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.
1,773
datasets available to search
ShareScore release 0.9.0
Dataset results
1,773 results for “Predictive model”
Earthquake data for the Japan region from 2000 to 2023 and the CNN_LSTM magnitude prediction model.
Open the record for dataset details and reuse information.
[OUTDATED] Data set [ref. paper "Predictive modeling of drivers' brake reaction time through machine learning methods"]
Open the record for dataset details and reuse information.
Database for the manuscript "Improving the predictive skill of a distributed hydrological model by calibration on spatial patterns with multiple satellite datasets"
<p>******************************************************************************************************************************************************<strong>NOTICE: </strong>all datasets and tools provided in this database can and should only be used to reproduce the original experiment for which the database was created. The use of any datasets and tools in this database is subject to third party restrictions. Before copying or using this database for other purposes than reproducing the original experiment for which it was created, please ask for adequate authorisations to the author (Moctar Dembélé, mocdembele@gmail.com), who might additionaly need the authorization of the providers of the data and the tools available in this database. ******************************************************************************************************************************************************</p> <p>This database provides model outputs for the manuscript 'Improving the predictive skill of a distributed hydrological model by calibration on spatial patterns with multiple satellite datasets' by Dembélé et al.</p> <p>The content of each folder is as follows:</p> <p>-OF5 contains the model outputs for the model calibration case Q</p> <p>-OF42 contains the model outputs for the model calibration case MV-Q</p> <p>-OF46 contains the model outputs for the model calibration case MV-St</p> <p>-OF47 contains the model outputs for the model calibration case MV-Su</p> <p>-OF48 contains the model outputs for the model calibration case MV-Ea</p> <p>-OF49 contains the model outputs for the model calibration case MV</p> <p>-Input contains the data needed to setup and run the model</p> <p>-multiOFanalysis contains the results and the files of the analysis of the model outputs using the MATLAB software.</p> <p>For further information, please contact Moctar Dembélé, mocdembele@gmail.com</p> <p> </p>
Raw_Data_Diagnosis of tuberculous pericarditis: A Diagnostic Prediction Model Based on LASSO Logistic Regression
Open the record for dataset details and reuse information.
Predicting the skin sensitization potential of small molecules with machine learning models trained on biologically meaningful descriptors
<p>In recent years a number of machine learning models for the prediction of the skin sensitization potential of small organic molecules have been reported and become available. These models generally perform well within their applicability domains but, as a result of the use of molecular fingerprints and other non-intuitive descriptors, the interpretability of the existing models is clearly limited. The aim of this work is to develop a strategy to replace the non-intuitive features by predicted outcomes of bioassays. We show that such replacement is indeed possible and that as few as ten interpretable, predicted bioactivities are sufficient to reach competitive performance. On a holdout data set of 257 compounds, the best model ("Skin Doctor CP:Bio") obtained an efficiency of 0.82 and an MCC of 0.52 (at the significance level of 0.20). Skin Doctor CP:Bio is available from the authors free of charge for academic research. The modeling strategies explored in this work are easily transferable and could be adopted for the development of more interpretable machine learning models for the prediction of the bioactivity and toxicity of small organic compounds.</p> <p>The corresponding research article has been published in <em>Pharmaceuticals</em> <strong>2021</strong>, <em>14</em>(8), 790, DOI: <a href="https://doi.org/10.3390/ph14080790">https://doi.org/10.3390/ph14080790</a></p>
Dataset related to article "Robot-assisted rehabilitation of hand function after stroke: Development of prediction models for reference to therapy"
<p>DATASET #1</p> <p>Il data set è composto da 174 osservazioni riferite ad un campione di n=174 pazienti.</p> <p>Le variabili prese in considerazione per lo studio del data set sono 21:</p> <ul> <li> <p>ID_Pazient: variabile quantitativa continua, indica il numero di identificazione del paziente</p> </li> <li> <p>Sex: variabile dicotomica, indica il sesso del paziente (Maschio=0, Femmina=1)</p> </li> <li> <p>Age: variabile quantitativa continua, indica l'età del paziente nel momento in cui è stata effettuata la valutazione</p> </li> <li> <p>EMG_Control: variabile dicotomica, indica la capacità (Si=1) o meno (No=0) del soggetto di controllare il dispositivo con i propri segnali elettromiografici</p> </li> <li> <p>Force_Control: variabile dicotomica, indica la capacità (Si=1) o meno (No=0) del paziente di controllare il dispositivo con la propria forza</p> </li> <li> <p>Month_Injury: variabile quantitativa continua, indica i mesi trascorsi dalla data in cui è avvenuto l'ictus</p> </li> <li> <p>Diagnosis: variabile dicotomica, indica la tipologia di ictus: (Ischemico=0, Emorragico =1)</p> </li> <li> <p>Hemisphere: variabile dicotomica, indica quale emisfero cerebrale è stato colpito dall'ictus (Destro=0, Sinistro=1)</p> </li> <li> <p>FM_UE: variabile quantitativa discreta, indica la misura della funzione motoria dell'arto superiore determinata somministrando la scala Fugl-Meyer Upper Extremity</p> </li> <li> <p>Sensitivity: variabile quantitativa discreta, indica la sezione per la misura della sensibilità della scala Fugl-Meyer</p> </li> <li> <p>Pain_ROM: variabile quantitativa discreta, indica la sezione per la misura di articolarità e dolore della scala Fugl-Meyer</p> </li> <li> <p>FIM: variabile quantitativa discreta, indica la misura di autonomia della persona nelle attività della vita quotidiana, determinata dalla somministrazione della scala Functional Independence Measure</p> </li> <li> <p>RPS: variabile quantitativa discreta, indica la misura della funzione di raggiungimento di un oggetto</p> </li> <li> <p>Peg_Sec: variabile quantitativa continua, indica la misura della destrezza manuale fine e coincide con il rapporto tra il numero di pioli e i secondi impiegati per inserirli in uno specifico supporto</p> </li> <li> <p>PectMaj: variabile qualitativa ordinata, indica la misura della spasticità del pettorale, secondo la Modified Ashworth Scale</p> </li> <li> <p>BicBrach: variabile qualitativa ordinata, indica la misura della spasticità del bicipite, secondo la Modified Ashworth Scale</p> </li> <li> <p>FlexCarp: variabile qualitativa ordinata, indica la misura della spasticità del flessore del carpo, secondo la Modified Ashworth Scale</p> </li> <li> <p>FlexProfDig: variabile qualitativa ordinata, indica la misura della spasticità del flessore profondo delle dita, secondo la Modified Ashworth Scale</p> </li> <li> <p>FlexSupDig: variabile qualitativa ordinata, indica la misura della spasticità del flessore superficiale delle dita, secondo la Modified Ashworth Scale</p> </li> <li> <p>Ashworth_TOT: variabile quantitativa discreta, indica la misura totale della Modified Ashworth Scale, data dalla somma delle 5 variabili precedenti</p> </li> <li> <p>BB_par: variabile quantitativa discreta, indica la misura della destrezza manuale grossolana dell'arto paretico</p> </li> </ul>
Dataset related to the article "Prediction of myocardial blood flow under stress conditions by means of a computational model"
<p>This record contains raw data related to the article “Prediction of myocardial blood flow under stress conditions by means<br> of a computational model”</p> <p><strong>Purpose. </strong>Quantification of myocardial blood flow (MBF) and functional assessment of coronary artery disease (CAD) can be achieved through stress myocardial computed tomography perfusion (stress-CTP). This requires an additional scan after the resting coronary computed tomography angiography (cCTA) and administration of an intravenous stressor. This complex protocol has limited reproducibility and non-negligible side effects for the patient. We aim to mitigate these drawbacks by proposing a computational model able to reproduce MBF maps.</p> <p><strong>Methods. </strong>A computational perfusion model was used to reproduce MBF maps. The model parameters were estimated by using information from cCTA and MBF measured from stress-CTP (MBF<sub>CTP</sub>) maps. The relative error between the computational MBF under stress conditions (MBF<sub>COMP</sub>) and MBF<sub>CTP</sub> was evaluated to assess the accuracy of the proposed computational model.</p> <p><strong>Results.</strong> Applying our method to 9 patients (4 control subjects without ischemica vs 5 patients with myocardial ischemia), we found an excellent agreement between the values of MBF<sub>COMP</sub> and MBF<sub>CTP</sub>. In all patients, the relative error was below 8% over all the myocardium, with an average-in-space value below 4%.</p> <p><strong>Conclusion. </strong>The results of this pilot work demonstrate the accuracy and reliability of the proposed computational model in reproducing MBF under stress conditions. This consistency test is a preliminary step in the framework of a more ambitious project which is currently under investigation, i.e. the construction of a computational tool able to predict MBF avoiding the stress protocol and potential side effects while reducing radiation exposure.</p>
Causal Modeling Using Network Ensemble Simulations Predicts Novel Lipid Metabolism Genes
GEO Series GSE15226. Mus musculus. 120 samples. Type: Expression profiling by array.
Matlab code associated with publication "Mathematical model of the multi-amino acid multi-transporter system predicts uptake flux in CHO cells"
<p>Matlab code associated with publication "Mathematical model of the multi-amino acid multi-transporter system predicts uptake flux in CHO cells" </p> <p>Published version : Ashley Sreejan, Mugdha Gadgil, Chetan J. Gadgil, Mathematical model of the multi-amino acid multi-transporter system predicts uptake flux in CHO cells, Journal of Biotechnology, Volume 344, 2022, Pages 40-49, ISSN 0168-1656</p> <p>Published version available at https://doi.org/10.1016/j.jbiotec.2021.12.003</p> <p>One version of the manuscript is available at doi:10.1101/2021.04.26.441392</p>
Predicted reflectance spectrum data of dwarf cassowary skin, and measured reflectance spectrum of model fruits, E. angustifolius fruits and C. floribunda fruits
<p>Raw predicted reflectance spectrum data of dwarf cassowary skin, along with TEMs used for fast Fourier transform, and raw measured reflectance spectrum data of model fruits, <em>E. angustifolius </em>fruits and <em>C. floribunda </em>fruits. TEMs provided by Richard O. Prum.</p> <p>Key: B60 – dark blue cassowary skin; B61 – light blue cassowary skin; VA01 – <em>C. floribunda </em>from Queensland, Australia; VA02 – Ripe <em>E. angustifolius </em>from Singapore Botanical Gardens; VA03 – Ripe <em>E. angustifolius </em>from Queensland, Australia; VA05 – Unripe <em>E. angustifolius </em>from Singapore Botanical Gardens; VA06 – Overripe <em>E. angustifolius </em>from Singapore Botanical Gardens; color names – model fruits of the respective colors</p>
Development and validation of a prediction model using sella magnetic resonance imaging-based radiomics and clinical parameters for diagnosis of growth hormone deficiency and idiopathic short stature: A multicenter, cross-sectional study
Open the record for dataset details and reuse information.
Individual risk prediction: comparing Random Forests with Cox proportional-hazards model by a simulation study
<p>Results provided for reproducibility revision</p>
dataset related to project: development of a prediction model for the identification of COVID-19 patients at risk of clinical deterioration in the ED
<p>definire</p>
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.