Human dihydrofolate reductase (hDHFR) is a crucial cellular enzyme in folate metabolic pathway, where it catalyzes the reduction of dihydrofolate into tetrahydrofolate (THF) and an important cofactor involved in DNA, RNA, protein biosynthesis and cell proliferation. Due to its importance, hDHFR has become a promising target for therapeutic development, particularly in treating cancer, bacterial infections, and autoimmune diseases. Its inhibition has found clinical value in antitumor, antimicrobial and antiprotozoal treatment; however, the emergence of resistance to existing hDHFR inhibitors necessitates the development of new and more potent compounds. In the current study, we propose a cheminformatics-based approach using machine learning to develop predictive models of hDHFR bioactivity. We used three types of molecular descriptors in the form of fingerprints, i.e., PubChem, Substructure, and MACCS, to capture structural properties associated with hDHFR inhibition. Predictive models were built using a random forest algorithm optimized through hyperparameter tuning. Feature selection was performed using Recursive Feature Elimination (RFE), and dataset dimensionality was reduced by removing outliers through Principal Component Analysis (PCA) to optimize model performance and reducing overfitting and weak predictivity. The resulting models are validated through external test sets, domain applicability analysis, and interpretation of influential molecular features via random forest feature importance selection plots and correlation matrix analysis. All three models exhibited strong predictive capabilities, with R-squared (R2) values ranging from 0.9849 to 0.9934 for the training set and 0.9381 to 0.9591 for the test set. These final predictive models were further incorporated into an accessible web application, enabling users to estimate the bioactivity of new compounds targeting hDHFR.
Argan oil production generates large amounts of press cake that remain underexploited despite their potential as a functional ingredient due to their high protein and fiber content. This study aimed to evaluate the effects of solid-state fermentation of argan press cake (APC) for 24 h and 48 h at 30 °C using Pediococcus pentosaceus LUHS183, Pediococcus acidilactici LUHS29, and Lactiplantibacillus plantarum LUHS135. The effects of fermentation were assessed by determining pH, viable counts of lactic acid bacteria (LAB), free amino acid (FAA) profiles, including γ-aminobutyric acid, biogenic amine (BA) concentrations, fatty acid (FA) and volatile compound (VC) profiles. Additionally, antimicrobial activity was evaluated against 15 pathogenic strains. Fermented samples showed LAB growth, lower pH values than the control, and antimicrobial activity against several of the tested strains. FAA profiles varied among the samples. Only two of the eight BA analyzed, namely spermidine and spermine, were detected in all APC samples. Their concentrations in the control were 29.4 ± 2.29 mg/kg and 29.7 ± 3.66 mg/kg, respectively. Unfermented and fermented samples shared the same predominant FA. Overall, the observed biochemical profiles and antimicrobial activity support further investigation of fermented APC as a potential value-added ingredient in food applications.
Argan oil production generates large amounts of press cake that remain underexploited despite its potential as a functional ingredient. The objective of this study therefore aimed to evaluate the effects of solid-state fermentation (24h and 48h at 30 °C) using three strains of lactic acid bacteria (LAB)—Pediococcus pentosaceus, Pediococcus acidilactici, and Lactiplantibacillus plantarum on the functional properties of argan press cake (APC). The effects of fermentation were assessed by determining pH, LAB viable counts, free amino acid (FAA) profiles (including γ-aminobutyric acid), biogenic amine (BA) concentrations, fatty acid (FA) and volatile compound (VC) profiles. Additionally, the antimicrobial activity were evaluated against 15 pathogenic strains. The results showed growth of LAB, followed by a decrease in pH, which correlated with antimicrobial activity against pathogens in the fermented samples. As for free amino acids, their bioavailability increased in the fermented samples. Only two biogenic amines namely spermidine (29.4 ± 2.29 mg/kg) and spermine (29.7 ± 3.66 mg/kg) were identified in all argan cake samples. Furthermore, no changes were observed in the fatty acid profile. Overall, solid-state fermentation improved the biochemical and antimicrobial properties of argan press cake without compromising its lipid quality or safety.
About Me
I m Sakho Mahamadou Phd Student at faculty of Medecine and Pharmlacy of Tangier
I m Sakho Mahamadou Phd Student at faculty of Medecine and Pharmlacy of Tangier