Bacterial infections and resistance to antibiotic drugs represent the highest challenges to public health. The search for new and promising compounds with anti-bacterial activity is a very urgent matter. In order to promote the development of platforms enabling to the discovery of compounds with anti-bacterial activity, Fourier Transformed Mid-Infrared (FT-MIR) spectroscopy associated with the machine learning algorithms were used to predict the impact of compounds extracted from Cynara cardunculus against Escherichia coli cells. According to the plant tissue (seeds, dry and fresh leaves, and flowers) and the solvents (ethanol, methanol, acetone, ethyl acetate, and water), compounds with different compositions concerning, phenol content, antioxidant, and antimicrobial activity were obtained. Principal component analysis of spectra, allowed to discriminate compounds that inhibit the E. coli growth, according to the conventional assay. The supervised classification models enabled the prediction of the compound's impact on the E. coli growth, with the accuracy for the test data: Partial least squares-discriminant analysis of 94%; Support vector machines of 89%; k-Nearest neighbor of 72%; and a Backpropagation network of 100%. According to the promising results, the integration of FT-MIR spectroscopy with machine learning presents a high potential to promote the discovery of new compounds with antibacterial activity, thereby streamlining the drug exploratory process.

In globe artichoke both the edible portion and the waste biomass are recognized as valuable sources of bioactive compounds. For this study, heads with 30 cm-long floral stems, including 2-3 leaves, were harvested from five genotypes which included two traditional vegetatively-propagated varietal types (‘Brindisino,’ and ‘Violetto di Foggia,’) and three "seed"-propagated hybrids (‘Tempo,’ ‘Opal,’ and ‘Madrigal’). The study aimed to determine the total and individual polyphenolic concentrations (measured spectrophotometrically and by HPLC) and antioxidant activity (AA) in different artichoke parts, namely the "hearts" (H), head waste (HW), stem waste (SW), and leaf waste (LW). ‘Brindisino’ SW exhibited the highest accumulation of luteolin (26,317 mg kg−1 F.W.), while ‘Tempo’ H displayed the highest cynarin content (190 mg kg−1 F.W.). ‘Tempo’ HW and H showed the highest levels of apigenin (640 mg kg−1 F.W.), and the greatest source of chlorogenic acid was found in the HW of ‘Opal’ and the H of ‘Brindisino’ (4,300 mg kg−1 F.W.). The hybrids generally exhibited lower total polyphenolic concentrations than the traditional genotypes, particularly evident in the LW. The SW demonstrated the highest concentration of total polyphenols (18,000 mg kg−1 F.W.), followed by the edible H and non-edible HW (12,000 mg kg−1 F.W.), while the LW exhibited the lowest concentration (2,000 mg kg−1 F.W.). Interestingly, the AA did not precisely align with the total polyphenolic concentration, showing slight variations between the examined parts and genotypes.