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.
52
datasets available to search
ShareScore release 0.9.0
Dataset results
52 results for “Data Training Sets”
Training data and test data sets for simultaneous inversion of velocity density based on U-T
<p>Here are the training and testing data sets involved in the numerical experiments in the article that has been submitted to the journal “Journal of Geophysical Research: Solid Earth”, named “Joint Model and Data-Driven Simultaneous Inversion of Velocity and Density”: Marmousi model. Each dataset consists of two parts: a training dataset and a testing dataset. Both training and testing data sets contain three parts: seismic data, velocity model and density model.</p>
Anndata object of 10x Mouse Brain 5k data set for scDGD training
<p>This data from 10x (5k Adult Mouse Brain Nuclei Isolated with Chromium Nuclei Isolation Kit, Single Cell Gene Expression Dataset by Cell Ranger 7.0.0, 2022) is comprised of 7377 cells from the adult mouse brain with 32285 features. Cell type annotations were approximated using CellTpyist with the `Developing_Mouse_Brain` reference model and majority voting. This resulted in 7 distinct cell types.</p>
Testing and training data sets for: A novel representation of time-resolved particle emissions from pyrolyzing wood
Open the record for dataset details and reuse information.
Data from: Effect of ecological momentary assessment, goal-setting and personalized phone-calls on adherence to interval walking training using the InterWalk application among patients with type 2 diabetes – a pilot randomized controlled trial
Objectives: The objective was to investigate the feasibility and usability of structured text-messages, goal-setting and phone-calls on adherence to a 12-week self-conducted interval walking training (IWT) program, delivered by the InterWalk smartphone among patients with type 2 diabetes (T2D). Methods: In a two-arm pilot randomized controlled trial (Denmark, March 2014 to February 2015), patients with T2D (18-80 years with a Body Mass Index of 18 and 40 kg/m2) were randomly allocated to 12 weeks of IWT with (intervention) or without additional support (control). The primary outcome was the difference between groups in accumulated time of interval walking training across 12 weeks. All patients were encouraged to use the InterWalk application to perform IWT for ≥90 minute/week. Patients in the intervention group made individual goals regarding lifestyle change, received automated text-messages once a week, inquiring about exercise adherence. In case of consistent non-adherence, the patients would receive a phone-call inquiring about the reason for non-adherence. The control group did not receive additional support. Information about training adherence was assessed objectively. Usability of structured text-messages was assessed based on response rates and self-reported satisfaction after 12-weeks. Results: Thirty-seven patients with T2D (66 years, 65% female, hemoglobin 1Ac 50.3 mmol/mol) where included (n=18 and n=19 in intervention and control group, respectively). The retention rate was 83%. The intervention group accumulated [95%CI] 345 -7, 698 minutes of IWT more than the control group. The response rate for the text-messages was 83% (68% for males and 90% for females). Forty-one percent of the intervention and 25% of the control group were very satisfied with their participation. Conclusion: The combination of structured text-messages, goal-setting with the possibility of follow-up phone calls are considered feasible interventions to attain training adherence when using the InterWalk app during a 12-week period in patients with T2D. Some uncertainty about the effect size of adherence remains.
Data set from: Robot-Assisted Gait Training in Patients with Multiple Sclerosis: A Randomized Controlled Crossover Trial.
<p>Data set from the paper "Robot-Assisted Gait Training in Patients with Multiple Sclerosis: A Randomized Controlled Crossover Trial" doi: <a href="https://dx.doi.org/10.3390%2Fmedicina57070713">10.3390/medicina57070713</a></p>
Linkage of hospital records and death certificates by a search engine and machine learning: training and test set data
<p>INTRODUCTION: Vital status is of central importance to hospital clinical research. However, hospital information systems record only in-hospital death information. Recently, the French government released a publicly available dataset containing death-certificate data for over 25 million individuals. The objective of this study was to link French death certificates to the Bordeaux University Hospital records to complete the vital status information.</p> <p>MATERIALS AND METHODS: Our linkage strategy was composed of a search engine to reduce the number of comparisons and machine-learning algorithms. The overall pipeline was evaluated by assembling a file containing 3,565 in-hospital deaths and 15,000 alive persons.</p> <p>RESULTS: The recall and precision of our linkage strategy were 97.5% and 99.97% for the upper threshold and 99.4% and 98.9% for the lower threshold, respectively.</p> <p>CONCLUSION: In this article, we demonstrated the feasibility of accurately linking hospital records with death certificates using a search engine and machine learning.</p>
Data set - The design and evaluation of an integrated training load and injury/illness surveillance system in competitive swimming.
<p>Dataset for paper as per title above. </p>
Blinded Predictions and Post-hoc Analysis of the Second Solubility Challenge Data: Exploring Training Data and Feature Set Selection for Machine and Deep Learning Models
<p>Training and test datasets and scripts for training models.</p>
Abundance Trend Indicator - Models, Prediction, Stacked Environmental Data and Training Set Similarity
<p># Readme</p> <p>These trained models can be used to predict the abundance trends of New Zealand's forest species and can be used together with the code in https://github.com/lnilya/abundance-trend-indicator</p> <p>Since the process of using the models requires coding expertise and some setting up, please make sure to reach out to ilya.shabanov@vuw.ac.nz for any questions. All files will require the code in the repository to be read and used. </p> <p>If you want to explore the results generated with these models, please visit https://ati-nz-predictions-7e6f3d514735.herokuapp.com/ for a user-friendly, interactive UI.</p> <p>## Contents</p> <p>_models: Contains the trained models (Artificial Neural Network (ANN), Random Forest (RF), SVMW (Support vector machine) and GLM (logistic regression)) at different degrees of noise filtering, different datasets and variable sets. The model files also contain test and training scores. To load the files please refer to the readme in the code repository: ttps://github.com/lnilya/abundance-trend-indicator</p> <p><br>_predictions/_environment: Contains the predictor variables for the study area (New Zealand, 1950-2019) that are needed by the models to make predictions. </p> <p>_predictions/_similarity: Contains the masks of areas that can be predicted by models and are similar to the training set.</p> <p>_predictions/_ati: Contain the predicted results for the abundance trend. These can be explored on https://ati-nz-predictions-7e6f3d514735.herokuapp.com/ </p> <p> </p>
One Hand project - Transfer of prosthesis control skill after training in VR, data set pre-test post-test
Open the record for dataset details and reuse information.
HDNNP training data set for Cu2S
<p>High-dimensional neural network potential (HDNNP) training data set for copper sulfide (Cu<sub>2</sub>S). Unpack archive and see README.pdf for details.</p>
HDNNP training data set for H2O
<p>High-dimensional neural network potential (HDNNP) training data set for water. Unpack archive and see README.pdf for details.</p>
Linkage of hospital records and death certificates by a search engine and machine learning: training and test set data
Open the record for dataset details and reuse information.
Data from: Effect of ecological momentary assessment, goal-setting and personalized phone-calls on adherence to interval walking training using the InterWalk application among patients with type 2 diabetes – a pilot randomized controlled trial
Open the record for dataset details and reuse information.
STRIPE training data set
Open the record for dataset details and reuse information.
University of Denver Collections as Data - HTR Train and Validation Set JCRS_2020_5_27
<p><a href="https://zenodo.org/api/files/333ecb88-1f48-4ffd-b39e-5e70b800c276/HTR_Train_Set_JCRS_2020_5_27.zip">HTR_Train_Set_JCRS_2020_5_27.zip</a> <br> Description</p>
Training data set for inverse pyrolysis machine learning
<p>For dataset description see https://doi.org/10.5281/zenodo.6606247</p>
Raw motif mapping bedfile data and model training set class probabilities
<p>Leveraging prior viral genome sequencing data to make predictions on whether an unknown, emergent virus harbors a 'phenotype-of-concern' has been a long-sought goal of genomic epidemiology. A predictive phenotype model built from nucleotide-level information alone is challenging with respect to RNA viruses due to the ultra-high intra-sequence variance of their genomes, even within closely related clades. We developed a degenerate k-mer method to accommodate this high intra-sequence variation of RNA virus genomes for modeling frameworks. By leveraging a taxonomy-guided 'group-shuffle-split' cross validation paradigm on complete coronavirus assemblies from prior to October 2018, we trained multiple regularized logistic regression classifiers at the nucleotide k-mer level. We demonstrate the feasibility of this method by finding models accurately predicting withheld SARS-CoV-2 genome sequences as human pathogens and accurately predicting withheld Swine Acute Diarrhea Syndrome coronavirus (SADS-CoV) genome sequences as non-human pathogens. Feature selection using L1 regularization identified several degenerate nucleotide predictor motifs with high model coefficients for the human pathogen class that were present across widely disparate clades of coronaviruses. However, these motifs differed in which genes they were present in, what specific codons were used to encode them, and what the translated amino acid motif was. This emphasizes the importance of a phenetic view of emerging pathogenic RNA viruses, as opposed to the canonical phylogenetic interpretations most commonly used to track and manage viral zoonoses. Applying our model to more recent Orthocoronavirinae genomes deposited since October 2018 yields a novel contextual view of pathogen potential across bat-related, canine-related, porcine-related, and rodent-related coronaviruses and critical adaptations which may have contributed to the emergence of the pandemic SARS-CoV-2 virus. Finally, we discuss the next steps to achieve robust predictive ensembles and the utility of these models (and their associated predictor motifs) to novel biosurveillance protocols that substantially increase the 'pound-for-pound' information content of field-collected sequencing data and make a strong argument for the necessity of routine collection and sequencing of zoonotic viruses. </p>
Raw motif mapping bedfile data and model training set class probabilities
Open the record for dataset details and reuse information.
'Learning the production cross sections of the Inert Doublet Model' training data set.
<p>Training data set used in the ''Learning the production cross sections of the Inert Doublet Model'' subproject, made of 50000 samples with 5 input values (MH0, MA0, MHC, lam2, lamL) and 8 target values (xsec_3535_13TeV, xsec_3636_13TeV, xsec_3737_13TeV, xsec_3537_13TeV, xsec_3637_13TeV, xsec_3735_13TeV, xsec_3736_13TeV, xsec_3536_13TeV) from a parameter space of the Inert Doublet Model chosen as: 50< MH0, MA0, MHC<3000GeV;−2π < lam2,lamL<2π. The cross sections were computed at leading order using MADGRAPH2.6.4 and the IDM UFO implementation from the FeynRules data base.</p> <p> </p> <p> </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.