Abstract:
Prominent for its strong pro-inflammatory properties, interleukin-6 (IL-6) is an important immunological regulator. Even though IL-6 is known to promote inflammation, in certain situations it can exhibit surprising anti-inflammatory properties. This dual character emphasizes how crucial it is to identify the peptides generated by IL-6. In order to overcome the drawbacks of manual identification, which are often expensive, our work presents Stacking, an ensemble learning approach based on stacking that is intended to provide accurate and effective IL-6-inducing peptide identification. Ten Amino-Acid-Composition-based Feature Extraction techniques are examined, including AAC, APAAC, CKSAAP, CTDC, DPC, Moran and PAAC. With the help of a Logistic Regression meta-learner and eight improved base learners (LGBM, RF, SVM, Decision Tree, XGBClassifier, LR and KNN), the Stacking model achieves an excellent 97.10% identification rate, 0.9433 MCC, and 0.9766 specificity. We examine the effects of several enhancement strategies on the accuracy of IL-6 predictions through experimental evaluations, contrasting single models with ensemble combinations based on stacking. Our findings show that the suggested methodology isfar more effective than its individual equivalents in identifying peptides that induce IL-6. Improving IL-6 prediction advances the search for anti-inflammatory drugs.
