Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
90
datasets available to search
ShareScore release 0.9.0
Dataset results
90 results for “toxicity prediction”
Predicted and experimental chemical and ecotoxicological properties for the toxic unit based hazard assessment
<p><strong>Description</strong></p> <p>This dataset contains ecotoxicity data of 1585 chemicals of environmental concern (CECs) and chemical identifiers. The ecotoxicity data was retrieved from <a href="https://cfpub.epa.gov/ecotox">US EPA ECOTOX Knowlegdebase</a> in ASCII file format and was aggregated for the ecotoxicity groups algae, crustaceans, and fish based on the ideas of <a href="https://dx.doi.org/10.1002/etc.3460">Busch et al. 2016</a>. The dataset includes the 5-percentile, the mean and the geomean of all retrieved ecotoxicity for each compound. Missing ecotoxicity data was estimated with ECOSAR 1.0 algorithms for green algae, daphnids, and fish using <a href="https://www.ufz.de/index.php?en=34593">ChemProp 6.8</a>. The main purpose of this dataset is the <a href="http://doi.org/10.1016/0043-1354(70)90018-7">toxic unit</a> (TU) based hazard assessment of environmental water samples. Chemical properties were estimated using <a href="https://github.com/kmansouri/OPERA">OPERA 2.7</a>, <a href="https://chemaxon.com/products/instant-jchem">Instant JChem</a>, and ACD Percepta 2015 based on QSAR-ready SMILES derived from OPERA 2.7. All data aggregated from EcoTox Knowledgebase (e.g., raw values, species, etc.) is available in the dataset in the detailed sheets. REcoTox, the processing script written in R is available on <a href="https://github.com/tsufz/REcoTox/releases/latest">GitHub</a>.</p> <p><strong>CAUTION</strong></p> <p>It needs to be emphasized that quantitative-structure activity relationship data is just an estimate, which does not necessarily reflect the real property and behaviour of a modelled compound. The calculated data needs to be reviewed in deep. Especially for non-polar or very polar compounds, the QSAR predictions might fail. If a compound ranks high in the TU ranking, it is required to search for literature or regulative data evidences to underpin the finding to avoid false positive prioritizations.</p> <p><strong>RELEASE NOTE</strong></p> <p>Version 210714_v1 was created with <a href="https://github.com/tsufz/REcoTox/releases/tag/v0.1.0">REcoTox version v0.1.0</a>.</p>
RDF version of the data from Choi, JS., Ha, M.K., Trinh, T.X. et al. Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources. Sci Rep 8, 6110 (2018)
<p>RDF version of the data from Choi, JS., Ha, M.K., Trinh, T.X. et al. Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources. Sci Rep 8, 6110 (2018)</p>
Consensus models to predict oral rat acute toxicity and validation on a dataset coming from the industrial context
<p>We report predictive models of acute oral systemic toxicity representing a follow-up of our previous work in the framework of the NICEATM project. It includes the update of original models through the addition of new data and an external validation of the models using a dataset relevant for the chemical industry context. A regression model for LD50 and classification model for toxicity classes according to the Global Harmonized System categories were prepared. ISIDA descriptors were used to encode molecular structures. Machine learning algorithms included Support Vector Machine (SVM), Random Forest (RF) and Naïve Bayesian. Selected individual models were combined in consensus.</p> <p>The different datasets were compared using the Generative Topographic Mapping approach. It appeared that the NICEATM datasets were lacking some relevant chemotypes for chemical industry. The new models trained on enlarged data sets have applicability domain (AD) sufficiently large to accommodate industrial compounds. The fraction of compounds inside the models’ AD increased from 58 % (NICEATM model) to 94 % (new model). Yet, the increase of training sets only slightly improved of the models’ prediction performance: RMSE values decreased from 0.56 to 0.47 and balanced accuracies increased from 0.69 to 0.71 for NICEATM and new models, respectively.</p>
RDF version of the data from Choi, JS. et al. Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources (2018)
<p>This is an RDFied version of the dataset published in Choi, JS., Ha, M.K., Trinh, T.X. et al. Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources. Sci Rep 8, 6110 (2018)</p> <p>The original dataset publication DOI: <a href="https://doi.org/10.1038/s41598-018-24483-z">https://doi.org/10.1038/s41598-018-24483-z</a></p> <p>The Original publication authors: Jang-Sik Choi, My Kieu Ha, Tung Xuan Trinh, Tae Hyun Yoon & Hyung-Gi Byun</p>
Conformer datasets for "Equivariant Graph Neural Networks for Toxicity Prediction"
<p>Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain.</p> <p>PAPER</p> <p>https://pubs.acs.org/doi/full/10.1021/acs.chemrestox.3c00032</p> <p>CODE and MODELS:</p> <p>The conformer data sets and trained toxicity models will be published upon acceptance of this work. The code has been made available at <a href="https://github.com/jule-c/ET-Tox">https://github.com/jule-c/ET-Tox</a>, and the processed data as well as pretrained models for training and testing can be downloaded from <a href="../record/7942946">https://zenodo.org/record/7942946</a>. We can provide the full list of conformers as XYZ files upon request.</p>
Overview of available toxicity data for calystegines - results of the in silico genotoxicity predictions
<p>Results of the<em> in silico</em> genotoxicity predictions complementing the EFSA scientific report on calystegines: https://doi.org/10.2903/j.efsa.2019.5574</p>
Predicted drug-likeness and toxicity properties of Salvia fruticosa compounds
<p>The datasets present computationally predicted drug-likeness and toxicity profiles of <em>Salvia frutocosa</em> compounds.</p>
Images of daphnids (control and exposed to NMs) over multiple generations, scored by experts as toxic or non-toxic and the resulting deepDaph predictions
<p>Background</p> <p>This study showcases a pioneering application of deep learning methodologies in ecotoxicology, aimed at facilitating hazard assessment and safer design of engineered nanomaterials (ENMs). The research hinges on a high-quality dataset comprising microscopic images of Daphnia magna exposed to various ENMs, collected systematically under controlled conditions.</p> <p>The Dataset: A Cornerstone of Nanoinformatics</p> <p>Our dataset, which will be openly accessible on Zenodo, serves as a foundational resource for the ecotoxicology community. It contains high-resolution images tagged with intricate details like malformations, tail lengths, lipid concentrations, and lipid deposit shapes. Researchers can use this exhaustive dataset to train a variety of predictive models for diverse applications.</p> <p>Methodology</p> <p>We employ two different deep learning architectures to process the dataset. These architectures automatically detect malformations and assess the impact of ENMs on D. magna by classifying various biological structures based on lipid densities.</p> <p>Results and Validation</p> <p>The developed models demonstrate high statistical validation, confirming their prediction accuracy on external D. magna images. Our dataset and the associated models not only accelerate manual procedures but also pave the way for automated, high-throughput analyses in ecotoxicology.</p> <p>Future Prospects</p> <p>The dataset holds the potential to extend investigations into predicting the impacts on future generations from parental exposures, thus reducing the time and cost of multi-generational toxicity assays.</p>
Status quo in data availability and predictive models of nano-mixture toxicity
<p>Supplementary materials for manuscript: Status quo in data availability and predictive models of nano-mixture toxicity.</p> <p>This table contains the list of 183 curated literature used in this study.</p>
Prioritization of unknown features based on predicted toxicity categories
<p> The fish toxicity data set, the filtered CompTox data set, and the pesticide mixture datasets used for the development of the prioritization algorithms described elsewhere.</p>
Machine learning pipeline to train toxicity prediction model of FunTox-Networks
<p>Machine Learning pipeline used to provide toxicity prediction in FunTox-Networks</p> <p>01_DATA # preprocessing and filtering of raw activity data from ChEMBL<br> - Chembl_v25 # latest activity assay data set from ChEMBL (retrieved Nov 2019)<br> - filt_stats.R # Filtering and preparation of raw data<br> - Filtered # output data sets from filt_stats.R<br> - toxicity_direction.csv # table of toxicity measurements and their proportionality to toxicity</p> <p>02_MolDesc # Calculation of molecular descriptors for all compounds within the filtered ChEMBL data set<br> - datastore # files with all compounds and their calculated molecular descriptors based on SMILES<br> - scripts<br> - calc_molDesc.py # calculates for all compounds based on their smiles the molecular descriptors<br> - chemopy-1.1 # used python package for descriptor calculation as decsribed in: https://doi.org/10.1093/bioinformatics/btt105</p> <p>03_Averages # Calculation of moving averages for levels and organisms as required for calculation of Z-scores<br> - datastore # output files with statistics calculated by make_Z.R<br> - scripts<br> -make_Z.R # script to calculate statistics to calculate Z-scores as used by the regression models<br> <br> 04_ZScores # Calculation of Z-scores and preparation of table to fit regression models<br> - datastore # Z-normalized activity data and molecular descriptors in the form as used for fitting regression models<br> - scripts<br> -calc_Ztable.py # based on activity data, molecular descriptors and Z-statistics, the learning data is calculated</p> <p>05_Regression # Performing regression. Preparation of data by removing of outliers based on a linear regression model. Learning of random forest regression models. Validation of learning process by cross validation and tuning of hyperparameters.</p> <p>- datastore # storage of all random forest regression models and average level of Z output value per level and organism (zexp_*.tsv)<br> - scripts<br> - data_preperation.R # set up of regression data set, removal of outliers and optional removal of fields and descriptors<br> - Rforest_CV.R # analysis of machine learning by cross validation, importance of regression variables and tuning of hyperparameters (number of trees, split of variables)<br> - Rforest.R # based on analysis of Rforest_CV.R learning of final models</p> <p>rregrs_output<br> # early analysis of regression model performance with the package RRegrs as described in: https://doi.org/10.1186/s13321-015-0094-2</p>
Single species acute lethal toxicity tests are not predictive of relative population, community and ecosystem effects of two salinity types
<p>Human mediated salinity increases are occurring in freshwaters globally, with consequent negative effects on freshwater biodiversity. Salinity comprises multiple anions and cations. While total concentrations are typically used to infer effects, individual ion concentrations and ion ratios are critical in determining effects. Moreover, estimates of toxicity from single species laboratory tests, may not accurately predict relative effects on populations, communities and ecosystems. Here we compare salinity increases from synthetic marine salts (SMS) and sodium bicarbonate (NaHCO3) in an outdoor mesocosm experiment in south-eastern Australia. We found different effects of salt types on stream macroinvertebrates at the population, community, and ecosystem function levels, where similar effects were predicted from single species laboratory tests. Our results caution against the use of single species laboratory derived toxicological data to predict both environmentally safe salinity levels and the relative effects of different salt sources on freshwater biodiversity.</p>
Predicting Severe Toxicity of Targeted Therapies in Elderly Patients With Cancer
ClinicalTrials.gov study NCT02751827. IPD Sharing: NO. Countries: 1. Publications: 1.
Single species acute lethal toxicity tests are not predictive of relative population, community and ecosystem effects of two salinity types
Open the record for dataset details and reuse information.
Integrating QSAR models predicting acute contact toxicity and mode of action profiling in honey bees (A. mellifera): Data curation using open source databases, performance testing and validation
<p>This excel file (DOI: <a href="https://doi.org/10.5281/zenodo.3755675">https://doi.org/10.5281/zenodo.3755675</a>) provides the collection of raw data used for developing the first integrative Quantitative Structure-Activity Relationship (QSAR) model using EFSA's OpenFoodTox, US-EPA ECOTOX and Pesticide Properties DataBase i) to predict acute contact toxicity (LD<sub>50</sub>) and ii) to profile the Mode of Action (MoA) of pesticides active substances in honey bees (<em>Apis mellifera</em>)<em>. </em>Chemical identifiers (e.g. SMILES, CAS n., InChI) and acute contact toxicity data (LD<sub>50</sub>) on honey bees were used to develop and validate i) a two-category QSAR model (toxic/non-toxic; n=411) (sensitivity =0.93), specificity =0.85), balanced accuracy =0.90), Matthews correlation coefficient MCC=0.78), and ii) a regression-based model (n=113) (R2=0.74; MAE=0.52). Similarly, current study proposes the first MoA profiling for 113 pesticides active substances and the first harmonised MoA classification scheme for acute contact toxicity in honey bees, including LD<sub>50s</sub> data points from three different databases such as EFSA's OpenFoodTox, US-EPA ECOTOX and Pesticide Properties DataBase. Such classification allows to further define MoAs and the target site of Plant Protection Products (PPPs) active substances, thus enabling regulators and scientists to refine chemical grouping and toxicity extrapolations for single chemicals and component-based mixture risk assessment of multiple chemicals.</p> <p>The full data collection and analysis of QSAR models, toxicity data (LD<sub>50</sub>) and Mode of Action (Moa) data are described in Carnesecchi et al., 2020 (DOI: doi.org/10.1016/j.scitotenv.2020.139243).</p> <p>This work was supported by the European Food Safety Authority (EFSA) [contract number: OC/EFSA/SCER/2018/01 and NP/EFSA/AFSCO/2016/02 (Edoardo Carnesecchi)].</p>
Gene Signature predicts autoimmune toxicity in metastatic melanoma
Open the record for dataset details and reuse information.
Immune signatures predict development of autoimmune toxicity in immune checkpoint inhibitor-treated patients with cancer
<p><strong>Immune signatures predict development of autoimmune toxicity in immune</strong><strong> checkpoint inhibitor-treated patients with cancer</strong></p> <p> </p> <p>Nicolas Gonzalo Nuñez<sup>1</sup>*, Fiamma Berner<sup>2</sup>*, Ekaterina Friebel<sup>1</sup>*, Susanne Unger<sup>1</sup>, Nina Wyss<sup>2,3</sup>, Julia Martinez Gomez<sup>4</sup>, Mette-Triin Purde<sup>2</sup>, Rebekka Niederer<sup>2,3</sup>, Maximilian Porsch<sup>5</sup>, Christa Lichtensteiger<sup>2</sup>, Rafaela Kramer<sup>6</sup>, Michael Erdmann<sup>6</sup>, Christina Schmitt<sup>7</sup>, Lucy Heinzerling<sup>6,7</sup>, Marie-Therese Abdou<sup>2</sup>, Julia Karbach<sup>8</sup>, Dirk Schadendorf<sup>9</sup>, Lisa Zimmer<sup>9</sup>, Selma Ugurel<sup>9</sup>, Niklas Klümper<sup>10,11,12</sup>, Michael Hölzel<sup>10,11</sup>, Laura Power<sup>1</sup>, Stefanie Kreutmair<sup>1</sup>, Mariaelena Capone<sup>13</sup>, Gabriele Madonna<sup>13</sup>, Lacin Cevhertas<sup>14,15</sup>, Anja Heider<sup>14</sup>, Teresa Amaral<sup>16,17</sup>, Omar Hasan Ali<sup>2,3,4,18</sup>, David Bomze<sup>2,19</sup>, Florentia Dimitriou<sup>4</sup>, Stefan Diem<sup>20</sup>, Paolo Antonio Ascierto<sup>13</sup>, Reinhard Dummer<sup>4</sup>, Elke Jäger<sup>8</sup>, Christoph Driessen<sup>20</sup>, Mitchell P. Levesque<sup>4</sup>, Willem van de Veen<sup>14</sup>, Markus Joerger<sup>20</sup>, Martin Früh<sup>20,21</sup>, Burkhard Becher<sup>1</sup>**, Lukas Flatz<sup>2,3,4,20,22</sup>**</p> <p> </p> <p>*/** these authors contributed equally</p> <p> Affiliations</p> <p>1. Institute of Experimental Immunology, University of Zurich, Zurich, Switzerland</p> <p>2. Institute of Immunobiology, Medical Research Center, Kantonsspital St. Gallen, St.Gallen, Switzerland</p> <p>3. Department of Dermatology, Kantonsspital St. Gallen, St.Gallen, Switzerland</p> <p>4. Department of Dermatology, University Hospital Zurich, Zurich, Switzerland</p> <p>5. Department of Radiology, Kantonsspital St. Gallen, St.Gallen, Switzerland</p> <p>6. Department of Dermatology, University of Erlangen-Nuremberg, Erlangen, Germany</p> <p>7. Ludwig Maximilian University of Munich, Munich, Germany</p> <p>8. Department of Oncology and Hematology, Krankenhaus Nordwest, Frankfurt, Germany</p> <p>9. Department of Dermatology, Comprehensive Cancer Center (Westdeutsches Tumorzentrum) University Hospital Essen, Essen, Germany</p> <p>10. Institute for Experimental Oncology, University Hospital Bonn, Bonn, Germany</p> <p>11. Center for Integrated Oncology Cologne/Bonn, University Hospital Bonn, Bonn, Germany</p> <p>12. Department of Urology, University Hospital Bonn, Bonn, Germany</p> <p>13. Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, Napoli, Italy</p> <p>14. Swiss Institute of Allergy and Asthma Research (SIAF), University of Zurich, Davos, Switzerland</p> <p>15. Department of Medical Immunology, Institute of Health Sciences, Bursa Uludag University, Bursa, Turkey</p> <p>16. Skin Cancer Center, Department of Dermatology, University Hospital Tübingen, Tübingen, Germany</p> <p>17. iFIT Cluster of Excellence (EXC 2180), University of Tübingen, Tübingen, Germany</p> <p>18. Department of Medical Genetics, Life Sciences Institute, University of British Columbia, Vancouver, Canada</p> <p>19. Sackler Faculty of Medicine, Tel-Aviv University, Israel</p> <p>20. Department of Oncology, Kantonsspital St. Gallen, St.Gallen, Switzerland</p> <p>21. Department of Medical Oncology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland</p> <p>22. Universitäts-Hautklinik, University of Tübingen, Tübingen, Germany</p> <p> </p> <p> </p>
Fatty acids homeostasis during fasting predicts protection from chemotherapy toxicity
<p>Fasting exerts beneficial effects in mice and humans, including protection from chemotherapy toxicity. To explore the involved mechanisms, we collect blood from humans and mice before and after 36 or 24 hours of fasting, respectively, and measure lipid composition of erythrocyte membranes, circulating micro RNAs (miRNAs), and RNA expression at peripheral blood mononuclear cells (PBMCs). Fasting coordinately affects the proportion of polyunsaturated versus saturated and monounsaturated fatty acids at the erythrocyte membrane; and reduces the expression of insulin signaling-related genes in PBMCs. When fasted for 24 hours before and 24 hours after administration of oxaliplatin or doxorubicin, mice show a strong protection from toxicity in several tissues. Erythrocyte membrane lipids and PBMC gene expression define two separate groups of individuals that accurately predict a differential protection from chemotherapy toxicity, with important clinical implications. Our results reveal a mechanism of fasting associated with lipid homeostasis, and provide biomarkers of fasting to predict fasting-mediated protection from chemotherapy toxicity.</p>
Prediction of Delayed Toxic Cardiomyopathy in Children
ClinicalTrials.gov study NCT05781672. IPD Sharing: YES. Countries: 1. Publications: 1.
Evaluation of an Apoptotic Test for Predicting Late Toxicities After Radiotherapy in Breast and Prostate Cancer Patients
ClinicalTrials.gov study NCT00893035. IPD Sharing: Not stated. Countries: 1. Publications: 41.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.