A systematic analysis and data mining of opioid-related adverse events submitted to the FAERS database.

The opioid epidemic has become a serious national crisis in the United States. An indepth systematic analysis of opioid-related adverse events (AEs) can clarify the risks presented by opioid exposure, as well as the individual risk profiles of specific opioid drugs and the potential relationships among the opioids. In this study, 92 opioids were identified from the list of all Food and Drug Administration (FDA)-approved drugs, annotated by RxNorm and were classified into 13 opioid groups: buprenorphine, codeine, dihydrocodeine, fentanyl, hydrocodone, hydromorphone, meperidine, methadone, morphine, oxycodone, oxymorphone, tapentadol, and tramadol. A total of 14,970,399 AE reports were retrieved and downloaded from the FDA Adverse Events Reporting System (FAERS) from 2004, Quarter 1 to 2020, Quarter 3. After data processing, Empirical Bayes Geometric Mean (EBGM) was then applied which identified 3317 pairs of potential risk signals within the 13 opioid groups. Based on these potential safety signals, a comparative analysis was pursued to provide a global overview of opioid-related AEs for all 13 groups of FDA-approved prescription opioids. The top 10 most reported AEs for each opioid class were then presented. Both network analysis and hierarchical clustering analysis were conducted to further explore the relationship between opioids. Results from the network analysis revealed a close association among fentanyl, oxycodone, hydrocodone, and hydromorphone, which shared more than 22 AEs. In addition, much less commonly reported AEs were shared among dihydrocodeine, meperidine, oxymorphone, and tapentadol. On the contrary, the hierarchical clustering analysis further categorized the 13 opioid classes into two groups by comparing the full profiles of presence/absence of AEs. The results of network analysis and hierarchical clustering analysis were not only consistent and cross-validated each other but also provided a better and deeper understanding of the associations and relationships between the 13 opioid groups with respect to their adverse effect profiles.

Developing a SARS-CoV-2 main protease binding prediction random forest model for drug repurposing for COVID-19 treatment.

The coronavirus disease 2019 (COVID-19) global pandemic resulted in millions of people becoming infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and close to seven million deaths worldwide. It is essential to further explore and design effective COVID-19 treatment drugs that target the main protease of SARS-CoV-2, a major target for COVID-19 drugs. In this study, machine learning was applied for predicting the SARS-CoV-2 main protease binding of Food and Drug Administration (FDA)-approved drugs to assist in the identification of potential repurposing candidates for COVID-19 treatment. Ligands bound to the SARS-CoV-2 main protease in the Protein Data Bank and compounds experimentally tested in SARS-CoV-2 main protease binding assays in the literature were curated. These chemicals were divided into training (516 chemicals) and testing (360 chemicals) data sets. To identify SARS-CoV-2 main protease binders as potential candidates for repurposing to treat COVID-19, 1188 FDA-approved drugs from the Liver Toxicity Knowledge Base were obtained. A random forest algorithm was used for constructing predictive models based on molecular descriptors calculated using Mold2 software. Model performance was evaluated using 100 iterations of fivefold cross-validations which resulted in 78.8% balanced accuracy. The random forest model that was constructed from the whole training dataset was used to predict SARS-CoV-2 main protease binding on the testing set and the FDA-approved drugs. Model applicability domain and prediction confidence on drugs predicted as the main protease binders discovered 10 FDA-approved drugs as potential candidates for repurposing to treat COVID-19. Our results demonstrate that machine learning is an efficient method for drug repurposing and, thus, may accelerate drug development targeting SARS-CoV-2.

RxNorm for drug name normalization: a case study of prescription opioids in the FDA adverse events reporting system.

Numerous studies have been conducted on the US Food and Drug Administration (FDA) Adverse Events Reporting System (FAERS) database to assess post-marketing reporting rates for drug safety review and risk assessment. However, the drug names in the adverse event (AE) reports from FAERS were heterogeneous due to a lack of uniformity of information submitted mandatorily by pharmaceutical companies and voluntarily by patients, healthcare professionals, and the public. Studies using FAERS and other spontaneous reporting AEs database without drug name normalization may encounter incomplete collection of AE reports from non-standard drug names and the accuracies of the results might be impacted. In this study, we demonstrated applicability of RxNorm, developed by the National Library of Medicine, for drug name normalization in FAERS. Using prescription opioids as a case study, we used RxNorm application program interface (API) to map all FDA-approved prescription opioids described in FAERS AE reports to their equivalent RxNorm Concept Unique Identifiers (RxCUIs) and RxNorm names. The different names of the opioids were then extracted, and their usage frequencies were calculated in collection of more than 14.9 million AE reports for 13 FDA-approved prescription opioid classes, reported over 17 years. The results showed that a significant number of different names were consistently used for opioids in FAERS reports, with 2,086 different names (out of 7,892) used at least three times and 842 different names used at least ten times for each of the 92 RxNorm names of FDA-approved opioids. Our method of using RxNorm API mapping was confirmed to be efficient and accurate and capable of reducing the heterogeneity of prescription opioid names significantly in the AE reports in FAERS; meanwhile, it is expected to have a broad application to different sets of drug names from any database where drug names are diverse and unnormalized. It is expected to be able to automatically standardize and link different representations of the same drugs to build an intact and high-quality database for diverse research, particularly postmarketing data analysis in pharmacovigilance initiatives.

Deep Learning Models for Predicting Gas Adsorption Capacity of Nanomaterials.

Metal-organic frameworks (MOFs), a class of porous nanomaterials, have been widely used in gas adsorption-based applications due to their high porosities and chemical tunability. To facilitate the discovery of high-performance MOFs for different applications, a variety of machine learning models have been developed to predict the gas adsorption capacities of MOFs. Most of the predictive models are developed using traditional machine learning algorithms. However, the continuously increasing sizes of MOF datasets and the complicated relationships between MOFs and their gas adsorption capacities make deep learning a suitable candidate to handle such big data with increased computational power and accuracy. In this study, we developed models for predicting gas adsorption capacities of MOFs using two deep learning algorithms, multilayer perceptron (MLP) and long short-term memory (LSTM) networks, with a hypothetical set of about 130,000 structures of MOFs with methane and carbon dioxide adsorption data at different pressures. The models were evaluated using 10 iterations of 10-fold cross validations and 100 holdout validations. The MLP and LSTM models performed similarly with high prediction accuracy. The models for predicting gas adsorption at a higher pressure outperformed the models for predicting gas adsorption at a lower pressure. The deep learning models are more accurate than the random forest models reported in the literature, especially for predicting gas adsorption capacities at low pressures. Our results demonstrated that deep learning algorithms have a great potential to generate models that can accurately predict the gas adsorption capacities of MOFs.

Assessing reproducibility of inherited variants detected with short-read whole genome sequencing.

BACKGROUND: Reproducible detection of inherited variants with whole genome sequencing (WGS) is vital for the implementation of precision medicine and is a complicated process in which each step affects variant call quality. Systematically assessing reproducibility of inherited variants with WGS and impact of each step in the process is needed for understanding and improving quality of inherited variants from WGS. RESULTS: To dissect the impact of factors involved in detection of inherited variants with WGS, we sequence triplicates of eight DNA samples representing two populations on three short-read sequencing platforms using three library kits in six labs and call variants with 56 combinations of aligners and callers. We find that bioinformatics pipelines (callers and aligners) have a larger impact on variant reproducibility than WGS platform or library preparation. Single-nucleotide variants (SNVs), particularly outside difficult-to-map regions, are more reproducible than small insertions and deletions (indels), which are least reproducible when > 5 bp. Increasing sequencing coverage improves indel reproducibility but has limited impact on SNVs above 30×. CONCLUSIONS: Our findings highlight sources of variability in variant detection and the need for improvement of bioinformatics pipelines in the era of precision medicine with WGS.

Elucidation of Agonist and Antagonist Dynamic Binding Patterns in ER-α by Integration of Molecular Docking, Molecular Dynamics Simulations and Quantum Mechanical Calculations.

Estrogen receptor alpha (ERα) is a ligand-dependent transcriptional factor in the nuclear receptor superfamily. Many structures of ERα bound with agonists and antagonists have been determined. However, the dynamic binding patterns of agonists and antagonists in the binding site of ERα remains unclear. Therefore, we performed molecular docking, molecular dynamics (MD) simulations, and quantum mechanical calculations to elucidate agonist and antagonist dynamic binding patterns in ERα. 17ß-estradiol (E2) and 4-hydroxytamoxifen (OHT) were docked in the ligand binding pockets of the agonist and antagonist bound ERα. The best complex conformations from molecular docking were subjected to 100 nanosecond MD simulations. Hierarchical clustering was conducted to group the structures in the trajectory from MD simulations. The representative structure from each cluster was selected to calculate the binding interaction energy value for elucidation of the dynamic binding patterns of agonists and antagonists in the binding site of ERα. The binding interaction energy analysis revealed that OHT binds ERα more tightly in the antagonist conformer, while E2 prefers the agonist conformer. The results may help identify ERα antagonists as drug candidates and facilitate risk assessment of chemicals through ER-mediated responses.

Software-Assisted Pattern Recognition of Persistent Organic Pollutants in Contaminated Human and Animal Food.

Persistent Organic Pollutants (POPs) are a serious food safety concern due to their persistence and toxic effects. To promote food safety and protect human health, it is important to understand the sources of POPs and how to minimize human exposure to these contaminants. The POPs Program within the U.S. Food and Drug Administration (FDA), manually evaluates congener patterns of POPs-contaminated samples and sometimes compares the finding to other previously analyzed samples with similar patterns. This manual comparison is time consuming and solely depends on human expertise. To improve the efficiency of this evaluation, we developed software to assist in identifying potential sources of POPs contamination by detecting similarities between the congener patterns of a contaminated sample and potential environmental source samples. Similarity scores were computed and used to rank potential source samples. The software has been tested on a diverse set of incurred samples by comparing results from the software with those from human experts. We demonstrated that the software provides results consistent with human expert observation. This software also provided the advantage of reliably evaluating an increased sample lot which increased overall efficiency.

Persistent Organic Pollutants in Food: Contamination Sources, Health Effects and Detection Methods.

Persistent organic pollutants (POPs) present in foods have been a major concern for food safety due to their persistence and toxic effects. To ensure food safety and protect human health from POPs, it is critical to achieve a better understanding of POP pathways into food and develop strategies to reduce human exposure. POPs could present in food in the raw stages, transferred from the environment or artificially introduced during food preparation steps. Exposure to these pollutants may cause various health problems such as endocrine disruption, cardiovascular diseases, cancers, diabetes, birth defects, and dysfunctional immune and reproductive systems. This review describes potential sources of POP food contamination, analytical approaches to measure POP levels in food and efforts to control food contamination with POPs.

Correction to: Similarities and differences between variants called with human reference genome HG19 or HG38.

After publication of this supplement article.

Study of serious adverse drug reactions using FDA-approved drug labeling and MedDRA.

BACKGROUND: Adverse Drug Reactions (ADRs) are of great public health concern. FDA-approved drug labeling summarizes ADRs of a drug product mainly in three sections, i.e., Boxed Warning (BW), Warnings and Precautions (WP), and Adverse Reactions (AR), where the severity of ADRs are intended to decrease in the order of BW > WP > AR. Several reported studies have extracted ADRs from labeling documents, but most, if not all, did not discriminate the severity of the ADRs by the different labeling sections. Such a practice could overstate or underestimate the impact of certain ADRs to the public health. In this study, we applied the Medical Dictionary for Regulatory Activities (MedDRA) to drug labeling and systematically analyzed and compared the ADRs from the three labeling sections with a specific emphasis on analyzing serious ADRs presented in BW, which is of most drug safety concern. RESULTS: This study investigated New Drug Application (NDA) labeling documents for 1164 single-ingredient drugs using Oracle Text search to extract MedDRA terms. We found that only a small portion of MedDRA Preferred Terms (PTs), 3819 out of 21,920 or 17.42%, were observed in a whole set of documents. In detail, 466/3819 (12.0%) PTs were in BW, 2023/3819 (53.0%) were in WP, and 2961/3819 (77.5%) were in AR sections. We also found a higher overlap of top 20 occurring BW PTs with WP sections compared to AR sections. Within the MedDRA System Organ Class levels, serious ADRs (sADRs) from BW were prevalent in Nervous System disorders and Vascular disorders. A Hierarchical Cluster Analysis (HCA) revealed that drugs within the same therapeutic category shared the same ADR patterns in BW (e.g., nervous system drug class is highly associated with drug abuse terms such as dependence, substance abuse, and respiratory depression). CONCLUSIONS: This study demonstrated that combining MedDRA standard terminologies with data mining techniques facilitated computer-aided ADR analysis of drug labeling. We also highlighted the importance of labeling sections that differ in seriousness and application in drug safety. Using sADRs primarily related to BW sections, we illustrated a prototype approach for computer-aided ADR monitoring and studies which can be applied to other public health documents.

Similarities and differences between variants called with human reference genome HG19 or HG38.

BACKGROUND: Reference genome selection is a prerequisite for successful analysis of next generation sequencing (NGS) data. Current practice employs one of the two most recent human reference genome versions: HG19 or HG38. To date, the impact of genome version on SNV identification has not been rigorously assessed. METHODS: We conducted analysis comparing the SNVs identified based on HG19 vs HG38, leveraging whole genome sequencing (WGS) data from the genome-in-a-bottle (GIAB) project. First, SNVs were called using 26 different bioinformatics pipelines with either HG19 or HG38. Next, two tools were used to convert the called SNVs between HG19 and HG38. Lastly we calculated conversion rates, analyzed discordant rates between SNVs called with HG19 or HG38, and characterized the discordant SNVs. RESULTS: The conversion rates from HG38 to HG19 (average 95%) were lower than the conversion rates from HG19 to HG38 (average 99%). The conversion rates varied slightly among the various calling pipelines. Around 1.5% SNVs were discordantly converted between HG19 or HG38. The conversions from HG38 to HG19 had more SNVs which failed conversion and more discordant SNVs than the opposite conversion (HG19 to HG38). Most of the discordant SNVs had low read depth, were low confidence SNVs as defined by GIAB, and/or were predominated by G/C alleles (52% observed versus 42% expected). CONCLUSION: A significant number of SNVs could not be converted between HG19 and HG38. Based on careful review of our comparisons, we recommend HG38 (the newer version) for NGS SNV analysis. To summarize, our findings suggest caution when translating identified SNVs between different versions of the human reference genome.

Structural Changes Due to Antagonist Binding in Ligand Binding Pocket of Androgen Receptor Elucidated Through Molecular Dynamics Simulations.

When a small molecule binds to the androgen receptor (AR), a conformational change can occur which impacts subsequent binding of co-regulator proteins and DNA. In order to accurately study this mechanism, the scientific community needs a crystal structure of the Wild type AR (WT-AR) ligand binding domain, bound with antagonist. To address this open need, we leveraged molecular docking and molecular dynamics (MD) simulations to construct a structure of the WT-AR ligand binding domain bound with antagonist bicalutamide. The structure of mutant AR (Mut-AR) bound with this same antagonist informed this study. After molecular docking analysis pinpointed the suitable binding orientation of a ligand in AR, the model was further optimized through 1 µs of MD simulations. Using this approach, three molecular systems were studied: (1) WT-AR bound with agonist R1881, (2) WT-AR bound with antagonist bicalutamide, and (3) Mut-AR bound with bicalutamide. Our structures were very similar to the experimentally determined structures of both WT-AR with R1881 and Mut-AR with bicalutamide, demonstrating the trustworthiness of this approach. In our model, when WT-AR is bound with bicalutamide, Val716/Lys720/Gln733, or Met734/Gln738/Glu897 move and thus disturb the positive and negative charge clumps of the AF2 site. This disruption of the AF2 site is key for understanding the impact of antagonist binding on subsequent co-regulator binding. In conclusion, the antagonist induced structural changes in WT-AR detailed in this study will enable further AR research and will facilitate AR targeting drug discovery.

Consensus Modeling for Prediction of Estrogenic Activity of Ingredients Commonly Used in Sunscreen Products.

Sunscreen products are predominantly regulated as over-the-counter (OTC) drugs by the US FDA. The "active" ingredients function as ultraviolet filters. Once a sunscreen product is generally recognized as safe and effective (GRASE) via an OTC drug review process, new formulations using these ingredients do not require FDA review and approval, however, the majority of ingredients have never been tested to uncover any potential endocrine activity and their ability to interact with the estrogen receptor (ER) is unknown, despite the fact that this is a very extensively studied target related to endocrine activity. Consequently, we have developed an in silico model to prioritize single ingredient estrogen receptor activity for use when actual animal data are inadequate, equivocal, or absent. It relies on consensus modeling to qualitatively and quantitatively predict ER binding activity. As proof of concept, the model was applied to ingredients commonly used in sunscreen products worldwide and a few reference chemicals. Of the 32 chemicals with unknown ER binding activity that were evaluated, seven were predicted to be active estrogenic compounds. Five of the seven were confirmed by the published data. Further experimental data is needed to confirm the other two predictions.

Inhibition of bile salt transport by drugs associated with liver injury in primary hepatocytes from human, monkey, dog, rat, and mouse.

Interference of bile salt transport is one of the underlying mechanisms for drug-induced liver injury (DILI). We developed a novel bile salt transport activity assay involving in situ biosynthesis of bile salts from their precursors in primary human, monkey, dog, rat, and mouse hepatocytes in suspension as well as LC-MS/MS determination of extracellular bile salts transported out of hepatocytes. Glycine- and taurine-conjugated bile acids were rapidly formed in hepatocytes and effectively transported into the extracellular medium. The bile salt formation and transport activities were time‒ and bile-acid-concentration‒dependent in primary human hepatocytes. The transport activity was inhibited by the bile salt export pump (BSEP) inhibitors ketoconazole, saquinavir, cyclosporine, and troglitazone. The assay was used to test 86 drugs for their potential to inhibit bile salt transport activity in human hepatocytes, which included 35 drugs associated with severe DILI (sDILI) and 51 with non-severe DILI (non-sDILI). Approximately 60% of the sDILI drugs showed potent inhibition (with IC50 values <50 µM), but only about 20% of the non-sDILI drugs showed this strength of inhibition in primary human hepatocytes and these drugs are associated only with cholestatic and mixed hepatocellular cholestatic (mixed) injuries. The sDILI drugs, which did not show substantial inhibition of bile salt transport activity, are likely to be associated with immune-mediated liver injury. Twenty-four drugs were also tested in monkey, dog, rat and mouse hepatocytes. Species differences in potency were observed with mouse being less sensitive than other species to inhibition of bile salt transport. In summary, a novel assay has been developed using hepatocytes in suspension from human and animal species that can be used to assess the potential for drugs and/or drug-derived metabolites to inhibit bile salt transport and/or formation activity. Drugs causing sDILI, except those by immune-mediated mechanism, are highly associated with potent inhibition of bile salt transport.

A Rat α-Fetoprotein Binding Activity Prediction Model to Facilitate Assessment of the Endocrine Disruption Potential of Environmental Chemicals.

Endocrine disruptors such as polychlorinated biphenyls (PCBs), diethylstilbestrol (DES) and dichlorodiphenyltrichloroethane (DDT) are agents that interfere with the endocrine system and cause adverse health effects. Huge public health concern about endocrine disruptors has arisen. One of the mechanisms of endocrine disruption is through binding of endocrine disruptors with the hormone receptors in the target cells. Entrance of endocrine disruptors into target cells is the precondition of endocrine disruption. The binding capability of a chemical with proteins in the blood affects its entrance into the target cells and, thus, is very informative for the assessment of potential endocrine disruption of chemicals. α-fetoprotein is one of the major serum proteins that binds to a variety of chemicals such as estrogens. To better facilitate assessment of endocrine disruption of environmental chemicals, we developed a model for α-fetoprotein binding activity prediction using the novel pattern recognition method (Decision Forest) and the molecular descriptors calculated from two-dimensional structures by Mold² software. The predictive capability of the model has been evaluated through internal validation using 125 training chemicals (average balanced accuracy of 69%) and external validations using 22 chemicals (balanced accuracy of 71%). Prediction confidence analysis revealed the model performed much better at high prediction confidence. Our results indicate that the model is useful (when predictions are in high confidence) in endocrine disruption risk assessment of environmental chemicals though improvement by increasing number of training chemicals is needed.

Pathway Analysis Revealed Potential Diverse Health Impacts of Flavonoids that Bind Estrogen Receptors.

Flavonoids are frequently used as dietary supplements in the absence of research evidence regarding health benefits or toxicity. Furthermore, ingested doses could far exceed those received from diet in the course of normal living. Some flavonoids exhibit binding to estrogen receptors (ERs) with consequential vigilance by regulatory authorities at the U.S. EPA and FDA. Regulatory authorities must consider both beneficial claims and potential adverse effects, warranting the increases in research that has spanned almost two decades. Here, we report pathway enrichment of 14 targets from the Comparative Toxicogenomics Database (CTD) and the Herbal Ingredients' Targets (HIT) database for 22 flavonoids that bind ERs. The selected flavonoids are confirmed ER binders from our earlier studies, and were here found in mainly involved in three types of biological processes, ER regulation, estrogen metabolism and synthesis, and apoptosis. Besides cancers, we conjecture that the flavonoids may affect several diseases via apoptosis pathways. Diseases such as amyotrophic lateral sclerosis, viral myocarditis and non-alcoholic fatty liver disease could be implicated. More generally, apoptosis processes may be importantly evolved biological functions of flavonoids that bind ERs and high dose ingestion of those flavonoids could adversely disrupt the cellular apoptosis process.

Applying network analysis and Nebula (neighbor-edges based and unbiased leverage algorithm) to ToxCast data.

BACKGROUND: ToxCast data have been used to develop models for predicting in vivo toxicity. To predict the in vivo toxicity of a new chemical using a ToxCast data based model, its ToxCast bioactivity data are needed but not normally available. The capability of predicting ToxCast bioactivity data is necessary to fully utilize ToxCast data in the risk assessment of chemicals. OBJECTIVES: We aimed to understand and elucidate the relationships between the chemicals and bioactivity data of the assays in ToxCast and to develop a network analysis based method for predicting ToxCast bioactivity data. METHODS: We conducted modularity analysis on a quantitative network constructed from ToxCast data to explore the relationships between the assays and chemicals. We further developed Nebula (neighbor-edges based and unbiased leverage algorithm) for predicting ToxCast bioactivity data. RESULTS: Modularity analysis on the network constructed from ToxCast data yielded seven modules. Assays and chemicals in the seven modules were distinct. Leave-one-out cross-validation yielded a Q(2) of 0.5416, indicating ToxCast bioactivity data can be predicted by Nebula. Prediction domain analysis showed some types of ToxCast assay data could be more reliably predicted by Nebula than others. CONCLUSIONS: Network analysis is a promising approach to understand ToxCast data. Nebula is an effective algorithm for predicting ToxCast bioactivity data, helping fully utilize ToxCast data in the risk assessment of chemicals.

Comparing genetic variants detected in the 1000 genomes project with SNPs determined by the International HapMap Consortium.

Single-nucleotide polymorphisms (SNPs) determined based on SNP arrays from the international HapMap consortium (HapMap) and the genetic variants detected in the 1000 genomes project (1KGP) can serve as two references for genomewide association studies (GWAS). We conducted comparative analyses to provide a means for assessing concerns regarding SNP array-based GWAS findings as well as for realistically bounding expectations for next generation sequencing (NGS)-based GWAS. We calculated and compared base composition, transitions to transversions ratio, minor allele frequency and heterozygous rate for SNPs from HapMap and 1KGP for the 622 common individuals. We analysed the genotype discordance between HapMap and 1KGP to assess consistency in the SNPs from the two references. In 1KGP, 90.58% of 36,817,799 SNPs detected were not measured in HapMap. More SNPs with minor allele frequencies less than 0.01 were found in 1KGP than HapMap. The two references have low disc ordance (generally smaller than 0.02) in genotypes of common SNPs, with most discordance from heterozygous SNPs. Our study demonstrated that SNP array-based GWAS findings were reliable and useful, although only a small portion of genetic variances were explained. NGS can detect not only common but also rare variants, supporting the expectation that NGS-based GWAS will be able to incorporate a much larger portion of genetic variance than SNP arrays-based GWAS.

Development and Validation of Decision Forest Model for Estrogen Receptor Binding Prediction of Chemicals Using Large Data Sets.

Some chemicals in the environment possess the potential to interact with the endocrine system in the human body. Multiple receptors are involved in the endocrine system; estrogen receptor α (ERα) plays very important roles in endocrine activity and is the most studied receptor. Understanding and predicting estrogenic activity of chemicals facilitates the evaluation of their endocrine activity. Hence, we have developed a decision forest classification model to predict chemical binding to ERα using a large training data set of 3308 chemicals obtained from the U.S. Food and Drug Administration's Estrogenic Activity Database. We tested the model using cross validations and external data sets of 1641 chemicals obtained from the U.S. Environmental Protection Agency's ToxCast project. The model showed good performance in both internal (92% accuracy) and external validations (∼ 70-89% relative balanced accuracies), where the latter involved the validations of the model across different ER pathway-related assays in ToxCast. The important features that contribute to the prediction ability of the model were identified through informative descriptor analysis and were related to current knowledge of ER binding. Prediction confidence analysis revealed that the model had both high prediction confidence and accuracy for most predicted chemicals. The results demonstrated that the model constructed based on the large training data set is more accurate and robust for predicting ER binding of chemicals than the published models that have been developed using much smaller data sets. The model could be useful for the evaluation of ERα-mediated endocrine activity potential of environmental chemicals.

A heuristic approach to determine an appropriate number of topics in topic modeling.

BACKGROUND: Topic modelling is an active research field in machine learning. While mainly used to build models from unstructured textual data, it offers an effective means of data mining where samples represent documents, and different biological endpoints or omics data represent words. Latent Dirichlet Allocation (LDA) is the most commonly used topic modelling method across a wide number of technical fields. However, model development can be arduous and tedious, and requires burdensome and systematic sensitivity studies in order to find the best set of model parameters. Often, time-consuming subjective evaluations are needed to compare models. Currently, research has yielded no easy way to choose the proper number of topics in a model beyond a major iterative approach. METHODS AND RESULTS: Based on analysis of variation of statistical perplexity during topic modelling, a heuristic approach is proposed in this study to estimate the most appropriate number of topics. Specifically, the rate of perplexity change (RPC) as a function of numbers of topics is proposed as a suitable selector. We test the stability and effectiveness of the proposed method for three markedly different types of grounded-truth datasets: Salmonella next generation sequencing, pharmacological side effects, and textual abstracts on computational biology and bioinformatics (TCBB) from PubMed. CONCLUSION: The proposed RPC-based method is demonstrated to choose the best number of topics in three numerical experiments of widely different data types, and for databases of very different sizes. The work required was markedly less arduous than if full systematic sensitivity studies had been carried out with number of topics as a parameter. We understand that additional investigation is needed to substantiate the method's theoretical basis, and to establish its generalizability in terms of dataset characteristics.