We developed a support vector machine based web server called SVM-PB-Pred, to predict the Protein Block for any given amino acid sequence. The input features of SVM-PB-Pred include i) sequence profiles (PSSM) and ii) actual secondary structures (SS) from DSSP method or predicted secondary structures from NPS@ and GOR4 methods. There were three combined input features PSSM+SS(DSSP), PSSM+SS(NPS@) and PSSM+SS(GOR4) used to test and train the SVM models. Similarly, four datasets RS90, DB433, LI1264 and SP1577 were used to develop the SVM models. These four SVM models developed were tested using three different benchmarking tests namely; (i) self consistency, (ii) seven fold cross validation test and (iii) independent case test. The maximum possible prediction accuracy of ~70% was observed in self consistency test for the SVM models of both LI1264 and SP1577 datasets, where PSSM+SS(DSSP) input features was used to test. The prediction accuracies were reduced to ~53% for PSSM+SS(NPS@) and ~43% for PSSM+SS(GOR4) in independent case test, for the SVM models of above two same datasets. Using our method, it is possible to predict the protein block letters for any query protein sequence with ~53% accuracy, when the SP1577 dataset and predicted secondary structure from NPS@ server were used. The SVM-PB-Pred server can be freely accessed through http://bioinfo.bdu.ac.in/~svmpbpred.

No abstract

Segmentation is a process of converting inhomogeneous data into homogeneous data. There are many segmentation techniques available inthe literature. Among these techniques, finite Gaussian Mixture Model using EM algorithm is one mostly used. However, Gaussian Mixture Model is suited well when the image under consideration is symmetric. But in reality, medical images are asymmetric. Hence, it is needed to develop new algorithms for segmenting non -symmetric images. Therefore, skew symmetric mixture model is utilized for this purpose. The segmentation is carried out by using Fuzzy C-Means clustering technique and the updated parameters are obtained through EM algorithm. The model is tested with 8 images and the segmentation evaluation is carried out by using objective evaluation criteria namely Jaccard Coefficient (JC) and Volumetric Similarity (VS), Variation of Information (VOI), Global Consistency Error (GCE) and Probabilistic Rand Index (PRI). The performance evaluation of reconstructed images is carried out by using image quality metrics. The experimentation is carried out using T 1 weighted images and the results are compared with the existing models.

No abstract

No abstract