International Journal of Bioinformatics Research

285-288

Authors: MUTHUKRISHNAN S., PURI M., LEFEVRE C

A method has been developed for predicting blood proteins using the SVM based machine learning approach. In this prediction method a two-step strategy was deployed to predict blood proteins and their subclasses. We have developed models of blood proteins and achieved the maximum accuracies of 90.57% and 91.39% with Matthews correlation coefficient (MCC) of 0.89 and 0.90 using single amino acid and dipeptide composition respectively. Furthermore, the method is able to predict major subclasses of blood proteins; albumin, globulin, fibrinogen and regulatory proteins with a maximum accuracy 90.38%, 92.83%, 87.41%, 92.52% and 85.27%, 89.07%, 94.82%, 86.31 for albumin, globulin, fibrinogen, and regulatory proteins respectively. All modules were trained, tested, and evaluated using the fivefold cross-validation technique.

276-281

Authors: GOMASE V.S., CHITLANGE N.R., CHANGBHALE S.S., SHERKHANE A.S., KALE K.V

Urogenital schistosomiasis is frequently occurring parasitic disease in tropical countries, S. haematobium is main causative agent responcible for urogenital schistosomiasis; till date no effective invention made to against urogenital schistosomiasis. In this analysis we a have predicted suitable antigenic peptides from Schistosoma haematobium 23-kDa transmembrane protein for peptide vaccine design against urogenital schistosomiasis based on cross protection phenomenon as, an ample immune response can be generated with a single protein subunit. We found MHC class II binding peptides of S. haematobium 23-kDa are important determinant against the diseased condition. The analysis shows S. haematobium 23-kDa transmembrane protein having 218 amino acids, which shows 210 nonamers. In this assay, we have predicted MHC-I binding peptides for 8mer_H2_Db allele (optimal score is 14.128), 9mer_H2_Db allele (optimal score is 20.065), 10mer_H2_Db allele (optimal score is 13.776), 11mer_H2_Db allele (optimal score is 31.213). We also predicted the SVM based MHCII-IAb peptide regions, 152-DYGPNIPAS, 51-WQAAPIAII, 50-VWQAAPIAI, 142-FHCCGAKGP, 97-AELAAAIVA (optimal score is 14.911); MHCII-IAd peptide regions, 100-AAAIVAVVY, 71-LGCCGAIKE, 192-FGVCFFQLL, 186-IVACVAFGV (optimal score is 13.112); and MHCII-IAg7 peptide regions 42-QYGDNLHKV, 101-AAIVAVVYK, 28-VLIGAGAYV, 103-IVAVVYKDR, 203-VIACCLGRQ (optimal score is 11.605) which shows potential binders from S. haematobium 23-kDa transmembrane protein. The method integrates prediction of MHC class I binding proteasomal C- terminal cleavage peptides and Six potential antigenic peptides at average propensity 1.094 having highest local hydrophilicity. Thus a small antigen fragment can induce immune response against whole antigen. This approach can be applied for designing subunit and synthetic peptide vaccines.

265-268

Authors: GORE V.S

Objective- To study the complications of ND:YAG Laser capsulotomy. Participants- Patients between age group of 08 to 80 who is having significant posterior capsular opacification leading to decreased visual acuity from early post operative days. Material and Method- 200 patients with PCO were studied for post ND:YAG laser complications. The patient who is not having any organic cause of decreased vision and who have completed at least three months after cataract surgery were selected. ND:YAG laser procedure was performed and their visual acuity improvement along with complications associated with this procedure were studied. Results- The procedure is absolutely safe if strict selection (inclusion/exclusion) criteria is followed. Most of complications are transient which can be managed by proper medication. Complications like retinal detachment or cystoid macular edema are multifactoral and can not always be only due to laser capsulotomy alone. Endophthalmitis is rare complication but highly unpredictable which can not be ruled out but be well treated with newer generation intravitreal drugs or vitrectomy surgery. Most of the patients 86% were significantly benifited by improved visual acuity.

245-248

Authors: RICHA GUPTA, ARCHANA TIWARI, MAHAVIR YADAV

Molecular mechanics (MM) these days tends to be concerned only with prediction of local minima on molecular potential energy surfaces. QSAR properties are often calculated in order to assist high-volume screening studies in pharmaceuticals applications. Should we want to study the motions of the molecule, all that would be needed would be to investigate the normal modes of vibration (which can be obtained from the hessian). MM does not take account of zero point vibrations and the calculations refer to a molecule at 0 K, when it is completely at rest. Workers in the modeling field often refer to MM as energy minimization. Molecular modeling is readily available for QSAR studies, pharmacophore studies. Its implementation can be for the design of vaccine, and drugs for therapeutic use.

254-257

Authors: GIORGIO A

The advent of computer systems in support of medical procedures has significantly improved healthcare services quality, and the patients’ general quality of life. Nevertheless, these benefits not always improve patient’s health directly. For example, in the case of an emergency relief to an injured or sick person, it is essential to obtain timely patient's past medical history in order to prevent the supply of incorrect treatments which could further aggravate the situation. In this context, the designed system wants to demonstrate how to dramatically improve medical history acquisition procedures and face the most serious situations, using RFID technology; not forgetting, among others, important aspects as integration into an existing computer system, or the economic factor.

202-206

Authors: ANUBHA DUBEY, USHA CHOUHAN

MicroRNAs (miRNA's) constitute a large family of non coding RNAs that function to regulate gene expression. Wet lab experiments usually used to classify the miRNA of plants and animals are highly expensive, labor intensive and time consuming. Thus there arises a need for computational approach for classification of plant and animal miRNA. These computational approaches are fast and economical as compared to wet lab techniques. Here a machine learning approach is used to classify miRNA of HIV, plants and animals. The new SVM learning algorithm called Weka LibSVM has been used for classification of plant and animal and HIVmiRNA. The model has been tested on available data and it gives results with 95% accuracy.

214-220

Authors: GANGMAN YI, JAEHEE JUNG

Gene Ontology (GO) is a controlled vocabulary to describe the gene function. Each GO term is constructed by a hierarchical structure of gene function, so it is suitable for describing relationships of gene functions. We applied Bayesian network model as a training model using GO terms to identify unknown gene functions, and used Bayesian network model with three different heterogeneous data sets and multi-layered classifier to automatically predict gene functions. This proposed model is comprised of a base-classifier and a meta-classifier. The base-classifier serves a base of meta-classifier with Bayesian network model and meta-classifier plays role of classifying the designated GO term from the root node. A comparative analysis of our suggested model and other gene functional annotation systems shows that our model outperforms than others especially in terms of a number of correctly predicted proteins.

227-235

Authors: REKAYA R., ROBBINS K., BERTRAND K.

In recent years there has been much focus on the use of single nucleotide polymorphism (SNP) fine genome mapping to identify causative mutations for traits of interest; however, many studies focus only on the marginal effects of markers, ignoring potential gene interactions. Simulation studies have shown that this approach may not be powerful enough to detect important loci when gene interactions are present. Although several attempts have been made to study potential gene interaction, the number of SNP markers considered in these studies is often limited. Given the prohibitive computation cost of modeling interactions in studies involving a large number SNP, there is a need for methods that can account for potential gene interactions in a computationally efficient manner to be developed. In this study, the ant colony optimization algorithm (ACA) and logistic regression on large number of SNP genotypes were used. Our procedure was compared to sliding window (SW/H), and single locus genotype association (RG) methods used in haplotype analyses. A binary trait simulated using an epistatic model and HapMap ENCODE SNP genotypes was used to evaluate each algorithm. Results show that the ACA outperformed SW/H and RG under several simulation scenarios, yielding substantial increases in power to detect genomic regions associated with the simulated trait.