Martin Marzidovšek

Martin Marzidovšek, Vid Podpečan, Erminia Conti et al.

BEFANA is a free and open-source software tool for ecological network analysis and visualisation. It is adapted to ecologists' needs and allows them to study the topology and dynamics of ecological networks as well as apply selected machine learning algorithms. BEFANA is implemented in Python, and structured as an ordered collection of interactive computational notebooks. It relies on widely used open-source libraries, and aims to achieve simplicity, interactivity, and extensibility. BEFANA provides methods and implementations for data loading and preprocessing, network analysis and interactive visualisation, modelling with experimental data, and predictive modelling with machine learning. We showcase BEFANA through a concrete example of a detrital soil food web of agricultural grasslands, and demonstrate all of its main components and functionalities.

Martin Marzidovšek, Janja Francé, Vid Podpečan et al.

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 toxin concentrations in mussels (Mytilus galloprovincialis), we train and evaluate the performance of ML models to accurately predict diarrhetic shellfish poisoning (DSP) events. The random forest model provided the best prediction of positive toxicity results based on the F1 score. Explainability methods such as permutation importance and SHAP identified key species (Dinophysis fortii and D. caudata) and environmental factors (salinity, river discharge and precipitation) as the best predictors of DSP outbreaks. These findings are important for improving early warning systems and supporting sustainable aquaculture practices.

Matej Martinc, Blaž Škrlj, Sergej Pirkmajer et al.

The abundance of literature related to the widespread COVID-19 pandemic is beyond manual inspection of a single expert. Development of systems, capable of automatically processing tens of thousands of scientific publications with the aim to enrich existing empirical evidence with literature-based associations is challenging and relevant. We propose a system for contextualization of empirical expression data by approximating relations between entities, for which representations were learned from one of the largest COVID-19-related literature corpora. In order to exploit a larger scientific context by transfer learning, we propose a novel embedding generation technique that leverages SciBERT language model pretrained on a large multi-domain corpus of scientific publications and fine-tuned for domain adaptation on the CORD-19 dataset. The conducted manual evaluation by the medical expert and the quantitative evaluation based on therapy targets identified in the related work suggest that the proposed method can be successfully employed for COVID-19 therapy target discovery and that it outperforms the baseline FastText method by a large margin.