an unconventional composition of catalytic residues represent a valuable source of novel biocatalysts.IMPORTANCE The present study describes a novel haloalkane dehalogenase, DsvA, originating from a mildly thermophilic bacterium, Saccharomonospora viridis strain DSM 43017. We report its high thermostability, remarkable operational stability at high temperatures, and an (S)-enantiopreference, which makes this enzyme an attractive biocatalyst for practical applications. Sequence analysis revealed that DsvA possesses an unusual composition of halide-stabilizing tryptophan residues in its active site. We constructed and biochemically characterized two single point mutants and one double point mutant and identified the noncanonical halide-stabilizing residue. Our study underlines the importance of searching for noncanonical catalytic residues in protein sequences.

Recognizing Ion Ligand-Binding Residues by Random Forest Algorithm Based on Optimized Dihedral Angle.

The prediction of ion ligand–binding residues in protein sequences is a challenging work that contributes to understand the specific functions of proteins in life processes. In this article, we selected binding residues of 14 ion ligands as research objects, including four acid radical ion ligands and 10 metal ion ligands. Based on the amino acid sequence information, we selected the composition and position conservation information of amino acids, the predicted structural information, and physicochemical properties of amino acids as basic feature parameters. We then performed a statistical analysis and reclassification for dihedral angle and proposed new methods on the extraction of feature parameters. The methods mainly included applying information entropy on the extraction of polarization charge and hydrophilic–hydrophobic information of amino acids and using position weight matrices on the extraction of position conservation information. In the prediction model, we used the random forest algorithm and obtained better prediction results than previous works. With the independent test, the Matthew's correlation coefficient and accuracy of 10 metal ion ligand–binding residues were larger than 0.07 and 52%, respectively; the corresponding evaluation values of four acid radical ion ligand–binding residues were larger than 0.15 and 86%, respectively. Further, we classified and combined the phi and psi angles and optimized prediction model for each ion ligand–binding residue.

GlyStruct: glycation prediction using structural properties of amino acid residues

BackgroundGlycation is a one of the post-translational modifications (PTM) where sugar molecules and residues in protein sequences are covalently bonded. It has become one of the clinically important PTM in recent times attributed to many chronic and age related complications. Being a non-enzymatic reaction, it is a great challenge when it comes to its prediction due to the lack of significant bias in the sequence motifs.ResultsWe developed a classifier, GlyStruct based on support vector machine, to predict glycated and non-glycated lysine residues using structural properties of amino acid residues. The features used were secondary structure, accessible surface area and the local backbone torsion angles. For this work, a benchmark dataset was extracted containing 235 glycated and 303 non-glycated lysine residues. GlyStruct demonstrated improved performance of approximately 10% in comparison to benchmark method of Gly-PseAAC. The performance for GlyStruct on the metrics, sensitivity, specificity, accuracy and Mathew’s correlation coefficient were 0.7013, 0.7989, 0.7562, and 0.5065, respectively for 10-fold cross-validation.ConclusionGlycation has emerged to be one of the clinically important PTM of proteins in recent times. Therefore, the development of computational tools become necessary to predict glycation, which could help medical professionals administer drugs and manage patients more effectively. The proposed predictor manages to classify glycated and non-glycated lysine residues with promising results consistently on various cross-validation schemes and outperforms other state of the art methods.

A novel method for predicting RNA-interacting residues in proteins using a combination of feature-based and sequence template-based methods

RNA-binding proteins (RBPs) play a significant role in many cellular processes and regulation of gene expression, therefore, accurately identifying the RNA-interacting residues in protein sequences is crucial to detect the structure of RBPs and infer their function for new drug design. The protein sequence as basic information has been widely used in many protein researches with the combination of machine learning techniques. Here, we propose a sequence-based method to predict the RNA-protein interacting residues in protein sequences. The prediction method is composed of two predictors including a feature-based predictor and a sequence template-based predictor. The feature-based predictor applies the random forest (RF) classifier with the protein sequence information. After getting the classification probability, an adjustment procedure is used in consideration of neighbouring correlation between RNA interacting residues. The sequence template-based predictor selects the optimal template of the query sequence by multiple sequence alignment and matches the interacting residues in template sequence into the query sequence. With the combination of two predictors, the coverage and prediction performance of our method have been greatly improved, the MCC value increases from 0.467 and 0.352 to 0.499 in our validation set. In order to evaluate our proposed method, an independent testing set is utilized to compare with other two hybrid methods. As a result, our method achieves better performance than the other two methods with an overall accuracy of 0.817, an MCC value of 0.511 and an F-score of 0.605, which demonstrates that our method can reliably predict the RNA interacting residues in protein sequences. Moreover, the effectiveness of our newly proposed adjustment procedure in the feature-based predictor is examined and analyzed in detail.

Hot spot prediction in protein-protein interactions by an ensemble system

BackgroundHot spot residues are functional sites in protein interaction interfaces. The identification of hot spot residues is time-consuming and laborious using experimental methods. In order to address the issue, many computational methods have been developed to predict hot spot residues. Moreover, most prediction methods are based on structural features, sequence characteristics, and/or other protein features.ResultsThis paper proposed an ensemble learning method to predict hot spot residues that only uses sequence features and the relative accessible surface area of amino acid sequences. In this work, a novel feature selection technique was developed, an auto-correlation function combined with a sliding window technique was applied to obtain the characteristics of amino acid residues in protein sequence, and an ensemble classifier with SVM and KNN base classifiers was built to achieve the best classification performance.ConclusionThe experimental results showed that our model yields the highest F1 score of 0.92 and an MCC value of 0.87 on ASEdb dataset. Compared with other machine learning methods, our model achieves a big improvement in hot spot prediction.Availabilityhttp://deeplearner.ahu.edu.cn/web/HotspotEL.htm.

Global pentapeptide statistics are far away from expected distributions

The relationships between polypeptide composition, sequence, structure and function have been puzzling biologists ever since first protein sequences were determined. Here, we study the statistics of occurrence of all possible pentapeptide sequences in known proteins. To compensate for the non-uniform distribution of individual amino acid residues in protein sequences, we investigate separately all possible permutations of every given amino acid composition. For the majority of permutation groups we find that pentapeptide occurrences deviate strongly from the expected binomial distributions, and that the observed distributions are also characterized by high numbers of outlier sequences. An analysis of identified outliers shows they often contain known motifs and rare amino acids, suggesting that they represent important functional elements. We further compare the pentapeptide composition of regions known to correspond to protein domains with that of non-domain regions. We find that a substantial number of pentapeptides is clearly strongly favored in protein domains. Finally, we show that over-represented pentapeptides are significantly related to known functional motifs and to predicted ancient structural peptides.

Prediction of Nitrated Tyrosine Residues in Protein Sequences by Extreme Learning Machine and Feature Selection Methods.

Accurately recognizing nitrated tyrosine residues from protein sequences would pave a way for understanding the mechanism of nitration and the screening of the tyrosine residues in sequences. In this study, we proposed a prediction model that used the extreme learning machine (ELM) algorithm as the prediction engine to identify nitrated tyrosine residues. To encode each tyrosine residue, a sliding window technique was adopted to extract a peptide segment for each tyrosine residue, from which a number of features were extracted. These features were analyzed by a popular feature selection method, Minimum Redundancy Maximum Relevance (mRMR) method, producing a feature list, in which all features were ranked in a rigorous way. Then, the Incremental Feature Selection (IFS) method was utilized to discover the optimal features, on which the optimal ELM-based prediction model was built. This model produced satisfactory results on the training dataset with a Matthews correlation coefficient of 0.757. The model was also evaluated by an independent test dataset that contained only positive samples, yielding a sensitivity of 0.938. Compared to other prediction models that use classic machine learning algorithms as prediction engines on the same datasets with their own optimal features, the optimal ELM-based prediction model produced much better results, indicating the superiority of the proposed model for the identification of nitrated tyrosine residues from protein sequences.

Prediction of microRNA-binding residues in protein using a Laplacian support vector machine based on sequence information.

The identification of microRNA (miRNA)-binding protein residues significantly impacts several research areas, including gene regulation and expression. We propose a method, PmiRBR, which combines a novel hybrid feature with the Laplacian support vector machine (LapSVM) algorithm to predict miRNA-binding residues in protein sequences. The hybrid feature is constituted by secondary structure, conservation scores, and a novel feature, which includes evolutionary information combined with the physicochemical properties of amino acids. Performance comparisons of the various features indicate that our novel feature contributes the most to prediction improvement. Our results demonstrate that PmiRBR can achieve 85.96% overall accuracy, with 43.89% sensitivity and 90.56% specificity. PmiRBR significantly outperforms other approaches at miRNA-binding residue prediction.

PDP-CON: prediction of domain/linker residues in protein sequences using a consensus approach.

The prediction of domain/linker residues in protein sequences is a crucial task in the functional classification of proteins, homology-based protein structure prediction, and high-throughput structural genomics. In this work, a novel consensus-based machine-learning technique was applied for residue-level prediction of the domain/linker annotations in protein sequences using ordered/disordered regions along protein chains and a set of physicochemical properties. Six different classifiers—decision tree, Gaussian naïve Bayes, linear discriminant analysis, support vector machine, random forest, and multilayer perceptron—were exhaustively explored for the residue-level prediction of domain/linker regions. The protein sequences from the curated CATH database were used for training and cross-validation experiments. Test results obtained by applying the developed PDP-CON tool to the mutually exclusive, independent proteins of the CASP-8, CASP-9, and CASP-10 databases are reported. An n-star quality consensus approach was used to combine the results yielded by different classifiers. The average PDP-CON accuracy and F-measure values for the CASP targets were found to be 0.86 and 0.91, respectively. The dataset, source code, and all supplementary materials for this work are available at https://cmaterju.org/cmaterbioinfo/ for noncommercial use.Electronic supplementary materialThe online version of this article (doi:10.1007/s00894-016-2933-0) contains supplementary material, which is available to authorized users.

SNBRFinder: A Sequence-Based Hybrid Algorithm for Enhanced Prediction of Nucleic Acid-Binding Residues.

Protein-nucleic acid interactions are central to various fundamental biological processes. Automated methods capable of reliably identifying DNA- and RNA-binding residues in protein sequence are assuming ever-increasing importance. The majority of current algorithms rely on feature-based prediction, but their accuracy remains to be further improved. Here we propose a sequence-based hybrid algorithm SNBRFinder (Sequence-based Nucleic acid-Binding Residue Finder) by merging a feature predictor SNBRFinderF and a template predictor SNBRFinderT. SNBRFinderF was established using the support vector machine whose inputs include sequence profile and other complementary sequence descriptors, while SNBRFinderT was implemented with the sequence alignment algorithm based on profile hidden Markov models to capture the weakly homologous template of query sequence. Experimental results show that SNBRFinderF was clearly superior to the commonly used sequence profile-based predictor and SNBRFinderT can achieve comparable performance to the structure-based template methods. Leveraging the complementary relationship between these two predictors, SNBRFinder reasonably improved the performance of both DNA- and RNA-binding residue predictions. More importantly, the sequence-based hybrid prediction reached competitive performance relative to our previous structure-based counterpart. Our extensive and stringent comparisons show that SNBRFinder has obvious advantages over the existing sequence-based prediction algorithms. The value of our algorithm is highlighted by establishing an easy-to-use web server that is freely accessible at http://ibi.hzau.edu.cn/SNBRFinder.

Discriminating between lysine sumoylation and lysine acetylation using mRMR feature selection and analysis.

Post-translational modifications (PTMs) are crucial steps in protein synthesis and are important factors contributing to protein diversity. PTMs play important roles in the regulation of gene expression, protein stability and metabolism. Lysine residues in protein sequences have been found to be targeted for both types of PTMs: sumoylations and acetylations; however, each PTM has a different cellular role. As experimental approaches are often laborious and time consuming, it is challenging to distinguish the two types of PTMs on lysine residues using computational methods. In this study, we developed a method to discriminate between sumoylated lysine residues and acetylated residues. The method incorporated several features: PSSM conservation scores, amino acid factors, secondary structures, solvent accessibilities and disorder scores. By using the mRMR (Maximum Relevance Minimum Redundancy) method and the IFS (Incremental Feature Selection) method, an optimal feature set was selected from all of the incorporated features, with which the classifier achieved 92.14% accuracy with an MCC value of 0.7322. Analysis of the optimal feature set revealed some differences between acetylation and sumoylation. The results from our study also supported the previous finding that there exist different consensus motifs for the two types of PTMs. The results could suggest possible dominant factors governing the acetylation and sumoylation of lysine residues, shedding some light on the modification dynamics and molecular mechanisms of the two types of PTMs, and provide guidelines for experimental validations.

Longitudinal analysis of intra-host simian immunodeficiency virus recombination in varied tissues of the rhesus macaque model for neuroAIDS

Human immunodeficiency virus intra-host recombination has never been studied in vivo both during early infection and throughout disease progression. The CD8-depleted rhesus macaque model of neuroAIDS was used to investigate the impact of recombination from early infection up to the onset of neuropathology in animals inoculated with a simian immunodeficiency virus (SIV) swarm. Several lymphoid and non-lymphoid tissues were collected longitudinally at 21 days post-infection (p.i.), 61 days p.i. and necropsy (75-118 days p.i.) from four macaques that developed SIV-encephalitis or meningitis, as well as from two animals euthanized at 21 days p.i. The number of recombinant sequences and breakpoints in different tissues and over time from each primate were compared. Breakpoint locations were mapped onto predicted RNA and protein secondary structures. Recombinants were found at each time point and in each primate as early as 21 days p.i. No association was found between recombination rates and specific tissue of origin. Several identical breakpoints were identified in sequences derived from different tissues in the same primate and among different primates. Breakpoints predominantly mapped to unpaired nucleotides or pseudoknots in RNA secondary structures, and proximal to glycosylation sites and cysteine residues in protein sequences, suggesting selective advantage in the emergence of specific recombinant sequences. Results indicate that recombinant sequences can become fixed very early after infection with a heterogeneous viral swarm. Features of RNA and protein secondary structure appear to play a role in driving the production of recombinants and their selection in the rapid disease model of neuroAIDS.

Sequence-Based Prediction of DNA-Binding Residues in Proteins with Conservation and Correlation Information

The recognition of DNA-binding residues in proteins is critical to our understanding of the mechanisms of DNA-protein interactions, gene expression, and for guiding drug design. Therefore, a prediction method DNABR (DNA Binding Residues) is proposed for predicting DNA-binding residues in protein sequences using the random forest (RF) classifier with sequence-based features. Two types of novel sequence features are proposed in this study, which reflect the information about the conservation of physicochemical properties of the amino acids, and the correlation of amino acids between different sequence positions in terms of physicochemical properties. The first type of feature uses the evolutionary information combined with the conservation of physicochemical properties of the amino acids while the second reflects the dependency effect of amino acids with regards to polarity charge and hydrophobic properties in the protein sequences. Those two features and an orthogonal binary vector which reflect the characteristics of 20 types of amino acids are used to build the DNABR, a model to predict DNA-binding residues in proteins. The DNABR model achieves a value of 0.6586 for Matthew’s correlation coefficient (MCC) and 93.04 percent overall accuracy (ACC) with a68.47 percent sensitivity (SE) and 98.16 percent specificity (SP), respectively. The comparisons with each feature demonstrate that these two novel features contribute most to the improvement in predictive ability. Furthermore, performance comparisons with other approaches clearly show that DNABR has an excellent prediction performance for detecting binding residues in putative DNA-binding protein. The DNABR web-server system is freely available at http://www.cbi.seu.edu.cn/DNABR/.

Firestar —advances in the prediction of functionally important residues

firestar is a server for predicting catalytic and ligand-binding residues in protein sequences. Here, we present the important developments since the first release of firestar. Previous versions of the server required human interpretation of the results; the server is now fully automatized. firestar has been implemented as a web service and can now be run in high-throughput mode. Prediction coverage has been greatly improved with the extension of the FireDB database and the addition of alignments generated by HHsearch. Ligands in FireDB are now classified for biological relevance. Many of the changes have been motivated by the critical assessment of techniques for protein structure prediction (CASP) ligand-binding prediction experiment, which provided us with a framework to test the performance of firestar. URL: http://firedb.bioinfo.cnio.es/Php/FireStar.php.