Inflammation is modulated by a host of molecular regulators, such as cytokines, complement eicosanoids, growth factors, and peptides. The key modulators of inflammation are cytokines, which participate in both acute and chronic inflammation. Cytokines can be classified based on the nature of immune response, cell type, location, and receptor type, used for signaling. Critical pro-inflammatory cytokines include interleukin (IL)-1, IL-6, IL-8, IL-12, IL-18, interferon (IFN)- γ, and tumor necrosis factor (TNF)-α. The role of peptides in inflammation can be proven via pathophysiological events, such as the release of tachykinins from sensory nerves for mediation of neurogenic inflammation and bradykinin from local and systemic inflammation. It prevent that the cell produce the peptides to defend to that are known as pro-inflammatory inducing peptides (PIPs), which can be utilized as therapeutic candidates to alleviate and cure various diseases. In this study they used the ensemble machine learning to predict the PIPs.
1) Amino acid composition 2) Dipeptide composition 3) Composition-translation-distribution 4) Amino-acid Index features 5) Physio-chemical properties
Machines : #
1) Support Vector Machine 2) Random Forest 3) Extremely randomized trees
Steps to execute: #
Step1: Submit to the web server (http://www.thegleelab.org/PIP-EL/) Step2: Result from the web page
Reference : #
- Manavalan, B.; Shin, T. H.; Kim, M. O.; Lee, G., PIP-EL: A New Ensemble Learning Method for Improved Proinflammatory Peptide Predictions. Frontiers in Immunology 2018, 9, (1783).