Integration of machine learning in 3D-QSAR CoMSIA models for the identification of lipid antioxidant peptides

The comparative molecular similarity indices analysis (CoMSIA) method is a widely used 3D-quantitative structure-activity relationship (QSAR) approach in the field of medicinal chemistry and drug design. However, relying solely on the Partial Least Square algorithm to build models using numerous CoMSIA indices has, in some cases, led to statistically underperforming models. This issue has also affected 3D-CoMSIA models constructed for the ferric thiocyanate (FTC) dataset from linoleic antioxidant measurements. In this study, a novel modeling routine has been developed incorporating various machine learning (ML) techniques to explore different options for feature selection, model fitting, and tuning algorithms with the ultimate goal of arriving at optimal 3D-CoMSIA models with high predictivity for the FTC activity. Recursive Feature Selection and SelectFromModel techniques were applied for feature selection, resulting in a significant improvement in model fitting and predictivity (R2, RCV2, and R2_test) of 24 estimators. However, these selection methods did not fully address the problem of overfitting and, in some instances, even exacerbated it. On the other hand, hyperparameter tuning for tree-based models resulted in dissimilar levels of model generalization for four tree-based models. GB-RFE coupled with GBR (hyperparameters: learning_rate = 0.01, max_depth = 2, n_estimators = 500, subsample = 0.5) was the only combination that effectively mitigated overfitting and demonstrated superior performance (RCV2 of 0.690, R2_test of 0.759, and R2 of 0.872) compared to the best linear model, PLS (with RCV2 of 0.653, R2_test of 0.575, and R2 of 0.755). Therefore, it was subsequently utilized to screen potential antioxidants among a range of Tryptophyllin L tripeptide fragments, leading to the synthesis and testing of three peptides: F-P-5Htp, F-P-W, and P-5Htp-L. These peptides exhibited promising activity levels, with FTC values of 4.2 ± 0.12, 4.4 ± 0.11, and 1.72 ± 0.15, respectively.

Antioxidant activities of major tryptophyllin L peptides: A joint investigation of Gaussian-based 3D-QSAR and radical scavenging experiments

The red tree frog Litoria rubella from Australia has been studied for several decades showing that their dorsal skin glands secrete a number of small peptides containing a Pro-Trp sequence, known as tryptophyllin L peptides. Although peptides from many genera of Australian frogs have been reported to possess a variety of biological activities, the bioactivities of this peptide family have remained to be discovered. In this study, we investigated the antioxidant potency of a number of tryptophyllin L peptides for the first time using a joint statistical and experimental approach in which predictions based on Gaussian three-dimensional quantitative structure-activity relationship (3D-QSAR) models were employed to guide an in vitro experimental investigation. Two tryptophyllin tripeptides P-W-L (OH) and P-W-L (NH₂ ) were predicted to have the Trolox equivalent antioxidant capacity (TEAC) values of 0.80 and 0.87 μM Trolox/μM peptide, respectively. With those promising results, antioxidant capabilities of five tryptophyllin L peptides with the common core Pro-Trp-Leu were synthesized and subjected to 1,1-diphenyl-2-picrylhydrazyl (DPPH), ferric reducing ability of plasma (FRAP) and 2,2'-azino-bis(3-ethylbenzothiazoline-6-sulphonic acid) radical cation (ABTS˙⁺ ) radical scavenging assays. The tests indicated that all the tested tryptophyllin L peptides, noticeably S-P-W-L (OH) and F-P-W-L (NH₂ ), are strong ABTS˙⁺ radical scavengers and moderate scavengers in the other two assays. The results, thus, suggested that the tryptophyllin L peptides are likely to be a part of the skin antioxidant system helping the frog to cope with drastic change in oxygen exposure and humidity, as they inhabit over a large area of Australia with a wide climate variation.