Die Plant Science Student Conference (PSSC) wird seit 20 Jahren im jährlichen Wechsel von Studierenden der beiden Leibniz-Institute IPK und IPB organisiert. Im Interview erläutern Christina Wäsch (IPK) und Carolin Apel (IPB),…
Über 600 Gäste kamen am 4. Juli ans IPB zur Langen Nacht, die Wissen schafft, um bei unserem Wissenschafts-Quiz-Parcours viel Neues zu erfahren und ihre Kenntnisse unter Beweis zu stellen. Unser Programm in diesem Jahr…
Herrera-Rocha, F.; Fernández-Niño, M.; Duitama, J.; P. Cala, M.; José Chica, M.; A. Wessjohann, L.; D. Davari, M.; Fernando González Barrios, A.;FlavorMiner: A Machine Learning Platform for Extracting Molecular Flavor Profiles from Structural DataChemRxiv(2024)DOI: 10.26434/chemrxiv-2024-821xm
Flavor is the main factor driving consumers acceptance of food products. However, tracking the biochemistry of flavor is a formidable challenge due to the complexity of food composition. Current methodologies for linking individual molecules to flavor in foods and beverages are expensive and time-consuming. Predictive models based on machine learning (ML) are emerging as an alternative to speed up this process. Nonetheless, the optimal approach to predict flavor features of molecules remains elusive. In this work we present FlavorMiner, an ML-based multilabel flavor predictor. FlavorMiner seamlessly integrates different combinations of algorithms and mathematical representations, augmented with class balance strategies to address the inherent class of the input dataset. Notably, Random Forest and K-Nearest Neighbors combined with Extended Connectivity Fingerprint and RDKit molecular descriptors consistently outperform other combinations in most cases. Resampling strategies surpass weight balance methods in mitigating bias associated with class imbalance. FlavorMiner exhibits remarkable accuracy, with an average ROC AUC score of 0.88. This algorithm was used to analyze cocoa metabolomics data, unveiling its profound potential to help extract valuable insights from intricate food metabolomics data. FlavorMiner can be used for flavor mining in any food product, drawing from a diverse training dataset that spans over 934 distinct food products.
Publikation
Abel, S.; Naumann, C.;Evolution of phosphate scouting in the terrestrial biospherePhilosophical Transactions of the Royal Society B: Biological Sciences37920230355(2024)DOI: 10.1098/rstb.2023.0355
Chemistry assigns phosphorus and its most oxidized form, inorganic phosphate, unique roles for propelling bioenergetics and metabolism in all domains of life, possibly since its very origin on prebiotic Earth. For plants, access to the vital mineral nutrient profoundly affects growth, development and vigour, thus constraining net primary productivity in natural ecosystems and crop production in modern agriculture. Unlike other major biogenic elements, the low abundance and uneven distribution of phosphate in Earth’s crust result from the peculiarities of phosphorus cosmochemistry and geochemistry. Here, we trace the chemical evolution of the element, the geochemical phosphorus cycle and its acceleration during Earth’s history until the present (Anthropocene) as well as during the evolution and rise of terrestrial plants. We highlight the chemical and biological processes of phosphate mobilization and acquisition, first evolved in bacteria, refined in fungi and algae and expanded into powerful phosphate-prospecting strategies during land plant colonization. Furthermore, we review the evolution of the genetic and molecular networks from bacteria to terrestrial plants, which monitor intracellular and extracellular phosphate availabilities and coordinate the appropriate responses and adjustments to fluctuating phosphate supply. Lastly, we discuss the modern global phosphorus cycle deranged by human activity and the challenges imposed ahead.
This article is part of the theme issue ‘Evolution and diversity of plant metabolism’.