Pfmpred

From DrugPedia: A Wikipedia for Drug discovery

PFMpred is developed for predicting mitochondrial proteins of malaria parasite P. falciparum .

[edit] Background

The rate of human death due to malaria is increasing day-by-day. Thus the malaria causing parasite Plasmodium falciparum (PF) is of highest concern now. With the wealth of data available now, this information can be used to understand the protein localization. The sub-cellular localization of proteins is of utmost importance to know how these help the parasite to infect the red blood cells of human. The mitochondrial genome of PF is only 6kb in size, the smallest yet discovered. Thus here is an attempt to find the mitochondrial localization proteins.

[edit] Result

The present study describes a method developed for predicting mitochondrial proteins of malaria parasite. All models were trained and tested on 175 proteins (40 mitochondrial & 135 non-mitochondrial proteins) and evaluated using five-fold cross validation. We developed a Support Vector Machine (SVM) model for predicting mitochondrial proteins of Plasmodium falciparum, using amino acids and dipeptides composition and achieved maximum MCC 0.38 and 0.51 respectively. In this study, split amino acid composition (SAAC) is used where composition of N-termini, C-termini and rest of protein is computed separately. The performance of SVM model improved significantly from MCC 0.38 to 0.73 when SAAC was used as input instead of simple amino acid composition. In addition, SVM model has been developed using composition of PSSM profile with MCC 0.75 and accuracy 91.38%. We achieved maximum MCC 0.81 with accuracy 92% using a hybrid model, which combines PSSM profile and SAAC.

[edit] Conclusion

It has been observed that certain amino acids are more abundant in mitochondrial proteins than non-mitochondrial proteins. Thus it is possible to predict mitochondrial proteins from its residue composition-using machine learning technique. When evaluated on an independent dataset our method performs better than existing methods.

[edit] Availability

A web server PFMpred has been developed for predicting mitochondrial proteins of malaria parasites PFMPred.