A non-invasive, sensor-based approach to exploit the autofluorescence of saffron (Crocus sativus L.) for on-site evaluation of aging.

So far, compliance with ISO 3632 standard specifications for top-quality saffron guarantees good agricultural and post-harvest production practices. Tracking early-stage oxidation remains challenging. Our study aims to address this issue by exploring the visible, fluorescence, and near-infrared spectra of category I saffron. Using a multi-spectral sensor, we tested fresh and artificially aged saffron in powder form. High autofluorescence intensities at 600-700 nm allowed calibration for the 'content of aged saffron'. Samples with minimum coloring strength (200-220 units) were classified as 70% aged, while those exceeding maximum aroma strength (50 units) as 100% aged. Consistent patterns across origin, age, and processing history indicated potential for objectively assessing early-oxidation markers. Further analyses uncovered multiple contributing fluorophores, including cis-apocarotenoids, correlated with FTIR-based aging markers. Our findings underscore that sensing autofluorescence of traded saffron presents an innovative quality diagnostic approach, paving new research pathways for assessing the remaining shelf-life along its supply chain.

Discovering the hidden messages within cell trajectories using a deep learning approach for in vitro evaluation of cancer drug treatments.

We describe a novel method to achieve a universal, massive, and fully automated analysis of cell motility behaviours, starting from time-lapse microscopy images. The approach was inspired by the recent successes in application of machine learning for style recognition in paintings and artistic style transfer. The originality of the method relies i) on the generation of atlas from the collection of single-cell trajectories in order to visually encode the multiple descriptors of cell motility, and ii) on the application of pre-trained Deep Learning Convolutional Neural Network architecture in order to extract relevant features to be used for classification tasks from this visual atlas. Validation tests were conducted on two different cell motility scenarios: 1) a 3D biomimetic gels of immune cells, co-cultured with breast cancer cells in organ-on-chip devices, upon treatment with an immunotherapy drug; 2) Petri dishes of clustered prostate cancer cells, upon treatment with a chemotherapy drug. For each scenario, single-cell trajectories are very accurately classified according to the presence or not of the drugs. This original approach demonstrates the existence of universal features in cell motility (a so called "motility style") which are identified by the DL approach in the rationale of discovering the unknown message in cell trajectories.