Submit to Topical Collection Review for IJERPH

Journal Menu

Journal Browser

Predictive Toxicology (Closed)

Print Collection Flyer
Collection Editors
Collection Information
Keywords
Related Special Issue
Published Papers

A topical collection in International Journal of Environmental Research and Public Health (ISSN 1660-4601). This collection belongs to the section "Environmental Sciences".

Viewed by 21662

Share This Topical Collection

Editor

Dr. Minjun Chen

E-Mail Website
Collection Editor

National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR 72079, USA
Interests: bioinformatics; drug-induced liver injury; drug safety; biomarker discovery; toxicogenomics
Special Issues, Collections and Topics in MDPI journals

Topical Collection Information

Dear Colleagues,

The recent advances of toxicogenomics, high-throughput screening, stem cells, and image analysis are creating unique opportunities to improve our ability to predict risk in humans and the development of predictive toxicology. These modern biotechnologies are producing big toxicological data and require advanced artificial intelligence technologies to evaluate the potential for predicting toxicity. The application of conventional machine learning algorithms, such as logical regression, decision tree, and support vector machines, have largely enhanced our capability to recover useful knowledge from the increasing volume of toxicity data. A recent study reported by researchers from John Hopkins University, demonstrated that using artificial intelligent algorithms trained on chemical-safety, big data could be more predictive and outperform expensive animals studies on some toxicities. Notably, the development of deep learning techniques, with the help of advanced computer technologies (e.g., the use of graphical processing units (GPU)) and complicated neural network algorithms, have brought about breakthroughs in computer vision and pattern recognition, image and speech recognition, drug discovery, and toxicology. In several public scientific challenges, including the Merck-sponsored Kaggle competition in 2012 and the Tox21 Data Challenge in 2015, deep learning algorithms demonstrated a superior predictive performance to convenient machine learning algorithms.

In this Topical Collection, we focus on exploring the relationship between the toxicity of xenobiotics and their chemical structures, disturbed cellular, and molecular pathways by the application of artificial intelligent methods to improve the prediction of toxicity risk. In addition, we especially encourage submissions on applying deep learning techniques to process datasets from high-dimensional gene expression, image and high-throughput screening, and chemical structures.

You may choose our Joint Topical Collection in Toxics.

Dr. Minjun Chen
Collection Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the collection website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Environmental Research and Public Health is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2500 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

Predictive toxicology
Artificial intelligence
Big data
Machine learning
Deep learning
Toxicogenomics
High throughput screening
Image analysis
Chemical structure

Related Special Issue

Predictive Toxicology in Toxics (1 article)

Published Papers (8 papers)

Download All Papers

2022

Jump to: 2021

10 pages, 6621 KiB

Open AccessArticle

NeuroCORD: A Language Model to Facilitate COVID-19-Associated Neurological Disorder Studies

by Leihong Wu, Syed Ali, Heather Ali, Tyrone Brock, Joshua Xu and Weida Tong

Int. J. Environ. Res. Public Health 2022, 19(16), 9974; https://doi.org/10.3390/ijerph19169974 - 12 Aug 2022

Viewed by 1378

Abstract

COVID-19 can lead to multiple severe outcomes including neurological and psychological impacts. However, it is challenging to manually scan hundreds of thousands of COVID-19 articles on a regular basis. To update our knowledge, provide sound science to the public, and communicate effectively, it is critical to have an efficient means of following the most current published data. In this study, we developed a language model to search abstracts using the most advanced artificial intelligence (AI) to accurately retrieve articles on COVID-19-associated neurological disorders. We applied this NeuroCORD model to the largest benchmark dataset of COVID-19, CORD-19. We found that the model developed on the training set yielded 94% prediction accuracy on the test set. This result was subsequently verified by two experts in the field. In addition, when applied to 96,000 non-labeled articles that were published after 2020, the NeuroCORD model accurately identified approximately 3% of them to be relevant for the study of COVID-19-associated neurological disorders, while only 0.5% were retrieved using conventional keyword searching. In conclusion, NeuroCORD provides an opportunity to profile neurological disorders resulting from COVID-19 in a rapid and efficient fashion, and its general framework could be used to study other COVID-19-related emerging health issues. Full article

► Show Figures

Figure 1

13 pages, 1239 KiB

Open AccessArticle

Contrast Media Adverse Drug Reactions in Highly Polluted Environment

by Natalia Sauer, Wojciech Szlasa, Laura Jonderko, Krystyna Głowacka, Katarzyna Karłowicz-Bodalska and Anna Wiela-Hojeńska

Int. J. Environ. Res. Public Health 2022, 19(12), 7077; https://doi.org/10.3390/ijerph19127077 - 09 Jun 2022

Cited by 1 | Viewed by 2325

Abstract

Iodinated- (ICM) and gadolinium-based (GCM) contrast media are used in radiology imaging techniques, such as computer tomography (CT) and magnetic resonance (MR), respectively. The paper aims to analyze the adverse drug reactions of ICM and GCM on different sites of the body in a highly polluted environment. We analyzed the pharmacovigilance in contrast media on the basis of reports submitted to the Regional Center for Monitoring of Adverse Drug Reactions (ADR) at the Department of Clinical Pharmacology in Wrocław. Safety profiles were compared between different ICM and GCM and at the system organ level using the proportional reporting ratio (PRR). We analyzed 124 reports of adverse reactions related to contrast agents between 2006 and 2021. Our findings revealed that ADR combinations occurred more frequently after the use of iodinated contrast agents (72.08%) than gadolinium contrast agents (27.92%). Iomeprol and Iopromide were identified as the most frequently reported media. Each medium presented a different safety profile. Skin disorders are the most common adverse drug reactions among patients using both iodine- and gadolinium-based contrast media. Gadolinium-based contrast agents are characterized by similar organ toxicity. Conversely, iodine-based contrast agents are more diverse—some of which show tissue specificity, such as Iodixanol for the gastrointestinal system or Iohexol for the respiratory tract. This study shows relatively high occurrence of respiratory tract related ADRs in Wrocław. We also prove that it is possible to choose the most optimal contrast agent for patients with specific organ site problems to omit the possible complications. Full article

► Show Figures

Figure 1

2021

Jump to: 2022

12 pages, 787 KiB

Open AccessArticle

Machine Learning to Identify Interaction of Single-Nucleotide Polymorphisms as a Risk Factor for Chronic Drug-Induced Liver Injury

by Roland Moore, Kristin Ashby, Tsung-Jen Liao and Minjun Chen

Int. J. Environ. Res. Public Health 2021, 18(20), 10603; https://doi.org/10.3390/ijerph182010603 - 10 Oct 2021

Cited by 4 | Viewed by 1967

Abstract

Drug-induced liver injury (DILI) is a major cause of drug development failure and drug withdrawal from the market after approval. The identification of human risk factors associated with susceptibility to DILI is of paramount importance. Increasing evidence suggests that genetic variants may lead to inter-individual differences in drug response; however, individual single-nucleotide polymorphisms (SNPs) usually have limited power to predict human phenotypes such as DILI. In this study, we aim to identify appropriate statistical methods to investigate gene–gene and/or gene–environment interactions that impact DILI susceptibility. Three machine learning approaches, including Multivariate Adaptive Regression Splines (MARS), Multifactor Dimensionality Reduction (MDR), and logistic regression, were used. The simulation study suggested that all three methods were robust and could identify the known SNP–SNP interaction when up to 4% of genotypes were randomly permutated. When applied to a real-life DILI chronicity dataset, both MARS and MDR, but not logistic regression, identified combined genetic variants having better associations with DILI chronicity in comparison to the use of individual SNPs. Furthermore, a simple decision tree model using the SNPs identified by MARS and MDR was developed to predict DILI chronicity, with fair performance. Our study suggests that machine learning approaches may help identify gene–gene interactions as potential risk factors for better assessing complicated diseases such as DILI chronicity. Full article

► Show Figures

Figure 1

11 pages, 2874 KiB

Open AccessArticle

Cytotoxicity and Apoptosis Induced by Chenopodium ambrosioides L. Essential Oil in Human Normal Liver Cell Line L02 via the Endogenous Mitochondrial Pathway Rather Than the Endoplasmic Reticulum Stress

by Xiao-Ying Wang, Jun-Mei Hao, Qiu-Rong Ren, Hai-Ying Li, Jing-Song Wu, Xiao-Huan Zhu, Jin-Yao Chen, Ya-Nan Wang and Li-Shi Zhang

Int. J. Environ. Res. Public Health 2021, 18(14), 7469; https://doi.org/10.3390/ijerph18147469 - 13 Jul 2021

Cited by 2 | Viewed by 2208

Abstract

Chenopodium ambrosioides L. (C. ambrosioides) has been used as dietary condiments and as traditional medicine in South America. The oil of Chenopodium ambrosioides L. (C. ambrosioides) can be used as a natural antioxidant in food processing. It also has analgesic, sedating, and deworming effects, and can be used along with the whole plant for its medical effects: decongestion, as an insecticide, and to offer menstruation pain relief. This study was conducted to investigate the cytotoxicity and apoptosis effects of an essential oil from C. ambrosioides in vitro. The cytotoxicity evaluation of the essential oil from C. ambrosioides on human normal liver cell line L02 was assessed by 3-(4,5-dimethyl-2-thiazolyl)-2,5-diphenyl-2-H-tetrazolium bromide (MTT) assay. AO/EB dual fluorescent staining assay and Annexin V-FITC were used for apoptosis analysis. The changes in mitochondrial membrane potential (MMP) were analyzed with 5,5,6,6′-tetrachloro-1,1,3,3,-tetraethyl-imidacarbocyanine iodide (JC-1) dye under a fluorescence microscope. The level of apoptosis related protein expression was quantified by Western blot. The L02 cells were treated with the essential oil from C. ambrosioides at 24, 48, and 72 h, and the IC₅₀ values were 65.45, 58.03, and 35.47 μg/mL, respectively. The AO/EB staining showed that viable apoptotic cells, non-viable apoptotic cells, and non-viable non-apoptotic cells appeared among the L02 cells under the fluorescence microscope. Cell cycle arrest at the S phase and cell apoptosis increased through flow cytometry in the L02 cells treated with the essential oil. MMP decreased in a concentration-dependent manner, as seen through JC-1 staining under the fluorescence microscope. In the L02 cells as shown by Western blot and qPCR, the amount of the apoptosis-related proteins and the mRNA expression levels of cytochrome C, Bax, Caspase-9, and Caspase-3 increased, Bcl-2 decreased, and Caspase-12, which is expressed in the endoplasmic reticulum, showed no obvious changes in protein amount or mRNA expression level. The essential oil form C. ambrosioides had a cytotoxic effect on L02 cells. It could inhibit L02 cell proliferation, arrest the cell cycle at the S phase, and induce L02 cell apoptosis through the endogenous mitochondrial pathway. Full article

► Show Figures

Figure 1

14 pages, 7090 KiB

Open AccessArticle

Machine Learning for Predicting Risk of Drug-Induced Autoimmune Diseases by Structural Alerts and Daily Dose

by Yue Wu, Jieqiang Zhu, Peter Fu, Weida Tong, Huixiao Hong and Minjun Chen

Int. J. Environ. Res. Public Health 2021, 18(13), 7139; https://doi.org/10.3390/ijerph18137139 - 03 Jul 2021

Cited by 7 | Viewed by 2961

Abstract

An effective approach for assessing a drug’s potential to induce autoimmune diseases (ADs) is needed in drug development. Here, we aim to develop a workflow to examine the association between structural alerts and drugs-induced ADs to improve toxicological prescreening tools. Considering reactive metabolite (RM) formation as a well-documented mechanism for drug-induced ADs, we investigated whether the presence of certain RM-related structural alerts was predictive for the risk of drug-induced AD. We constructed a database containing 171 RM-related structural alerts, generated a dataset of 407 AD- and non-AD-associated drugs, and performed statistical analysis. The nitrogen-containing benzene substituent alerts were found to be significantly associated with the risk of drug-induced ADs (odds ratio = 2.95, p = 0.0036). Furthermore, we developed a machine-learning-based predictive model by using daily dose and nitrogen-containing benzene substituent alerts as the top inputs and achieved the predictive performance of area under curve (AUC) of 70%. Additionally, we confirmed the reactivity of the nitrogen-containing benzene substituent aniline and related metabolites using quantum chemistry analysis and explored the underlying mechanisms. These identified structural alerts could be helpful in identifying drug candidates that carry a potential risk of drug-induced ADs to improve their safety profiles. Full article

► Show Figures

Figure 1

15 pages, 6864 KiB

Open AccessArticle

Assessment of the Toxicity of Quantum Dots through Biliometric Analysis

by Lishi Zhong, Lili Zhang, Yimeng Li, Xue Liang, Lu Kong, Xiaobing Shen and Tianshu Wu

Int. J. Environ. Res. Public Health 2021, 18(11), 5768; https://doi.org/10.3390/ijerph18115768 - 27 May 2021

Cited by 12 | Viewed by 2668

Abstract

Along with the rapid development of nanotechnology, the biosafety of quantum dots (QDs), a widely used kind of nanoparticles, has grabbed the attentions of researchers, because QDs have excellent and unique optical properties that other commonly used nanoparticles, like walled carbon nanotubes, do not have. The understanding of the toxicity of QDs is an important premise for their application in wider fields, including biology and medicine. This study sought to analyze scientific publications on the toxicity of QDs and to construct a bibliometric model for qualitative and quantitative evaluation of these publications over the past decade, which visually presented the status quo and future development trend on the toxicological study of QDs. A search for data using the triple blind method revealed that, as of 31 December 2018, there were 5269 papers published on the toxicity of QDs. RSC ADVANCES (5-year IF, 3.096) ranked first in the number of publications. China had the largest number of publications (2233) and the highest H-index (119), but the United States was still the leading country with regards to the quality of the research. LIU Y (106 publications) published the most papers, while Hardman R (304 co-citations) had the most co-citations. The keyword “walled carbon nanotube” ranked first in the research frontier. The findings not only determine a development trend of the toxicological study of QDs, but also identify further research directions in this field. Full article

► Show Figures

Figure 1

11 pages, 2120 KiB

Open AccessArticle

Multi-Drug Featurization and Deep Learning Improve Patient-Specific Predictions of Adverse Events

by Ioannis N. Anastopoulos, Chloe K. Herczeg, Kasey N. Davis and Atray C. Dixit

Int. J. Environ. Res. Public Health 2021, 18(5), 2600; https://doi.org/10.3390/ijerph18052600 - 05 Mar 2021

Cited by 7 | Viewed by 4242 | Correction

Abstract

While the clinical approval process is able to filter out medications whose utility does not offset their adverse drug reaction profile in humans, it is not well suited to characterizing lower frequency issues and idiosyncratic multi-drug interactions that can happen in real world diverse patient populations. With a growing abundance of real-world evidence databases containing hundreds of thousands of patient records, it is now feasible to build machine learning models that incorporate individual patient information to provide personalized adverse event predictions. In this study, we build models that integrate patient specific demographic, clinical, and genetic features (when available) with drug structure to predict adverse drug reactions. We develop an extensible graph convolutional approach to be able to integrate molecular effects from the variable number of medications a typical patient may be taking. Our model outperforms standard machine learning methods at the tasks of predicting hospitalization and death in the UK Biobank dataset yielding an R² of 0.37 and an AUC of 0.90, respectively. We believe our model has potential for evaluating new therapeutic compounds for individualized toxicities in real world diverse populations. It can also be used to prioritize medications when there are multiple options being considered for treatment. Full article

► Show Figures

Figure 1

13 pages, 3535 KiB

Open AccessArticle

Polydatin Beneficial Effects in Zebrafish Larvae Undergoing Multiple Stress Types

by Andrea Pessina, Mariangela Di Vincenzo, Francesca Maradonna, Francesca Marchegiani, Fabiola Olivieri, Basilio Randazzo, Giorgia Gioacchini and Oliana Carnevali

Int. J. Environ. Res. Public Health 2021, 18(3), 1116; https://doi.org/10.3390/ijerph18031116 - 27 Jan 2021

Cited by 4 | Viewed by 2464

Abstract

Polydatin is a polyphenol, whose beneficial properties, including anti-inflammatory and antioxidant activity, have been largely demonstrated. At the same time, copper has an important role in the correct organism homeostasis and alteration of its concentration can induce oxidative stress. In this study, the efficacy of polydatin to counteract the stress induced by CuSO₄ exposure or by caudal fin amputation was investigated in zebrafish larvae. The study revealed that polydatin can reduced the stress induced by a 2 h exposure to 10 µM CuSO₄ by lowering the levels of il1b and cxcl8b.1 and reducing neutrophils migration in the head and along the lateral line. Similarly, polydatin administration reduced the number of neutrophils in the area of fin cut. In addition, polydatin upregulates the expression of sod1 mRNA and CAT activity, both involved in the antioxidant response. Most of the results obtained in this study support the working hypothesis that polydatin administration can modulate stress response and its action is more effective in mitigating the effects rather than in preventing chemical damages. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Predictive Toxicology (Closed)

Share This Topical Collection

Editor

Topical Collection Information

Keywords

Related Special Issue

Published Papers (8 papers)

2022

Jump to: 2021

2021

Jump to: 2022

Further Information

Guidelines

MDPI Initiatives

Follow MDPI