In the current era, one of the major challenges is to manage the treatment of drug/antibiotic-resistant strains of bacteria. Phage therapy, a century-old technique, may serve as an alternative to antibiotics in treating bacterial infections caused by drug-resistant strains of bacteria. In this review, a systematic attempt has been made to summarize phage-based therapy in depth. This review has been divided into the following two sections: general information and computer-aided phage therapy (CAPT). In the case of general information, we cover the history of phage therapy, the mechanism of action, the status of phage-based products (approved and clinical trials) and the challenges. This review emphasizes CAPT, where we have covered primary phage-associated resources, phage prediction methods and pipelines. This review covers a wide range of databases and resources, including viral genomes and proteins, phage receptors, host genomes of phages, phage-host interactions and lytic proteins. In the post-genomic era, identifying the most suitable phage for lysing a drug-resistant strain of bacterium is crucial for developing alternate treatments for drug-resistant bacteria and this remains a challenging problem. Thus, we compile all phage-associated prediction methods that include the prediction of phages for a bacterial strain, the host for a phage and the identification of interacting phage-host pairs. Most of these methods have been developed using machine learning and deep learning techniques. This review also discussed recent advances in the field of CAPT, where we briefly describe computational tools available for predicting phage virions, the life cycle of phages and prophage identification. Finally, we describe phage-based therapy's advantages, challenges and opportunities.

There are a number of antigens that induce autoimmune response against β-cells, leading to type 1 diabetes mellitus (T1DM). Recently, several antigen-specific immunotherapies have been developed to treat T1DM. Thus, identification of T1DM associated peptides with antigenic regions or epitopes is important for peptide based-therapeutics (e.g. immunotherapeutic). In this study, for the first time, an attempt has been made to develop a method for predicting, designing, and scanning of T1DM associated peptides with high precision. We analysed 815 T1DM associated peptides and observed that these peptides are not associated with a specific class of HLA alleles. Thus, HLA binder prediction methods are not suitable for predicting T1DM associated peptides. First, we developed a similarity/alignment based method using Basic Local Alignment Search Tool and achieved a high probability of correct hits with poor coverage. Second, we developed an alignment-free method using machine learning techniques and got a maximum AUROC of 0.89 using dipeptide composition. Finally, we developed a hybrid method that combines the strength of both alignment free and alignment-based methods and achieves maximum area under the receiver operating characteristic of 0.95 with Matthew's correlation coefficient of 0.81 on an independent dataset. We developed a web server 'DMPPred' and stand-alone server for predicting, designing and scanning T1DM associated peptides (https://webs.iiitd.edu.in/raghava/dmppred/).

This paper describes a method Pprint2, which is an improved version of Pprint developed for predicting RNA-interacting residues in a protein. Training and independent/validation datasets used in this study comprises of 545 and 161 non-redundant RNA-binding proteins, respectively. All models were trained on training dataset and evaluated on the validation dataset. The preliminary analysis reveals that positively charged amino acids such as H, R and K, are more prominent in the RNA-interacting residues. Initially, machine learning based models have been developed using binary profile and obtain maximum area under curve (AUC) 0.68 on validation dataset. The performance of this model improved significantly from AUC 0.68 to 0.76, when evolutionary profile is used instead of binary profile. The performance of our evolutionary profile-based model improved further from AUC 0.76 to 0.82, when convolutional neural network has been used for developing model. Our final model based on convolutional neural network using evolutionary information achieved AUC 0.82 with Matthews correlation coefficient of 0.49 on the validation dataset. Our best model outperforms existing methods when evaluated on the independent/validation dataset. A user-friendly standalone software and web-based server named 'Pprint2' has been developed for predicting RNA-interacting residues (https://webs.iiitd.edu.in/raghava/pprint2 and https://github.com/raghavagps/pprint2).

Human leukocyte antigens (HLA) regulate various innate and adaptive immune responses and play a crucial immunomodulatory role. Recent studies revealed that non-classical HLA-(HLA-E & HLA-G) based immunotherapies have many advantages over traditional HLA-based immunotherapy, particularly against cancer and COVID-19 infection. In the last two decades, several methods have been developed to predict the binders of classical HLA alleles. In contrast, limited attempts have been made to develop methods for predicting non-classical HLA binding peptides, due to the scarcity of sufficient experimental data. Of note, in order to facilitate the scientific community, we have developed an artificial intelligence-based method for predicting binders of class-Ib HLA alleles. All the models were trained and tested on experimentally validated data obtained from the recent release of IEDB. The machine learning models achieved more than 0.98 AUC for HLA-G alleles on validation dataset. Similarly, our models achieved the highest AUC of 0.96 and 0.94 on the validation dataset for HLA-E*01:01 and HLA-E*01:03, respectively. We have summarized the models developed in the past for non-classical HLA and validated the performance with the models developed in this study. Moreover, to facilitate the community, we have utilized our tool for predicting the potential non-classical HLA binding peptides in the spike protein of different variants of virus causing COVID-19, including Omicron (B.1.1.529). One of the major challenges in the field of immunotherapy is to identify the promiscuous binders or antigenic regions that can bind to a large number of HLA alleles. To predict the promiscuous binders for the non-classical HLA alleles, we developed a web server HLAncPred (https://webs.iiitd.edu.in/raghava/hlancpred) and standalone package.

DNA-protein interaction is one of the most crucial interactions in the biological system, which decides the fate of many processes such as transcription, regulation and splicing of genes. In this study, we trained our models on a training dataset of 646 DNA-binding proteins having 15 636 DNA interacting and 298 503 non-interacting residues. Our trained models were evaluated on an independent dataset of 46 DNA-binding proteins having 965 DNA interacting and 9911 non-interacting residues. All proteins in the independent dataset have less than 30% of sequence similarity with proteins in the training dataset. A wide range of traditional machine learning and deep learning (1D-CNN) techniques-based models have been developed using binary, physicochemical properties and Position-Specific Scoring Matrix (PSSM)/evolutionary profiles. In the case of machine learning technique, eXtreme Gradient Boosting-based model achieved a maximum area under the receiver operating characteristics (AUROC) curve of 0.77 on the independent dataset using PSSM profile. Deep learning-based model achieved the highest AUROC of 0.79 on the independent dataset using a combination of all three profiles. We evaluated the performance of existing methods on the independent dataset and observed that our proposed method outperformed all the existing methods. In order to facilitate scientific community, we developed standalone software and web server, which are accessible from https://webs.iiitd.edu.in/raghava/dbpred.

Proteins/peptides have shown to be promising therapeutic agents for a variety of diseases. However, toxicity is one of the obstacles in protein/peptide-based therapy. The current study describes a web-based tool, ToxinPred2, developed for predicting the toxicity of proteins. This is an update of ToxinPred developed mainly for predicting toxicity of peptides and small proteins. The method has been trained, tested and evaluated on three datasets curated from the recent release of the SwissProt. To provide unbiased evaluation, we performed internal validation on 80% of the data and external validation on the remaining 20% of data. We have implemented the following techniques for predicting protein toxicity; (i) Basic Local Alignment Search Tool-based similarity, (ii) Motif-EmeRging and with Classes-Identification-based motif search and (iii) Prediction models. Similarity and motif-based techniques achieved a high probability of correct prediction with poor sensitivity/coverage, whereas models based on machine-learning techniques achieved balance sensitivity and specificity with reasonably high accuracy. Finally, we developed a hybrid method that combined all three approaches and achieved a maximum area under receiver operating characteristic curve around 0.99 with Matthews correlation coefficient 0.91 on the validation dataset. In addition, we developed models on alternate and realistic datasets. The best machine learning models have been implemented in the web server named 'ToxinPred2', which is available at https://webs.iiitd.edu.in/raghava/toxinpred2/ and a standalone version at https://github.com/raghavagps/toxinpred2. This is a general method developed for predicting the toxicity of proteins regardless of their source of origin.

Increasing use of therapeutic peptides for treating cancer has received considerable attention of the scientific community in the recent years. The present study describes the in silico model developed for predicting and designing anticancer peptides (ACPs). ACPs residue composition analysis show the preference of A, F, K, L and W. Positional preference analysis revealed that residues A, F and K are favored at N-terminus and residues L and K are preferred at C-terminus. Motif analysis revealed the presence of motifs like LAKLA, AKLAK, FAKL and LAKL in ACPs. Machine learning models were developed using various input features and implementing different machine learning classifiers on two datasets main and alternate dataset. In the case of main dataset, dipeptide composition based ETree classifier model achieved maximum Matthews correlation coefficient (MCC) of 0.51 and 0.83 area under receiver operating characteristics (AUROC) on the training dataset. In the case of alternate dataset, amino acid composition based ETree classifier performed best and achieved the highest MCC of 0.80 and AUROC of 0.97 on the training dataset. Five-fold cross-validation technique was implemented for model training and testing, and their performance was also evaluated on the validation dataset. Best models were implemented in the webserver AntiCP 2.0, which is freely available at https://webs.iiitd.edu.in/raghava/anticp2/. The webserver is compatible with multiple screens such as iPhone, iPad, laptop and android phones. The standalone version of the software is available at GitHub; docker-based container also developed.

Interleukin 6 (IL-6) is a pro-inflammatory cytokine that stimulates acute phase responses, hematopoiesis and specific immune reactions. Recently, it was found that the IL-6 plays a vital role in the progression of COVID-19, which is responsible for the high mortality rate. In order to facilitate the scientific community to fight against COVID-19, we have developed a method for predicting IL-6 inducing peptides/epitopes. The models were trained and tested on experimentally validated 365 IL-6 inducing and 2991 non-inducing peptides extracted from the immune epitope database. Initially, 9149 features of each peptide were computed using Pfeature, which were reduced to 186 features using the SVC-L1 technique. These features were ranked based on their classification ability, and the top 10 features were used for developing prediction models. A wide range of machine learning techniques has been deployed to develop models. Random Forest-based model achieves a maximum AUROC of 0.84 and 0.83 on training and independent validation dataset, respectively. We have also identified IL-6 inducing peptides in different proteins of SARS-CoV-2, using our best models to design vaccine against COVID-19. A web server named as IL-6Pred and a standalone package has been developed for predicting, designing and screening of IL-6 inducing peptides (https://webs.iiitd.edu.in/raghava/il6pred/).

Dengue virus (DENV) researchers often face challenges with the highly time-consuming process of collecting and curating information on known inhibitors during the standard drug discovery process. To this end, however, required collective information is not yet available on a single platform. Hence, we have developed the DenvInD database for experimentally validated DENV inhibitors against its known targets presently hosted at https://webs.iiitd.edu.in/raghava/denvind/. This database provides comprehensive information, i.e. PubChem IDs, SMILES, IC50, EC50, CC50, and wherever available Ki values of the 484 compounds in vitro validated as inhibitors against respective drug targets of DENV. Also, the DenvInD database has been linked to the user-friendly web-based interface and accessibility features, such as simple search, advanced search and data browsing. All the required data curation was conducted manually from the reported scientific literature and PubChem. The collected information was then organized into the DenvInD database using sequence query language under user interface by hypertext markup language. DenvInD is the first useful repository of its kind which would augment the DENV drug discovery research by providing essential information on known DENV inhibitors for molecular docking, computational screening, pharmacophore modeling and quantitative structure-activity relationship modeling.

AlgPred 2.0 is a web server developed for predicting allergenic proteins and allergenic regions in a protein. It is an updated version of AlgPred developed in 2006. The dataset used for training, testing and validation consists of 10 075 allergens and 10 075 non-allergens. In addition, 10 451 experimentally validated immunoglobulin E (IgE) epitopes were used to identify antigenic regions in a protein. All models were trained on 80% of data called training dataset, and the performance of models was evaluated using 5-fold cross-validation technique. The performance of the final model trained on the training dataset was evaluated on 20% of data called validation dataset; no two proteins in any two sets have more than 40% similarity. First, a Basic Local Alignment Search Tool (BLAST) search has been performed against the dataset, and allergens were predicted based on the level of similarity with known allergens. Second, IgE epitopes obtained from the IEDB database were searched in the dataset to predict allergens based on their presence in a protein. Third, motif-based approaches like multiple EM for motif elicitation/motif alignment and search tool have been used to predict allergens. Fourth, allergen prediction models have been developed using a wide range of machine learning techniques. Finally, the ensemble approach has been used for predicting allergenic protein by combining prediction scores of different approaches. Our best model achieved maximum performance in terms of area under receiver operating characteristic curve 0.98 with Matthew's correlation coefficient 0.85 on the validation dataset. A web server AlgPred 2.0 has been developed that allows the prediction of allergens, mapping of IgE epitope, motif search and BLAST search (https://webs.iiitd.edu.in/raghava/algpred2/).

BACKGROUND: Molecular docking studies on protein-peptide interactions are a challenging and time-consuming task because peptides are generally more flexible than proteins and tend to adopt numerous conformations. There are several benchmarking studies on protein-protein, protein-ligand and nucleic acid-ligand docking interactions. However, a series of docking methods is not rigorously validated for protein-peptide complexes in the literature. Considering the importance and wide application of peptide docking, we describe benchmarking of 6 docking methods on 133 protein-peptide complexes having peptide length between 9 to 15 residues. The performance of docking methods was evaluated using CAPRI parameters like FNAT, I-RMSD, L-RMSD. RESULT: Firstly, we performed blind docking and evaluate the performance of the top docking pose of each method. It was observed that FRODOCK performed better than other methods with average L-RMSD of 12.46 Å. The performance of all methods improved significantly for their best docking pose and achieved highest average L-RMSD of 3.72 Å in case of FRODOCK. Similarly, we performed re-docking and evaluated the performance of the top and best docking pose of each method. We achieved the best performance in case of ZDOCK with average L-RMSD 8.60 Å and 2.88 Å for the top and best docking pose respectively. Methods were also evaluated on 40 protein-peptide complexes used in the previous benchmarking study, where peptide have length up to 5 residues. In case of best docking pose, we achieved the highest average L-RMSD of 4.45 Å and 2.09 Å for the blind docking using FRODOCK and re-docking using AutoDock Vina respectively. CONCLUSION: The study shows that FRODOCK performed best in case of blind docking and ZDOCK in case of re-docking. There is a need to improve the ranking of docking pose generated by different methods, as the present ranking scheme is not satisfactory. To facilitate the scientific community for calculating CAPRI parameters between native and docked complexes, we developed a web-based service named PPDbench ( http://webs.iiitd.edu.in/raghava/ppdbench/ ).

The conventional approach for designing vaccine against a particular disease involves stimulation of the immune system using the whole pathogen responsible for the disease. In the post-genomic era, a major challenge is to identify antigenic regions or epitopes that can stimulate different arms of the immune system. In the past two decades, numerous methods and databases have been developed for designing vaccine or immunotherapy against various pathogen-causing diseases. This review describes various computational resources important for designing subunit vaccines or epitope-based immunotherapy. First, different immunological databases are described that maintain epitopes, antigens and vaccine targets. This is followed by in silico tools used for predicting linear and conformational B-cell epitopes required for activating humoral immunity. Finally, information on T-cell epitope prediction methods is provided that includes indirect methods like prediction of Major Histocompatibility Complex and transporter-associated protein binders. Different studies for validating the predicted epitopes are also examined critically. This review enlists novel in silico resources and tools available for predicting humoral and cell-mediated immune potential. These predicted epitopes could be used for designing epitope-based vaccines or immunotherapy as they may activate the adaptive immunity. Authors emphasized the need to develop tools for the prediction of adjuvants to activate innate and adaptive immune system simultaneously. In addition, attention has also been given to novel prediction methods to predict general therapeutic properties of peptides like half-life, cytotoxicity and immune toxicity.

BACKGROUND: In past number of methods have been developed for predicting post-translational modifications in proteins. In contrast, limited attempt has been made to understand post-transcriptional modifications. Recently it has been shown that tRNA modifications play direct role in the genome structure and codon usage. This study is an attempt to understand kingdom-wise tRNA modifications particularly uridine modifications (UMs), as majority of modifications are uridine-derived. RESULTS: A three-steps strategy has been applied to develop an efficient method for the prediction of UMs. In the first step, we developed a common prediction model for all the kingdoms using a dataset from MODOMICS-2008. Support Vector Machine (SVM) based prediction models were developed and evaluated by five-fold cross-validation technique. Different approaches were applied and found that a hybrid approach of binary and structural information achieved highest Area under the curve (AUC) of 0.936. In the second step, we used newly added tRNA sequences (as independent dataset) of MODOMICS-2012 for the kingdom-wise prediction performance evaluation of previously developed (in the first step) common model and achieved performances between the AUC of 0.910 to 0.949. In the third and last step, we used different datasets from MODOMICS-2012 for the kingdom-wise individual prediction models development and achieved performances between the AUC of 0.915 to 0.987. CONCLUSIONS: The hybrid approach is efficient not only to predict kingdom-wise modifications but also to classify them into two most prominent UMs: Pseudouridine (Y) and Dihydrouridine (D). A webserver called tRNAmod (http://crdd.osdd.net/raghava/trnamod/) has been developed, which predicts UMs from both tRNA sequences and whole genome.

BACKGROUND: In past, a number of peptides have been reported to possess highly diverse properties ranging from cell penetrating, tumor homing, anticancer, anti-hypertensive, antiviral to antimicrobials. Owing to their excellent specificity, low-toxicity, rich chemical diversity and availability from natural sources, FDA has successfully approved a number of peptide-based drugs and several are in various stages of drug development. Though peptides are proven good drug candidates, their usage is still hindered mainly because of their high susceptibility towards proteases degradation. We have developed an in silico method to predict the half-life of peptides in intestine-like environment and to design better peptides having optimized physicochemical properties and half-life. RESULTS: In this study, we have used 10mer (HL10) and 16mer (HL16) peptides dataset to develop prediction models for peptide half-life in intestine-like environment. First, SVM based models were developed on HL10 dataset which achieved maximum correlation R/R2 of 0.57/0.32, 0.68/0.46, and 0.69/0.47 using amino acid, dipeptide and tripeptide composition, respectively. Secondly, models developed on HL16 dataset showed maximum R/R2 of 0.91/0.82, 0.90/0.39, and 0.90/0.31 using amino acid, dipeptide and tripeptide composition, respectively. Furthermore, models that were developed on selected features, achieved a correlation (R) of 0.70 and 0.98 on HL10 and HL16 dataset, respectively. Preliminary analysis suggests the role of charged residue and amino acid size in peptide half-life/stability. Based on above models, we have developed a web server named HLP (Half Life Prediction), for predicting and designing peptides with desired half-life. The web server provides three facilities; i) half-life prediction, ii) physicochemical properties calculation and iii) designing mutant peptides. CONCLUSION: In summary, this study describes a web server 'HLP' that has been developed for assisting scientific community for predicting intestinal half-life of peptides and to design mutant peptides with better half-life and physicochemical properties. HLP models were trained using a dataset of peptides whose half-lives have been determined experimentally in crude intestinal proteases preparation. Thus, HLP server will help in designing peptides possessing the potential to be administered via oral route (http://www.imtech.res.in/raghava/hlp/).

BACKGROUND: Dicer, an RNase III enzyme, plays a vital role in the processing of pre-miRNAs for generating the miRNAs. The structural and sequence features on pre-miRNA which can facilitate position and efficiency of cleavage are not well known. A precise cleavage by Dicer is crucial because an inaccurate processing can produce miRNA with different seed regions which can alter the repertoire of target genes. RESULTS: In this study, a novel method has been developed to predict Dicer cleavage sites on pre-miRNAs using Support Vector Machine. We used the dataset of experimentally validated human miRNA hairpins from miRBase, and extracted fourteen nucleotides around Dicer cleavage sites. We developed number of models using various types of features and achieved maximum accuracy of 66% using binary profile of nucleotide sequence taken from 5p arm of hairpin. The prediction performance of Dicer cleavage site improved significantly from 66% to 86% when we integrated secondary structure information. This indicates that secondary structure plays an important role in the selection of cleavage site. All models were trained and tested on 555 experimentally validated cleavage sites and evaluated using 5-fold cross validation technique. In addition, the performance was also evaluated on an independent testing dataset that achieved an accuracy of ~82%. CONCLUSION: Based on this study, we developed a webserver PHDcleav (http://www.imtech.res.in/raghava/phdcleav/) to predict Dicer cleavage sites in pre-miRNA. This tool can be used to investigate functional consequences of genetic variations/SNPs in miRNA on Dicer cleavage site, and gene silencing. Moreover, it would also be useful in the discovery of miRNAs in human genome and design of Dicer specific pre-miRNAs for potent gene silencing.

BACKGROUND: The vitamins are important cofactors in various enzymatic-reactions. In past, many inhibitors have been designed against vitamin binding pockets in order to inhibit vitamin-protein interactions. Thus, it is important to identify vitamin interacting residues in a protein. It is possible to detect vitamin-binding pockets on a protein, if its tertiary structure is known. Unfortunately tertiary structures of limited proteins are available. Therefore, it is important to develop in-silico models for predicting vitamin interacting residues in protein from its primary structure. RESULTS: In this study, first we compared protein-interacting residues of vitamins with other ligands using Two Sample Logo (TSL). It was observed that ATP, GTP, NAD, FAD and mannose preferred {G,R,K,S,H}, {G,K,T,S,D,N}, {T,G,Y}, {G,Y,W} and {Y,D,W,N,E} residues respectively, whereas vitamins preferred {Y,F,S,W,T,G,H} residues for the interaction with proteins. Furthermore, compositional information of preferred and non-preferred residues along with patterns-specificity was also observed within different vitamin-classes. Vitamins A, B and B6 preferred {F,I,W,Y,L,V}, {S,Y,G,T,H,W,N,E} and {S,T,G,H,Y,N} interacting residues respectively. It suggested that protein-binding patterns of vitamins are different from other ligands, and motivated us to develop separate predictor for vitamins and their sub-classes. The four different prediction modules, (i) vitamin interacting residues (VIRs), (ii) vitamin-A interacting residues (VAIRs), (iii) vitamin-B interacting residues (VBIRs) and (iv) pyridoxal-5-phosphate (vitamin B6) interacting residues (PLPIRs) have been developed. We applied various classifiers of SVM, BayesNet, NaiveBayes, ComplementNaiveBayes, NaiveBayesMultinomial, RandomForest and IBk etc., as machine learning techniques, using binary and Position-Specific Scoring Matrix (PSSM) features of protein sequences. Finally, we selected best performing SVM modules and obtained highest MCC of 0.53, 0.48, 0.61, 0.81 for VIRs, VAIRs, VBIRs, PLPIRs respectively, using PSSM-based evolutionary information. All the modules developed in this study have been trained and tested on non-redundant datasets and evaluated using five-fold cross-validation technique. The performances were also evaluated on the balanced and different independent datasets. CONCLUSIONS: This study demonstrates that it is possible to predict VIRs, VAIRs, VBIRs and PLPIRs from evolutionary information of protein sequence. In order to provide service to the scientific community, we have developed web-server and standalone software VitaPred (http://crdd.osdd.net/raghava/vitapred/).

BACKGROUND: Small molecular cofactors or ligands play a crucial role in the proper functioning of cells. Accurate annotation of their target proteins and binding sites is required for the complete understanding of reaction mechanisms. Nicotinamide adenine dinucleotide (NAD+ or NAD) is one of the most commonly used organic cofactors in living cells, which plays a critical role in cellular metabolism, storage and regulatory processes. In the past, several NAD binding proteins (NADBP) have been reported in the literature, which are responsible for a wide-range of activities in the cell. Attempts have been made to derive a rule for the binding of NAD+ to its target proteins. However, so far an efficient model could not be derived due to the time consuming process of structure determination, and limitations of similarity based approaches. Thus a sequence and non-similarity based method is needed to characterize the NAD binding sites to help in the annotation. In this study attempts have been made to predict NAD binding proteins and their interacting residues (NIRs) from amino acid sequence using bioinformatics tools. RESULTS: We extracted 1556 proteins chains from 555 NAD binding proteins whose structure is available in Protein Data Bank. Then we removed all redundant protein chains and finally obtained 195 non-redundant NAD binding protein chains, where no two chains have more than 40% sequence identity. In this study all models were developed and evaluated using five-fold cross validation technique on the above dataset of 195 NAD binding proteins. While certain type of residues are preferred (e.g. Gly, Tyr, Thr, His) in NAD interaction, residues like Ala, Glu, Leu, Lys are not preferred. A support vector machine (SVM) based method has been developed using various window lengths of amino acid sequence for predicting NAD interacting residues and obtained maximum Matthew's correlation coefficient (MCC) 0.47 with accuracy 74.13% at window length 17. We also developed a SVM based method using evolutionary information in the form of position specific scoring matrix (PSSM) and obtained maximum MCC 0.75 with accuracy 87.25%. CONCLUSION: For the first time a sequence-based method has been developed for the prediction of NAD binding proteins and their interacting residues, in the absence of any prior structural information. The present model will aid in the understanding of NAD+ dependent mechanisms of action in the cell. To provide service to the scientific community, we have developed a user-friendly web server, which is available from URL http://www.imtech.res.in/raghava/nadbinder/.

BACKGROUND: Guanosine triphosphate (GTP)-binding proteins play an important role in regulation of G-protein. Thus prediction of GTP interacting residues in a protein is one of the major challenges in the field of the computational biology. In this study, an attempt has been made to develop a computational method for predicting GTP interacting residues in a protein with high accuracy (Acc), precision (Prec) and recall (Rc). RESULT: All the models developed in this study have been trained and tested on a non-redundant (40% similarity) dataset using five-fold cross-validation. Firstly, we have developed neural network based models using single sequence and PSSM profile and achieved maximum Matthews Correlation Coefficient (MCC) 0.24 (Acc 61.30%) and 0.39 (Acc 68.88%) respectively. Secondly, we have developed a support vector machine (SVM) based models using single sequence and PSSM profile and achieved maximum MCC 0.37 (Prec 0.73, Rc 0.57, Acc 67.98%) and 0.55 (Prec 0.80, Rc 0.73, Acc 77.17%) respectively. In this work, we have introduced a new concept of predicting GTP interacting dipeptide (two consecutive GTP interacting residues) and tripeptide (three consecutive GTP interacting residues) for the first time. We have developed SVM based model for predicting GTP interacting dipeptides using PSSM profile and achieved MCC 0.64 with precision 0.87, recall 0.74 and accuracy 81.37%. Similarly, SVM based model have been developed for predicting GTP interacting tripeptides using PSSM profile and achieved MCC 0.70 with precision 0.93, recall 0.73 and accuracy 83.98%. CONCLUSION: These results show that PSSM based method performs better than single sequence based method. The prediction models based on dipeptides or tripeptides are more accurate than the traditional model based on single residue. A web server "GTPBinder" http://www.imtech.res.in/raghava/gtpbinder/ based on above models has been developed for predicting GTP interacting residues in a protein.

BACKGROUND: Identification of novel drug targets and their inhibitors is a major challenge in the field of drug designing and development. Diaminopimelic acid (DAP) pathway is a unique lysine biosynthetic pathway present in bacteria, however absent in mammals. This pathway is vital for bacteria due to its critical role in cell wall biosynthesis. One of the essential enzymes of this pathway is dihydrodipicolinate synthase (DHDPS), considered to be crucial for the bacterial survival. In view of its importance, the development and prediction of potent inhibitors against DHDPS may be valuable to design effective drugs against bacteria, in general. RESULTS: This paper describes a methodology for predicting novel/potent inhibitors against DHDPS. Here, quantitative structure activity relationship (QSAR) models were trained and tested on experimentally verified 23 enzyme's inhibitors having inhibitory value (Ki) in the range of 0.005-22(mM). These inhibitors were docked at the active site of DHDPS (1YXD) using AutoDock software, which resulted in 11 energy-based descriptors. For QSAR modeling, Multiple Linear Regression (MLR) model was engendered using best four energy-based descriptors yielding correlation values R/q2 of 0.82/0.67 and MAE of 2.43. Additionally, Support Vector Machine (SVM) based model was developed with three crucial descriptors selected using F-stepping remove-one approach, which enhanced the performance by attaining R/q2 values of 0.93/0.80 and MAE of 1.89. To validate the performance of QSAR models, external cross-validation procedure was adopted which accomplished high training/testing correlation values (q2/r2) in the range of 0.78-0.83/0.93-0.95. CONCLUSIONS: Our results suggests that ligand-receptor binding interactions for DHDPS employing QSAR modeling seems to be a promising approach for prediction of antibacterial agents. To serve the experimentalist to develop novel/potent inhibitors, a webserver "KiDoQ" has been developed http://crdd.osdd.net/raghava/kidoq, which allows the prediction of Ki value of a new ligand molecule against DHDPS.

BACKGROUND: An explosive global spreading of multidrug resistant Mycobacterium tuberculosis (Mtb) is a catastrophe, which demands an urgent need to design or develop novel/potent antitubercular agents. The Lysine/DAP biosynthetic pathway is a promising target due its specific role in cell wall and amino acid biosynthesis. Here, we report identification of potential antitubercular candidates targeting Mtb dihydrodipicolinate synthase (DHDPS) enzyme of the pathway using virtual screening protocols. RESULTS: In the present study, we generated three sets of drug-like molecules in order to screen potential inhibitors against Mtb drug target DHDPS. The first set of compounds was a combinatorial library, which comprised analogues of pyruvate (substrate of DHDPS). The second set of compounds consisted of pyruvate-like molecules i.e. structurally similar to pyruvate, obtained using 3D flexible similarity search against NCI and PubChem database. The third set constituted 3847 anti-infective molecules obtained from PubChem. These compounds were subjected to Lipinski's rule of drug-like five filters. Finally, three sets of drug-like compounds i.e. 4088 pyruvate analogues, 2640 pyruvate-like molecules and 1750 anti-infective molecules were docked at the active site of Mtb DHDPS (PDB code: 1XXX used in the molecular docking calculations) to select inhibitors establishing favorable interactions. CONCLUSION: The above-mentioned virtual screening procedures helped in the identification of several potent candidates that possess inhibitory activity against Mtb DHDPS. Therefore, these novel scaffolds/candidates which could have the potential to inhibit Mtb DHDPS enzyme would represent promising starting points as lead compounds and certainly aid the experimental designing of antituberculars in lesser time.

BACKGROUND: Antibacterial peptides are one of the effecter molecules of innate immune system. Over the last few decades several antibacterial peptides have successfully approved as drug by FDA, which has prompted an interest in these antibacterial peptides. In our recent study we analyzed 999 antibacterial peptides, which were collected from Antibacterial Peptide Database (APD). We have also developed methods to predict and classify these antibacterial peptides using Support Vector Machine (SVM). RESULTS: During analysis we observed that certain residues are preferred over other in antibacterial peptide, particularly at the N and C terminus. These observation and increased data of antibacterial peptide in APD encouraged us to again develop a new and more robust method for predicting antibacterial peptides in protein from their amino acid sequence or given peptide have antibacterial properties or not. First, the binary patterns of the 15 N terminus residues were used for predicting antibacterial peptide using SVM and achieved accuracy of 85.46% with 0.705 Mathew's Correlation Coefficient (MCC). Then we used the binary pattern of 15 C terminus residues and achieved accuracy of 85.05% with 0.701 MCC, latter on we developed prediction method by combining N & C terminus and achieved an accuracy of 91.64% with 0.831 MCC. Finally we developed SVM based model using amino acid composition of whole peptide and achieved 92.14% accuracy with MCC 0.843. In this study we used five-fold cross validation technique to develop all these models and tested the performance of these models on an independent dataset. We further classify antibacterial peptides according to their sources and achieved an overall accuracy of 98.95%. We further classify antibacterial peptides in their respective family and got a satisfactory result. CONCLUSION: Among antibacterial peptides, there is preference for certain residues at N and C terminus, which helps to discriminate them from non-antibacterial peptides. Amino acid composition of antibacterial peptides helps to demarcate them from non-antibacterial peptide and their further classification in source and family. Antibp2 will be helpful in discovering efficacious antibacterial peptide, which we hope will be helpful against antibiotics resistant bacteria. We also developed user friendly web server for the biological community.

BACKGROUND: Flavin binding proteins (FBP) plays a critical role in several biological functions such as electron transport system (ETS). These flavoproteins contain very tightly bound, sometimes covalently, flavin adenine dinucleotide (FAD) or flavin mono nucleotide (FMN). The interaction between flavin nucleotide and amino acids of flavoprotein is essential for their functionality. Thus identification of FAD interacting residues in a FBP is an important step for understanding their function and mechanism. RESULTS: In this study, we describe models developed for predicting FAD interacting residues using 15, 17 and 19 window pattern. Support vector machine (SVM) based models have been developed using binary pattern of amino acid sequence of protein and achieved maximum accuracy 69.65% with Mathew's Correlation Coefficient (MCC) 0.39 and Area Under Curve (AUC) 0.773. The performance of these models have been improved significantly from 69.65% to 82.86% with MCC 0.66 and AUC 0.904, when evolutionary information is used as input in SVM. The evolutionary information was generated in form of position specific score matrix (PSSM) profile by using PSI-BLAST at e-value 0.001. All models were developed on 198 non-redundant FAD binding protein chains containing 5172 FAD interacting residues and evaluated using fivefold cross-validation technique. CONCLUSION: This study suggests that evolutionary information of 17 amino acid patterns perform best for FAD interacting residues prediction. We also developed a web server which predicts FAD interacting residues in a protein which is freely available for academics.

BACKGROUND: MicroRNAs (miRNAs) are produced by the sequential processing of a long hairpin RNA transcript by Drosha and Dicer, an RNase III enzymes, and form transitory small RNA duplexes. One strand of the duplex, which incorporates into RNA-induced silencing complex (RISC) and silences the gene expression is called guide strand, or miRNA; while the other strand of duplex is degraded and called the passenger strand, or miRNA*. Predicting the guide strand of miRNA is important for better understanding the RNA interference pathways. RESULTS: This paper describes support vector machine (SVM) models developed for predicting the guide strands of miRNAs. All models were trained and tested on a dataset consisting of 329 miRNA and 329 miRNA* pairs using five fold cross validation technique. Firstly, models were developed using mono-, di-, and tri-nucleotide composition of miRNA strands and achieved the highest accuracies of 0.588, 0.638 and 0.596 respectively. Secondly, models were developed using split nucleotide composition and achieved maximum accuracies of 0.553, 0.641 and 0.602 for mono-, di-, and tri-nucleotide respectively. Thirdly, models were developed using binary pattern and achieved the highest accuracy of 0.708. Furthermore, when integrating the secondary structure features with binary pattern, an accuracy of 0.719 was seen. Finally, hybrid models were developed by combining various features and achieved maximum accuracy of 0.799 with sensitivity 0.781 and specificity 0.818. Moreover, the performance of this model was tested on an independent dataset that achieved an accuracy of 0.80. In addition, we also compared the performance of our method with various siRNA-designing methods on miRNA and siRNA datasets. CONCLUSION: In this study, first time a method has been developed to predict guide miRNA strands, of miRNA duplex. This study demonstrates that guide and passenger strand of miRNA precursors can be distinguished using their nucleotide sequence and secondary structure. This method will be useful in understanding microRNA processing and can be implemented in RNA silencing technology to improve the biological and clinical research. A web server has been developed based on SVM models described in this study (http://crdd.osdd.net:8081/RISCbinder/).

BACKGROUND: One of the major challenges in post-genomic era is to provide functional annotations for large number of proteins arising from genome sequencing projects. The function of many proteins depends on their interaction with small molecules or ligands. ATP is one such important ligand that plays critical role as a coenzyme in the functionality of many proteins. There is a need to develop method for identifying ATP interacting residues in a ATP binding proteins (ABPs), in order to understand mechanism of protein-ligands interaction. RESULTS: We have compared the amino acid composition of ATP interacting and non-interacting regions of proteins and observed that certain residues are preferred for interaction with ATP. This study describes few models that have been developed for identifying ATP interacting residues in a protein. All these models were trained and tested on 168 non-redundant ABPs chains. First we have developed a Support Vector Machine (SVM) based model using primary sequence of proteins and obtained maximum MCC 0.33 with accuracy of 66.25%. Secondly, another SVM based model was developed using position specific scoring matrix (PSSM) generated by PSI-BLAST. The performance of this model was improved significantly (MCC 0.5) from the previous one, where only the primary sequence of the proteins were used. CONCLUSION: This study demonstrates that it is possible to predict 'ATP interacting residues' in a protein with moderate accuracy using its sequence. The evolutionary information is important for the identification of 'ATP interacting residues', as it provides more information compared to the primary sequence. This method will be useful for researchers studying ATP-binding proteins. Based on this study, a web server has been developed for predicting 'ATP interacting residues' in a protein http://www.imtech.res.in/raghava/atpint/.

BACKGROUND: The nucleus, a highly organized organelle, plays important role in cellular homeostasis. The nuclear proteins are crucial for chromosomal maintenance/segregation, gene expression, RNA processing/export, and many other processes. Several methods have been developed for predicting the nuclear proteins in the past. The aim of the present study is to develop a new method for predicting nuclear proteins with higher accuracy. RESULTS: All modules were trained and tested on a non-redundant dataset and evaluated using five-fold cross-validation technique. Firstly, Support Vector Machines (SVM) based modules have been developed using amino acid and dipeptide compositions and achieved a Mathews correlation coefficient (MCC) of 0.59 and 0.61 respectively. Secondly, we have developed SVM modules using split amino acid compositions (SAAC) and achieved the maximum MCC of 0.66. Thirdly, a hidden Markov model (HMM) based module/profile was developed for searching exclusively nuclear and non-nuclear domains in a protein. Finally, a hybrid module was developed by combining SVM module and HMM profile and achieved a MCC of 0.87 with an accuracy of 94.61%. This method performs better than the existing methods when evaluated on blind/independent datasets. Our method estimated 31.51%, 21.89%, 26.31%, 25.72% and 24.95% of the proteins as nuclear proteins in Saccharomyces cerevisiae, Caenorhabditis elegans, Drosophila melanogaster, mouse and human proteomes respectively. Based on the above modules, we have developed a web server NpPred for predicting nuclear proteins http://www.imtech.res.in/raghava/nppred/. CONCLUSION: This study describes a highly accurate method for predicting nuclear proteins. SVM module has been developed for the first time using SAAC for predicting nuclear proteins, where amino acid composition of N-terminus and the remaining protein were computed separately. In addition, our study is a first documentation where exclusively nuclear and non-nuclear domains have been identified and used for predicting nuclear proteins. The performance of the method improved further by combining both approaches together.

BACKGROUND: The expansion of raw protein sequence databases in the post genomic era and availability of fresh annotated sequences for major localizations particularly motivated us to introduce a new improved version of our previously forged eukaryotic subcellular localizations prediction method namely "ESLpred". Since, subcellular localization of a protein offers essential clues about its functioning, hence, availability of localization predictor would definitely aid and expedite the protein deciphering studies. However, robustness of a predictor is highly dependent on the superiority of dataset and extracted protein attributes; hence, it becomes imperative to improve the performance of presently available method using latest dataset and crucial input features. RESULTS: Here, we describe augmentation in the prediction performance obtained for our most popular ESLpred method using new crucial features as an input to Support Vector Machine (SVM). In addition, recently available, highly non-redundant dataset encompassing three kingdoms specific protein sequence sets; 1198 fungi sequences, 2597 from animal and 491 plant sequences were also included in the present study. First, using the evolutionary information in the form of profile composition along with whole and N-terminal sequence composition as an input feature vector of 440 dimensions, overall accuracies of 72.7, 75.8 and 74.5% were achieved respectively after five-fold cross-validation. Further, enhancement in performance was observed when similarity search based results were coupled with whole and N-terminal sequence composition along with profile composition by yielding overall accuracies of 75.9, 80.8, 76.6% respectively; best accuracies reported till date on the same datasets. CONCLUSION: These results provide confidence about the reliability and accurate prediction of SVM modules generated in the present study using sequence and profile compositions along with similarity search based results. The presently developed modules are implemented as web server "ESLpred2" available at http://www.imtech.res.in/raghava/eslpred2/.

BACKGROUND: Malaria parasite secretes various proteins in infected RBC for its growth and survival. Thus identification of these secretory proteins is important for developing vaccine/drug against malaria. The existing motif-based methods have got limited success due to lack of universal motif in all secretory proteins of malaria parasite. RESULTS: In this study a systematic attempt has been made to develop a general method for predicting secretory proteins of malaria parasite. All models were trained and tested on a non-redundant dataset of 252 secretory and 252 non-secretory proteins. We developed SVM models and achieved maximum MCC 0.72 with 85.65% accuracy and MCC 0.74 with 86.45% accuracy using amino acid and dipeptide composition respectively. SVM models were developed using split-amino acid and split-dipeptide composition and achieved maximum MCC 0.74 with 86.40% accuracy and MCC 0.77 with accuracy 88.22% respectively. In this study, for the first time PSSM profiles obtained from PSI-BLAST, have been used for predicting secretory proteins. We achieved maximum MCC 0.86 with 92.66% accuracy using PSSM based SVM model. All models developed in this study were evaluated using 5-fold cross-validation technique. CONCLUSION: This study demonstrates that secretory proteins have different residue composition than non-secretory proteins. Thus, it is possible to predict secretory proteins from its residue composition-using machine learning technique. The multiple sequence alignment provides more information than sequence itself. Thus performance of method based on PSSM profile is more accurate than method based on sequence composition. A web server PSEApred has been developed for predicting secretory proteins of malaria parasites,the URL can be found in the Availability and requirements section.

BACKGROUND: Identification of DNA-binding proteins is one of the major challenges in the field of genome annotation, as these proteins play a crucial role in gene-regulation. In this paper, we developed various SVM modules for predicting DNA-binding domains and proteins. All models were trained and tested on multiple datasets of non-redundant proteins. RESULTS: SVM models have been developed on DNAaset, which consists of 1153 DNA-binding and equal number of non DNA-binding proteins, and achieved the maximum accuracy of 72.42% and 71.59% using amino acid and dipeptide compositions, respectively. The performance of SVM model improved from 72.42% to 74.22%, when evolutionary information in form of PSSM profiles was used as input instead of amino acid composition. In addition, SVM models have been developed on DNAset, which consists of 146 DNA-binding and 250 non-binding chains/domains, and achieved the maximum accuracy of 79.80% and 86.62% using amino acid composition and PSSM profiles. The SVM models developed in this study perform better than existing methods on a blind dataset. CONCLUSION: A highly accurate method has been developed for predicting DNA-binding proteins using SVM and PSSM profiles. This is the first study in which evolutionary information in form of PSSM profiles has been used successfully for predicting DNA-binding proteins. A web-server DNAbinder has been developed for identifying DNA-binding proteins and domains from query amino acid sequences http://www.imtech.res.in/raghava/dnabinder/.

BACKGROUND: Antibacterial peptides are important components of the innate immune system, used by the host to protect itself from different types of pathogenic bacteria. Over the last few decades, the search for new drugs and drug targets has prompted an interest in these antibacterial peptides. We analyzed 486 antibacterial peptides, obtained from antimicrobial peptide database APD, in order to understand the preference of amino acid residues at specific positions in these peptides. RESULTS: It was observed that certain types of residues are preferred over others in antibacterial peptides, particularly at the N and C terminus. These observations encouraged us to develop a method for predicting antibacterial peptides in proteins from their amino acid sequence. First, the N-terminal residues were used for predicting antibacterial peptides using Artificial Neural Network (ANN), Quantitative Matrices (QM) and Support Vector Machine (SVM), which resulted in an accuracy of 83.63%, 84.78% and 87.85%, respectively. Then, the C-terminal residues were used for developing prediction methods, which resulted in an accuracy of 77.34%, 82.03% and 85.16% using ANN, QM and SVM, respectively. Finally, ANN, QM and SVM models were developed using N and C terminal residues, which achieved an accuracy of 88.17%, 90.37% and 92.11%, respectively. All the models developed in this study were evaluated using five-fold cross validation technique. These models were also tested on an independent or blind dataset. CONCLUSION: Among antibacterial peptides, there is preference for certain residues at N and C termini, which helps to demarcate them from non-antibacterial peptides. Both the termini play a crucial role in imparting the antibacterial property to these peptides. Among the methods developed, SVM shows the best performance in predicting antibacterial peptides followed by QM and ANN, in that order. AntiBP (Antibacterial peptides) will help in discovering efficacious antibacterial peptides, which we hope will prove to be a boon to combat the dreadful antibiotic resistant bacteria. A user friendly web server has also been developed to help the biological community, which is accessible at http://www.imtech.res.in/raghava/antibp/.

BACKGROUND: In past number of methods have been developed for predicting subcellular location of eukaryotic, prokaryotic (Gram-negative and Gram-positive bacteria) and human proteins but no method has been developed for mycobacterial proteins which may represent repertoire of potent immunogens of this dreaded pathogen. In this study, attempt has been made to develop method for predicting subcellular location of mycobacterial proteins. RESULTS: The models were trained and tested on 852 mycobacterial proteins and evaluated using five-fold cross-validation technique. First SVM (Support Vector Machine) model was developed using amino acid composition and overall accuracy of 82.51% was achieved with average accuracy (mean of class-wise accuracy) of 68.47%. In order to utilize evolutionary information, a SVM model was developed using PSSM (Position-Specific Scoring Matrix) profiles obtained from PSI-BLAST (Position-Specific Iterated BLAST) and overall accuracy achieved was of 86.62% with average accuracy of 73.71%. In addition, HMM (Hidden Markov Model), MEME/MAST (Multiple Em for Motif Elicitation/Motif Alignment and Search Tool) and hybrid model that combined two or more models were also developed. We achieved maximum overall accuracy of 86.8% with average accuracy of 89.00% using combination of PSSM based SVM model and MEME/MAST. Performance of our method was compared with that of the existing methods developed for predicting subcellular locations of Gram-positive bacterial proteins. CONCLUSION: A highly accurate method has been developed for predicting subcellular location of mycobacterial proteins. This method also predicts very important class of proteins that is membrane-attached proteins. This method will be useful in annotating newly sequenced or hypothetical mycobacterial proteins. Based on above study, a freely accessible web server TBpred http://www.imtech.res.in/raghava/tbpred/ has been developed.

UNLABELLED: The key requirement for successful immunochemical assay is the availability of antibodies with high specificity and desired affinity. Small molecules, when used as haptens, are not immunogenic. However, on conjugating with carrier molecule they elicit antibody response. The production of anti-hapten antibodies of desired specificity largely depends on the hapten design (preserving greatly the chemical structure and spatial conformation of target compound), selection of the appropriate carrier protein and the conjugation method. This manuscript describes a curated database HaptenDB, where information is collected from published literature and web resources. The current version of the database has 2021 entries for 1087 haptens and 25 carrier proteins, where each entry provides comprehensive details about (1) nature of the hapten, (2) 2D and 3D structures of haptens, (3) carrier proteins, (4) coupling method, (5) method of anti-hapten antibody production, (6) assay method (used for characterization) and (7) specificities of antibodies. The current version of HaptenDB covers a wide array of haptens including pesticides, herbicides, insecticides, drugs, vitamins, steroids, hormones, toxins, dyes, explosives, etc. It provides internal and external links to various databases/resources to obtain further information about the nature of haptens, carriers and respective antibodies. For structure similarity comparison of haptens, the database also integrates tools like JME Editor and JMOL for sketching, displaying and manipulating hapten 2D/3D structures online. So the database would be of great help in identifying functional group(s) in smaller molecules using antibodies as well as for the development of immunodiagnostics/therapeutics by providing data and procedures available so far for the generation of specific or cross-reactive antibodies. AVAILABILITY: HaptenDB is available on http://www.imtech.res.in/raghava/haptendb/ and http://bioinformatics.uams.edu/raghava/haptendb/ (Mirror site).

BACKGROUND: Diverse modeling approaches viz. neural networks and multiple regression have been followed to date for disease prediction in plant populations. However, due to their inability to predict value of unknown data points and longer training times, there is need for exploiting new prediction softwares for better understanding of plant-pathogen-environment relationships. Further, there is no online tool available which can help the plant researchers or farmers in timely application of control measures. This paper introduces a new prediction approach based on support vector machines for developing weather-based prediction models of plant diseases. RESULTS: Six significant weather variables were selected as predictor variables. Two series of models (cross-location and cross-year) were developed and validated using a five-fold cross validation procedure. For cross-year models, the conventional multiple regression (REG) approach achieved an average correlation coefficient (r) of 0.50, which increased to 0.60 and percent mean absolute error (%MAE) decreased from 65.42 to 52.24 when back-propagation neural network (BPNN) was used. With generalized regression neural network (GRNN), the r increased to 0.70 and %MAE also improved to 46.30, which further increased to r = 0.77 and %MAE = 36.66 when support vector machine (SVM) based method was used. Similarly, cross-location validation achieved r = 0.48, 0.56 and 0.66 using REG, BPNN and GRNN respectively, with their corresponding %MAE as 77.54, 66.11 and 58.26. The SVM-based method outperformed all the three approaches by further increasing r to 0.74 with improvement in %MAE to 44.12. Overall, this SVM-based prediction approach will open new vistas in the area of forecasting plant diseases of various crops. CONCLUSION: Our case study demonstrated that SVM is better than existing machine learning techniques and conventional REG approaches in forecasting plant diseases. In this direction, we have also developed a SVM-based web server for rice blast prediction, a first of its kind worldwide, which can help the plant science community and farmers in their decision making process. The server is freely available at http://www.imtech.res.in/raghava/rbpred/.

BACKGROUND: Percentage Identity (PID) is frequently quoted in discussion of sequence alignments since it appears simple and easy to understand. However, although there are several different ways to calculate percentage identity and each may yield a different result for the same alignment, the method of calculation is rarely reported. Accordingly, quantification of the variation in PID caused by the different calculations would help in interpreting PID values in the literature. In this study, the variation in PID was quantified systematically on a reference set of 1028 alignments generated by comparison of the protein three-dimensional structures. Since the alignment algorithm may also affect the range of PID, this study also considered the effect of algorithm, and the combination of algorithm and PID method. RESULTS: The maximum variation in PID due to the calculation method was 11.5% while the effect of alignment algorithm on PID was up to 14.6% across three popular alignment methods. The combined effect of alignment algorithm and PID calculation gave a variation of up to 22% on the test data, with an average of 5.3% +/- 2.8% for sequence pairs with < 30% identity. In order to see which PID method was most highly correlated with structural similarity, four different PID calculations were compared to similarity scores (Sc) from the comparison of the corresponding protein three-dimensional structures. The highest correlation coefficient for a PID calculation was 0.80. In contrast, the more sophisticated Z-score calculated by reference to randomized sequences gave a correlation coefficient of 0.84. CONCLUSION: Although it is well known amongst expert sequence analysts that PID is a poor score for discriminating between protein sequences, the apparent simplicity of the percentage identity score encourages its widespread use in establishing cutoffs for structural similarity. This paper illustrates that not only is PID a poor measure of sequence similarity when compared to the Z-score, but that there is also a large uncertainty in reported PID values. Since better alternatives to PID exist to quantify sequence similarity, these should be quoted where possible in preference to PID. The findings presented here should prove helpful to those new to sequence analysis, and in warning those who seek to interpret the value of a PID reported in the literature.

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/

BACKGROUND: A large number of papers have been published on analysis of microarray data with particular emphasis on normalization of data, detection of differentially expressed genes, clustering of genes and regulatory network. On other hand there are only few studies on relation between expression level and composition of nucleotide/protein sequence, using expression data. There is a need to understand why particular genes/proteins express more in particular conditions. In this study, we analyze 3468 genes of Saccharomyces cerevisiae obtained from Holstege et al., (1998) to understand the relationship between expression level and amino acid composition. RESULTS: We compute the correlation between expression of a gene and amino acid composition of its protein. It was observed that some residues (like Ala, Gly, Arg and Val) have significant positive correlation (r > 0.20) and some other residues (Like Asp, Leu, Asn and Ser) have negative correlation (r < -0.15) with the expression of genes. A significant negative correlation (r = -0.18) was also found between length and gene expression. These observations indicate the relationship between percent composition and gene expression level. Thus, attempts have been made to develop a Support Vector Machine (SVM) based method for predicting the expression level of genes from its protein sequence. In this method the SVM is trained with proteins whose gene expression data is known in a given condition. Then trained SVM is used to predict the gene expression of other proteins of the same organism in the same condition. A correlation coefficient r = 0.70 was obtained between predicted and experimentally determined expression of genes, which improves from r = 0.70 to 0.72 when dipeptide composition was used instead of residue composition. The method was evaluated using 5-fold cross validation test. We also demonstrate that amino acid composition information along with gene expression data can be used for improving the function classification of proteins. CONCLUSION: There is a correlation between gene expression and amino acid composition that can be used to predict the expression level of genes up to a certain extent. A web server based on the above strategy has been developed for calculating the correlation between amino acid composition and gene expression and prediction of expression level http://kiwi.postech.ac.kr/raghava/lgepred/. This server will allow users to study the evolution from expression data.

Abstract Summary: Prediction of peptides binding with MHC class II allele HLA-DRB1*0401 can effectively reduce the number of experiments required for identifying helper T cell epitopes. This paper describes support vector machine (SVM) based method developed for identifying HLA-DRB1*0401 binding peptides in an antigenic sequence. SVM was trained and tested on large and clean data set consisting of 567 binders and equal number of non-binders. The accuracy of the method was 86% when evaluated through 5-fold cross-validation technique. Available: A web server HLA-DR4Pred based on above approach is available at http://www.imtech.res.in/raghava/hladr4pred/ and http://bioinformatics.uams.edu/mirror/hladr4pred/ (Mirror Site). Supplementary information: http://www.imtech.res.in/raghava/hladr4pred/info.html

MOTIVATION: The prediction of beta-turns is an important element of protein secondary structure prediction. Recently, a highly accurate neural network based method Betatpred2 has been developed for predicting beta-turns in proteins using position-specific scoring matrices (PSSM) generated by PSI-BLAST and secondary structure information predicted by PSIPRED. However, the major limitation of Betatpred2 is that it predicts only beta-turn and non-beta-turn residues and does not provide any information of different beta-turn types. Thus, there is a need to predict beta-turn types using an approach based on multiple sequence alignment, which will be useful in overall tertiary structure prediction. RESULTS: In the present work, a method has been developed for the prediction of beta-turn types I, II, IV and VIII. For each turn type, two consecutive feed-forward back-propagation networks with a single hidden layer have been used where the first sequence-to-structure network has been trained on single sequences as well as on PSI-BLAST PSSM. The output from the first network along with PSIPRED predicted secondary structure has been used as input for the second-level structure-to-structure network. The networks have been trained and tested on a non-homologous dataset of 426 proteins chains by 7-fold cross-validation. It has been observed that the prediction performance for each turn type is improved significantly by using multiple sequence alignment. The performance has been further improved by using a second level structure-to-structure network and PSIPRED predicted secondary structure information. It has been observed that Type I and II beta-turns have better prediction performance than Type IV and VIII beta-turns. The final network yields an overall accuracy of 74.5, 93.5, 67.9 and 96.5% with MCC values of 0.29, 0.29, 0.23 and 0.02 for Type I, II, IV and VIII beta-turns, respectively, and is better than random prediction. AVAILABILITY: A web server for prediction of beta-turn types I, II, IV and VIII based on above approach is available at http://www.imtech.res.in/raghava/betaturns/ and http://bioinformatics.uams.edu/mirror/betaturns/ (mirror site).

MOTIVATION: Repetitive DNA sequences, besides having a variety of regulatory functions, are one of the principal causes of genomic instability. Understanding their origin and evolution is of fundamental importance for genome studies. The identification of repeats and their units helps in deducing the intra-genomic dynamics as an important feature of comparative genomics. A major difficulty in identification of repeats arises from the fact that the repeat units can be either exact or imperfect, in tandem or dispersed, and of unspecified length. RESULTS: The Spectral Repeat Finder program circumvents these problems by using a discrete Fourier transformation to identify significant periodicities present in a sequence. The specific regions of the sequence that contribute to a given periodicity are located through a sliding window analysis, and an exact search method is then used to find the repetitive units. Efficient and complete detection of repeats is provided together with interactive and detailed visualization of the spectral analysis of input sequence. We demonstrate the utility of our method with various examples that contain previously unannotated repeats. A Web server has been developed for convenient access to the automated program. AVAILABILITY: The Web server is available at http://www.imtech.res.in/raghava/srf and http://www2.imtech.res.in/raghava/srf

Abstract Summary: MHCBN is a comprehensive database of Major Histocompatibility Complex (MHC) binding and non-binding peptides compiled from published literature and existing databases. The latest version of the database has 19 777 entries including 17 129 MHC binders and 2648 MHC non-binders for more than 400 MHC molecules. The database has sequence and structure data of (a) source proteins of peptides and (b) MHC molecules. MHCBN has a number of web tools that include: (i) mapping of peptide on query sequence; (ii) search on any field; (iii) creation of data sets; and (iv) online data submission. The database also provides hypertext links to major databases like SWISS-PROT, PDB, IMGT/HLA-DB, GenBank and PUBMED. Availability: MHCBN is available at http://www.imtech.res.in/raghava/mhcbn/. It’s SRS version is available from http://srs.ebi.ac.uk/ Contact: [email protected] Supplementary information: http://www.imtech.res.in/raghava/mhcbn/supl/ * To whom correspondence should be addressed.

SUMMARY: ProPred1 is an on-line web tool for the prediction of peptide binding to MHC class-I alleles. This is a matrix-based method that allows the prediction of MHC binding sites in an antigenic sequence for 47 MHC class-I alleles. The server represents MHC binding regions within an antigenic sequence in user-friendly formats. These formats assist user in the identification of promiscuous MHC binders in an antigen sequence that can bind to large number of alleles. ProPred1 also allows the prediction of the standard proteasome and immunoproteasome cleavage sites in an antigenic sequence. This server allows identification of MHC binders, who have the cleavage site at the C terminus. The simultaneous prediction of MHC binders and proteasome cleavage sites in an antigenic sequence leads to the identification of potential T-cell epitopes. AVAILABILITY: Server is available at http://www.imtech.res.in/raghava/propred1/. Mirror site of this server is available at http://bioinformatics.uams.edu/mirror/propred1/ SUPPLEMENTARY INFORMATION: Matrices and document on server are available at http://www.imtech.res.in/raghava/propred1/page2.html

BACKGROUND: The alignment of two or more protein sequences provides a powerful guide in the prediction of the protein structure and in identifying key functional residues, however, the utility of any prediction is completely dependent on the accuracy of the alignment. In this paper we describe a suite of reference alignments derived from the comparison of protein three-dimensional structures together with evaluation measures and software that allow automatically generated alignments to be benchmarked. We test the OXBench benchmark suite on alignments generated by the AMPS multiple alignment method, then apply the suite to compare eight different multiple alignment algorithms. The benchmark shows the current state-of-the art for alignment accuracy and provides a baseline against which new alignment algorithms may be judged. RESULTS: The simple hierarchical multiple alignment algorithm, AMPS, performed as well as or better than more modern methods such as CLUSTALW once the PAM250 pair-score matrix was replaced by a BLOSUM series matrix. AMPS gave an accuracy in Structurally Conserved Regions (SCRs) of 89.9% over a set of 672 alignments. The T-COFFEE method on a data set of families with <8 sequences gave 91.4% accuracy, significantly better than CLUSTALW (88.9%) and all other methods considered here. The complete suite is available from http://www.compbio.dundee.ac.uk. CONCLUSIONS: The OXBench suite of reference alignments, evaluation software and results database provide a convenient method to assess progress in sequence alignment techniques. Evaluation measures that were dependent on comparison to a reference alignment were found to give good discrimination between methods. The STAMP Sc Score which is independent of a reference alignment also gave good discrimination. Application of OXBench in this paper shows that with the exception of T-COFFEE, the majority of the improvement in alignment accuracy seen since 1985 stems from improved pair-score matrices rather than algorithmic refinements. The maximum theoretical alignment accuracy obtained by pooling results over all methods was 94.5% with 52.5% accuracy for alignments in the 0-10 percentage identity range. This suggests that further improvements in accuracy will be possible in the future.

Abstract Summary: FTG is a web server for analyzing nucleotide sequences to predict the genes using Fourier transform techniques. This server implements the existing Fourier transform algorithms for gene prediction and allows the rapid visualization of analysis by output in GIF format. Availability: The server is available at http://www.imtech.res.in/raghava/ftg/ Contact: [email protected] Supplementary information: http://www.imtech.res.in/raghava/ftg/help/supl.html * To whom correspondence should be addressed.

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/

MOTIVATION: beta-turn is an important element of protein structure. In the past three decades, numerous beta-turn prediction methods have been developed based on various strategies. For a detailed discussion about the importance of beta-turns and a systematic introduction of the existing prediction algorithms for beta-turns and their types, please see a recent review (Chou, Analytical Biochemistry, 286, 1-16, 2000). However at present, it is still difficult to say which method is better than the other. This is because of the fact that these methods were developed on different sets of data. Thus, it is important to evaluate the performance of beta-turn prediction methods. RESULTS: We have evaluated the performance of six methods of beta-turn prediction. All the methods have been tested on a set of 426 non-homologous protein chains. It has been observed that the performance of the neural network based method, BTPRED, is significantly better than the statistical methods. One of the reasons for its better performance is that it utilizes the predicted secondary structure information. We have also trained, tested and evaluated the performance of all methods except BTPRED and GORBTURN, on new data set using a 7-fold cross-validation technique. There is a significant improvement in performance of all the methods when secondary structure information is incorporated. Moreover, after incorporating secondary structure information, the Sequence Coupled Model has yielded better results in predicting beta-turns as compared with other methods. In this study, both threshold dependent and independent (ROC) measures have been used for evaluation.

UNLABELLED: ProPred is a graphical web tool for predicting MHC class II binding regions in antigenic protein sequences. The server implement matrix based prediction algorithm, employing amino-acid/position coefficient table deduced from literature. The predicted binders can be visualized either as peaks in graphical interface or as colored residues in HTML interface. This server might be a useful tool in locating the promiscuous binding regions that can bind to several HLA-DR alleles. AVAILABILITY: The server is available at http://www.imtech.res.in/raghava/propred/ CONTACT: [email protected] SUPPLEMENTARY INFORMATION: http://www.imtech.res.in/raghava/propred/page3.html