Sudheer Gupta

In silico approach for predicting toxicity of peptides and proteins.

Background Over the past few decades, scientific research has been focused on developing peptide/protein-based therapies to treat various diseases. With the several advantages over small molecules, including high specificity, high penetration, ease of manufacturing, peptides have emerged as promising therapeutic molecules against many diseases. However, one of the bottlenecks in peptide/protein-based therapy is their toxicity. Therefore, in the present study, we developed in silico models for predicting toxicity of peptides and proteins. Description We obtained toxic peptides having 35 or fewer residues from various databases for developing prediction models. Non-toxic or random peptides were obtained from SwissProt and TrEMBL. It was observed that certain residues like Cys, His, Asn, and Pro are abundant as well as preferred at various positions in toxic peptides. We developed models based on machine learning technique and quantitative matrix using various properties of peptides for predicting toxicity of peptides. The performance of dipeptide-based model in terms of accuracy was 94.50% with MCC 0.88. In addition, various motifs were extracted from the toxic peptides and this information was combined with dipeptide-based model for developing a hybrid model. In order to evaluate the over-optimization of the best model based on dipeptide composition, we evaluated its performance on independent datasets and achieved accuracy around 90%. Based on above study, a web server, ToxinPred has been developed, which would be helpful in predicting (i) toxicity or non-toxicity of peptides, (ii) minimum mutations in peptides for increasing or decreasing their toxicity, and (iii) toxic regions in proteins. Conclusion ToxinPred is a unique in silico method of its kind, which will be useful in predicting toxicity of peptides/proteins. In addition, it will be useful in designing least toxic peptides and discovering toxic regions in proteins. We hope that the development of ToxinPred will provide momentum to peptide/protein-based drug discovery (http://crdd.osdd.net/raghava/toxinpred/).

CancerDR: cancer drug resistance database.

Cancer therapies are limited by the development of drug resistance, and mutations in drug targets is one of the main reasons for developing acquired resistance. The adequate knowledge of these mutations in drug targets would help to design effective personalized therapies. Keeping this in mind, we have developed a database “CancerDR”, which provides information of 148 anti-cancer drugs, and their pharmacological profiling across 952 cancer cell lines. CancerDR provides comprehensive information about each drug target that includes; (i) sequence of natural variants, (ii) mutations, (iii) tertiary structure, and (iv) alignment profile of mutants/variants. A number of web-based tools have been integrated in CancerDR. This database will be very useful for identification of genetic alterations in genes encoding drug targets, and in turn the residues responsible for drug resistance. CancerDR allows user to identify promiscuous drug molecules that can kill wide range of cancer cells. CancerDR is freely accessible at http://crdd.osdd.net/raghava/cancerdr/

CancerPPD: a database of anticancer peptides and proteins

CancerPPD (http://crdd.osdd.net/raghava/cancerppd/) is a repository of experimentally verified anticancer peptides (ACPs) and anticancer proteins. Data were manually collected from published research articles, patents and from other databases. The current release of CancerPPD consists of 3491 ACP and 121 anticancer protein entries. Each entry provides comprehensive information related to a peptide like its source of origin, nature of the peptide, anticancer activity, N- and C-terminal modifications, conformation, etc. Additionally, CancerPPD provides the information of around 249 types of cancer cell lines and 16 different assays used for testing the ACPs. In addition to natural peptides, CancerPPD contains peptides having non-natural, chemically modified residues and D-amino acids. Besides this primary information, CancerPPD stores predicted tertiary structures as well as peptide sequences in SMILES format. Tertiary structures of peptides were predicted using the state-of-art method, PEPstr and secondary structural states were assigned using DSSP. In order to assist users, a number of web-based tools have been integrated, these include keyword search, data browsing, sequence and structural similarity search. We believe that CancerPPD will be very useful in designing peptide-based anticancer therapeutics.

Prediction of IL4 Inducing Peptides

The secretion of Interleukin-4 (IL4) is the characteristic of T-helper 2 responses. IL4 is a cytokine produced by CD4+ T cells in response to helminthes and other extracellular parasites. It has a critical role in guiding antibody class switching, hematopoiesis and inflammation, and the development of appropriate effector T-cell responses. In this study, it is the first time an attempt has been made to understand whether it is possible to predict IL4 inducing peptides. The data set used in this study comprises 904 experimentally validated IL4 inducing and 742 noninducing MHC class II binders. Our analysis revealed that certain types of residues are preferred at certain positions in IL4 inducing peptides. It was also observed that IL4 inducing and noninducing epitopes differ in compositional and motif pattern. Based on our analysis we developed classification models where the hybrid method of amino acid pairs and motif information performed the best with maximum accuracy of 75.76% and MCC of 0.51. These results indicate that it is possible to predict IL4 inducing peptides with reasonable precession. These models would be useful in designing the peptides that may induce desired Th2 response.

Identification of B-cell epitopes in an antigen for inducing specific class of antibodies

BackgroundIn the past, numerous methods have been developed for predicting antigenic regions or B-cell epitopes that can induce B-cell response. To the best of authors’ knowledge, no method has been developed for predicting B-cell epitopes that can induce a specific class of antibody (e.g., IgA, IgG) except allergenic epitopes (IgE). In this study, an attempt has been made to understand the relation between primary sequence of epitopes and the class of antibodies generated.ResultsThe dataset used in this study has been derived from Immune Epitope Database and consists of 14725 B-cell epitopes that include 11981 IgG, 2341 IgE, 403 IgA specific epitopes and 22835 non-B-cell epitopes. In order to understand the preference of residues or motifs in these epitopes, we computed and compared amino acid and dipeptide composition of IgG, IgE, IgA inducing epitopes and non-B-cell epitopes. Differences in composition profiles of different classes of epitopes were observed, and few residues were found to be preferred. Based on these observations, we developed models for predicting antibody class-specific B-cell epitopes using various features like amino acid composition, dipeptide composition, and binary profiles. Among these, dipeptide composition-based support vector machine model achieved maximum Matthews correlation coefficient of 0.44, 0.70 and 0.45 for IgG, IgE and IgA specific epitopes respectively. All models were developed on experimentally validated non-redundant dataset and evaluated using five-fold cross validation. In addition, the performance of dipeptide-based model was also evaluated on independent dataset.ConclusionPresent study utilizes the amino acid sequence information for predicting the tendencies of antigens to induce different classes of antibodies. For the first time, in silico models have been developed for predicting B-cell epitopes, which can induce specific class of antibodies. A web service called IgPred has been developed to serve the scientific community. This server will be useful for researchers working in the field of subunit/epitope/peptide-based vaccines and immunotherapy (http://crdd.osdd.net/raghava/igpred/).ReviewersThis article was reviewed by Dr. M Michael Gromiha, Dr Christopher Langmead (nominated by Dr Robert Murphy) and Dr Lina Ma (nominated by Dr Zhang Zhang).

Herceptin Resistance Database for Understanding Mechanism of Resistance in Breast Cancer Patients

Monoclonal antibody Trastuzumab/Herceptin is considered as frontline therapy for Her2-positive breast cancer patients. However, it is not effective against several patients due to acquired or de novo resistance. In last one decade, several assays have been performed to understand the mechanism of Herceptin resistance with/without supplementary drugs. This manuscript describes a database HerceptinR, developed for understanding the mechanism of resistance at genetic level. HerceptinR maintains information about 2500 assays performed against various breast cancer cell lines (BCCs), for improving sensitivity of Herceptin with or without supplementary drugs. In order to understand Herceptin resistance at genetic level, we integrated genomic data of BCCs that include expression, mutations and copy number variations in different cell lines. HerceptinR will play a vital role in i) designing biomarkers to identify patients eligible for Herceptin treatment and ii) identification of appropriate supplementary drug for a particular patient. HerceptinR is available at http://crdd.osdd.net/raghava/herceptinr/.

Prediction of vitamin interacting residues in a vitamin binding protein using evolutionary information

BackgroundThe 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.ResultsIn 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.ConclusionsThis 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/).

VaccineDA: Prediction, design and genome-wide screening of oligodeoxynucleotide-based vaccine adjuvants.

Immunomodulatory oligodeoxynucleotides (IMODNs) are the short DNA sequences that activate the innate immune system via toll-like receptor 9. These sequences predominantly contain unmethylated CpG motifs. In this work, we describe VaccineDA (Vaccine DNA adjuvants), a web-based resource developed to design IMODN-based vaccine adjuvants. We collected and analyzed 2193 experimentally validated IMODNs obtained from the literature. Certain types of nucleotides (e.g., T, GT, TC, TT, CGT, TCG, TTT) are dominant in IMODNs. Based on these observations, we developed support vector machine-based models to predict IMODNs using various compositions. The developed models achieved the maximum Matthews Correlation Coefficient (MCC) of 0.75 with an accuracy of 87.57% using the pentanucleotide composition. The integration of motif information further improved the performance of our model from the MCC of 0.75 to 0.77. Similarly, models were developed to predict palindromic IMODNs and attained a maximum MCC of 0.84 with the accuracy of 91.94%. These models were evaluated using a five-fold cross-validation technique as well as validated on an independent dataset. The models developed in this study were integrated into VaccineDA to provide a wide range of services that facilitate the design of DNA-based vaccine adjuvants (http://crdd.osdd.net/raghava/vaccineda/).

Prioritization of anticancer drugs against a cancer using genomic features of cancer cells: A step towards personalized medicine.

In this study, we investigated drug profile of 24 anticancer drugs tested against a large number of cell lines in order to understand the relation between drug resistance and altered genomic features of a cancer cell line. We detected frequent mutations, high expression and high copy number variations of certain genes in both drug resistant cell lines and sensitive cell lines. It was observed that a few drugs, like Panobinostat, are effective against almost all types of cell lines, whereas certain drugs are effective against only a limited type of cell lines. Tissue-specific preference of drugs was also seen where a drug is more effective against cell lines belonging to a specific tissue. Genomic features based models have been developed for each anticancer drug and achieved average correlation between predicted and actual growth inhibition of cell lines in the range of 0.43 to 0.78. We hope, our study will throw light in the field of personalized medicine, particularly in designing patient-specific anticancer drugs. In order to serve the scientific community, a webserver, CancerDP, has been developed for predicting priority/potency of an anticancer drug against a cancer cell line using its genomic features (http://crdd.osdd.net/raghava/cancerdp/).

Peptide toxicity prediction.

Last decade has witnessed the revival of interest in peptides as potential therapeutics candidates. However, one of the bottlenecks in the success of therapeutic peptides in clinics is their toxicity towards eukaryotic cells. Therefore, considerable efforts have been made over the years both in wet and dry lab to overcome this limitation. With the advances in peptide synthesis, now it is possible to fine-tune the physicochemical properties of peptides by incorporating several chemical modifications and thus to optimize the peptide functionality in order to minimize the toxicity without compromising their therapeutic activity. Also various in silico tools for peptide toxicity prediction and peptide designing have been developed, which facilitates designing of therapeutic peptides with desired toxicity. In this chapter, we have discussed both wet lab and dry lab approaches used to optimize peptide toxicity. More emphasis has been given to describe the in silico method, ToxinPred, to predict the toxicity of peptide and about how to design a peptide or protein with desired toxicity by mutating minimum number of amino acids.