Digitalni repozitorij raziskovalnih organizacij Slovenije

Iskanje po repozitoriju
A+ | A- | Pomoč | SLO | ENG

Iskalni niz: išči po
išči po
išči po
išči po

Možnosti:
  Ponastavi


Iskalni niz: "avtor" (Barbara Koroušić-Seljak) .

1 - 10 / 32
Na začetekNa prejšnjo stran1234Na naslednjo stranNa konec
1.
Explainable machine learning for assessing the metabolomic and elemental profiles of tomatoes irrigated with treated wastewater
Anja Vehar, Jan Drole, Tome Eftimov, Nina Kacjan-Maršić, Barbara Koroušić-Seljak, Ester Heath, Nives Ogrinc, 2026, izvirni znanstveni članek

Povzetek: While reusing treated wastewater (TWW) for irrigation provides a sustainable solution to water scarcity, it can potentially introduce contaminants that may threaten crop safety and quality. Consequently, further research is needed to understand the effects of TWW on the metabolomic and elemental profiles of irrigated crops. This study investigated how using TWW affect metabolism and element uptake in tomatoes grown in soil (lysimeters) and soilless (hydroponics) systems. Soil-grown tomatoes were irrigated with potable water, treated wastewater, and treated wastewater spiked with 14 CECs (0.1 mg/L), which included bisphenols, non-steroidal anti-inflammatory drugs, estrogens, and caffeine. Hydroponically grown tomatoes were grown in a nutrient solution, with or without CECs. Tomatoes were assessed by analysing sugars, organic acids, polyphenols, carotenoids, amino acids, fatty acids, and elements. Classification machine learning models were applied, and the best-performing model, a decision tree classifier, achieved 88% accuracy in distinguishing treatments under stratified five-fold cross-validation. The SHAP method identified key metabolites (ascorbic, palmitic, margaric, oleic, linoleic, behenic acids) and elements (Cd, Co, Cs, Cu, P, Na) that drive treatment differentiation. This study demonstrates how explainable machine learning can decode complex metabolic interactions, providing insights into the effects of using treated wastewater in agriculture.
Ključne besede: contaminants of emerging concern, metabolites, explainable machine learning
Objavljeno v DiRROS: 04.09.2026; Ogledov: 77; Prenosov: 58
.pdf Celotno besedilo (6,13 MB)
Gradivo ima več datotek! Več...

2.
Large language models in food and nutrition science : opportunities, challenges, and the case of FoodyLLM
Ana Gjorgjevikj, Matej Martinc, Gjorgjina Cenikj, Jan Drole, Nives Ogrinc, Sašo Džeroski, Barbara Koroušić-Seljak, Tome Eftimov, 2026, izvirni znanstveni članek

Povzetek: Background Reliable nutrient profiling and semantic interoperability are essential for scalable dietary assessment, food labeling (e.g., traffic-light schemes), and FAIR integration of food composition and consumption data. However, general-purpose large language models (LLMs) are not systematically exposed to structured recipe–nutrition mappings and food ontologies, limiting their accuracy and trustworthiness in food and nutrition tasks. Scope and approach We review recent LLM advances in life sciences and healthcare and analyze the gap in food and nutrition applications. To address this gap, we introduce FoodyLLM, a domain-specialized LLM fine-tuned on 225k task-aligned QA pairs for (i) recipe nutrient estimation, (ii) traffic-light classification, and (iii) ontology-based entity linking to support FAIR food data interoperability. We benchmark FoodyLLM against strong general-purpose baselines (e.g., Llama 3 8B, Gemini 2.0) under zero-/few-shot prompting across five evaluation folds. Key findings Across all tasks, FoodyLLM substantially outperforms general-purpose LLMs for nutrient estimation across all macronutrients (fat, protein, salt, saturates, sugar), accuracy increases from 0.43 to 0.63 to 0.91–0.97; for traffic-light classification across all nutrients and color categories, macro F1 improves from 0.46 to 0.80 to 0.86–0.97; and for ontology-based food entity linking across FoodOn, SNOMED-CT, and Hansard, macro F1 increases from 0.33 to 0.44 (best general-purpose baseline) to 0.93–0.98 on artificial NEL data, and from 0.24 to 0.51 to 0.67–0.84 on real corpora (CafeteriaSA and CafeteriaFCD). Overall, our results demonstrate the practical value of domain-specialized LLMs in food and nutrition research. They enable automated dietary assessment, large-scale nutritional monitoring, and FAIR data integration, while opening new pathways toward sustainable and personalized nutrition.
Ključne besede: FoodyLLM, nutrient estimation, data interoperability
Objavljeno v DiRROS: 04.03.2026; Ogledov: 1214; Prenosov: 511
.pdf Celotno besedilo (6,37 MB)
Gradivo ima več datotek! Več...

3.
Changing the default order of food items in an online grocery store may nudge healthier food choices
Eva Valenčič, Emma Beckett, Clare Elizabeth Collins, Barbara Koroušić-Seljak, Tamara Bucher, 2024, izvirni znanstveni članek

Povzetek: Restructuring food environments, such as online grocery stores, has the potential to improve consumer health by encouraging healthier food choices. The aim of this study was to investigate whether repositioning foods within an experimental online grocery store can be used to nudge healthier choices. Specifically, we investigated whether repositioning product categories displayed on the website main page, and repositioning individual products within those categories, will influence selection. Adults residing in Australia (n = 175) were randomised to either intervention (high-fibre foods on top) or comparator condition (high-fibre foods on the bottom). Participants completed a shopping task using the experimental online grocery store, with a budget of up to AU$100 to for one person's weekly groceries. The results of this study show that the total fibre content per 100 kcal per cart (p < .001) and total fibre content per cart (p = .036) was higher in the intervention compared to comparator condition. Moreover, no statistical difference between conditions was found for the total number of fibre-source foods (p = .67), the total energy per cart (p = .17), and the total grocery price per cart (p = .70) indicating no evidence of implications for affordability. Approximately half of the participants (48%) reported that they would like to have the option to sort foods based on a specific nutrient criterion when shopping online. This study specifically showed that presenting higher-fibre products and product categories higher up on the online grocery store can increase the fibre content of customers' purchases. These findings have important implications for consumers, digital platform operators, researchers in health and food domains, and for policy makers.
Ključne besede: online grocery stores, digital nudging, consumer health, food environment, choice behavior, snacks, snack choice, healthy food, food choice
Objavljeno v DiRROS: 19.01.2026; Ogledov: 811; Prenosov: 525
.pdf Celotno besedilo (2,18 MB)
Gradivo ima več datotek! Več...

4.
NutriBase – management system for the integration and interoperability of food- and nutrition-related data and knowledge
Eva Valenčič, Emma Beckett, Tamara Bucher, Clare Elizabeth Collins, Barbara Koroušić-Seljak, 2025, izvirni znanstveni članek

Povzetek: Contemporary data and knowledge management and exploration are challenging due to regular releases, updates, and different types and formats. In the food and nutrition domain, solutions for integrating such data and knowledge with respect to the FAIR (Findability, Accessibility, Interoperability, and Reusability) principles are still lacking.
Objavljeno v DiRROS: 19.01.2026; Ogledov: 511; Prenosov: 225
.pdf Celotno besedilo (3,23 MB)

5.
Measuring biological age : insights from omics studies
Eva Kočar, Robert Šket, Ana Halužan Vasle, Gorazd Avguštin, Evgen Benedik, Barbara Koroušić-Seljak, Pavle Simić, Antonio Martinko, Shawnda A. Morrison, Maroje Sorić, Mihaela Skrt, Tomaž Polak, Tine Tesovnik, Barbara Jenko Bizjan, Jernej Kovač, Tadej Battelino, Damjana Rozman, Nataša Poklar Ulrih, Bojana Bogovič Matijašić, Gregor Jurak, Miha Moškon, Tadeja Režen, 2026, pregledni znanstveni članek

Povzetek: Biological ageing is a systemic, multifactorial process driven by progressive molecular and cellular alterations whose complexity necessitates systems-level approaches. Advances in high-throughput omics technologies now allow simultaneous quantification of millions of biomolecules from a single specimen, enabling longitudinal, integrative profiling across multiple molecular layers. This review synthesizes recent progress in applying genomics, epigenomics, metabolomics and microbiomics to ageing research, highlighting their contributions to biomarker discovery, mechanistic insight, and translational opportunities. Genomic studies reveal genetic variants that promote extreme longevity, while epigenetic clocks provide robust predictors of biological age. The blood proteome can be used to calculate proteome-based scores and evaluate temporal changes in ageing trajectories in an organ- and sex-specific manner. Metabolomic signatures identify key metabolites reflecting ageing trajectories, and microbiome research demonstrates that gut microbial composition mirrors and modulates biological ageing, with microbiome clocks emerging. The omics approaches have further elucidated the impact of exercise and diet providing evidence that interventions can reduce biological age. The integration of multi-omics with clinical and lifestyle data, powered by machine learning and artificial intelligence, is paving the way for a holistic definition of biological age and the development of personalized healthy ageing strategies. This review highlights how the omics technologies and computational modelling are transforming ageing biology into strategies for personalized healthy ageing.
Ključne besede: ageing, biological ageing, omics, physical fitness, nutrition, computational modelling
Objavljeno v DiRROS: 08.01.2026; Ogledov: 958; Prenosov: 465
.pdf Celotno besedilo (2,08 MB)
Gradivo ima več datotek! Več...

6.
7.
8.
9.
10.
Iskanje izvedeno v 0.22 sek.
Na vrh