Background: Peptides are a class of molecules that can be presented as good antimicrobials and with mechanisms that avoid resistance, and the design of peptides with good activity can be complex and laborious. The study of their quantitative structure–activity relationships through machine learning algorithms can shed light on a rational and effective design. Methods: Information on the antimicrobial activity of peptides was collected, and their structures were characterized by molecular descriptors generation to design regression and classification models based on machine learning algorithms. The contribution of each descriptor in the generated models was evaluated by determining its relative importance and, finally, the antimicrobial activity of new peptides was estimated. Results: A structured database of antimicrobial peptides and their descriptors was obtained, with which 56 machine learning models were generated. Random Forest-based models showed better performance, and of these, regression models showed variable performance (R2 = 0.339–0.574), while classification models showed good performance (MCC = 0.662–0.755 and ACC = 0.831–0.877). Those models based on bacterial groups showed better performance than those based on the entire dataset. The properties of the new peptides generated are related to important descriptors that encode physicochemical properties such as lower molecular weight, higher charge, propensity to form alpha-helical structures, lower hydrophobicity, and higher frequency of amino acids such as lysine and serine. Conclusions: Machine learning models allowed to establish the structure–activity relationships of antimicrobial peptides. Classification models performed better than regression models. These models allowed us to make predictions and new peptides with high antimicrobial potential were proposed.
Background: Peru is one of the most biodiverse countries in the world, which is reflected in its wealth of knowledge about medicinal plants. However, there is a lack of information regarding intestinal absorption and the permeability of natural products. The human colon adenocarcinoma cell line (Caco-2) is an in vitro assay used to measure apparent permeability. This study aims to develop a quantitative structure–property relationship (QSPR) model using machine learning algorithms to predict the apparent permeability of the Caco-2 cell in natural products from Peru. Methods: A dataset of 1817 compounds, including experimental log Papp values and molecular descriptors, was utilized. Six QSPR models were constructed: a multiple linear regression (MLR) model, a partial least squares regression (PLS) model, a support vector machine regression (SVM) model, a random forest (RF) model, a gradient boosting machine (GBM) model, and an SVM–RF–GBM model. Results: An evaluation of the testing set revealed that the MLR and PLS models exhibited an RMSE = 0.47 and R2 = 0.63. In contrast, the SVM, RF, and GBM models showcased an RMSE = 0.39–0.40 and R2 = 0.73–0.74. Notably, the SVM–RF–GBM model demonstrated superior performance, with an RMSE = 0.38 and R2 = 0.76. The model predicted log Papp values for 502 natural products falling within the applicability domain, with 68.9% (n = 346) showing high permeability, suggesting the potential for intestinal absorption. Additionally, we categorized the natural products into six metabolic pathways and assessed their drug-likeness. Conclusions: Our results provide insights into the potential intestinal absorption of natural products in Peru, thus facilitating drug development and pharmaceutical discovery efforts.
The ability of multifunctional food-derived peptides to act on different body targets make them promising alternatives in the prevention/management of chronic disorders. The potential of Erythrina edulis (pajuro) protein as a source of multifunctional peptides was proven. Fourteen selected synthetic peptides identified in an alcalase hydrolyzate from pajuro protein showed in vitro antioxidant, anti-hypertensive, anti-diabetic, and/or anti-obesity effects. The radical scavenging properties of the peptides could be responsible for the potent protective effects observed against the oxidative damage caused by FeSO4 in neuroblastoma cells. Moreover, their affinity towards the binding cavity of angiotensin-converting enzyme (ACE) and dipeptidyl peptidase IV (DPP-IV) were predicted by molecular modeling. The results demonstrated that some peptides such as YPSY exhibited promising binding at both enzymes, supporting the role of pajuro protein as a novel ingredient of functional foods or nutraceuticals for prevention/management of oxidative stress, hypertension, and metabolic-alteration-associated chronic diseases.
Outdoor air pollution is a mixture of multiple atmospheric pollutants, among which nitrogen oxide (NOx) stands out due to its association with several diseases. NOx reactivity can conduct to DNA damage as severe as interstrand crosslinks (ICL) formation, that in turn is able to block DNA replication and transcription. Experimental studies have suggested that the ICL formation due to NOx is realized through a diazonium intermediate (DI). In this work, we have modeled the DI structure, including a DNA double-strand composed of two base pairs GC/CG, being diazotized as one of the guanine nucleotides. The structural stability of DNA with DI lesion was essayed through 500 ns molecular dynamics simulations. It was found that the DNA structure of the oligonucleotide is stable when the DI is present since the loss of a Guanine–Cytosine hydrogen bond is replaced by the presence of two cation-π interactions. Additionally, we have studied the mechanism of formation of a crosslink between the two guanine nucleobases from the modeled DI by carrying out DFT calculations at the M06-L/DNP+ level of theory. Our results show that the mechanism is thermodynamically favored by a strong stabilization of the ICL product, and the process is kinetically viable since its limiting stage is accessible.
Binding of fibroblast growth factor (FGF) to a heparan sulfate proteoglycan (HSPG) is required for paracrine FGF signaling. To improve our understanding of FGF:HSPG association, we developed a method to monitor the in vivo export of Drosophila Branchless (Bnl), an FGF ortholog. We detected Bnl on the surface of ∼10% of Bnl-producing cells, and the amount of Bnl was reduced on the surface of cells depleted of heparan sulfate (HS). HS depletion also non-autonomously decreased the activity of cytonemes that extend from cells that receive Bnl. These results are consistent with the idea that Bnl export to the cell surface is regulated not constitutive, that intracellular Bnl:HSPG binding in producing cells is essential for FGF export, and that cells that take up Bnl actively participate in its release from producing cells.