Olive anthracnose, mainly caused by Colletotrichum acutatum, is considered a key biotic constraint of the olive crop worldwide. This work aimed to evaluate the ability of the endophytes Aureobasidium pullulans and Sarocladium summerbellii isolated from olive trees to reduce C. acutatum growth and anthracnose symptoms, and to assess A. pullulans-mediated changes in olive fruit volatile organic compounds (VOCs) and their consequences on anthracnose development. Among the endophytes tested, only A. pullulans significantly reduced the incidence (up to 10-fold) and severity (up to 35-fold) of anthracnose in detached fruits, as well as the growth (up to 1.3-fold), sporulation (up to 5.9-fold) and germination (up to 3.5-fold) of C. acutatum in dual culture assays. Gas chromatography–mass spectrometry analysis of olives inoculated with A. pullulans + C. acutatum and controls (olives inoculated with C. acutatum, A. pullulans or Tween) led to the identification of 37 VOCs, with alcohols being the most diversified and abundant class. The volatile profile of A. pullulans + C. acutatum revealed qualitative and quantitative differences from the controls and varied over the time course of microbial interactions. The most significant differences among treatments were observed at a maximal reduction in anthracnose development. At this stage, a set of VOCs, particularly Z-3-hexen-1-ol, benzyl alcohol and nonanal, were highly positively correlated with the A. pullulans + C. acutatum treatment, suggesting they play a critical role in anthracnose reduction. 6-Methyl-5-hepten-2-one and 2-nonanone were positively associated with the C. acutatum treatment and thus likely have a role in pathogen infection.

Next-Generation Sequencing (NGS) is used as a diagnostic strategy for identifying pathogenic genetic variants in children and adults. However, the analysis is complex, requiring specialized bioinformaticians, and it can take weeks to finalize one study. This has been a limiting factor for the application of NGS in the screening of populations for rare genetic diseases. In this work, we show two case studies, where we applied an AI-driven bioinformatics framework in a diagnostic and a preventive scenario, respectively. The AI analysis was accurate and substantially faster than using conventional bioinformatics tools. Our results support the concept that AI-driven bioinformatics is a scalable solution for rendering accurate results and enabling a more widely available genetic screening for rare diseases.