Explainable machine learning for predicting diarrhetic shellfish poisoning events in the Adriatic Sea using long-term monitoring data.

In this study, explainable machine learning techniques are applied to predict the toxicity of mussels in the Gulf of Trieste (Adriatic Sea) caused by harmful algal blooms. By analysing a newly created 28-year dataset containing records of toxic phytoplankton in mussel farming areas and diarrhetic shellfish toxins in mussels (Mytilus galloprovincialis), we train and evaluate the performance of machine learning (ML) models to accurately predict diarrhetic shellfish poisoning (DSP) events. Based on the F1 score, the random forest model provided the best prediction of toxicity results at which the harvesting of mussels is stopped according to EU regulations.

Okadaic acid as a major problem for the seafood safety (Mytilus galloprovincialis) and the dynamics of toxic phytoplankton in the Slovenian coastal sea (Gulf of Trieste, Adriatic Sea).

This article presents the first results on shellfish toxicity in the Slovenian sea (Gulf of Trieste, Adriatic Sea) since the analytical methods for the detection of biotoxins (PSP, ASP, DSP and other lipophilic toxins) in bivalve molluscs were included in the national monitoring program in 2013. In addition to toxins, the composition and abundance of toxic phytoplankton and general environmental characteristics of the seawater (surface temperature and salinity) were also monitored. During the 2014-2019 study period, only lipophilic toxins were detected (78 positive tests out of 446 runs), of which okadaic acid (OA) predominated in 97 % of cases, while dinophysistoxin-2 and yessotoxins only gave a positive result in one sampling event each.

On-chip recapitulation of the tumor microenvironment: A decade of progress.

One of the hurdles to the development of new anticancer therapies is the lack of in vitro models which faithfully reproduce the in vivo tumor microenvironment (TME). Understanding the dynamic relationships between the components of the TME in a controllable, scalable, and reliable setting would indeed support the discovery of biological targets impacting cancer diagnosis and therapy. Cancer research is increasingly shifting from traditional two-dimensional (2D) cell culture toward three-dimensional (3D) culture models, which have been demonstrated to increase the significance and predictive value of in vitro data.

Exploring the mesoscale connectivity of phytoplankton periodic assemblages' succession in northern Adriatic pelagic habitats.

An appropriate model for phytoplankton distribution patterns is critical for understanding biogeochemical cycles and trophic interactions in the oceans and seas. Because phytoplankton dynamics in coastal waters are more complex due to shallow depth and proximity to land, more accurate models applied to the correct spatial and temporal scales are needed. Our study investigates the role of the atmosphere and hydrosphere in pelagic habitat by modelling phytoplankton assemblages at two Long Term Ecological Research sites in the northern Adriatic Sea using niche-forming environmental variables (wind, temperature, salinity, river discharge, rain, and water column stratification).