Machine Learning and Deep Learning in Chemical Health and Safety: A Systematic Review of Techniques and Applications

Advances in artificial intelligence for drug delivery and development: A comprehensive review

Artificial intelligence (AI) has emerged as a powerful tool to revolutionize the healthcare sector, including drug delivery and development. This review explores the current and future applications of AI in the pharmaceutical industry, focusing on drug delivery and development. It covers various aspects such as smart drug delivery networks, sensors, drug repurposing, statistical modeling, and simulation of biotechnological and biological systems. The integration of AI with nanotechnologies and nanomedicines is also examined. AI offers significant advancements in drug discovery by efficiently identifying compounds, validating drug targets, streamlining drug structures, and prioritizing response templates. Techniques like data mining, multitask learning, and high-throughput screening contribute to better drug discovery and development innovations. The review discusses AI applications in drug formulation and delivery, clinical trials, drug safety, and pharmacovigilance. It addresses regulatory considerations and challenges associated with AI in pharmaceuticals, including privacy, data security, and interpretability of AI models. The review concludes with future perspectives, highlighting emerging trends, addressing limitations and biases in AI models, and emphasizing the importance of collaboration and knowledge sharing. It provides a comprehensive overview of AI's potential to transform the pharmaceutical industry and improve patient care while identifying further research and development areas.

Classification of battery compounds using structure-free Mendeleev encodings

Machine learning is a valuable tool that can accelerate the discovery and design of materials occupying combinatorial chemical spaces. However, the prerequisite need for vast amounts of training data can be prohibitive when significant resources are needed to characterize or simulate candidate structures. Recent results have shown that structure-free encoding of complex materials, based entirely on chemical compositions, can overcome this impediment and perform well in unsupervised learning tasks. In this study, we extend this exploration to supervised classification, and show how structure-free encoding can accurately predict classes of material compounds for battery applications without time consuming measurement of bonding networks, lattices or densities. SCIENTIFIC CONTRIBUTION: The comprehensive evaluation of structure-free encodings of complex materials in classification tasks, including binary and multi-class separation, inclusive of three classifiers based on different logic function, is measured four metrics and learning curves. The encoding is applied to two data sets from computational and experimental sources, and the outcomes visualised using 5 approaches to confirms the suitability and superiority of Mendeleev encoding. These methods are general and accessible using source software, to provide simple, intuitive and interpretable materials informatics outcomes to accelerate materials design.

Systematic approaches to machine learning models for predicting pesticide toxicity

Pesticides play an important role in modern agriculture by protecting crops from pests and diseases. However, the negative consequences of pesticides, such as environmental contamination and adverse effects on human and ecological health, underscore the importance of accurate toxicity predictions. To address this issue, artificial intelligence models have emerged as valuable methods for predicting the toxicity of organic compounds. In this review article, we explore the application of machine learning (ML) for pesticide toxicity prediction. This review provides a detailed summary of recent developments, prediction models, and datasets used for pesticide toxicity prediction. In this analysis, we compared the results of several algorithms that predict the harmfulness of various classes of pesticides. Furthermore, this review article identified emerging trends and areas for future direction, showcasing the transformative potential of machine learning in promoting safer pesticide usage and sustainable agriculture.

Detection and characterization of spike architecture based on deep learning and X-ray computed tomography in barley

BACKGROUND

Spike is the grain-bearing organ in cereal crops, which is a key proxy indicator determining the grain yield and quality. Machine learning methods for image analysis of spike-related phenotypic traits not only hold the promise for high-throughput estimating grain production and quality, but also lay the foundation for better dissection of the genetic basis for spike development. Barley (Hordeum vulgare L.) is one of the most important crops globally, ranking as the fourth largest cereal crop in terms of cultivated area and total yield. However, image analysis of spike-related traits in barley, especially based on CT-scanning, remains elusive at present.

RESULTS

In this study, we developed a non-invasive, high-throughput approach to quantitatively measuring the multitude of spike architectural traits in barley through combining X-ray computed tomography (CT) and a deep learning model (UNet). Firstly, the spikes of 11 barley accessions, including 2 wild barley, 3 landraces and 6 cultivars were used for X-ray CT scanning to obtain the tomographic images. And then, an optimized 3D image processing method was used to point cloud data to generate the 3D point cloud images of spike, namely 'virtual' spike, which is then used to investigate internal structures and morphological traits of barley spikes. Furthermore, the virtual spike-related traits, such as spike length, grain number per spike, grain volume, grain surface area, grain length and grain width as well as grain thickness were efficiently and non-destructively quantified. The virtual values of these traits were highly consistent with the actual value using manual measurement, demonstrating the accuracy and reliability of the developed model. The reconstruction process took 15 min approximately, 10 min for CT scanning and 5 min for imaging and features extraction, respectively.

CONCLUSIONS

This study provides an efficient, non-invasive and useful tool for dissecting barley spike architecture, which will contribute to high-throughput phenotyping and breeding for high yield in barley and other crops.

Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network

Morphological measurements of nanoparticles in electron microscopy images are tedious, laborious, and often succumb to human errors. Deep learning methods in artificial intelligence (AI) paved the way for automated image understanding. This work proposes a deep neural network (DNN) for the automated segmentation of a Au spiky nanoparticle (SNP) in electron microscopic images, and the network is trained with a spike-focused loss function. The segmented images are used for the growth measurement of the Au SNP. The auxiliary loss function captures the spikes of the nanoparticle, which prioritizes the detection of spikes in the border regions. The growth of the particles measured by the proposed DNN is as good as the measurement in manually segmented images of the particles. The proposed DNN composition with the training methodology meticulously segments the particle and consequently provides accurate morphological analysis. Furthermore, the proposed network is tested on an embedded system for integration with the microscope hardware for real-time morphological analysis.

A Physical Organic Approach towards Statistical Modeling of Tetrazole and Azide Decomposition

Nitrogen atom-rich heterocycles and organic azides have found extensive use in many sectors of modern chemistry from drug discovery to energetic materials. The prediction and understanding of their energetic properties are thus key to the safe and effective application of these compounds. In this work, we disclose the use of multivariate linear regression modeling for the prediction of the decomposition temperature and impact sensitivity of structurally diverse tetrazoles and organic azides. We report a data-driven approach for property prediction featuring a collection of quantum mechanical parameters and computational workflows. The statistical models reported herein carry predictive accuracy as well as chemical interpretability. Model validation was successfully accomplished via tetrazole test sets with parameters generated exclusively in silico. Mechanistic analysis of the statistical models indicated distinct divergent pathways of thermal and impact-initiated decomposition.

Predicting Chemical End-of-Life Scenarios Using Structure-Based Classification Models

Analyzing chemicals and their effects on the environment from a life cycle viewpoint can produce a thorough analysis that takes end-of-life (EoL) activities into account. Chemical risk assessment, predicting environmental discharges, and finding EoL paths and exposure scenarios all depend on chemical flow data availability. However, it is challenging to gain access to such data and systematically determine EoL activities and potential chemical exposure scenarios. As a result, this work creates quantitative structure-transfer relationship (QSTR) models for aiding environmental managment decision-making based on chemical structure-based machine learning (ML) models to predict potential industrial EoL activities, chemical flow allocation, environmental releases, and exposure routes. Further multi-label classification methods may improve the predictability of QSTR models according to the ML experiment tracking. The developed QSTR models will assist stakeholders in predicting and comprehending potential EoL management activities and recycling loops, enabling environmental decision-making and EoL exposure assessment for new or existing chemicals in the global marketplace.

Predicting Chemical Carcinogens Using a Hybrid Neural Network Deep Learning Method

Determining environmental chemical carcinogenicity is urgently needed as humans are increasingly exposed to these chemicals. In this study, we developed a hybrid neural network (HNN) method called HNN-Cancer to predict potential carcinogens of real-life chemicals. The HNN-Cancer included a new SMILES feature representation method by modifying our previous 3D array representation of 1D SMILES simulated by the convolutional neural network (CNN). We developed binary classification, multiclass classification, and regression models based on diverse non-congeneric chemicals. Along with the HNN-Cancer model, we developed models based on the random forest (RF), bootstrap aggregating (Bagging), and adaptive boosting (AdaBoost) methods for binary and multiclass classification. We developed regression models using HNN-Cancer, RF, support vector regressor (SVR), gradient boosting (GB), kernel ridge (KR), decision tree with AdaBoost (DT), KNeighbors (KN), and a consensus method. The performance of the models for all classifications was assessed using various statistical metrics. The accuracy of the HNN-Cancer, RF, and Bagging models were 74%, and their AUC was ~0.81 for binary classification models developed with 7994 chemicals. The sensitivity was 79.5% and the specificity was 67.3% for the HNN-Cancer, which outperforms the other methods. In the case of multiclass classification models with 1618 chemicals, we obtained the optimal accuracy of 70% with an AUC 0.7 for HNN-Cancer, RF, Bagging, and AdaBoost, respectively. In the case of regression models, the correlation coefficient (R) was around 0.62 for HNN-Cancer and RF higher than the SVM, GB, KR, DTBoost, and NN machine learning methods. Overall, the HNN-Cancer performed better for the majority of the known carcinogen experimental datasets. Further, the predictive performance of HNN-Cancer on diverse chemicals is comparable to the literature-reported models that included similar and less diverse molecules. Our HNN-Cancer could be used in identifying potentially carcinogenic chemicals for a wide variety of chemical classes.

Representation, mining and analysis of unsafe behaviour based on pan-scene data

To describe the safety rules of various industrial process data and explore the characteristics of unsafe behaviour, the association rules of unsafe behaviour based on pan-scene were proposed in this study. First, based on the scene data theory, unsafe behaviour was described by eight dimensions (time, location, behavioural individual, unsafe action, behavioural attribute, behavioural trace, professional category and risk level) to achieve scene data description and structural transformation. Second, the Apriori algorithm was used to explore the distribution rules of unsafe behaviour dimensions and the interaction between different dimensions from two perspectives: single-dimensional statistical analysis and multidimensional association rule mining. Finally, through SPSS Modeler software, an empirical analysis of pan-scene data for subway construction was conducted, and the association rules between type of work, construction stage, working time and unsafe action were identified. Some strong association rules were produced by the association analysis. For example, during the 13:00-17:00 of the excavation floor stage, the most frequent unsafe action of machine operators is the irregular binding of lifting objects. This result could explain why some unsafe actions are prone to occur in different construction stages and working times for workers of different types, which can be controlled and managed in a targeted manner, thus reducing the possibility of accidents.

Comprehensive Survey of Machine Learning Systems for COVID-19 Detection

The last two years are considered the most crucial and critical period of the COVID-19 pandemic affecting most life aspects worldwide. This virus spreads quickly within a short period, increasing the fatality rate associated with the virus. From a clinical perspective, several diagnosis methods are carried out for early detection to avoid virus propagation. However, the capabilities of these methods are limited and have various associated challenges. Consequently, many studies have been performed for COVID-19 automated detection without involving manual intervention and allowing an accurate and fast decision. As is the case with other diseases and medical issues, Artificial Intelligence (AI) provides the medical community with potential technical solutions that help doctors and radiologists diagnose based on chest images. In this paper, a comprehensive review of the mentioned AI-based detection solution proposals is conducted. More than 200 papers are reviewed and analyzed, and 145 articles have been extensively examined to specify the proposed AI mechanisms with chest medical images. A comprehensive examination of the associated advantages and shortcomings is illustrated and summarized. Several findings are concluded as a result of a deep analysis of all the previous works using machine learning for COVID-19 detection, segmentation, and classification.

Redundancy Analysis to Reduce the High-Dimensional Near-Infrared Spectral Information to Improve the Authentication of Olive Oil

The high price of marketing of extra virgin olive oil (EVOO) requires the introduction of cost-effective and sustainable procedures that facilitate its authentication, avoiding fraud in the sector. Contrary to classical techniques (such as chromatography), near-infrared (NIR) spectroscopy does not need derivatization of the sample with proper integration of separated peaks and is more reliable, rapid, and cost-effective. In this work, principal component analysis (PCA) and then redundancy analysis (RDA)—which can be seen as a constrained version of PCA—are used to summarize the high-dimensional NIR spectral information. Then PCA and RDA factors are contemplated as explanatory variables in models to authenticate oils from qualitative or quantitative analysis, in particular, in the prediction of the percentage of EVOO in blended oils or in the classification of EVOO or other vegetable oils (sunflower, hazelnut, corn, or linseed oil) by the use of some machine learning algorithms. As a conclusion, the results highlight the potential of RDA factors in prediction and classification because they appreciably improve the results obtained from PCA factors in calibration and validation.

Machine Learning for Evaluating the Cytotoxicity of Mixtures of Nano-TiO2 and Heavy Metals: QSAR Model Apply Random Forest Algorithm after Clustering Analysis

With the development and application of nanomaterials, their impact on the environment and organisms has attracted attention. As a common nanomaterial, nano-titanium dioxide (nano-TiO₂) has adsorption properties to heavy metals in the environment. Quantitative structure-activity relationship (QSAR) is often used to predict the cytotoxicity of a single substance. However, there is little research on the toxicity of interaction between nanomaterials and other substances. In this study, we exposed human renal cortex proximal tubule epithelial (HK-2) cells to mixtures of eight heavy metals with nano-TiO₂, measured absorbance values by CCK-8, and calculated cell viability. PLS and two ensemble learning algorithms are used to build multiple QSAR models for data sets, and the test set R² is increased from 0.38 to 0.78 and 0.85, and RMSE is decreased from 0.18 to 0.12 and 0.10. After selecting the better random forest algorithm, the K-means clustering algorithm is used to continue to optimize the model, increasing the test set R² to 0.95 and decreasing the RMSE to 0.08 and 0.06. As a reliable machine algorithm, random forest can be used to predict the toxicity of the mixture of nano-metal oxides and heavy metals. The cluster analysis can effectively improve the stability and predictability of the model, and provide a new idea for the prediction of cytotoxicity model in the future.

Decoding the Role of Epigenetics in Breast Cancer Using Formal Modeling and Machine-Learning Methods

Breast carcinogenesis is known to be instigated by genetic and epigenetic modifications impacting multiple cellular signaling cascades, thus making its prevention and treatments a challenging endeavor. However, epigenetic modification, particularly DNA methylation-mediated silencing of key TSGs, is a hallmark of cancer progression. One such tumor suppressor gene (TSG) RUNX3 (Runt-related transcription factor 3) has been a new insight in breast cancer known to be suppressed due to local promoter hypermethylation mediated by DNA methyltransferase 1 (DNMT1). However, the precise mechanism of epigenetic-influenced silencing of the RUNX3 signaling resulting in cancer invasion and metastasis remains inadequately characterized. In this study, a biological regulatory network (BRN) has been designed to model the dynamics of the DNMT1–RUNX3 network augmented by other regulators such as p21, c-myc, and p53. For this purpose, the René Thomas qualitative modeling was applied to compute the unknown parameters and the subsequent trajectories signified important behaviors of the DNMT1–RUNX3 network (i.e., recovery cycle, homeostasis, and bifurcation state). As a result, the biological system was observed to invade cancer metastasis due to persistent activation of oncogene c-myc accompanied by consistent downregulation of TSG RUNX3. Conversely, homeostasis was achieved in the absence of c-myc and activated TSG RUNX3. Furthermore, DNMT1 was endorsed as a potential epigenetic drug target to be subjected to the implementation of machine-learning techniques for the classification of the active and inactive DNMT1 modulators. The best-performing ML model successfully classified the active and least-active DNMT1 inhibitors exhibiting 97% classification accuracy. Collectively, this study reveals the underlined epigenetic events responsible for RUNX3-implicated breast cancer metastasis along with the classification of DNMT1 modulators that can potentially drive the perception of epigenetic-based tumor therapy.

Isometric Stratified Ensembles: A Partial and Incremental Adaptive Applicability Domain and Consensus-Based Classification Strategy for Highly Imbalanced Data Sets with Application to Colloidal Aggregation

Partial and incremental stratification analysis of a quantitative structure-interference relationship (QSIR) is a novel strategy intended to categorize classification provided by machine learning techniques. It is based on a 2D mapping of classification statistics onto two categorical axes: the degree of consensus and level of applicability domain. An internal cross-validation set allows to determine the statistical performance of the ensemble at every 2D map stratum and hence to define isometric local performance regions with the aim of better hit ranking and selection. During training, isometric stratified ensembles (ISE) applies a recursive decorrelated variable selection and considers the cardinal ratio of classes to balance training sets and thus avoid bias due to possible class imbalance. To exemplify the interest of this strategy, three different highly imbalanced PubChem pairs of AmpC β-lactamase and cruzain inhibition assay campaigns of colloidal aggregators and complementary aggregators data set available at the AGGREGATOR ADVISOR predictor web page were employed. Statistics obtained using this new strategy show outperforming results compared to former published tools, with and without a classical applicability domain. ISE performance on classifying colloidal aggregators shows from a global AUC of 0.82, when the whole test data set is considered, up to a maximum AUC of 0.88, when its highest confidence isometric stratum is retained.

Machine Learning Applied to the Modeling of Pharmacological and ADMET Endpoints

The well-known concept of quantitative structure-activity relationships (QSAR) has been gaining significant interest in the recent years. Data, descriptors, and algorithms are the main pillars to build useful models that support more efficient drug discovery processes with in silico methods. Significant advances in all three areas are the reason for the regained interest in these models. In this book chapter we review various machine learning (ML) approaches that make use of measured in vitro/in vivo data of many compounds. We put these in context with other digital drug discovery methods and present some application examples.

Multifaceted targeting strategies in cancer against the human notch 3 protein: a computational study

Notch receptors play a significant role in the development and the regulation of cell-fate in several multicellular organisms. For normal differentiation, genomes are essential as their regular roles and play a role in cancer is dysregulated. Notch 3 has been shown to play a major role in lung cancer function and therefore, inhibition of notch 3 protein activation represents a clear plan for cancer treatment. This study accomplished a combined structure- and ligand-based pharmacophore hypothesis to explore novel notch 3 inhibitors. The analysis identified common lead molecule ZINC000013449462 that showed better XP GScore and binding energy score than the reference inhibitor DAPT. The identified lead compound that passed all the druggable characteristics exhibited stable binding. Furthermore, the lead molecule can also form hydrogen and salt bridge interactions with binding site residues Asp1621 and Arg1465 residues, respectively of the active pockets of notch 3 protein. In essence, the inhibitory activity of the hit was validated across 109 NSCLC cell lines by employing a deep neural network algorithm. Our study proposes that ZINC000013449462 would be a possible prototype molecule towards the notch 3 target and further examined by clinical studies to combat NSCLC.

In silico prediction of chemical-induced hematotoxicity with machine learning and deep learning methods

Chemical-induced hematotoxicity is an important concern in the drug discovery, since it can often be fatal when it happens. It is quite useful for us to give special attention to chemicals which can cause hematotoxicity. In the present study, we focused on in silico prediction of chemical-induced hematotoxicity with machine learning (ML) and deep learning (DL) methods. We collected a large data set contained 632 hematotoxic chemicals and 1525 approved drugs without hematotoxicity. Computational models were built using several different machine learning and deep learning algorithms integrated on the Online Chemical Modeling Environment (OCHEM). Based on the three best individual models, a consensus model was developed. It yielded the prediction accuracy of 0.83 and balanced accuracy of 0.77 on external validation. The consensus model and the best individual model developed with random forest regression and classification algorithm (RFR) and QNPR descriptors were made available at https://ochem.eu/article/135149 , respectively. The relevance of 8 commonly used molecular properties and chemical-induced hematotoxicity was also investigated. Several molecular properties have an obvious differentiating effect on chemical-induced hematotoxicity. Besides, 12 structural alerts responsible for chemical hematotoxicity were identified using frequency analysis of substructures from Klekota-Roth fingerprint. These results should provide meaningful knowledge and useful tools for hematotoxicity evaluation in drug discovery and environmental risk assessment.

A Novel Automated Framework for QSAR Modeling of Highly Imbalanced Leishmania High-Throughput Screening Data

In silico prediction of antileishmanial activity using quantitative structure-activity relationship (QSAR) models has been developed on limited and small datasets. Nowadays, the availability of large and diverse high-throughput screening data provides an opportunity to the scientific community to model this activity from the chemical structure. In this study, we present the first KNIME automated workflow to modeling a large, diverse, and highly imbalanced dataset of compounds with antileishmanial activity. Because the data is strongly biased toward inactive compounds, a novel strategy was implemented based on the selection of different balanced training sets and a further consensus model using single decision trees as the base model and three criteria for output combinations. The decision tree consensus was adopted after comparing its classification performance to consensuses built upon Gaussian-Naı̈ve-Bayes, Support-Vector-Machine, Random-Forest, Gradient-Boost, and Multi-Layer-Perceptron base models. All these consensuses were rigorously validated using internal and external test validation sets and were compared against each other using Friedman and Bonferroni-Dunn statistics. For the retained decision tree-based consensus model, which covers 100% of the chemical space of the dataset and with the lowest consensus level, the overall accuracy statistics for test and external sets were between 71 and 74% and 71 and 76%, respectively, while for a reduced chemical space (21%) and with an incremental consensus level, the accuracy statistics were substantially improved with values for the test and external sets between 86 and 92% and 88 and 92%, respectively. These results highlight the relevance of the consensus model to prioritize a relatively small set of active compounds with high prediction sensitivity using the Incremental Consensus at high level values or to predict as many compounds as possible, lowering the level of Incremental Consensus. Finally, the workflow developed eliminates human bias, improves the procedure reproducibility, and allows other researchers to reproduce our design and use it in their own QSAR problems.

Computational Investigation Identified Potential Chemical Scaffolds for Heparanase as Anticancer Therapeutics

Heparanase (Hpse) is an endo-β-D-glucuronidase capable of cleaving heparan sulfate side chains. Its upregulated expression is implicated in tumor growth, metastasis and angiogenesis, thus making it an attractive target in cancer therapeutics. Currently, a few small molecule inhibitors have been reported to inhibit Hpse, with promising oral administration and pharmacokinetic (PK) properties. In the present study, a ligand-based pharmacophore model was generated from a dataset of well-known active small molecule Hpse inhibitors which were observed to display favorable PK properties. The compounds from the InterBioScreen database of natural (69,034) and synthetic (195,469) molecules were first filtered for their drug-likeness and the pharmacophore model was used to screen the drug-like database. The compounds acquired from screening were subjected to molecular docking with Heparanase, where two molecules used in pharmacophore generation were used as reference. From the docking analysis, 33 compounds displayed higher docking scores than the reference and favorable interactions with the catalytic residues. Complex interactions were further evaluated by molecular dynamics simulations to assess their stability over a period of 50 ns. Furthermore, the binding free energies of the 33 compounds revealed 2 natural and 2 synthetic compounds, with better binding affinities than reference molecules, and were, therefore, deemed as hits. The hit compounds presented from this in silico investigation could act as potent Heparanase inhibitors and further serve as lead scaffolds to develop compounds targeting Heparanase upregulation in cancer.

Exploring safe and potent bioactives for the treatment of non-small cell lung cancer

Activating and suppressing mutations in the MAPK pathway receptors are the primary causes of NSCLC. Of note, MEK inhibition is considered a promising strategy because of the diverse structures and harmful effects of upstream receptors in MAPK pathway. Thus, we explore a total of 1574 plant-based bioactive compounds activity against MEK using an energy-based virtual screening strategy. Molecular docking, binding free energy, and drug-likeness analysis were performed through GLIDE, Prime MM-GBSA, and QikProp module, respectively. The findings indicate that 5-O-caffeoylshikimic acid has an increased binding affinity to MEK protein. Further, molecular dynamic simulations and MM-PBSA analysis were performed to explore the ligand activity in real-life situations. In essence, compounds inhibitory activity was validated across 77 lung cancer cell lines using multimodal attention-based neural network algorithm. Eventually, our analysis highlight that 5-O-caffeoylshikimic acid obtained from the bark of Rhizoma smilacis glabrae would be developed as a potential compound for treating NSCLC.