Earlier study on thymine distribution in coding frames of mRNAs reveals that frame 1 prefers to have a defined number of thymine. The same in untranslated regions (UTRs) are further looked in to check this distribution in different frames. The results reveal that there is no such preference over the thymine distribution in different frames. Also confirms the earlier report of defined number of thymine in different frames of coding regions.

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.

Significant gene biclusters are important in medical science in many ways. They can be used in drug discovery, identification of severe diseases, finding the gene pathways and many more. We are using two algorithms to find the final significant biclusters from the DNA microarrays. In first algorithm, transform discrete values are used while in second algorithm, actual numerical values are used as an input. The results are tested on both synthetic as well as on real database. The output for the real database i.e. Yeast Cell Cycle is discussed at the end.