Browsing by Author "MUHAMMAD UMAR MUNIR"

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Ampep
    (UMT.Lahore, 2019) MUHAMMAD UMAR MUNIR
    With the advancement in cellular biology the use of Antimicrobial peptides (AMPs) against many drug resistance pathogens have also been increased. AMPs have a broad range of activity and can work as antibacterial, anti-cytokine, antifungal, antiviral and sometimes even as anticancer peptides. Since the emergence of multi drug resistant bacterial infections, many researchers have proposed the use of Antimicrobial peptides (AMPs) to fight against these such microbial infection. AMPs are found in many living organisms. These peptides play an important role in host immune defense in multiple living organisms including cells, plants and complex living organisms. The traditional methods of distinguishing AMPs from non-AMPs is based only on wet-lab experiments. Such experiments are both time- consuming and expensive. With the recent development in bio-informatics more and more researchers are contributing their effort to apply computational models on such problems. The main objective of this thesis is to accurately predict AMPs from non-AMPs using 5-step rule approach. In the paper, we have proposed a predication algorithm for classifying AMPs from non-AMPs. This proposed methodology used Artificial Neural Network (ANN) to predict such peptide sequences. We have used a total of 1900 AMPs and 4000 non-AMPs in our training dataset. System performance is validated via 10-fold cross validation approach and an overall accuracy of 99.3% have been achieved. Results are also compared to other methodologies hence our proposed methodology outperformed existing methodologies in term of prediction results.