Search

Multitask learning allows to model multiple tasks simultaneously through information sharing. In the context of quantitative structure–activity relationships and computational toxicology, multitask learning is gaining more and more interest, owed to its potential to improve the predictive performance of underrepresented tasks and to predict the multi-property profile of molecules. In this chapter, after introducing the multitask problem formulation, we present a hands-on tutorial on multitask neural networks.

According to the 2021 World Drug Report, around 275 million people use drugs of abuse, and 36 million people suffer from addiction, fostering a thriving market for illicit substances. In Italy, 30,083 people were reported to the Judicial Authority for offenses in violation of the Italian Law D.P.R. 309/1990. These offences are sentenced after a qualitative–quantitative analysis of seized materials. Given the large quantity of seized drugs and the need to perform accurate analytical determinations, Italian forensic laboratories struggle to complete analyses in a short time, delaying the entire reporting process needed to achieve sentencing. For this purpose, an UHPLC-MS/MS-based platform was developed at the University of Milano-Bicocca to support law-enforcement authorities. Software was designed to easily manage street seizure acquisition, documentation registration, and sampling. A sensitive UHPLC-MS/MS method was fully validated for the quantification of the traditional illicit substances (cocaine, heroin, 6-MAM, morphine, amphetamine, methamphetamine, MDMA, ketamine, GHB, GBL, LSD, trans-∆9-THC, and THCA) at the ppb level. The final report is relayed to the Prefecture in 3–4 days, even within 24 h for urgent requests. The platform allows for semi-automatic data handling to minimize erroneous results for an accurate report generation by standardized procedures.

A Box-Behnken experimental design was implemented in model wine (MW) to clarify the impact of copper, iron, and oxygen in the photo-degradation of riboflavin (RF) and methionine (Met) by means of response surface methodology (RSM). Analogous experiments were undertaken in MW containing caffeic acid or catechin. The results evidenced the impact of copper, iron, and oxygen in the photo-induced reaction between RF and Met. In particular, considering a number of volatile sulfur compounds (VSCs) that act as markers of light-struck taste (LST), both transition metals can favor VSC formation, which was shown for the first time for iron. Oxygen in combination can also affect the concentration of VSCs, and a lower content of VSCs was revealed in the presence of phenols, especially caffeic acid. The perception of "cabbage" sensory character indicative of LST can be related to the transition metals as well as to the different phenols, with potentially strong prevention by phenolic acids.

The capacity to discriminate safe from dangerous compounds has played an important role in the evolution of species, including human beings. Highly evolved senses such as taste receptors allow humans to navigate and survive in the environment through information that arrives to the brain through electrical pulses. Specifically, taste receptors provide multiple bits of information about the substances that are introduced orally. These substances could be pleasant or not according to the taste responses that they trigger. Tastes have been classified into basic (sweet, bitter, umami, sour and salty) or non-basic (astringent, chilling, cooling, heating, pungent), while some compounds are considered as multitastes, taste modifiers or tasteless. Classification-based machine learning approaches are useful tools to develop predictive mathematical relationships in such a way as to predict the taste class of new molecules based on their chemical structure. This work reviews the history of multicriteria quantitative structure-taste relationship modelling, starting from the first ligand-based (LB) classifier proposed in 1980 by Lemont B. Kier and concluding with the most recent studies published in 2022.

We present an optimization of the toroidal self-organizing map (SOM) algorithm for the accurate visualization of hyperspectral data. This represents a significant advancement on our previous work, in which we demonstrated the use of toroidal SOMs for the visualization of time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging data. We have previously shown that the toroidal SOM can be used, unsupervised, to produce a multicolor similarity map of the analysis area, in which pixels with similar mass spectra are assigned a similar color. Here, we use an additional algorithm, relational perspective mapping (RPM), to produce more accurate visualizations of hyperspectral data. The SOM output is used as an input for the RPM algorithm, which is a nonlinear dimensionality reduction technique designed to produce a two-dimensional map of high-dimensional data. Using the topological information provided by the SOM, RPM provides complementary distance information. The result is a color scheme that more accurately reflects the local spectral distances between pixels in the data. We exemplify SOM-RPM using ToF-SIMS imaging data from a mouse tumor tissue section. The similarity maps produced are compared with those produced by two leading hyperspectral visualization techniques in the field of mass spectrometry imaging: t-distributed stochastic neighborhood embedding (t-SNE) and uniform manifold approximation and projection (UMAP). We evaluate the performance of each technique both qualitatively and quantitatively, investigating the correlations between distances in the models and distances in the data. SOM-RPM is demonstrably highly competitive with t-SNE and UMAP, according to our evaluations. Furthermore, the use of a neural network offers distinct advantages in data characterization, which we discuss. We also show how spectra extracted from regions of interest identified by SOM-RPM can be further analyzed using linear discriminant analysis for the validation and characterization of the surface chemistry.

Several similarity/diversity measures for data mining, chemometrics, and chemoinformatics are presented and discussed toward the different data they are applied to. After a short presentation of the axioms for dissimilarity and similarity functions, their relationships and the required data pretreatment, the theoretical definitions and formulas of distance and similarity measures for real‐valued, binary, ranked, frequency, and mixed‐type data are provided along with the main concepts on distances between sets and meta‐distances. Simple examples of calculation are given and extended comparisons are performed on the distances defined for real valued and binary data.

The interest in multitask and deep learning strategies has been increasing in the last few years, in application to large and complex dataset for quantitative structure-activity relationship (QSAR) analysis. Multitask approaches allow the simultaneous prediction of molecular properties that are related, through information sharing, whereas deep learning strategies increase the potential of capturing nonlinear relationships. In this work, we compare the binary classification capability of multitask deep and shallow neural networks to single-task strategies used as benchmark (i.e., as k-nearest neighbours, N-nearest neighbours, random forest and Naïve Bayes), as well as multitask supervised self-organizing maps. Comparison was carried out with an extended QSAR dataset containing annotations of molecular binding, agonism and antagonism activity on 11 nuclear receptors, for a total of 14,963 molecules, divided into training and test sets and labelled for their bioactivity on at least one of 30 binary tasks. Additional 304 chemicals were used as external evaluation set to further validate models. Although no approach systematically overperformed the others, task-specific differences were found, suggesting the benefit of multitask learning for tasks that are less represented. On average, some of the single-task approaches and multitask deep learning strategies had similar performances. However, the latter can have advantages, such as a simpler management of predictions and applicability domain assessment for future samples. On the other hand, the parameter tuning required by neural networks are generally time expensive suggesting that the modelling strategy should be evaluated case by case.

Several public efforts are aimed at discovering patterns or classifiers in the high-dimensional bioactivity space that predict tissue, organ or whole animal toxicological endpoints. The current study sought to assess and compare the predictions of the Globally Harmonized System (GHS) categories and Dangerous Goods (DG) classifications based on Lethal Dose (LD50) from several available tools (ACD/Labs, Leadscope, T.E.S.T., CATMoS, CaseUltra). External validation was done using dataset of 375 substances to demonstrate their predictive capacity. All models showed very good performance for identifying non-toxic compounds, which would be useful for DG classification, developing or triaging new chemicals, prioritizing existing chemicals for more detailed and rigorous toxicity assessments, and assessing non-active pharmaceutical intermediates. This would ultimately reduce animal use and improve risk assessments. Category-to-category prediction was not optimal, mainly due to the tendency to overpredict the outcome and the general limitations of acute oral toxicity (AOT) in vivo studies. Overprediction does not specifically pose a risk to human health, it can impact transport and material packaging requirements. Performance for compounds with LD50 ≤ 300 mg/kg (approx. 5% of the dataset) was the poorest among all groups and could be potentially improved by including expert review and read-across to similar substances.

Ranking and multi-criteria decision-making approaches are useful tools to analyse multivariate data and obtain useful insights into data structure and the relationships between samples and variables. In this study, we present a new ranking approach, named Deep Ranking Analysis by Kendall Eigenvectors (DRAKE), which is based on the Power-Weakness Ratio analysis and provides a set of sequential rankings. Such a sequential ranking procedure allows to gather deeper insights into the analysed dataset. Moreover, by a “retro”-regression procedure, the relevance of each variable in determining the final rankings can be assessed, while a consensus ranking can be obtained by a Principal Component Analysis (PCA). In this study, we present the theory of the novel method, and show two applications to real datasets.

BACKGROUND: Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditional rodent acute toxicity tests. In silico models built using existing data facilitate rapid acute toxicity predictions without using animals. OBJECTIVES: The U.S. Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) Acute Toxicity Workgroup organized an international collaboration to develop in silico models for predicting acute oral toxicity based on five different end points: Lethal Dose 50 (LD50 value, U.S. Environmental Protection Agency hazard (four) categories, Globally Harmonized System for Classification and Labeling hazard (five) categories, very toxic chemicals [LD50 (LD50≤50mg/kg)], and nontoxic chemicals (LD50>2,000mg/kg). METHODS: An acute oral toxicity data inventory for 11,992 chemicals was compiled, split into training and evaluation sets, and made available to 35 participating international research groups that submitted a total of 139 predictive models. Predictions that fell within the applicability domains of the submitted models were evaluated using external validation sets. These were then combined into consensus models to leverage strengths of individual approaches. RESULTS: The resulting consensus predictions, which leverage the collective strengths of each individual model, form the Collaborative Acute Toxicity Modeling Suite (CATMoS). CATMoS demonstrated high performance in terms of accuracy and robustness when compared with in vivo results. DISCUSSION: CATMoS is being evaluated by regulatory agencies for its utility and applicability as a potential replacement for in vivo rat acute oral toxicity studies. CATMoS predictions for more than 800,000 chemicals have been made available via the National Toxicology Program's Integrated Chemical Environment tools and data sets (ice.ntp.niehs.nih.gov). The models are also implemented in a free, standalone, open-source tool, OPERA, which allows predictions of new and untested chemicals to be made. https://doi.org/10.1289/EHP8495.

Nuclear receptors (NRs) are involved in fundamental human health processes and are a relevant target for toxicological risk assessment. To help prioritize chemicals that can mimic natural hormones and be endocrine disruptors, computational models can be a useful tool.1,2 In this work we i) created an exhaustive collection of NR modulators and ii) applied machine learning methods to fill the data-gap and prioritize NRs modulators by building predictive models.

Neural networks are rapidly gaining popularity in chemical modeling and Quantitative Structure–Activity Relationship (QSAR) thanks to their ability to handle multitask problems. However, outcomes of neural networks depend on the tuning of several hyperparameters, whose small variations can often strongly affect their performance. Hence, optimization is a fundamental step in training neural networks although, in many cases, it can be very expensive from a computational point of view. In this study, we compared four of the most widely used approaches for tuning hyperparameters, namely, grid search, random search, tree-structured Parzen estimator, and genetic algorithms on three multitask QSAR datasets. We mainly focused on parsimonious optimization and thus not only on the performance of neural networks, but also the computational time that was taken into account. Furthermore, since the optimization approaches do not directly provide information about the influence of hyperparameters, we applied experimental design strategies to determine their effects on the neural network performance. We found that genetic algorithms, tree-structured Parzen estimator, and random search require on average 0.08% of the hours required by grid search; in addition, tree-structured Parzen estimator and genetic algorithms provide better results than random search.

Heparin has been used successfully as a clinical antithrombotic for almost one century. Its isolation from animal sources (mostly porcine intestinal mucosa) involves multistep purification processes starting from the slaughterhouse (as mucosa) to the pharmaceutical plant (as the API). This complex supply chain increases the risk of contamination and adulteration, mainly with non-porcine ruminant material. The structural similarity of heparins from different origins, the natural variability of the heparin within samples from each source as well as the structural changes induced by manufacturing processes, require increasingly sophisticated methods capable of detecting low levels of contamination. The application of suitable multivariate classification approaches on API 1H NMRspectra serve as rapid and reliable tools for product authentication and the detection of contaminants. Soft Independent Modeling of Class Analogies (SIMCA), Discriminant Analysis (DA), Partial Least Square Discriminant Analysis (PLS-DA) and local classification methods (kNN, BNN and N3) were tested on about one hundred certified heparin samples produced by 14 different manufacturers revealing that Partial Least Squares Discriminant Analysis (PLS-DA) provided the best discrimination of contaminated batches, with a balanced accuracy of 97%.

The advantages of applying multivariate analysis to mass spectrometry imaging (MSI) data have been thoroughly demonstrated in recent decades. The identification and visualization of complex relationships between pixels in a hyperspectral data set can provide unique insights into the underlying surface chemistry. It is now recognized that most MSI data contain nonlinear relationships, which has led to increased application of machine learning approaches. Previously, we exemplified the use of the self-organizing map (SOM), a type of artificial neural network, for analyzing time-of-flight secondary ion mass spectrometry (TOF-SIMS) hyperspectral images. Recently, we developed a novel methodology, SOM-relational perspective mapping (RPM), which incorporates the algorithm RPM to improve visualization of the SOM for 2D TOF-SIMS images. Here, we use SOM-RPM to characterize and interpret 3D TOF-SIMS depth profile data, voxel-by-voxel. An organic Irganox™ multilayer standard sample was depth profiled using TOF-SIMS, and SOM-RPM was used to create 3D similarity maps of the depth-profiled sample, in which the mass spectral similarity of individual voxels is modeled with color similarity. We used this similarity map to segment the data into spatial features, demonstrating that the unsupervised method meaningfully differentiated between Irganox-3114 and Irganox-1010 nanometer-thin multilayer films. The method also identified unique clusters at the surface associated with environmental exposure and sample degradation. Key fragment ions characteristic of each cluster were identified, tying clusters to their underlying chemistries. SOM-RPM has the demonstrable ability to reduce vast data sets to simple 3D visualizations that can be used for clustering data and visualizing the complex relationships within.

© 2020 American Chemical Society. Combinatorial approaches to materials discovery offer promising potential for the rapid development of novel polymer systems. Polymer microarrays enable the high-throughput comparison of material physical and chemical properties - such as surface chemistry and properties like cell attachment or protein adsorption - in order to identify correlations that can progress materials development. A challenge for this approach is to accurately discriminate between highly similar polymer chemistries or identify heterogeneities within individual polymer spots. Time-of-flight secondary ion mass spectrometry (ToF-SIMS) offers unique potential in this regard, capable of describing the chemistry associated with the outermost layer of a sample with high spatial resolution and chemical sensitivity. However, this comes at the cost of generating large scale, complex hyperspectral imaging data sets. We have demonstrated previously that machine learning is a powerful tool for interpreting ToF-SIMS images, describing a method for color-tagging the output of a self-organizing map (SOM). This reduces the entire hyperspectral data set to a single reconstructed color similarity map, in which the spectral similarity between pixels is represented by color similarity in the map. Here, we apply the same methodology to a ToF-SIMS image of a printed polymer microarray for the first time. We report complete, single-pixel molecular discrimination of the 70 unique homopolymer spots on the array while also identifying intraspot heterogeneities thought to be related to intermixing of the polymer and the pHEMA coating. In this way, we show that the SOM can identify layers of similarity and clusters in the data, both with respect to polymer backbone structures and their individual side groups. Finally, we relate the output of the SOM analysis with fluorescence data from polymer-protein adsorption studies, highlighting how polymer performance can be visualized within the context of the global topology of the data set.

Background:Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones and alter synthesis, transport, or metabolic pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being addressed using high-throughput screening (HTS) in vitro approaches and computational modeling.Objectives:In support of the Endocrine Disruptor Screening Program, the U.S. Environmental Protection Agency (EPA) led two worldwide consortiums to virtually screen chemicals for their potential estrogenic and androgenic activities. Here, we describe the Collaborative Modeling Project for Androgen Receptor Activity (CoMPARA) efforts, which follows the steps of the Collaborative Estrogen Receptor Activity Prediction Project (CERAPP).Methods:The CoMPARA list of screened chemicals built on CERAPP’s list of 32,464 chemicals to include additional chemicals of interest, as well as simulated ToxCast™ metabolites, totaling 55,450 chemical structures. Computational toxicology scientists from 25 international groups contributed 91 predictive models for binding, agonist, and antagonist activity predictions. Models were underpinned by a common training set of 1,746 chemicals compiled from a combined data set of 11 ToxCast™/Tox21 HTS in vitro assays.Results:The resulting models were evaluated using curated literature data extracted from different sources. To overcome the limitations of single-model approaches, CoMPARA predictions were combined into consensus models that provided averaged predictive accuracy of approximately 80% for the evaluation set.Discussion:The strengths and limitations of the consensus predictions were discussed with example chemicals; then, the models were implemented into the free and open-source OPERA application to enable screening of new chemicals with a defined applicability domain and accuracy assessment. This implementation was used to screen the entire EPA DSSTox database of ∼875,000 chemicals, and their predicted AR activities have been made available on the EPA CompTox Chemicals dashboard and National Toxicology Program’s Integrated Chemical Environment. https://doi.org/10.1289/EHP5580

Soybean (Glycine max (L.) Merril) is a popular foodstuff and crop plant, used in human and animal food. In this work, multielement analysis of soybean grains samples in combination with chemometric tools was used to classify the geographical origins. For this purpose, 120 samples from three provinces of Argentina were analyzed for a panel of 20 trace elements by inductively coupled plasma mass spectrometry. First, we used principal component analysis for exploratory analysis. Then, supervised classification techniques such as support vector machine (SMV) discriminant analysis (SVM-DA), random forest, k-nearest neighbors, and class-modeling techniques such as soft independent modeling of class analogy (SIMCA), potential functions, and one-class SVM were applied as tools to establish a model of origin of samples. The performance of the techniques was compared using global indexes. Among all the models tested, SVM and SIMCA showed the highest percentages in terms of prediction ability in cross-validation with average values of 99.3% for SVM-DA and a median value of balanced accuracy of 96.0%, 91.7%, and 88.3% for the three origins using SIMCA. Results suggested that the developed methodology by chemometric techniques is robust and reliable for the geographical classification of soybean samples from Argentina.

Nuclear receptors (NRs) are key regulators of human health and constitute a relevant target for medicinal chemistry applications as well as for toxicological risk assessment. Several open databases dedicated to small molecules that modulate NRs exist; however, depending on their final aim (i.e., adverse effect assessment or drug design), these databases contain a different amount and type of annotated molecules, along with a different distribution of experimental bioactivity values. Stemming from these considerations, in this work we aim to provide a unified dataset, NURA (NUclear Receptor Activity) dataset, collecting curated information on small molecules that modulate NRs, to be intended for both pharmacological and toxicological applications. NURA contains bioactivity annotations for 15,247 molecules and 11 selected NRs, and it was obtained by integrating and curating data from toxicological and pharmacological databases (i.e., Tox21, ChEMBL, NR-DBIND and BindingDB). Our results show that NURA dataset is a useful tool to bridge the gap between toxicology- and medicinal-chemistry-related databases, as it is enriched in terms of number of molecules, structural diversity and covered atomic scaffolds compared to the single sources. To the best of our knowledge, NURA dataset is the most exhaustive collection of small molecules annotated for their modulation of the chosen nuclear receptors. NURA dataset is intended to support decision-making in pharmacology and toxicology, as well as to contribute to data-driven applications, such as machine learning. The dataset and the data curation pipeline can be downloaded free of charge on Zenodo at the following DOI: https://doi.org/10.5281/zenodo.3991561.

Chianti is a precious red wine and enjoys a high reputation for its high quality in the world wine market. Despite this, the production region is small and product needs efficient tools to protect its brands and prevent adulterations. In this sense, ICP-MS combined with chemometrics has demonstrated its usefulness in food authentication. In this study, Chianti/Chianti Classico, authentic wines from vineyard of Toscana region (Italy), together samples from 18 different geographical regions, were analyzed with the objective of differentiate them from other Italian wines. Partial Least Squares-Discriminant Analysis (PLS-DA) identified variables to discriminate wine geographical origin. Rare Earth Elements (REE), major and trace elements all contributed to the discrimination of Chianti samples. General model was not suited to distinguish PDO red wines from samples, with similar chemical fingerprints, collected in some regions. Specific classification models enhanced the capability of discrimination, emphasizing the discriminant role of some elements.

The characterization of 72 Italian honey samples from 8 botanical varieties was carried out by a comprehensive approach exploiting data fusion of IR, NIR and Raman spectroscopies, Proton Transfer Reaction - Time of Flight - Mass Spectrometry (PTR-MS) and electronic nose. High-, mid- and low-level data fusion approaches were tested to verify if the combination of several analytical sources can improve the classification ability of honeys from different botanical origins. Classification was performed on the fused data by Partial Least Squares - Discriminant Analysis; a strict validation protocol was used to estimate the predictive performances of the models. The best results were obtained with high-level data fusion combining Raman and NIR spectroscopy and PTR-MS, with classification performances better than those obtained on single analytical sources (accuracy of 99% and 100% on test and training samples respectively). The combination of just three analytical sources assures a limited time of analysis.

The assessment of the classification performance can be based on class indices, such as sensitivity, specificity and precision, which describe the classification results achieved on each modelled class. However, in several situations, it is useful to represent the global classification performance with a single number. Therefore, several measures have been introduced in literature to deal with this assessment, accuracy being the most known and used. These metrics have been proposed to generally face binary classification tasks and can behave differently depending on the classification scenario. In this study, different global measures of classification performances are compared by means of results achieved on an extended set of real multivariate datasets. The systematic comparison is carried out through multivariate analysis. Further investigations are then derived on specific indices to understand how the presence of unbalanced classes and the number of modelled classes can influence their behaviour. Finally, this work introduces a set of benchmark values based on different random classification scenarios. These benchmark thresholds can serve as the initial criterion to accept or reject a classification model on the basis of its performance.

Multivariate regression is a fundamental supervised chemometric approach that defines the relationship between a set of independent variables and a quantitative response. It enables the subsequent prediction of the response for future samples, thus avoiding its experimental measurement. Regression approaches have been widely applied for data analysis in different scientific fields. In this paper, we describe the regression toolbox for MATLAB, which is a collection of modules for calculating some well-known regression methods: Ordinary Least Squares (OLS), Partial Least Squares (PLS), Principal Component Regression (PCR), Ridge and local regression based on sample similarities, such as Binned Nearest Neighbours (BNN) and k-Nearest Neighbours (kNN) regression methods. Moreover, the toolbox includes modules to couple regression approaches with supervised variable selection based on All Subset models, Forward Selection, Genetic Algorithms and Reshaped Sequential Replacement. The toolbox is freely available at the Milano Chemometrics and QSAR Research Group website and provides a graphical user interface (GUI), which allows the calculation in a user-friendly graphical environment.

Atmospheric pollutants can originate the decay of historic paintings exposed to the outdoor elements. This is a cause of great concern, since such contaminants can produce physical-chemical alterations manifested initially in undesirable color change. This paper tests an unsupervised multivariate approach on discrete data color parameters in a pioneering study which combines spectrophotometric data and principal components analysis to detect unaesthetic color change on paint dosimeters in (semi)open-air monuments exposed long-term to the urban atmosphere of the city of Granada (South Spain). To this end the chromatic parameter of the CIEL*a*b* and CIEL*C*h* systems (L*, a*, b*, h*, C* and ΔE) were used as variables for subsequent multivariate analysis in order to determine the intrinsic color change trends. The aim is to evaluate the specific chromatic parameter(s) that cause the unaesthetic damage for each type of paint dosimeter, while also considering the influence of the binder (egg yolk/rabbit glue), the pigment (azurite, malachite and lapis lazuli) and for the first time, the grain size of the studied pigments (azurite). Results demonstrated that this approach is capable of discriminating samples on the basis of dosimeter composition, so enabling interpretation of their aging process. Azurite and lapis lazuli-laden dosimeters tended to turn green over time as a result of exposure to city air regardless of binder composition and location. By contrast, all malachite-laden dosimeters became bluer over time. Luminosity remained stronger in dosimeters prepared with collagen, an important parameter in binder discrimination. This information is also of great value for restoration purposes.

REACH requires that all chemicals produced or imported for more than 1 ton/year must be tested for ready biodegradability, a screening test for the assessment of chemical persistence. Since REACH encourages the use of in-silico approaches, several Quantitative Structure-Activity Relationship models have been calibrated to predict this property. Predictions obtained by different models can then be merged by means of specific consensus approaches, because it has been demonstrated that data integration can increase reliability and reduce the effects of contradictory data by averaging results. This study deals with integration of ready biodegradability predictions from eight different models. A set of 416 molecules, external to the training sets of all the considered models, was retrieved from the literature. Predictions were combined with three consensus approaches: majority voting criterion, Dempster–Shafer's theory of evidence and Bayesian consensus with discrete probability distributions. The different approaches were finally evaluated on the basis of the classification performance. On the basis of the obtained results we can conclude that application of consensus methodologies resulted in a reduction of uncertainty associated with biodegradability predictions and showed apparent advantages when sources of information are jointly analysed, without compromising the quality of predictions

The nuclear androgen receptor (AR) is one of the most relevant biological targets of Endocrine Disrupting Chemicals (EDCs), which produce adverse effects by interfering with hormonal regulation and endocrine system functioning. This paper describes novel in silico models to identify organic AR modulators in the context of the Collaborative Modeling Project of Androgen Receptor Activity (CoMPARA), coordinated by the National Center of Computational Toxicology (U.S. Environmental Protection Agency). The collaborative project involved 35 international research groups to prioritize the experimental tests of approximatively 40k compounds, based on the predictions provided by each participant. In this paper, we describe our machine learning approach to predict the binding to AR, which is based on a consensus of a multivariate Bernoulli Naive Bayes, a Random Forest, and N-Nearest Neighbor classification models. The approach was developed in compliance with the Organization of Economic Cooperation and Development (OECD) principles, trained on 1687 ToxCast molecules classified according to 11 in vitro assays, and further validated on a set of 3,882 external compounds. The models provided robust and reliable predictions and were used to gather novel data-driven insights on the structural features related to AR binding, agonism, and antagonism.

High-level data fusion strategies combine and integrate predictions obtained by means of individual models calibrated on single information sources. With respect to other fusion techniques, high-level methods aim at improving prediction performances, as well as reducing the total uncertainty associated with the final combined outcome. In fact, when only partial or even conflictual information is provided by the different sources, the high-level approach integrates the different information and therefore increases the reliability of the combined (fused) prediction. In this chapter, basic (i.e., majority voting) and advanced (i.e., Bayesian consensus with discrete probability distributions and Dempster-Shafter theory of evidence) high-level strategies are evaluated on real analytical multiblock datasets and their advantages and drawbacks described.

This study presents a sensitive electroanalytical method for the determination of capsaicinoids in chili extracts using flow injection with coulometric array detector. Flow injection method was developed based on the coulometric signal of capsaicinoids obtained by high performance liquid chromatography with coulometric detector (HPLC-ECD). Capsaicinoids concentration in 18 chili samples from Yucatán México cultivated in different types of soils was quantified using UHPLC-DAD and HPLC-ECD and expressed in Scoville units. The plants were cultivated in a greenhouse on three types of limestone soils, namely, red, black and brown. Chili peppers were harvested in two stages of maturity: immature (green), and mature (orange). HPLC-ECD method showed ten times higher sensitivity compared to the UHPLC-DAD. Capsaicinoid content in 18 chili samples was measured by flow injection method. The best correlation with the Scoville units was obtained by the analysis of the current signal of the sensor poised at +450 mV (R 2 =94). ANOVA analysis showed that the soil type and the harvest date were significant for the capsaicinoid content. Chili plants cultivated in red soil had higher capsaicinoid content. In addition, the capsaicinoid content was increasing at later harvest dates. In summary, the suggested flow injection method with coulometric array detector decreased the time of analysis from 15 min to 30 s. Therefore it can be successfully applied for the routine capsaicinoid analysis in chili.