An Online Nanoinformatics Platform Empowering Computational Modeling of Nanomaterials by Nanostructure Annotations and Machine Learning Toolkits.

Modern nanotechnology has generated numerous datasets from in vitro and in vivo studies on nanomaterials, with some available on nanoinformatics portals. However, these existing databases lack the digital data and tools suitable for machine learning studies. Here, we report a nanoinformatics platform that accurately annotates nanostructures into machine-readable data files and provides modeling toolkits. This platform, accessible to the public at https://vinas-toolbox.com/, has annotated nanostructures of 14 material types. The associated nanodescriptor data and assay test results are appropriate for modeling purposes. The modeling toolkits enable data standardization, data visualization, and machine learning model development to predict properties and bioactivities of new nanomaterials. Moreover, a library of virtual nanostructures with their predicted properties and bioactivities is available, directing the synthesis of new nanomaterials. This platform provides a data-driven computational modeling platform for the nanoscience community, significantly aiding in the development of safe and effective nanomaterials.

Integrating Concentration-Dependent Toxicity Data and Toxicokinetics To Inform Hepatotoxicity Response Pathways.

Failure of animal models to predict hepatotoxicity in humans has created a push to develop biological pathway-based alternatives, such as those that use in vitro assays. Public screening programs (e.g., ToxCast/Tox21 programs) have tested thousands of chemicals using in vitro high-throughput screening (HTS) assays. Developing pathway-based models for simple biological pathways, such as endocrine disruption, has proven successful, but development remains a challenge for complex toxicities like hepatotoxicity, due to the many biological events involved. To this goal, we aimed to develop a computational strategy for developing pathway-based models for complex toxicities. Using a database of 2171 chemicals with human hepatotoxicity classifications, we identified 157 out of 1600+ ToxCast/Tox21 HTS assays to be associated with human hepatotoxicity. Then, a computational framework was used to group these assays by biological target or mechanisms into 52 key event (KE) models of hepatotoxicity. KE model output is a KE score summarizing chemical potency against a hepatotoxicity-relevant biological target or mechanism. Grouping hepatotoxic chemicals based on the chemical structure revealed chemical classes with high KE scores plausibly informing their hepatotoxicity mechanisms. Using KE scores and supervised learning to predict in vivo hepatotoxicity, including toxicokinetic information, improved the predictive performance. This new approach can be a universal computational toxicology strategy for various chemical toxicity evaluations.

Data-Driven Quantitative Structure-Activity Relationship Modeling for Human Carcinogenicity by Chronic Oral Exposure.

Traditional methodologies for assessing chemical toxicity are expensive and time-consuming. Computational modeling approaches have emerged as low-cost alternatives, especially those used to develop quantitative structure-activity relationship (QSAR) models. However, conventional QSAR models have limited training data, leading to low predictivity for new compounds. We developed a data-driven modeling approach for constructing carcinogenicity-related models and used these models to identify potential new human carcinogens. To this goal, we used a probe carcinogen dataset from the US Environmental Protection Agency's Integrated Risk Information System (IRIS) to identify relevant PubChem bioassays. Responses of 25 PubChem assays were significantly relevant to carcinogenicity. Eight assays inferred carcinogenicity predictivity and were selected for QSAR model training. Using 5 machine learning algorithms and 3 types of chemical fingerprints, 15 QSAR models were developed for each PubChem assay dataset. These models showed acceptable predictivity during 5-fold cross-validation (average CCR = 0.71). Using our QSAR models, we can correctly predict and rank 342 IRIS compounds' carcinogenic potentials (PPV = 0.72). The models predicted potential new carcinogens, which were validated by a literature search. This study portends an automated technique that can be applied to prioritize potential toxicants using validated QSAR models based on extensive training sets from public data resources.

Integrating structure annotation and machine learning approaches to develop graphene toxicity models.

Modern nanotechnology provides efficient and cost-effective nanomaterials (NMs). The increasing usage of NMs arises great concerns regarding nanotoxicity in humans. Traditional animal testing of nanotoxicity is expensive and time-consuming. Modeling studies using machine learning (ML) approaches are promising alternatives to direct evaluation of nanotoxicity based on nanostructure features. However, NMs, including two-dimensional nanomaterials (2DNMs) such as graphenes, have complex structures making them difficult to annotate and quantify the nanostructures for modeling purposes. To address this issue, we constructed a virtual graphenes library using nanostructure annotation techniques. The irregular graphene structures were generated by modifying virtual nanosheets. The nanostructures were digitalized from the annotated graphenes. Based on the annotated nanostructures, geometrical nanodescriptors were computed using Delaunay tessellation approach for ML modeling. The partial least square regression (PLSR) models for the graphenes were built and validated using a leave-one-out cross-validation (LOOCV) procedure. The resulted models showed good predictivity in four toxicity-related endpoints with the coefficient of determination (R2) ranging from 0.558 to 0.822. This study provides a novel nanostructure annotation strategy that can be applied to generate high-quality nanodescriptors for ML model developments, which can be widely applied to nanoinformatics studies of graphenes and other NMs.

The impact of working from home on the success of Scrum projects: A multi-method study.

With the COVID-19 pandemic, Scrum teams had to switch abruptly from a traditional working setting into an enforced working from home one. This abrupt switch had an impact on software projects. Thus, it is necessary to understand how potential future disruptive events will impact Agile software teams' ability to deliver successful projects while working from home. To investigate this problem, we used a two-phased Multi-Method study. In the first phase, we uncover how working from home impacted Scrum practitioners through semi-structured interviews. Then, in the second phase, we propose a theoretical model that we test and generalize using Partial Least Squares-Structural Equation Modeling (PLS-SEM) surveying 138 software engineers who worked from home within Scrum projects. We concluded that all the latent variables identified in our model are reliable, and all the hypotheses are significant. This paper emphasizes the importance of supporting the three innate psychological needs of autonomy, competence, and relatedness in the home working environment. We conclude that the ability of working from home and the use of Scrum both contribute to project success, with Scrum acting as a mediator.

Satisfaction and performance of software developers during enforced work from home in the COVID-19 pandemic.

Following the onset of the COVID-19 pandemic and subsequent lockdowns, the daily lives of software engineers were heavily disrupted as they were abruptly forced to work remotely from home. To better understand and contrast typical working days in this new reality with work in pre-pandemic times, we conducted one exploratory (N = 192) and one confirmatory study (N = 290) with software engineers recruited remotely. Specifically, we build on self-determination theory to evaluate whether and how specific activities are associated with software engineers' satisfaction and productivity. To explore the subject domain, we first ran a two-wave longitudinal study. We found that the time software engineers spent on specific activities (e.g., coding, bugfixing, helping others) while working from home was similar to pre-pandemic times. Also, the amount of time developers spent on each activity was unrelated to their general well-being, perceived productivity, and other variables such as basic needs. Our confirmatory study found that activity-specific variables (e.g., how much autonomy software engineers had during coding) do predict activity satisfaction and productivity but not by activity-independent variables such as general resilience or a good work-life balance. Interestingly, we found that satisfaction and autonomy were significantly higher when software engineers were helping others and lower when they were bugfixing. Finally, we discuss implications for software engineers, management, and researchers. In particular, active company policies to support developers' need for autonomy, relatedness, and competence appear particularly effective in a WFH context.

Predicting Prenatal Developmental Toxicity Based On the Combination of Chemical Structures and Biological Data.

For hazard identification, classification, and labeling purposes, animal testing guidelines are required by law to evaluate the developmental toxicity potential of new and existing chemical products. However, guideline developmental toxicity studies are costly, time-consuming, and require many laboratory animals. Computational modeling has emerged as a promising, animal-sparing, and cost-effective method for evaluating the developmental toxicity potential of chemicals, such as endocrine disruptors, without the use of animals. We aimed to develop a predictive and explainable computational model for developmental toxicants. To this end, a comprehensive dataset of 1244 chemicals with developmental toxicity classifications was curated from public repositories and literature sources. Data from 2140 toxicological high-throughput screening assays were extracted from PubChem and the ToxCast program for this dataset and combined with information about 834 chemical fragments to group assays based on their chemical-mechanistic relationships. This effort revealed two assay clusters containing 83 and 76 assays, respectively, with high positive predictive rates for developmental toxicants identified with animal testing guidelines (PPV = 72.4 and 77.3% during cross-validation). These two assay clusters can be used as developmental toxicity models and were applied to predict new chemicals for external validation. This study provides a new strategy for constructing alternative chemical developmental toxicity evaluations that can be replicated for other toxicity modeling studies.

From anecdote to evidence: the relationship between personality and need for cognition of developers.

There is considerable anecdotal evidence suggesting that software engineers enjoy engaging in solving puzzles and other cognitive efforts. A tendency to engage in and enjoy effortful thinking is referred to as a person's 'need for cognition.' In this article we study the relationship between software engineers' personality traits and their need for cognition. Through a large-scale sample study of 483 respondents we collected data to capture the six 'bright' personality traits of the HEXACO model of personality, and three 'dark' personality traits. Data were analyzed using several methods including a multiple Bayesian linear regression analysis. The results indicate that ca. 33% of variation in developers' need for cognition can be explained by personality traits. The Bayesian analysis suggests four traits to be of particular interest in predicting need for cognition: openness to experience, conscientiousness, honesty-humility, and emotionality. Further, we also find that need for cognition of software engineers is, on average, higher than in the general population, based on a comparison with prior studies. Given the importance of human factors for software engineers' performance in general, and problem solving skills in particular, our findings suggest several implications for recruitment, working behavior, and teaming.

Predictive modeling of estrogen receptor agonism, antagonism, and binding activities using machine- and deep-learning approaches.

As defined by the World Health Organization, an endocrine disruptor is an exogenous substance or mixture that alters function(s) of the endocrine system and consequently causes adverse health effects in an intact organism, its progeny, or (sub)populations. Traditional experimental testing regimens to identify toxicants that induce endocrine disruption can be expensive and time-consuming. Computational modeling has emerged as a promising and cost-effective alternative method for screening and prioritizing potentially endocrine-active compounds. The efficient identification of suitable chemical descriptors and machine-learning algorithms, including deep learning, is a considerable challenge for computational toxicology studies. Here, we sought to apply classic machine-learning algorithms and deep-learning approaches to a panel of over 7500 compounds tested against 18 Toxicity Forecaster assays related to nuclear estrogen receptor (ERα and ERß) activity. Three binary fingerprints (Extended Connectivity FingerPrints, Functional Connectivity FingerPrints, and Molecular ACCess System) were used as chemical descriptors in this study. Each descriptor was combined with four machine-learning and two deep- learning (normal and multitask neural networks) approaches to construct models for all 18 ER assays. The resulting model performance was evaluated using the area under the receiver- operating curve (AUC) values obtained from a fivefold cross-validation procedure. The results showed that individual models have AUC values that range from 0.56 to 0.86. External validation was conducted using two additional sets of compounds (n = 592 and n = 966) with established interactions with nuclear ER demonstrated through experimentation. An agonist, antagonist, or binding score was determined for each compound by averaging its predicted probabilities in relevant assay models as an external validation, yielding AUC values ranging from 0.63 to 0.91. The results suggest that multitask neural networks offer advantages when modeling mechanistically related endpoints. Consensus predictions based on the average values of individual models remain the best modeling strategy for computational toxicity evaluations.

Leveraging the Value of CDISC SEND Data Sets for Cross-Study Analysis: Incidence of Microscopic Findings in Control Animals.

Implementation of the Clinical Data Interchange Standards Consortium (CDISC)'s Standard for Exchange of Nonclinical Data (SEND) by the United States Food and Drug Administration Center for Drug Evaluation and Research (US FDA CDER) has created large quantities of SEND data sets and a tremendous opportunity to apply large-scale data analytic approaches. To fully realize this opportunity, differences in SEND implementation that impair the ability to conduct cross-study analysis must be addressed. In this manuscript, a prototypical question regarding historical control data (see Table of Contents graphic) was used to identify areas for SEND harmonization and to develop algorithmic strategies for nonclinical cross-study analysis within a variety of databases. FDA CDER's repository of >1800 sponsor-submitted studies in SEND format was queried using the statistical programming language R to gain insight into how the CDISC SEND Implementation Guides are being applied across the industry. For each component needed to answer the question (defined as "query block"), the frequency of data population was determined and ranged from 6 to 99%. For fields populated <90% and/or that did not have Controlled Terminology, data extraction methods such as data transformation and script development were evaluated. Data extraction was successful for fields such as phase of study, negative controls, and histopathology using scripts. Calculations to assess accuracy of data extraction indicated a high confidence in most query block searches. Some fields such as vehicle name, animal supplier name, and test facility name are not amenable to accurate data extraction through script development alone and require additional harmonization to confidently extract data. Harmonization proposals are discussed in this manuscript. Implementation of these proposals will allow stakeholders to capitalize on the opportunity presented by SEND data sets to increase the efficiency and productivity of nonclinical drug development, allowing the most promising drug candidates to proceed through development.

Polypharmacy as maintenance treatment in bipolar illness: A systematic review.

OBJECTIVES: Polypharmacy is common in maintenance treatment of bipolar illness, but proof of greater efficacy compared to monotherapy is assumed rather than well known. We systematically reviewed the evidence from the literature to provide recommendations for clinical management and future research. METHOD: A systematic review was conducted on the use of polypharmacy in bipolar prophylaxis. Relevant papers published in English through 31 December 2019 were identified searching the electronic databases MEDLINE, Embase, PsycINFO, and the Cochrane Library. RESULTS: Twelve studies matched inclusion criteria, including 10 randomized controlled trials (RCTs). The best drug combination in prevention is represented by lithium + valproic acid which showed a significant effect on time to mood relapses (HR = 0.57) compared to valproic acid monotherapy, especially for manic episodes (HR = 0.51). The effect was significant in terms of time to new drug treatment (HR = 0.51) and time to hospitalization (HR = 0.57). A significant reduction in the frequency of mood relapses was also reported for lithium + valproic acid vs. lithium monotherapy (RR=0.12); however, the trial had a small sample size. Lamotrigine + valproic acid reported significant efficacy in prevention of depressive episodes compared to lamotrigine alone. CONCLUSIONS: The literature to support a generally greater efficacy with polypharmacy in bipolar illness is scant and heterogeneous. Within that limited evidence base, the best drug combination in bipolar prevention is represented by lithium + valproic acid for manic, but not depressive episodes. Clinical practice should focus more on adequate monotherapy before considering polypharmacy.

Revealing Adverse Outcome Pathways from Public High-Throughput Screening Data to Evaluate New Toxicants by a Knowledge-Based Deep Neural Network Approach.

Traditional experimental testing to identify endocrine disruptors that enhance estrogenic signaling relies on expensive and labor-intensive experiments. We sought to design a knowledge-based deep neural network (k-DNN) approach to reveal and organize public high-throughput screening data for compounds with nuclear estrogen receptor α and ß (ERα and ERß) binding potentials. The target activity was rodent uterotrophic bioactivity driven by ERα/ERß activations. After training, the resultant network successfully inferred critical relationships among ERα/ERß target bioassays, shown as weights of 6521 edges between 1071 neurons. The resultant network uses an adverse outcome pathway (AOP) framework to mimic the signaling pathway initiated by ERα and identify compounds that mimic endogenous estrogens (i.e., estrogen mimetics). The k-DNN can predict estrogen mimetics by activating neurons representing several events in the ERα/ERß signaling pathway. Therefore, this virtual pathway model, starting from a compound's chemistry initiating ERα activation and ending with rodent uterotrophic bioactivity, can efficiently and accurately prioritize new estrogen mimetics (AUC = 0.864-0.927). This k-DNN method is a potential universal computational toxicology strategy to utilize public high-throughput screening data to characterize hazards and prioritize potentially toxic compounds.

Viral markers in nasopharyngeal carcinoma: A systematic review and meta-analysis on the detection of p16INK4a, human papillomavirus (HPV), and Ebstein-Barr virus (EBV).

PURPOSE: This study aimed to conduct a meta-analysis to investigate the distribution of EBV and HPV stratified according to histological NPC type. MATERIALS & METHODS: We performed a meta-analysis to produce pooled prevalence estimates in a random-effects model. We also performed calculations for attributable fractions of viral combinations in NPC, stratified according to histological type. RESULTS: There was a higher prevalence of HPV DNA in WHO Type I (34.4%) versus WHO Type II/III (18.4%). The attributable fractions of WHO Type I NPC was predominantly double negative EBV(-) HPV(-) NPC (56.4%), and EBV(-) HPV(+) NPC (21.5%), in contrast to the predominant infection in WHO Type II/III which was EBV(+) HPV(-) NPC (87.5%). Co-infection of both EBV and HPV was uncommon, and double-negative infection was more common in WHO Type I NPC. CONCLUSION: A significant proportion of WHO Type I NPC was either double-negative EBV(-)HPV(-) or EBV(-)HPV(+).

Predictors of well-being and productivity among software professionals during the COVID-19 pandemic - a longitudinal study.

The COVID-19 pandemic has forced governments worldwide to impose movement restrictions on their citizens. Although critical to reducing the virus' reproduction rate, these restrictions come with far-reaching social and economic consequences. In this paper, we investigate the impact of these restrictions on an individual level among software engineers who were working from home. Although software professionals are accustomed to working with digital tools, but not all of them remotely, in their day-to-day work, the abrupt and enforced work-from-home context has resulted in an unprecedented scenario for the software engineering community. In a two-wave longitudinal study (N = 192), we covered over 50 psychological, social, situational, and physiological factors that have previously been associated with well-being or productivity. Examples include anxiety, distractions, coping strategies, psychological and physical needs, office set-up, stress, and work motivation. This design allowed us to identify the variables that explained unique variance in well-being and productivity. Results include (1) the quality of social contacts predicted positively, and stress predicted an individual's well-being negatively when controlling for other variables consistently across both waves; (2) boredom and distractions predicted productivity negatively; (3) productivity was less strongly associated with all predictor variables at time two compared to time one, suggesting that software engineers adapted to the lockdown situation over time; and (4) longitudinal analyses did not provide evidence that any predictor variable causal explained variance in well-being and productivity. Overall, we conclude that working from home was per se not a significant challenge for software engineers. Finally, our study can assess the effectiveness of current work-from-home and general well-being and productivity support guidelines and provides tailored insights for software professionals.

Virtual Molecular Projections and Convolutional Neural Networks for the End-to-End Modeling of Nanoparticle Activities and Properties.

Digitalizing complex nanostructures into data structures suitable for machine learning modeling without losing nanostructure information has been a major challenge. Deep learning frameworks, particularly convolutional neural networks (CNNs), are especially adept at handling multidimensional and complex inputs. In this study, CNNs were applied for the modeling of nanoparticle activities exclusively from nanostructures. The nanostructures were represented by virtual molecular projections, a multidimensional digitalization of nanostructures, and used as input data to train CNNs. To this end, 77 nanoparticles with various activities and/or physicochemical property results were used for modeling. The resulting CNN model predictions show high correlations with the experimental results. An analysis of a trained CNN quantitatively showed that neurons were able to recognize distinct nanostructure features critical to activities and physicochemical properties. This "end-to-end" deep learning approach is well suited to digitalize complex nanostructures for data-driven machine learning modeling and can be broadly applied to rationally design nanoparticles with desired activities.

Exploiting machine learning for end-to-end drug discovery and development.

A variety of machine learning methods such as naive Bayesian, support vector machines and more recently deep neural networks are demonstrating their utility for drug discovery and development. These leverage the generally bigger datasets created from high-throughput screening data and allow prediction of bioactivities for targets and molecular properties with increased levels of accuracy. We have only just begun to exploit the potential of these techniques but they may already be fundamentally changing the research process for identifying new molecules and/or repurposing old drugs. The integrated application of such machine learning models for end-to-end (E2E) application is broadly relevant and has considerable implications for developing future therapies and their targeting.

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction.

The U.S. Environmental Protection Agency (EPA) periodically releases in vitro data across a variety of targets, including the estrogen receptor (ER). In 2015, the EPA used these data to construct mathematical models of ER agonist and antagonist pathways to prioritize chemicals for endocrine disruption testing. However, mathematical models require in vitro data prior to predicting estrogenic activity, but machine learning methods are capable of prospective prediction from the molecular structure alone. The current study describes the generation and evaluation of Bayesian machine learning models grouped by the EPA's ER agonist pathway model using multiple data types with proprietary software, Assay Central. External predictions with three test sets of in vitro and in vivo reference chemicals with agonist activity classifications were compared to previous mathematical model publications. Training data sets were subjected to additional machine learning algorithms and compared with rank normalized scores of internal five-fold cross-validation statistics. External predictions were found to be comparable or superior to previous studies published by the EPA. When assessing six additional algorithms for the training data sets, Assay Central performed similarly at a reduced computational cost. This study demonstrates that machine learning can prioritize chemicals for future in vitro and in vivo testing of ER agonism.

The effect of race in head and neck cancer: A meta-analysis controlling for socioeconomic status.

PURPOSE: To investigate the association between race and ethnicity and prognosis in head and neck cancers (HNC), while controlling for socioeconomic status (SES). MATERIALS AND METHODS: Medline, Scopus, EMBASE, and the Cochrane Library were used to identify studies for inclusion, from database inception till March 5th 2019. Studies that analyzed the role of race and ethnicity in overall survival (OS) for malignancies of the head and neck were included in this study. For inclusion, the study needed to report a multivariate analysis controlling for some proxy of SES (for example household income or employment status). Pooled estimates were generated using a random effects model. Subgroup analysis by tumor sub-site, meta-regression, and sensitivity analyses were also performed. RevMan 5.3, Meta Essentials, and OpenMeta[Analyst] were used for statistical analysis. RESULTS: Ten studies from 2004 to 2019 with a total of 108,990 patients were included for analysis in this study. After controlling for SES, tumor stage, and treatment variables, blacks were found to have a poorer survival compared to whites (HR = 1.27, 95%CI: 1.18-1.36, p < 0.00001). Subgroup analysis by sub-site and sensitivity analysis agreed with the primary result. No differences in survival across sub-sites were observed. Meta-regression did not identify any factors associated with the pooled estimate. CONCLUSIONS: In HNC, blacks have poorer OS compared to whites even after controlling for socioeconomic factors.

Opposing patterns of neuronal variability in the sensorimotor network mediate cyclothymic and depressive temperaments.

Affective temperaments have been described since the early 20th century and may play a central role in psychiatric illnesses, such as bipolar disorder (BD). However, the neuronal basis of temperament is still unclear. We investigated the relationship of temperament with neuronal variability in the resting state signal-measured by fractional standard deviation (fSD) of Blood-Oxygen-Level Dependent signal-of the different large-scale networks, that is, sensorimotor network (SMN), along with default-mode, salience and central executive networks, in standard frequency band (SFB) and its sub-frequencies slow4 and slow5, in a large sample of healthy subject (HC, n = 109), as well as in the various temperamental subgroups (i.e., cyclothymic, hyperthymic, depressive, and irritable). A replication study on an independent dataset of 121 HC was then performed. SMN fSD positively correlated with cyclothymic z-score and was significantly increased in the cyclothymic temperament compared to the depressive temperament subgroups, in both SFB and slow4. We replicated our findings in the independent dataset. A relationship between cyclothymic temperament and neuronal variability, an index of intrinsic neuronal activity, in the SMN was found. Cyclothymic and depressive temperaments were associated with opposite changes in the SMN variability, resembling changes previously described in manic and depressive phases of BD. These findings shed a novel light on the neural basis of affective temperament and also carry important implications for the understanding of a potential dimensional continuum between affective temperaments and BD, on both psychological and neuronal levels.

Multiple Machine Learning Comparisons of HIV Cell-based and Reverse Transcriptase Data Sets.

The human immunodeficiency virus (HIV) causes over a million deaths every year and has a huge economic impact in many countries. The first class of drugs approved were nucleoside reverse transcriptase inhibitors. A newer generation of reverse transcriptase inhibitors have become susceptible to drug resistant strains of HIV, and hence, alternatives are urgently needed. We have recently pioneered the use of Bayesian machine learning to generate models with public data to identify new compounds for testing against different disease targets. The current study has used the NIAID ChemDB HIV, Opportunistic Infection and Tuberculosis Therapeutics Database for machine learning studies. We curated and cleaned data from HIV-1 wild-type cell-based and reverse transcriptase (RT) DNA polymerase inhibition assays. Compounds from this database with ≤1 µM HIV-1 RT DNA polymerase activity inhibition and cell-based HIV-1 inhibition are correlated (Pearson r = 0.44, n = 1137, p < 0.0001). Models were trained using multiple machine learning approaches (Bernoulli Naive Bayes, AdaBoost Decision Tree, Random Forest, support vector classification, k-Nearest Neighbors, and deep neural networks as well as consensus approaches) and then their predictive abilities were compared. Our comparison of different machine learning methods demonstrated that support vector classification, deep learning, and a consensus were generally comparable and not significantly different from each other using 5-fold cross validation and using 24 training and test set combinations. This study demonstrates findings in line with our previous studies for various targets that training and testing with multiple data sets does not demonstrate a significant difference between support vector machine and deep neural networks.