Know Center Research

Publikationen

Malinverno Luca, Barros Vesna, Ghisoni Francesco, Visonà Giovanni, Kern Roman, Nickel Philip , Ventura Barbara Elvira, Simic Ilija, Stryeck Sarah, Manni Francesca , Ferri Cesar , Jean-Quartier Clair, Genga Laura , Schweikert Gabriele, Lovric Mario, Rosen-Zvi Michal
2023
Understanding the inner working of machine-learning models has become a crucial point of discussion in fairness and reliability of artificial intelligence (AI). In this perspective, we reveal insights from recently published scientific works on explainable AI (XAI) within the biomedical sciences. Specifically, we speculate that the COVID-19 pandemic is associated with the rate of publications in the field. Current research efforts seem to be directed more toward explaining black-box machine-learning models than designing novel interpretable architecture. Notably, an inflection period in the publication rate was observed in October 2020, when the quantity of XAI research in biomedical sciences surged upward significantly.While a universally accepted definition of explainability is unlikely, ongoing research efforts are pushing the biomedical field toward improving the robustness and reliability of applied machine learning, which we consider a positive trend.
Evangelidis Thomas, Giassa Ilektra-Chara , Lovric Mario
2022
Identifying hit compounds is a principal step in early-stage drug discovery. While many machine learning (ML) approaches have been proposed, in the absence of binding data, molecular docking is the most widely used option to predict binding modes and score hundreds of thousands of compounds for binding affinity to the target protein. Docking's effectiveness is critically dependent on the protein-ligand (P-L) scoring function (SF), thus re-scoring with more rigorous SFs is a common practice. In this pilot study, we scrutinize the PM6-D3H4X/COSMO semi-empirical quantum mechanical (SQM) method as a docking pose re-scoring tool on 17 diverse receptors and ligand decoy sets, totaling 1.5 million P-L complexes. We investigate the effect of explicitly computed ligand conformational entropy and ligand deformation energy on SQM P-L scoring in a virtual screening (VS) setting, as well as molecular mechanics (MM) versus hybrid SQM/MM structure optimization prior to re-scoring. Our results proclaim that there is no obvious benefit from computing ligand conformational entropies or deformation energies and that optimizing only the ligand's geometry on the SQM level is sufficient to achieve the best possible scores. Instead, we leverage machine learning (ML) to include implicitly the missing entropy terms to the SQM score using ligand topology, physicochemical, and P-L interaction descriptors. Our new hybrid scoring function, named SQM-ML, is transparent and explainable, and achieves in average 9\% higher AUC-ROC than PM6-D3H4X/COSMO and 3\% higher than Glide SP, but with consistent and predictable performance across all test sets, unlike the former two SFs, whose performance is considerably target-dependent and sometimes resembles that of a random classifier. The code to prepare and train SQM-ML models is available at \url{https://github.com/tevang/sqm-ml.git} and we believe that will pave the way for a new generation of hybrid SQM/ML protein-ligand scoring functions.
Stipanicev Drazenka, Repec Sinisa, Vucic Matej, Lovric Mario, Klobucar Goran
2022
In order to prevent the spread of COVID-19, contingency measures in the form of lockdowns were implemented all over the world, including in Croatia. The aim of this study was to detect if those severe, imposed restrictions of social interactions reflected on the water quality of rivers receiving wastewaters from urban areas. A total of 18 different pharmaceuticals (PhACs) and illicit drugs (IDrgs), as well as their metabolites, were measured for 16 months (January 2020–April 2021) in 12 different locations at in the Sava and Drava Rivers, Croatia, using UHPLC coupled to LCMS. This period encompassed two major Covid lockdowns (March–May 2020 and October 2020–March 2021). Several PhACs more than halved in river water mass flow during the lockdowns. The results of this study confirm that Covid lockdowns caused lower cumulative concentrations and mass flow of measured PhACs/IDrgs in the Sava and Drava Rivers. This was not influenced by the increased use of drugs for the treatment of the COVID-19, like antibiotics and steroidal anti-inflammatory drugs. The decreases in measured PhACs/IDrgs concentrations and mass flows were more pronounced during the first lockdown, which was stricter than the second.
Jean-Quartier Claire, Mazón Miguel Rey, Lovric Mario, Stryeck Sarah
2022
Research and development are facilitated by sharing knowledge bases, and the innovation process benefits from collaborative efforts that involve the collective utilization of data. Until now, most companies and organizations have produced and collected various types of data, and stored them in data silos that still have to be integrated with one another in order to enable knowledge creation. For this to happen, both public and private actors must adopt a flexible approach to achieve the necessary transition to break data silos and create collaborative data sharing between data producers and users. In this paper, we investigate several factors influencing cooperative data usage and explore the challenges posed by the participation in cross-organizational data ecosystems by performing an interview study among stakeholders from private and public organizations in the context of the project IDE@S, which aims at fostering the cooperation in data science in the Austrian federal state of Styria. We highlight technological and organizational requirements of data infrastructure, expertise, and practises towards collaborative data usage.
Malev Olga, Babic Sanja, Cota Anja Sima, Stipaničev Draženka, Repec Siniša, Drnić Martina, Lovric Mario, Bojanić Krunoslav, Radić Brkanac Sandra, Čož-Rakovac Rozelindra, Klobučar Göran
2022
This study focused on the short-term whole organism bioassays (WOBs) on fish (Danio rerio) and crustaceans (Gammarus fossarum and Daphnia magna) to assess the negative biological effects of water from the major European River Sava and the comparison of the obtained results with in vitro toxicity data (ToxCast database) and Risk Quotient (RQ) methodology. Pollution profiles of five sampling sites along the River Sava were assessed by simultaneous chemical analysis of 562 organic contaminants (OCs) of which 476 were detected. At each sampling site, pharmaceuticals/illicit drugs category was mostly represented by their cumulative concentration, followed by categories industrial chemicals, pesticides and hormones. An exposure-activity ratio (EAR) approach based on ToxCast data highlighted steroidal anti-inflammatory drugs, antibiotics, antiepileptics/neuroleptics, industrial chemicals and hormones as compounds with the highest biological potential. Summed EAR-based prediction of toxicity showed a good correlation with the estimated toxicity of assessed sampling sites using WOBs. WOBs did not exhibit increased mortality but caused various sub-lethal biological responses that were dependant relative to the sampling site pollution intensity as well as species sensitivity. Exposure of G. fossarum and D. magna to river water-induced lower feeding rates increased GST activity and TBARS levels. Zebrafish D. rerio embryo exhibited a significant decrease in heartbeat rate, failure in pigmentation formation, as well as inhibition of ABC transporters. Nuclear receptor activation was indicated as the biological target of greatest concern based on the EAR approach. A combined approach of short-term WOBs, with a special emphasis on sub-lethal endpoints, and chemical characterization of water samples compared against in vitro toxicity data from the ToxCast database and RQs can provide a comprehensive insight into the negative effect of pollutants on aquatic organisms.
Lovric Mario, Antunović Mario, Šunić Iva, Vuković Matej, Kecorius Simon, Kröll Mark, Bešlić Ivan, Godec Ranka, Pehnec Gordana, Geiger Bernhard, Grange Stuart K, Šimić Iva
2022
In this paper, the authors investigated changes in mass concentrations of particulate matter (PM) during the Coronavirus Disease of 2019 (COVID-19) lockdown. Daily samples of PM1, PM2.5 and PM10 fractions were measured at an urban background sampling site in Zagreb, Croatia from 2009 to late 2020. For the purpose of meteorological normalization, the mass concentrations were fed alongside meteorological and temporal data to Random Forest (RF) and LightGBM (LGB) models tuned by Bayesian optimization. The models’ predictions were subsequently de-weathered by meteorological normalization using repeated random resampling of all predictive variables except the trend variable. Three pollution periods in 2020 were examined in detail: January and February, as pre-lockdown, the month of April as the lockdown period, as well as June and July as the “new normal”. An evaluation using normalized mass concentrations of particulate matter and Analysis of variance (ANOVA) was conducted. The results showed that no significant differences were observed for PM1, PM2.5 and PM10 in April 2020—compared to the same period in 2018 and 2019. No significant changes were observed for the “new normal” as well. The results thus indicate that a reduction in mobility during COVID-19 lockdown in Zagreb, Croatia, did not significantly affect particulate matter concentration in the long-term
Hoffer Johannes Georg, Ofner Andreas Benjamin, Rohrhofer Franz Martin, Lovric Mario, Kern Roman, Lindstaedt Stefanie , Geiger Bernhard
2022
Most engineering domains abound with models derived from first principles that have beenproven to be effective for decades. These models are not only a valuable source of knowledge, but they also form the basis of simulations. The recent trend of digitization has complemented these models with data in all forms and variants, such as process monitoring time series, measured material characteristics, and stored production parameters. Theory-inspired machine learning combines the available models and data, reaping the benefits of established knowledge and the capabilities of modern, data-driven approaches. Compared to purely physics- or purely data-driven models, the models resulting from theory-inspired machine learning are often more accurate and less complex, extrapolate better, or allow faster model training or inference. In this short survey, we introduce and discuss several prominent approaches to theory-inspired machine learning and show how they were applied in the fields of welding, joining, additive manufacturing, and metal forming.
Lovric Mario, Duricic Tomislav, Tran Thi Ngoc Han, Hussain Hussain, Lacic Emanuel, Morten A. Rasmussen, Kern Roman
2021
Methods for dimensionality reduction are showing significant contributions to knowledge generation in high-dimensional modeling scenarios throughout many disciplines. By achieving a lower dimensional representation (also called embedding), fewer computing resources are needed in downstream machine learning tasks, thus leading to a faster training time, lower complexity, and statistical flexibility. In this work, we investigate the utility of three prominent unsupervised embedding techniques (principal component analysis—PCA, uniform manifold approximation and projection—UMAP, and variational autoencoders—VAEs) for solving classification tasks in the domain of toxicology. To this end, we compare these embedding techniques against a set of molecular fingerprint-based models that do not utilize additional pre-preprocessing of features. Inspired by the success of transfer learning in several fields, we further study the performance of embedders when trained on an external dataset of chemical compounds. To gain a better understanding of their characteristics, we evaluate the embedders with different embedding dimensionalities, and with different sizes of the external dataset. Our findings show that the recently popularized UMAP approach can be utilized alongside known techniques such as PCA and VAE as a pre-compression technique in the toxicology domain. Nevertheless, the generative model of VAE shows an advantage in pre-compressing the data with respect to classification accuracy.
Ciura Krzesimir, Fedorowicz Joanna, Zuvela Petar, Lovric Mario, Kapica Hanna, Baranowski Pawel, Sawicki Wieslaw, Wong Ming Wah, Sączewski Jaroslaw
2020
Currently, rapid evaluation of the physicochemical parameters of drug candidates, such as lipophilicity, is in high demand owing to it enabling the approximation of the processes of absorption, distribution, metabolism, and elimination. Although the lipophilicity of drug candidates is determined using the shake flash method (n-octanol/water system) or reversed phase liquid chromatography (RP-LC), more biosimilar alternatives to classical lipophilicity measurement are currently available. One of the alternatives is immobilized artificial membrane (IAM) chromatography. The present study is a continuation of our research focused on physiochemical characterization of biologically active derivatives of isoxazolo[3,4-b]pyridine-3(1H)-ones. The main goal of this study was to assess the affinity of isoxazolones to phospholipids using IAM chromatography and compare it with the lipophilicity parameters established by reversed phase chromatography. Quantitative structure–retention relationship (QSRR) modeling of IAM retention using differential evolution coupled with partial least squares (DE-PLS) regression was performed. The results indicate that in the studied group of structurally related isoxazolone derivatives, discrepancies occur between the retention under IAM and RP-LC conditions. Although some correlation between these two chromatographic methods can be found, lipophilicity does not fully explain the affinities of the investigated molecules to phospholipids. QSRR analysis also shows common factors that contribute to retention under IAM and RP-LC conditions. In this context, the significant influences of WHIM and GETAWAY descriptors in all the obtained models should be highlighted
Lovric Mario, Meister Richard, Steck Thomas, Fadljevic Leon, Gerdenitsch Johann, Schuster Stefan, Schiefermüller Lukas, Lindstaedt Stefanie , Kern Roman
2020
In industrial electro galvanizing lines aged anodes deteriorate zinc coating distribution over the strip width, leading to an increase in electricity and zinc cost. We introduce a data-driven approach in predictive maintenance of anodes to replace the cost- and labor-intensive manual inspection, which is still common for this task. The approach is based on parasitic resistance as an indicator of anode condition which might be aged or mis-installed. The parasitic resistance is indirectly observable via the voltage difference between the measured and baseline (theoretical) voltage for healthy anode. Here we calculate the baseline voltage by means of two approaches: (1) a physical model based on electrical and electrochemical laws, and (2) advanced machine learning techniques including boosting and bagging regression. The data was collected on one exemplary rectifier unit equipped with two anodes being studied for a total period of two years. The dataset consists of one target variable (rectifier voltage) and nine predictive variables used in the models, observing electrical current, electrolyte, and steel strip characteristics. For predictive modelling, we used Random Forest, Partial Least Squares and AdaBoost Regression. The model training was conducted on intervals where the anodes were in good condition and validated on other segments which served as a proof of concept that bad anode conditions can be identified using the parasitic resistance predicted by our models. Our results show a RMSE of 0.24 V for baseline rectifier voltage with a mean ± standard deviation of 11.32 ± 2.53 V for the best model on the validation set. The best-performing model is a hybrid version of a Random Forest which incorporates meta-variables computed from the physical model. We found that a large predicted parasitic resistance coincides well with the results of the manual inspection. The results of this work will be implemented in online monitoring of anode conditions to reduce operational cost at a production site
Obermeier, Melanie Maria, Wicaksono, Wisnu Adi, Taffner, Julian, Bergna, Alessandro, Poehlein, Anja, Cernava, Tomislav, Lindstaedt Stefanie , Lovric Mario, Müller Bogota, Christina Andrea, Berg, Gabriele
2020
The expanding antibiotic resistance crisis calls for a more in depth understanding of the importance of antimicrobial resistance genes (ARGs) in pristine environments. We, therefore, studied the microbiome associated with Sphagnum moss forming the main vegetation in undomesticated, evolutionary old bog ecosystems. In our complementary analysis of culture collections, metagenomic data and a fosmid library from different geographic sites in Europe, we identified a low abundant but highly diverse pool of resistance determinants, which targets an unexpectedly broad range of 29 antibiotics including natural and synthetic compounds. This derives both, from the extraordinarily high abundance of efflux pumps (up to 96%), and the unexpectedly versatile set of ARGs underlying all major resistance mechanisms. Multi-resistance was frequently observed among bacterial isolates, e.g. in Serratia, Rouxiella, Pandoraea, Paraburkholderia and Pseudomonas. In a search for novel ARGs, we identified the new class A β-lactamase Mm3. The native Sphagnum resistome comprising a highly diversified and partially novel set of ARGs contributes to the bog ecosystem´s plasticity. Our results reinforce the ecological link between natural and clinically relevant resistomes and thereby shed light onto this link from the aspect of pristine plants. Moreover, they underline that diverse resistomes are an intrinsic characteristic of plant-associated microbial communities, they naturally harbour many resistances including genes with potential clinical relevance
Žuvela, Petar, Lovric Mario, Yousefian-Jazi, Ali, Liu, J. Jay
2020
Numerous industrial applications of machine learning feature critical issues that need to be addressed. This work proposes a framework to deal with these issues, such as competing objectives and class imbalance in designing a machine vision system for the in-line detection of surface defects on glass substrates of thin-film transistor liquid crystal displays (TFT-LCDs). The developed inspection system composes of (i) feature engineering: extraction of only the defect-relevant features from images using two-dimensional wavelet decomposition and (ii) training ensemble classifiers (proof of concept with a C5.0 ensemble, random forests (RF), and adaptive boosting (AdaBoost)). The focus is on cost sensitivity, increased generalization, and robustness to handle class imbalance and address multiple competing manufacturing objectives. Comprehensive performance evaluation was conducted in terms of accuracy, sensitivity, specificity, and the Matthews correlation coefficient (MCC) by calculating their 12,000 bootstrapped estimates. Results revealed significant differences (p < 0.05) between the three developed diagnostic algorithms. RFR (accuracy of 83.37%, sensitivity of 60.62%, specificity of 89.72%, and MCC of 0.51) outperformed both AdaBoost (accuracy of 81.14%, sensitivity of 69.23%, specificity of 84.48%, and MCC of 0.50) and the C5.0 ensemble (accuracy of 78.35%, sensitivity of 65.35%, specificity of 82.03%, and MCC of 0.44) in all the metrics except sensitivity. AdaBoost exhibited stronger performance in detecting defective TFT-LCD glass substrates. These promising results demonstrated that the proposed ensemble approach is a viable alternative to manual inspections when applied to an industrial case study with issues such as competing objectives and class imbalance.
Malev, Olga, Lovric Mario, Stipaničev, Draženka, Repec, Siniša, Martinović-Weigelt, Dalma, Zanella, Davor, Đuretec, Valnea Sindiči, Barišić, Josip, Li, Mei, Klobučar, Göran
2020
Chemical analysis of plasma samples of wild fish from the Sava River (Croatia) revealed the presence of 90 different pharmaceuticals/illicit drugs and their metabolites (PhACs/IDrgs). The concentrations of these PhACs/IDrgs in plasma were 10 to 1, 000 times higher than their concentrations in river water. Antibiotics, allergy/cold medications and analgesics were categories with the highest plasma concentrations. Fifty PhACs/IDrgs were identified as chemicals of concern based on the fish plasma model (FPM) effect ratios (ER) and their potential to activate evolutionary conserved biological targets. Chemicals of concern were also prioritized by calculating exposure-activity ratios (EARs) where plasma concentrations of chemicals were compared to their bioactivities in comprehensive ToxCast suite of in vitro assays. Overall, the applied prioritization methods indicated stimulants (nicotine, cotinine) and allergy/cold medications (prednisolone, dexamethasone) as having the highest potential biological impact on fish. The FPM model pointed to psychoactive substances (hallucinogens/stimulants and opioids) and psychotropic substances in the cannabinoids category (i.e. CBD and THC). EAR confirmed above and singled out additional chemicals of concern - anticholesteremic simvastatin and antiepileptic haloperidol. Present study demonstrates how the use of a combination of chemical analyses, and bio-effects based risk predictions with multiple criteria can help identify priority contaminants in freshwaters. The results reveal a widespread exposure of fish to complex mixtures of PhACs/IDrgs, which may target common molecular targets. While many of the prioritized chemicals occurred at low concentrations, their adverse effect on aquatic communities, due to continuous chronic exposure and additive effects, should not be neglected.
Havaš Auguštin, Dubravka, Šarac, Jelena, Lovric Mario, Živković, Jelena, Malev, Olga, Fuchs, Nives, Novokmet, Natalija, Turkalj, Mirjana, Missoni, Saša
2020
Maternal nutrition and lifestyle in pregnancy are important modifiable factors for both maternal and offspring’s health. Although the Mediterranean diet has beneficial effects on health, recent studies have shown low adherence in Europe. This study aimed to assess the Mediterranean diet adherence in 266 pregnant women from Dalmatia, Croatia and to investigate their lifestyle habits and regional differences. Adherence to the Mediterranean diet was assessed through two Mediterranean diet scores. Differences in maternal characteristics (diet, education, income, parity, smoking, pre-pregnancy body mass index (BMI), physical activity, contraception) with regards to location and dietary habits were analyzed using the non-parametric Mann–Whitney U test. The machine learning approach was used to reveal other potential non-linear relationships. The results showed that adherence to the Mediterranean diet was low to moderate among the pregnant women in this study, with no significant mainland–island differences. The highest adherence was observed among wealthier women with generally healthier lifestyle choices. The most significant mainland–island differences were observed for lifestyle and socioeconomic factors (income, education, physical activity). The machine learning approach confirmed the findings of the conventional statistical method. We can conclude that adverse socioeconomic and lifestyle conditions were more pronounced in the island population, which, together with the observed non-Mediterranean dietary pattern, calls for more effective intervention strategies
Lovric Mario, Šimić Iva, Godec Ranka, Kröll Mark, Beslic Ivan
2020
Narrow city streets surrounded by tall buildings are favorable to inducing a general effect of a “canyon” in which pollutants strongly accumulate in a relatively small area because of weak or inexistent ventilation. In this study, levels of nitrogen-oxide (NO2), elemental carbon (EC) and organic carbon (OC) mass concentrations in PM10 particles were determined to compare between seasons and different years. Daily samples were collected at one such street canyon location in the center of Zagreb in 2011, 2012 and 2013. By applying machine learning methods we showed seasonal and yearly variations of mass concentrations for carbon species in PM10 and NO2, as well as their covariations and relationships. Furthermore, we compared the predictive capabilities of five regressors (Lasso, Random Forest, AdaBoost, Support Vector Machine and Partials Least squares) with Lasso regression being the overall best performing algorithm. By showing the feature importance for each model, we revealed true predictors per target. These measurements and application of machine learning of pollutants were done for the first time at a street canyon site in the city of Zagreb, Croatia.
Arslanovic Jasmina, Ajana Löw, Lovric Mario, Kern Roman
2020
Previous studies have suggested that artistic (synchronized) swimming athletes might showeating disorders symptoms. However, systematic research on eating disorders in artistic swimming is limited and the nature and antecedents of the development of eating disorders in this specific population of athletes is still scarce. Hence, the aim of our research was to investigate the eating disorder symptoms in artistic swimming athletes using the EAT-26 instrument, and to examine the relation of the incidence and severity of these symptoms to body mass index and body image dissatisfaction. Furthermore, we wanted to compare artistic swimmers with athletes of a non-leanness (but also an aquatic) sport, therefore we also included a group of female water-polo athletes of the same age. The sample consisted of 36 artistic swimmers and 34 female waterpolo players (both aged 13-16). To test the presence of the eating disorder symptoms the EAT-26 was used. The Mann-Whitney U Test (MWU) was used to test for the differences in EAT-26 scores. The EAT-26 total score and the Dieting subscale (one of the three subscale) showed significant differences between the two groups. The median value for EAT-26 total score was higher in the artistic swimmers’ group (C = 11) than in the waterpolo players’ group (C = 8). A decision tree classifier was used to discriminate the artistic swimmers and female water polo players based on the features from the EAT26 and calculated features. The most discriminative features were the BMI, the dieting subscale and the habit of post-meal vomiting.Our results suggest that artistic swimmers, at their typical competing age, show higher risk of developing eating disorders than female waterpoloplayers and that they are also prone to dieting weight-control behaviors to achieve a desired weight. Furthermore, results indicate that purgative behaviors, such as binge eating or self-induced vomiting, might not be a common weight-control behavior among these athletes. The results corroborate the findings that sport environment in leanness sports might contribute to the development of eating disorders. The results are also in line with evidence that leanness sports athletes are more at risk for developing restrictive than purgative eating behaviors, as the latter usually do not contribute to body weight reduction. As sport environment factors in artistic swimming include judging criteria that emphasize a specific body shape and performance, it is important to raise the awareness of mental health risks that such environment might encourage.
Lovric Mario, Molero Perez Jose Manuel, Kern Roman
2019
The authors present an implementation of the cheminformatics toolkit RDKit in a distributed computing environment, Apache Hadoop. Together with the Apache Spark analytics engine, wrapped by PySpark, resources from commodity scalable hardware can be employed for cheminformatic calculations and query operations with basic knowledge in Python programming and understanding of the resilient distributed datasets (RDD). Three use cases of cheminfomatical computing in Spark on the Hadoop cluster are presented; querying substructures, calculating fingerprint similarity and calculating molecular descriptors. The source code for the PySpark‐RDKit implementation is provided. The use cases showed that Spark provides a reasonable scalability depending on the use case and can be a suitable choice for datasets too big to be processed with current low‐end workstations
Lovric Mario
2018
Today's data amount is significantly increasing. A strong buzzword in research nowadays is big data.Therefore the chemistry student has to be well prepared for the upcoming age where he does not only rule the laboratories but is a modeler and data scientist as well. This tutorial covers the very basics of molecular modeling and data handling with the use of Python and Jupyter Notebook. It is the first in a series aiming to cover the relevant topics in machine learning, QSAR and molecular modeling, as well as the basics of Python programming
Babić Sanja, Barišić Josip, Stipaničev Draženka, Repec Siniša, Lovric Mario, Malev Olga, Čož-Rakovac Rozalindra, Klobučar GIV
2018
Quantitative chemical analyses of 428 organic contaminants (OCs) confirmed the presence of 313 OCs in the sediment extracts from river Sava, Croatia. Pharmaceuticals were present in higher concentration than pesticides thus confirming their increasing threat to freshwater ecosystems. Toxicity evaluation of the sediment extracts from four locations (Jesenice, Rugvica, Galdovo and Lukavec) using zebrafish embryotoxicity test (ZET) accompanied with semi-quantitative histopathological analyses exhibited good correlation with cumulative number and concentrations of OCs at investigated sites (10,048.6, 15,222.8, 1,247.6, and 9,130.5 ng/g respectively) and proved its role as a good indicator of toxic potential of complex contaminant mixtures. Toxicity prediction of sediment extracts and sediment was assessed using Toxic unit (TU) approach and PBT (persistence, bioaccumulation and toxicity) ranking. Also, prior-knowledge informed chemical-gene interaction models were generated and graph mining approaches used to identify OCs and genes most likely to be influential in these mixtures. Predicted toxicity of sediment extracts (TUext) for sampled locations was similar to the results obtained by ZET and associated histopathology resulting in Rugvica sediment as being the most toxic, followed by Jesenice, Lukavec and Galdovo. Sediment TU (TUsed) favoured OCs with low octanol-water partition coefficient like herbicide glyphosate and antibiotics ciprofloxacin and sulfamethazine thus indicating locations containing higher concentrations of these OCs (Galdovo and Rugvica) as most toxic. Results suggest that comprehensive in silico sediment toxicity predictions advocate providing equal attention to organic contaminants with either very low or very high log Kow