il10pred

il10pred predicts peptides that induce interleukin-10 (IL-10) to support identification of epitopes for epitope-based vaccine and therapeutic design targeting immune modulation.

Key Features:

• Predictive Modeling: Employs machine learning techniques to distinguish IL-10 inducing peptides from non-inducing peptides.
• Data-Driven Dataset: Models are trained on a dataset comprising 394 experimentally validated IL-10 inducing peptides and 848 non-inducing peptides.
• Motif Analysis: Identifies residues and sequence motifs that are more prevalent in IL-10 inducing peptides compared to non-inducing ones.
• Machine Learning Performance: Uses composition-based features (including dipeptide composition) and machine learning methods with a Random Forest model achieving a Matthews's Correlation Coefficient (MCC) of 0.59 and an accuracy of 81.24%.

Scientific Applications:

• Epitope-based vaccine design: Identification of IL-10 inducing peptides to inform selection of epitopes that modulate immune responses in vaccine development.
• Therapeutic immune modulation: Identification of peptides that induce IL-10 to support development of therapeutic strategies aimed at immune suppression or modulation.

Methodology:

Collected a dataset of experimentally validated IL-10 inducing (n=394) and non-inducing (n=848) peptides; analyzed peptide sequences to identify characteristic residues and motifs; developed composition-based models using machine learning, including Random Forest with dipeptide composition features.