Early childhood lower respiratory tract infection and premature adult death from respiratory disease in Great Britain: a national birth cohort study.

BACKGROUND: Lower respiratory tract infections (LRTIs) in early childhood are known to influence lung development and lifelong lung health, but their link to premature adult death from respiratory disease is unclear. We aimed to estimate the association between early childhood LRTI and the risk and burden of premature adult mortality from respiratory disease. METHODS: This longitudinal observational cohort study used data collected prospectively by the Medical Research Council National Survey of Health and Development in a nationally representative cohort recruited at birth in March, 1946, in England, Scotland, and Wales. We evaluated the association between LRTI during early childhood (age <2 years) and death from respiratory disease from age 26 through 73 years. Early childhood LRTI occurrence was reported by parents or guardians. Cause and date of death were obtained from the National Health Service Central Register. Hazard ratios (HRs) and population attributable risk associated with early childhood LRTI were estimated using competing risks Cox proportional hazards models, adjusted for childhood socioeconomic position, childhood home overcrowding, birthweight, sex, and smoking at age 20-25 years. We compared mortality within the cohort studied with national mortality patterns and estimated corresponding excess deaths occurring nationally during the study period. FINDINGS: 5362 participants were enrolled in March, 1946, and 4032 (75%) continued participating in the study at age 20-25 years. 443 participants with incomplete data on early childhood (368 [9%] of 4032), smoking (57 [1%]), or mortality (18 [<1%]) were excluded. 3589 participants aged 26 years (1840 [51%] male and 1749 [49%] female) were included in the survival analyses from 1972 onwards. The maximum follow-up time was 47·9 years. Among 3589 participants, 913 (25%) who had an LRTI during early childhood were at greater risk of dying from respiratory disease by age 73 years than those with no LRTI during early childhood (HR 1·93, 95% CI 1·10-3·37; p=0·021), after adjustment for childhood socioeconomic position, childhood home overcrowding, birthweight, sex, and adult smoking. This finding corresponded to a population attributable risk of 20·4% (95% CI 3·8-29·8) and 179 188 (95% CI 33 806-261 519) excess deaths across England and Wales between 1972 and 2019. INTERPRETATION: In this prospective, life-spanning, nationally representative cohort study, LRTI during early childhood was associated with almost a two times increased risk of premature adult death from respiratory disease, and accounted for one-fifth of these deaths. FUNDING: National Institute for Health and Care Research Imperial Biomedical Research Centre, Royal Brompton and Harefield National Health Service (NHS) Foundation Trust, Royal Brompton and Harefield Hospitals Charity and Imperial College Healthcare NHS Trust, UK Medical Research Council.

MetSim: Integrated Programmatic Access and Pathway Management for Xenobiotic Metabolism Simulators.

Xenobiotic metabolism is a key consideration in evaluating the hazards and risks posed by environmental chemicals. A number of software tools exist that are capable of simulating metabolites, but each reports its predictions in a different format and with varying levels of detail. This makes comparing the performance and coverage of the tools a practical challenge. To address this shortcoming, we developed a metabolic simulation framework called MetSim, which comprises three main components. A graph-based schema was developed to allow metabolism information to be harmonized. The schema was implemented in MongoDB to store and retrieve metabolic graphs for subsequent analysis. MetSim currently includes an application programming interface for four metabolic simulators: BioTransformer, the OECD Toolbox, EPA's chemical transformation simulator (CTS), and tissue metabolism simulator (TIMES). Lastly, MetSim provides functions to help evaluate simulator performance for specific data sets. In this study, a set of 112 drugs with 432 reported metabolites were compiled, and predictions were made using the 4 simulators. Fifty-nine of the 112 drugs were taken from the Small Molecule Pathway Database, with the remainder sourced from the literature. The human models within BioTransformer and CTS (Phase I only) and the rat models within TIMES and the OECD Toolbox (Phase I only) were used to make predictions for the chemicals in the data set. The recall and precision (recall, precision) ranked in order of highest recall for each individual tool were CTS (0.54, 0.017), BioTransformer (0.50, 0.008), Toolbox in vitro (0.40, 0.144), TIMES in vivo (0.40, 0.133), Toolbox in vivo (0.40, 0.118), and TIMES in vitro (0.39, 0.128). Combining all of the model predictions together increased the overall recall (0.73, 0.008). MetSim enabled insights into the performance and coverage of in silico metabolic simulators to be more efficiently derived, which in turn should aid future efforts to evaluate other data sets.

Systematic Approaches for the Encoding of Chemical Groups: A Case Study.

Regulatory authorities aim to organize substances into groups to facilitate prioritization within hazard and risk assessment processes. Often, such chemical groupings are not explicitly defined by structural rules or physicochemical property information. This is largely due to how these groupings are developed, namely, a manual expert curation process, which in turn makes updating and refining groupings, as new substances are evaluated, a practical challenge. Herein, machine learning methods were leveraged to build models that could preliminarily assign substances to predefined groups. A set of 86 groupings containing 2,184 substances as published on the European Chemicals Agency (ECHA) website were mapped to the U.S. Environmental Protection Agency (EPA) Distributed Toxicity Structure Database (DSSTox) content to extract chemical and structural information. Substances were represented using Morgan fingerprints, and two machine learning approaches were used to classify test substances into 56 groups containing at least 10 substances with a structural representation in the data set: k-nearest neighbor (kNN) and random forest (RF), that led to mean 5-fold cross-validation test accuracies (average F1 scores) of 0.781 and 0.853, respectively. With a 9% improvement, the RF classifier was significantly more accurate than KNN (p-value = 0.001). The approach offers promise as a means of the initial profiling of new substances into predefined groups to facilitate prioritization efforts and streamline the assessment of new substances when earlier groupings are available. The algorithm to fit and use these models has been made available in the accompanying repository, thereby enabling both use of the produced models and refitting of these models, as new groupings become available by regulatory authorities or industry.

Searching for LINCS to Stress: Using Text Mining to Automate Reference Chemical Curation.

Adaptive stress response pathways (SRPs) restore cellular homeostasis following perturbation but may activate terminal outcomes like apoptosis, autophagy, or cellular senescence if disruption exceeds critical thresholds. Because SRPs hold the key to vital cellular tipping points, they are targeted for therapeutic interventions and assessed as biomarkers of toxicity. Hence, we are developing a public database of chemicals that perturb SRPs to enable new data-driven tools to improve public health. Here, we report on the automated text-mining pipeline we used to build and curate the first version of this database. We started with 100 reference SRP chemicals gathered from published biomarker studies to bootstrap the database. Second, we used information retrieval to find co-occurrences of reference chemicals with SRP terms in PubMed abstracts and determined pairwise mutual information thresholds to filter biologically relevant relationships. Third, we applied these thresholds to find 1206 putative SRP perturbagens within thousands of substances in the Library of Integrated Network-Based Cellular Signatures (LINCS). To assign SRP activity to LINCS chemicals, domain experts had to manually review at least three publications for each of 1206 chemicals out of 181,805 total abstracts. To accomplish this efficiently, we implemented a machine learning approach to predict SRP classifications from texts to prioritize abstracts. In 5-fold cross-validation testing with a corpus derived from the 100 reference chemicals, artificial neural networks performed the best (F1-macro = 0.678) and prioritized 2479/181,805 abstracts for expert review, which resulted in 457 chemicals annotated with SRP activities. An independent analysis of enriched mechanisms of action and chemical use class supported the text-mined chemical associations (p < 0.05): heat shock inducers were linked with HSP90 and DNA damage inducers to topoisomerase inhibition. This database will enable novel applications of LINCS data to evaluate SRP activities and to further develop tools for biomedical information extraction from the literature.

A comparison of continuous cold flow and compression device and traditional icing regimen and no icing following anterior cruciate ligament reconstruction: A pilot study.

The aim of this study was to investigate the effectiveness of continuous cold flow and compression device as against traditional icing regimen and without icing after anterior cruciate ligament (ACL) reconstruction. All patients undergoing ACL reconstruction from June 2021 to August 2021 were enrolled in this study. Patients were randomly allocated to three groups: A control group (n=10) with no ice regimen post-operatively, a second control group (n=10) with ice bag, and a third group (n=10) with continuous cold flow and compression device (physiolab). All patients who had isolated ACL tear evident on magnetic resonance imaging were included. Pain intensity, limb girth, Oxford Knee Score, and 12-item survey form were measured pre- and post-operatively. Significant difference was noted between pain scores in all groups at two- and six-week follow-ups with p-value of 0.004 and 0.01. The test for "between subject effects" showed significant difference (p=0.007) in limb girth between the two groups. Cold and compression device can be used to reduce swelling immediately after ACL reconstruction.

Application of Cell Painting for chemical hazard evaluation in support of screening-level chemical assessments.

'Cell Painting' is an imaging-based high-throughput phenotypic profiling (HTPP) method in which cultured cells are fluorescently labeled to visualize subcellular structures (i.e., nucleus, nucleoli, endoplasmic reticulum, cytoskeleton, Golgi apparatus / plasma membrane and mitochondria) and to quantify morphological changes in response to chemicals or other perturbagens. HTPP is a high-throughput and cost-effective bioactivity screening method that detects effects associated with many different molecular mechanisms in an untargeted manner, enabling rapid in vitro hazard assessment for thousands of chemicals. Here, 1201 chemicals from the ToxCast library were screened in concentration-response up to ∼100 µM in human U-2 OS cells using HTPP. A phenotype altering concentration (PAC) was estimated for chemicals active in the tested range. PACs tended to be higher than lower bound potency values estimated from a broad collection of targeted high-throughput assays, but lower than the threshold for cytotoxicity. In vitro to in vivo extrapolation (IVIVE) was used to estimate administered equivalent doses (AEDs) based on PACs for comparison to human exposure predictions. AEDs for 18/412 chemicals overlapped with predicted human exposures. Phenotypic profile information was also leveraged to identify putative mechanisms of action and group chemicals. Of 58 known nuclear receptor modulators, only glucocorticoids and retinoids produced characteristic profiles; and both receptor types are expressed in U-2 OS cells. Thirteen chemicals with profile similarity to glucocorticoids were tested in a secondary screen and one chemical, pyrene, was confirmed by an orthogonal gene expression assay as a novel putative GR modulating chemical. Most active chemicals demonstrated profiles not associated with a known mechanism-of-action. However, many structurally related chemicals produced similar profiles, with exceptions such as diniconazole, whose profile differed from other active conazoles. Overall, the present study demonstrates how HTPP can be applied in screening-level chemical assessments through a series of examples and brief case studies.

Generalized Read-Across prediction using genra-py.

MOTIVATION: Generalized Read-Across (GenRA) is a data-driven approach to estimate physico-chemical, biological or eco-toxicological properties of chemicals by inference from analogues. GenRA attempts to mimic a human expert's manual read-across reasoning for filling data gaps about new chemicals from known chemicals with an interpretable and automated approach based on nearest-neighbors. A key objective of GenRA is to systematically explore different choices of input data selection and neighborhood definition to objectively evaluate predictive performance of automated read-across estimates of chemical properties. RESULTS: We have implemented genra-py as a python package that can be freely used for chemical safety analysis and risk assessment applications. Automated read-across prediction in genra-py conforms to the scikit-learn machine learning library's estimator design pattern, making it easy to use and integrate in computational pipelines. We demonstrate the data-driven application of genra-py to address two key human health risk assessment problems namely: hazard identification and point of departure estimation. AVAILABILITY AND IMPLEMENTATION: The package is available from github.com/i-shah/genra-py.

Navigating Transcriptomic Connectivity Mapping Workflows to Link Chemicals with Bioactivities.

Screening new compounds for potential bioactivities against cellular targets is vital for drug discovery and chemical safety. Transcriptomics offers an efficient approach for assessing global gene expression changes, but interpreting chemical mechanisms from these data is often challenging. Connectivity mapping is a potential data-driven avenue for linking chemicals to mechanisms based on the observation that many biological processes are associated with unique gene expression signatures (gene signatures). However, mining the effects of a chemical on gene signatures for biological mechanisms is challenging because transcriptomic data contain thousands of noisy genes. New connectivity mapping approaches seeking to distinguish signal from noise continue to be developed, spurred by the promise of discovering chemical mechanisms, new drugs, and disease targets from burgeoning transcriptomic data. Here, we analyze these approaches in terms of diverse transcriptomic technologies, public databases, gene signatures, pattern-matching algorithms, and statistical evaluation criteria. To navigate the complexity of connectivity mapping, we propose a harmonized scheme to coherently organize and compare published workflows. We first standardize concepts underlying transcriptomic profiles and gene signatures based on various transcriptomic technologies such as microarrays, RNA-Seq, and L1000 and discuss the widely used data sources such as Gene Expression Omnibus, ArrayExpress, and MSigDB. Next, we generalize connectivity mapping as a pattern-matching task for finding similarity between a query (e.g., transcriptomic profile for new chemical) and a reference (e.g., gene signature of known target). Published pattern-matching approaches fall into two main categories: vector-based use metrics like correlation, Jaccard index, etc., and aggregation-based use parametric and nonparametric statistics (e.g., gene set enrichment analysis). The statistical methods for evaluating the performance of different approaches are described, along with comparisons reported in the literature on benchmark transcriptomic data sets. Lastly, we review connectivity mapping applications in toxicology and offer guidance on evaluating chemical-induced toxicity with concentration-response transcriptomic data. In addition to serving as a high-level guide and tutorial for understanding and implementing connectivity mapping workflows, we hope this review will stimulate new algorithms for evaluating chemical safety and drug discovery using transcriptomic data.

Latent Variables Capture Pathway-Level Points of Departure in High-Throughput Toxicogenomic Data.

Estimation of points of departure (PoDs) from high-throughput transcriptomic data (HTTr) represents a key step in the development of next-generation risk assessment (NGRA). Current approaches mainly rely on single key gene targets, which are constrained by the information currently available in the knowledge base and make interpretation challenging as scientists need to interpret PoDs for thousands of genes or hundreds of pathways. In this work, we aimed to address these issues by developing a computational workflow to investigate the pathway concentration-response relationships in a way that is not fully constrained by known biology and also facilitates interpretation. We employed the Pathway-Level Information ExtractoR (PLIER) to identify latent variables (LVs) describing biological activity and then investigated in vitro LVs' concentration-response relationships using the ToxCast pipeline. We applied this methodology to a published transcriptomic concentration-response data set for 44 chemicals in MCF-7 cells and showed that our workflow can capture known biological activity and discriminate between estrogenic and antiestrogenic compounds as well as activity not aligning with the existing knowledge base, which may be relevant in a risk assessment scenario. Moreover, we were able to identify the known estrogen activity in compounds that are not well-established ER agonists/antagonists supporting the use of the workflow in read-across. Next, we transferred its application to chemical compounds tested in HepG2, HepaRG, and MCF-7 cells and showed that PoD estimates are in strong agreement with those estimated using a recently developed Bayesian approach (cor = 0.89) and in weak agreement with those estimated using a well-established approach such as BMDExpress2 (cor = 0.57). These results demonstrate the effectiveness of using PLIER in a concentration-response scenario to investigate pathway activity in a way that is not fully constrained by the knowledge base and to ease the biological interpretation and support the development of an NGRA framework with the ability to improve current risk assessment strategies for chemicals using new approach methodologies.

Wearable Healthcare Monitoring Based on a Microfluidic Electrochemical Integrated Device for Sensing Glucose in Natural Sweat.

Wearable sweat sensors offer the possibility of continuous real-time health monitoring of an individual at a low cost without invasion. A variety of sweat glucose sensors have been developed thus far to help diabetes patients frequently monitor blood glucose levels through sweat glucose as a surrogate marker. The present study demonstrates the development and characterization of a three-dimensional paper-based microfluidic electrochemical integrated device (3D PMED) for measuring glucose concentration in sweat in real-time via simple, non-invasive, capillary-action-based sample collection. The device was selective for glucose, and it detected glucose accurately in the clinically relevant range (0~2 mM) in an off-body setup. To the best of our knowledge, this is the first time NEXAR™ has been used for biosensing applications. Further, the developed glucose sensor has acceptable sensitivity of 16.8 µA/mM/cm2. Importantly, in an on-body setup, the device achieved a significant amperometric response to sweat glucose in a very short amount of time (a few seconds). With detailed investigations, this proof-of-concept study could help further the development of sensitive and selective sweat-based glucose sensing devices for real-time glucose monitoring in diabetes patients.

Clinical and functional outcomes of displaced proximal humerus fractures treated with PHILOS plate system and autologous bone graft.

This retrospective case series analyses the clinical and radiological outcomes of displaced proximal humerus fractures treated with PHILOS plate system and iliac crest bone autograft. Twenty-six patients with displaced fractures of proximal humerus, who were treated with PHILOS plate and autologous iliac crest bone grafts from January 2015 to September 2020, were included in this study. The inclusion criteria were proximal humerus fractures with displacement of more than 1cm and angulation of more than 45 degrees. The functional outcomes were evaluated using DASH and constant score. Radiological outcomes were measured by calculating the fracture union. The average age of the cohort was 47.28±13.69 years. Over all, the mean DASH score was 10.25 and constant score was 77.65 at three-year follow-up. The PHILOS plate with iliac crest bone autologous graft provides good radiological and functional outcomes, especially for the cases with bone defects and poor-bone stock.

Evaluation of Patient Perception and Satisfaction Toward the Use of Telemedicine During Pandemic of Novel Coronavirus in Pakistan.

Background:The trend of telemedicine is exponentially increasing worldwide due to the coronavirus disease (COVID-19) pandemic. However, patient satisfaction is always a concern regarding the use of telemedicine.Introduction:The aim of this study is to evaluate the perception and satisfaction level of patients toward the use of telemedicine during the pandemic of COVID-19 among Pakistani population.Materials and Methods:The survey questionnaires were distributed to 251 patients who received telemedicine consultation in any of three specializations: orthopedic, ophthalmology, and general medicine. The questionnaire contains 15 questions that covered four categories of patient satisfaction: interpersonal communication, caring, care delivery, and proficiency. Descriptive and analytical statistics were obtained by analyzing data using SPSS software version 20.Results:A total of 251 patients responded to the telemedicine questionnaire. Overall, 61.35% patients reported that they did not need any support for using technology during consultation and 96.41% of the patient population reported that telemedicine saved their travel time. It was found that gender, education, and age were significantly associated with the ease in technology with the p-value 0.012, 0.004 and <0.001, respectively, whereas the use of telemedicine again in future is found to be significantly associated with only education and age p-value <0.001. The statistically significant difference was found in three specialized consultation regarding the overall satisfaction, χ2 = 5.83, p-value = 0.05, with a mean rank in orthopedic is 133.6, 134.4 in ophthalmology, and 113.6 in internal medicine.Conclusion:Telemedicine is convenient and satisfactory way to provide health care services during pandemic. Although a considerable number of participants reported good response for telemedicine, there is a need of establishing local telemedicine guidelines, training of consultants and advancement in technology.

Incorporating Thiourea into Fluorescent Probes: A Reliable Strategy for Mitochondrion-Targeted Imaging and Superoxide Anion Tracking in Living Cells.

Three aggregation-induced emission active fluorescent compounds, TPA-Pyr-Octane, TPA-Pyr-Br, and TPA-Pyr-Thiourea (TPA = triphenylamine pyridinium), are synthesized; their tiny differences in chemical structures result in a huge difference in cell-imaging applications. Especially, incorporating thiourea into fluorescent probes is found as a reliable strategy for mitochondrion-targeted imaging and superoxide anion tracking in living cells, which is possibly due to the presence of hydrogen bonding between thiourea and mitochondrion proteins. This finding is very useful for the design of biosensors and delivery carriers in disease treatment.

Facile Polymerization Strategy for the Construction of Eu3+-Based Fluorescent Materials with the Capability of Distinguishing D2O from H2O.

Aggregation-induced emission (AIE) and antenna effect (AE) are two important luminescence behaviors. Connecting them into polymers is a promising but challenging work, which can supply opportunities for luminescence materials with extensive applications. In this work, AIE-active Eu3+-coordinated polymers (Poly-Eu-1, -2, -3, and -4) have been synthesized, and the efficient AE was verified. This finding presents a facile approach to obtain the Ln3+-based solid luminescence materials due to the synergistic effect from AIE and AE. Also, benefiting from the film-processing ability and water solubility, Poly-Eu-1, -2, -3, and -4 could be employed with different application purposes. In the solution phase, they can be used as sensitive optical probes to detect trace amounts of H2O and D2O, and the limit of detection (LOD) of Poly-Eu-2 toward D2O in H2O is determined to be 7.8 ppm. This discovery is a novel strategy for the construction of D2O optical sensors with a totally intervention-free style.

Defining toxicological tipping points in neuronal network development.

Measuring electrical activity of neural networks by microelectrode array (MEA) has recently shown promise for screening level assessments of chemical toxicity on network development and function. Important aspects of interneuronal communication can be quantified from a single MEA recording, including individual firing rates, coordinated bursting, and measures of network synchrony, providing rich datasets to evaluate chemical effects. Further, multiple recordings can be made from the same network, including during the formation of these networks in vitro. The ability to perform multiple recording sessions over the in vitro development of network activity may provide further insight into developmental effects of neurotoxicants. In the current study, a recently described MEA-based screen of 86 compounds in primary rat cortical cultures over 12 days in vitro was revisited to establish a framework that integrates all available primary measures of electrical activity from MEA recordings into a composite metric for deviation from normal activity (total scalar perturbation). Examining scalar perturbations over time and increasing concentration of compound allowed for definition of critical concentrations or "tipping points" at which the neural networks switched from recovery to non-recovery trajectories for 42 compounds. These tipping point concentrations occurred at predominantly lower concentrations than those causing overt cell viability loss or disrupting individual network parameters, suggesting tipping points may be a more sensitive measure of network functional loss. Comparing tipping points for six compounds with plasma concentrations known to cause developmental neurotoxicity in vivo demonstrated strong concordance and suggests there is potential for using tipping points for chemical prioritization.

3D printing for soft robotics - a review.

Soft robots have received an increasing attention due to their advantages of high flexibility and safety for human operators but the fabrication is a challenge. Recently, 3D printing has been used as a key technology to fabricate soft robots because of high quality and printing multiple materials at the same time. Functional soft materials are particularly well suited for soft robotics due to a wide range of stimulants and sensitive demonstration of large deformations, high motion complexities and varied multi-functionalities. This review comprises a detailed survey of 3D printing in soft robotics. The development of key 3D printing technologies and new materials along with composites for soft robotic applications is investigated. A brief summary of 3D-printed soft devices suitable for medical to industrial applications is also included. The growing research on both 3D printing and soft robotics needs a summary of the major reported studies and the authors believe that this review article serves the purpose.

Bisphenol A activates EGFR and ERK promoting proliferation, tumor spheroid formation and resistance to EGFR pathway inhibition in estrogen receptor-negative inflammatory breast cancer cells.

Emerging evidence from epidemiological studies suggests a link between environmental chemical exposure and progression of aggressive breast cancer subtypes. Of all clinically distinct types of breast cancers, the most lethal phenotypic variant is inflammatory breast cancer (IBC). Overexpression of epidermal growth factor receptors (EGFR/HER2) along with estrogen receptor (ER) negativity is common in IBC tumor cells, which instead of a solid mass present as rapidly proliferating diffuse tumor cell clusters. Our previous studies have demonstrated a role of an adaptive response of increased antioxidants in acquired resistance to EGFR-targeting drugs in IBC. Environmental chemicals are known to induce oxidative stress resulting in perturbations in signal transduction pathways. It is therefore of interest to identify chemicals that can potentiate EGFR mitogenic effects in IBC. Herein, we assessed in ER-negative IBC cells a subset of chemicals from the EPA ToxCast set for their effect on EGFR activation and in multiple cancer phenotypic assays. We demonstrated that endocrine-disrupting chemicals such as bisphenol A (BPA) and 2,2-bis(p-hydroxyphenyl)-1,1,1-trichloroethane can increase EGFR/ERK signaling. BPA also caused a corresponding increase in expression of SOD1 and anti-apoptotic Bcl-2, key markers of antioxidant and anti-apoptotic processes. BPA potentiated clonogenic growth and tumor spheroid formation in vitro, reflecting IBC-specific pathological characteristics. Furthermore, we identified that BPA was able to attenuate the inhibitory effect of an EGFR targeted drug in a longer-term anchorage-independent growth assay. These findings provide a potential mechanistic basis for environmental chemicals such as BPA in potentiating a hyperproliferative and death-resistant phenotype in cancer cells by activating mitogenic pathways to which the tumor cells are addicted for survival.

Predicting Organ Toxicity Using in Vitro Bioactivity Data and Chemical Structure.

Animal testing alone cannot practically evaluate the health hazard posed by tens of thousands of environmental chemicals. Computational approaches making use of high-throughput experimental data may provide more efficient means to predict chemical toxicity. Here, we use a supervised machine learning strategy to systematically investigate the relative importance of study type, machine learning algorithm, and type of descriptor on predicting in vivo repeat-dose toxicity at the organ-level. A total of 985 compounds were represented using chemical structural descriptors, ToxPrint chemotype descriptors, and bioactivity descriptors from ToxCast in vitro high-throughput screening assays. Using ToxRefDB, a total of 35 target organ outcomes were identified that contained at least 100 chemicals (50 positive and 50 negative). Supervised machine learning was performed using Naïve Bayes, k-nearest neighbor, random forest, classification and regression trees, and support vector classification approaches. Model performance was assessed based on F1 scores using 5-fold cross-validation with balanced bootstrap replicates. Fixed effects modeling showed the variance in F1 scores was explained mostly by target organ outcome, followed by descriptor type, machine learning algorithm, and interactions between these three factors. A combination of bioactivity and chemical structure or chemotype descriptors were the most predictive. Model performance improved with more chemicals (up to a maximum of 24%), and these gains were correlated (ρ = 0.92) with the number of chemicals. Overall, the results demonstrate that a combination of bioactivity and chemical descriptors can accurately predict a range of target organ toxicity outcomes in repeat-dose studies, but specific experimental and methodologic improvements may increase predictivity.