Search

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.

In the Arctic, new particle formation (NPF) and subsequent growth processes are the keys to produce Aitken-mode particles, which under certain conditions can act as cloud condensation nuclei (CCNs). The activation of Aitken-mode particles increases the CCN budget of Arctic low-level clouds and, accordingly, affects Arctic climate forcing. However, the growth mechanism of Aitken-mode particles from NPF into CCN range in the summertime Arctic boundary layer remains a subject of current research. In this combined Arctic cruise field and modeling study, we investigated Aitken-mode particle growth to sizes above 80 nm. A mechanism is suggested that explains how Aitken-mode particles can become CCN without requiring high water vapor supersaturation. Model simulations suggest the formation of semivolatile compounds, such as methanesulfonic acid (MSA) in fog droplets. When the fog droplets evaporate, these compounds repartition from CCNs into the gas phase and into the condensed phase of nonactivated Aitken-mode particles. For MSA, a mass increase factor of 18 is modeled. The postfog redistribution mechanism of semivolatile acidic and basic compounds could explain the observed growth of >20 nm h−1 for 60-nm particles to sizes above 100 nm. Overall, this study implies that the increasing frequency of NPF and fog-related particle processing can affect Arctic cloud properties in the summertime boundary layer.

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.

In this paper we present an approach to investigate changes in concentration of particulate matter (PM) mass concentrations during the COVID-19 lockdown. Concentrations of PM1, PM2.5 and PM10 were measured in an urban background sampling site on the north of Zagreb from 2009 to late 2020 on a 24h basis. The concentrations were fed alongside meteorological and temporal data to Random Forest (RF) 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. We examined three pollution periods in 2020 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”. We conducted an evaluation using normalized mass concentrations of particulate matter and Analysis of variance (ANOVA). The results showed that no significant difference (p = 0.33) was observed for PM2.5 and PM10 in April 2020 - compared to the same period in 2018 and 2019. The noticeable change in PM1 was observed in the same period related to a higher normalized concentration in 2018, but no difference between 2019 and 2020. No significant changes were observed for the “new normal” as well. Our results thus lead to the assumption that a reduction in mobility during COVID-19 lockdown did not significantly affect particulate matter concentration in long- term.

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.

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..

Despite widely and regularly used therapy asthma in children is not fully controlled. Recognizing the complexity of asthma phenotypes and endotypes imposed the concept of precision medicine in asthma treatment. By applying machine learning algorithms assessed with respect to their accuracy in predicting treatment outcome, we have successfully identified 4 distinct clusters in a pediatric asthma cohort with specific treatment outcome patterns according to changes in lung function (FEV1 and MEF50), airway inflammation (FENO) and disease control likely affected by discrete phenotypes at initial disease presentation, differing in the type and level of inflammation, age of onset, comorbidities, certain genetic and other physiologic traits. The smallest and the largest of the 4 clusters- 1 (N = 58) and 3 (N = 138) had better treatment outcomes compared to clusters 2 and 4 and were characterized by more prominent atopic markers and a predominant allelic (A allele) effect for rs37973 in the GLCCI1 gene previously associated with positive treatment outcomes in asthmatics. These patients also had a relatively later onset of disease (6 + yrs). Clusters 2 (N = 87) and 4 (N = 64) had poorer treatment success, but varied in the type of inflammation (predominantly neutrophilic for cluster 4 and likely mixed-type for cluster 2), comorbidities (obesity for cluster 2), level of systemic inflammation (highest hsCRP for cluster 2) and platelet count (lowest for cluster 4). The results of this study emphasize the issues in asthma management due to the overgeneralized approach to the disease, not taking into account specific disease phenotypes.

Here, we present a collection of publicly availableintrinsic aqueous solubility data of 829 drug-likecompounds. Four different machine learning algorithms(random forest, light GBM, partial least squares andLASSO) coupled with multi-stage permutationimportance for feature selection and Bayesian hyperparameter optimization were employed for theprediction of solubility based on chemical structuralinformation. Our results have shown that LASSOyielded the best predictive ability on an external test setwith and RMSE(test) of 0.70 log points and 105 featuresin the model. Taking into account the number ofdescriptors as well, an RF model achieved the bestbalance between complexity and predictive ability withan RMSE(test) of 0.72 with only 17 features. Wepropose a ranking score for choosing the best model, astest set performance is only one of the factors in creatingan applicable model. The ranking score is a weightedcombination of generalization, number of featuresinvolved and test set performance The data related to this paper can be downloaded from 10.5281/zenodo.3968754

The CompTox Chemistry Dashboard (ToxCast) contains one of the largest public databases on Zebrafish (Danio rerio) developmental toxicity. The data consists of 19 toxicological endpoints on unique 1018 compounds measured in relatively low concentration ranges. The endpoints are related to developmental effects occurring in dechorionated zebrafish embryos for 120 hours post fertilization and monitored via gross malformations and mortality. We report the predictive capability of 209 quantitative structure–activity relationship (QSAR) models developed by machine learning methods using penalization techniques and diverse model quality metrics to cope with the imbalanced endpoints. All these QSAR models were generated to test how the imbalanced classification (toxic or non-toxic) endpoints could be predicted regardless which of three algorithms is used: logistic regression, multi-layer perceptron, or random forests. Additionally, QSAR toxicity models are developed starting from sets of classical molecular descriptors, structural fingerprints and their combinations. Only 8 out of 209 models passed the 0.20 Matthew’s correlation coefficient value defined a priori as a threshold for acceptable model quality on the test sets. The best models were obtained for endpoints mortality (MORT), ActivityScore and JAW (deformation). The low predictability of the QSAR model developed from the zebrafish embryotoxicity data in the database is mainly due to a higher sensitivity of 19 measurements of endpoints carried out on dechorionated embryos at low concentrations.

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.

Asthma in children is a heterogeneous disease manifested by various phenotypes and endotypes. The level of disease control, as well as the effectiveness of anti-inflammatory treatment, is variable and inadequate in a significant portion of patients. By applying machine learning algorithms, we aimed to predict the treatment success in a pediatric asthma cohort and to identify the key variables for understanding the underlying mechanisms. We predicted the treatment outcomes in children with mild to severe asthma (N = 365), according to changes in asthma control, lung function (FEV1 and MEF50) and FENO values after 6 months of controller medication use, using Random Forest and AdaBoost classifiers. The highest prediction power is achieved for control- and, to a lower extent, for FENO-related treatment outcomes, especially in younger children. The most predictive variables for asthma control are related to asthma severity and the total IgE, which were also predictive for FENO-based outcomes. MEF50-related treatment outcomes were better predicted than the FEV1-based response, and one of the best predictive variables for this response was hsCRP, emphasizing the involvement of the distal airways in childhood asthma. Our results suggest that asthma control- and FENO-based outcomes can be more accurately predicted using machine learning than the outcomes according to FEV1 and MEF50. This supports the symptom control-based asthma management approach and its complementary FENO-guided tool in children. T2-high asthma seemed to respond best to the anti-inflammatory treatment. The results of this study in predicting the treatment success will help to enable treatment optimization and to implement the concept of precision medicine in pediatric asthma treatment.

Maternal nutrition and lifestyle in pregnancy are important modifiable factors for both maternal and offspring&rsquo, 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&ndash, 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&ndash, island differences. The highest adherence was observed among wealthier women with generally healthier lifestyle choices. The most significant mainland&ndash, 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.

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 1000 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.

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.

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.

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.

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.

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.

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.

Shortcomings of the correlation coefficient (Pearson's) as a measure for estimating and calculating the accuracy of predictive model properties are analysed. Here we discuss two such cases that can often occur in the application of the model in predicting properties of a new external set of compounds. The first problem in using the correlation coefficient is its insensitivity to the systemic error that must be expected in predicting properties of a novel external set of compounds, which is not a random sample selected from the training set. The second problem is that an external set can be arbitrarily large or small and have an arbitrary and uneven distribution of the measured value of the target variable, whose values are not known in advance. In these conditions, the correlation coefficient can be an overoptimistic measure of agreement of predicted values with the corresponding experimental values and can lead to a highly optimistic conclusion about the predictive ability of the model. Due to these shortcomings of the correlation coefficient, the use of standard error (root-mean-square-error) of prediction is suggested as a better quality measure of predictive capabilities of a model. In the case of classification models, the use of the difference between the real accuracy and the most probable random accuracy of the model shows very good characteristics in ranking different models according to predictive quality, having at the same time an obvious interpretation . This work is licensed under a Creative Commons Attribution 4.0 International License.

Airborne particles are composed of inorganic species and organic compounds. PM1 particles, with an aerodynamic diameter smaller than 1 &mu, m, are considered to be important in the context of adverse health effects. Many compounds bound to particulate matter, such as polycyclic aromatic hydrocarbons (PAH), are suspected to be genotoxic, mutagenic, and carcinogenic. In this study, PAHs in the PM1 particle fraction were measured for one year (1/1/2018&ndash, 31/12/2018). The measuring station was located in the northern residential part of Zagreb, the Croatian capital, close to a street with modest traffic. Significant differences were found between PAH concentrations during cold (January&ndash, March, October&ndash, December) and warm (April&ndash, September) periods of the year. In general, the mass concentrations of PAHs characteristic for car exhausts (benzo(ghi)perylene (BghiP), indeno(1,2,3-cd)pyrene (IP), and benzo(b)fluoranthene (BbF)) were higher during the whole year than concentrations of fluoranthene (Flu) and pyrene (Pyr), which originated mostly from domestic heating and biomass burning. Combustion of diesel and gasoline from vehicles was found to be one of the main PAH sources. The incremental lifetime cancer risk (ILCR) was estimated for three age groups of populations and the results were much lower than the acceptable risk level (1 &times, 10&minus, 6). However, more than ten times higher PAH concentrations in the cold part of the year, as well as associated health risk, emphasize the need for monitoring of PAHs in PM1. These data represent a valuable tool in future plans and actions to control PAH sources and to improve the quality of life of urban populations.

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.

Quantitative chemical analyses of 428 organic contaminants (OCs) indicated the presence of 313 OCs in the sediment extracts from Sava River, Croatia. Pharmaceuticals were present in higher concentrations 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 correlation with cumulative number and concentrations of OCs at the investigated sites (10.05, 15.22, 1.25, and 9.13 μg/g respectively). Toxicity of sediment extracts and sediment was predicted using toxic unit (TU) approach and persistence, bioaccumulation and toxicity (PBT) ranking. Additionally, influential OCs and genes were identified by graph mining of the prior knowledge informed, site-specific chemical-gene interaction models. Predicted toxicity of sediment extracts (TUext) was similar to the results obtained by ZET and associated histopathology with Rugvica sediment being the most toxic, followed by Jesenice, Lukavec and Galdovo. Sediment TU (TUsed) favoured OCs with low octanol-water partition coefficients like herbicide glyphosate and antibiotics ciprofloxacin and sulfamethazine thus indicating locations containing higher concentrations of these OCs (Galdovo and Rugvica) as the 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.

Impurities in pharmaceutical product are the unwanted chemical compounds that remain within the active pharmaceutical ingredient (API), or are formed during production process or by degradation of API. The presence of these unwanted chemical compounds even at small concentrations may influence the efficacy and safety of the pharmaceutical products. Different scientific researches showed that degradation products can be potentially genotoxic, mutagenic or carcinogenic, thus needing constant monitoring and impurity profiling. Techniques such as LC/MS/MS are widely used for impurity identification in pharmaceutical industries due to their high sensitivity, selectivity, and speed of analysis. Coupling high pressure liquid chromatography (HPLC) system with quadrupole time-of-flight (Q-TOF) mass spectrometry enables accurate mass measurement of both precursor and fragment ions ; however this technique is limited to the usage of volatile buffers. Additional time is required to develop an equivalent HPLC method with MS compatible mobile phase. Furthermore, it may add additional challenges and uncertainty if the impurity elution order is changed with the newly developed MS-compatible LC method. This limitation can be effectively resolved with a heart-cut approach employing two reversed phase LC conditions. Heart-cutting 2D-LC transfers fractions of interest from first to second dimension ensuring the best separation at the critical parts of the chromatogram. In order to investigate the stability of nonsteroidal anti-inflammatory drug (NSAID) Nepafenac, the selected model drug was subjected to forced degradation under different stress conditions such as oxidation, acid and base hydrolysis (Runje et al., 2016). The aim of this stability study was to propose the structure of unknown peaks and demonstrate the application of two-dimensional chromatography coupled with quadrupole time-of-flight (Q-TOF) mass detector for impurity profiling purposes. Major degradation impurities were determined and the peak purity was determined by usage of selected MS detector.