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.
558
datasets available to search
ShareScore release 0.9.0
Dataset results
558 results for “Training Data”
URL list for downloading training data for 'Maximum Likelihood Phylogeny Reconstruction'' (Galaxy Training Material)
<p>This data is used for Galaxy Training Network (GTN) training 'Maximum Likelihood Phylogeny Reconstruction'. It is a list of Zenodo URL pointers to a dataset of 173 amino acid alignments of orthologs found in chromosome 5 of four strains of S. cerevisiae. Original sequence data (https://zenodo.org/record/6610704) was processed in Galaxy following GTN 'Preparing genomic data for phylogeny reconstruction' training (10.48546/workflowhub.workflow.359.1) to generate alignments of orthologs.</p>
Training data for 'Functional annotation of protein sequences' tutorial (Galaxy Training Material)
<p>The data provided here are part of a Galaxy Training Network tutorial for functional annotation of protein sequences.</p>
Training data for 'Refining Manual Genome Annotations with Apollo (eukaryotes)' tutorial (Galaxy Training Material)
<p>The data provided here are part of a Galaxy Training Network tutorial for manual curation of eukaryotic genome annotation using Apollo.</p>
HippUnfold HCP-YA Training Data
<p>Hippocampal Tissue segmentations, T1w, T2w, and mean DWI b1000 images in upsampled 0.3mm left and right bounding boxes around the hippocampus. Subjects are from the HCP-1200 Young Adult dataset. These data were used to train the current HippUnfold U-net segmentation models.</p> <p>Unzip all the zip files, folders will be created for the labelmaps, T1w, T2w, and b1000 images for each hemisphere and subject. Left hipp labels are already L-R flipped to the right side.</p> <p>Labelmap lookup table:</p> <pre>index name abbreviation 1 hippocampal grey matter GM 2 SRLM or 'dark band' SRLM 3 neocortex (entorhinal or parahippocampal) MTLC 4 pial surface Pial 5 hippocampal-amygdalar transition area HATA 6 indusium griseum IndGris 7 cysts Cyst 8 dentate gyrus DG</pre> <p> </p>
Data from: Crowdsourcing training material for automated bird sound classification – a pilot study
<p>Data from the manuscript "Crowdsourcing training material for automated bird sound classification – a pilot study" by Petteri Lehikoinen, Meeri Rannisto, Ulisses Camargo, Aki Aintila, Patrik Lauha, Esko Piirainen, Panu Somervuo & Otso Ovaskainen</p>
Training data for 'Repeat masking with RepeatMasker' tutorial (Galaxy Training Material)
<p>Data needed for the 'Repeat masking with RepeatMasker' tutorial (Galaxy Training Material).</p> <p>The assembly was generated following the 'Genome assembly using PacBio data' tutorial</p>
Python scripts / Jupyter Notebooks and data for training segmentation models on slide scans of diatom preparations from river Menne
<p>This archive contains the Jupyter Notebooks and data used for the deep learning experiments published in Kloster et al. 2022: Improving deep learning-based segmentation of diatoms in gigapixel-sized virtual slides by object-based tile positioning and object integrity constraint.</p> <p>The notebooks are numbered according to the order in which they are to execute. Please refer to the comments and documentation within the notebooks as well as to the manuscript for details. The data (image data, mask data & segmentation ground truth in COCO format for several different tiling strategies) is stored in separate subfolders corresponding with data usage (model training, validation, test) and tiling strategy. Please refer to the "readme" files for detailed information.</p> <p> </p> <p> </p>
Single pixel s*t Landsat time series training data for CNN
<p>Single pixel s*t Landsat time series classification using 1D CNN</p> <p>Sep 22, 2022 update (version 2): <br> The 1D CNN classification codes are available at https://github.com/hankui/cnn_Landsat_time_series_classification_v2-Python</p> <p>The NLCD training data is available at 10.5281/zenodo.7106054</p> <p>The NLCD training data is derived from Landsat 5/7 analysis ready data (ARD) in year 2011 (as x predictor variable) and National Land Cover Database (NLCD) 2011 (as y response variable)</p> <p>The NLCD training data is distributed across Continental United States (CONUS) with 3,314,439 30m pixel locations</p> <p>The NLCD training data include (i) NLCD label with 15 classes, i.e., all NLCD classes except ice (https://www.mrlc.gov/data/legends/national-land-cover-database-class-legend-and-description)<br> (ii) year 2011 growing season Landsat ARD percentiles for Landsat 5/7 bands 2, 3, 4, 5 and 7 and for 8 band ratios derived from the five bands <br> (iii) percentiles include 10th, 20th, 25th, 30th, 35th, 40th, 50th (median), 60th, 65th, 70th, 75th, 80th, 90th so that <br> one can use 5 percentiles (10th, 25th, 50th, 75th, and 90th)<br> 7 percentiles (10th, 20th, 35th, 50th, 65th, 80th, and 90th)<br> 9 percentiles (10th, 20th, 30th, 40th, 50th, 60th, 70th, 80th, and 90th)<br> (iv) the pixel location represented in Landsat ARD tile h and v no. and the pixel i and j locations in the tile<br> (v) the no. of the cloud free observations in 2011 growing season derived for the pixel location<br> </p> <p>#*************************************************************************************************************#</p> <p>A munuscript describing how the data were derived and how the 1D CNN was adapted to the data is in review </p> <p><br> #*************************************************************************************************************#</p> <p>The codes were written in python (v3.7) and tensorflow (v2.6). </p> <p>The parameters are:</p> <p>(1) learning rate: cnn training initial learning rate 0.01 used in the paper </p> <p>(2) epoch: cnn training epochs 70 used in the paper </p> <p>(3) method: cnn training optimizer method 1: Adam method 2: dynamic learning rate used in the paper</p> <p>(4) L2: L2 regularization value; 0.001 used in paper </p> <p>(5) layer: no. of CNN layers (can be 4, 5 and 8) and 5 and 8 used in the paper</p> <p>(6) perc: training data percentages (can be 0.1, 0.5 and 0.9) tested in the paper; the evaluation is used the left 10% </p> <p>(7) gpui: which gpu process it will use (only applicable with multi-gpus) </p> <p>(8) IMG_HEIGHT: the no. of percentiles (can be 3, 5, 7 and 9) and 5, 7 and 9 used in the paper </p> <p>An example would be: </p> <p>version=7_4 </p> <p>layer=5; perc=0.1; gpui=0;IMG_HEIGHT=5</p> <p>method=0; learning_rate=0.01; epoch=10; iter=1; L2=0.001; sleep ${SLEEP}; ## Hank layer=5; perc=0.1; </p> <p>echo "python Pro_2d1d_CNN_v${version}.py ${learning_rate} ${epoch} ${method} ${L2} ${layer} ${perc} ${gpui} ${IMG_HEIGHT} "</p> <p>python Pro_2d1d_CNN_v${version}.py ${learning_rate} ${epoch} ${method} ${L2} ${layer} ${perc} ${gpui} ${IMG_HEIGHT} > layer${layer}.p${perc}.d${IMG_HEIGHT}.rate${learning_rate}.e${epoch}.L${L2}.v${version} & </p> <p><br> #*************************************************************************************************************#</p> <p>Aug 29, 2021 (version 1): <br> Training data: There are 2 input text files (csv) storing the 3,314,439 NLCD and 484,476 CDL land cover training samples:<br> NLCD training: ./NLCD/metric.ard.nlcd.Mar01.18.40.txt<br> CDL training: ./CDL/metric.ard.nlcd.Mar01.18.40.txt</p> <p>The codes and their usages are at: <br> https://github.com/hankui/cnn_Landsat_time_series_classification_v1-R<br> </p>
SSHOC Training Material Video 3 - Contributing metadata to the COVID-19 collection of the Ethnic and Migrant Minorities (EMM) Survey Registry as a data producer - training video in English, French and Spanish
<p>Contributing metadata to the COVID-19 collection of the Ethnic and Migrant Minorities (EMM) Survey Registry as a data producer</p> <p>A training video targeting COVID-19 survey producers to entice contributions to the COVID-19 collection of the EMM Survey Registry<br> <strong>Target Audience for the video</strong>: Survey producers (academic and non-academic) of COVID-19 surveys with EMM respondents</p>
Fast kinetics data of binding of azide to myoglobin, training data -- MetBio practicals
<p>These data files were acquired during the course of the 3rd <a href="http://frenchbic.cnrs.fr/">FrenchBIC</a> <a href="http://frenchbic.cnrs.fr/2021/01/25/3rd-frenchbic-summer-school-on-methods-for-studying-metals-in-biology/">MetBio summer school</a> taking place in and around Marseille. The data were acquired during the “stopped flow” practicals.</p> <p>The data correspond to the reaction of Myoglobin with various concentrations of azide, triggered using a stopped-flow apparatus and followed by UV/Visible spectroscopy.</p> <p>The concentrations of azide can be deduced from the names of the files and are expressed in millimolar. The concentrations of myoglobin are variable but always much lower than that of azide.</p> <p>The purpose of this dataset is to be used as training data for analysing multiwavelength kinetic data. It will be the subject of a data analysis tutorial using the free software <a href="https://bip.cnrs.fr/groups/bip06/software/">QSoas</a>, to be published <a href="https://vince-debian.blogspot.com/">there</a>.</p> <p>With the exception of the <code>WTV-Azide-0.5mm_3.txt</code>, all the files are in a “matrix” format, in which the first column gives the time and each column after the first corresponds to the absorbances over time of a single wavelength.</p> <p>The <code>WTV-Azide-0.5mm_3.txt</code> uses a different format, in which each line corresponds to a <em>wavelength</em> <em>time</em> <em>absorbance</em> triplet.</p> <p>Useful background reading:</p> <ul> <li> <p>Coletta <em>et al</em>, <strong>1996</strong>, DOI: 10.1111/j.1432-1033.1996.00049.x</p> </li> <li> <p>De Sanctis <em>et al</em>, <strong>2007</strong>, DOI: 10.1529/biophysj.106.098764</p> </li> </ul>
Training data for ChIP-seq data analysis (Galaxy Training Material): Identification of the binding sites of the Estrogen receptor
<p>The data provided here are part of a Galaxy Training Network tutorial that analyzes ChIP-seq data from a study published by Ross-Inness et al., 2012 (DOI:10.1038/nature10730) to identify the binding sites of the Estrogen receptor, a transcription factor known to be associated with different types of breast cancer.</p>
Training data for 'From peaks to gene' tutorial (Galaxy Training Material)
<p>The data provided here are part of a Galaxy Training Network tutorial that analyzes peaks from a study published by Li et al., 2012 (DOI:10.1016/j.stem.2012.04.023) to identify target genes</p>
Training data for 'Reference based RADSeq ' tutorial (Galaxy Training Material)
<p>The data provided here are part of a Galaxy Training Network tutorial that analyzes RAD-seq data from a study published by Hohelnlohe et al., 2010 (DOI:10.1371/journal.pgen.1000862) to identify and type single nucleotide polymorphisms (SNPs) in each of 100 individuals from two oceanic and three freshwater populations and thus estimate genetic diversity and differentiation among populations. </p>
MJFF Data Community - Creative Commons Training: Copyright and Open Licensing
<p>This training, provided by Shanna Hollich, the Learning and Training Manager of Creative Commons (CC), was hosted by the Michael J. Fox Foundation's Data Community of Practice (DCOP). For more information on the DCOP, please contact: researchcommunity@michaeljfox.org.</p> <p>In the ever-evolving digital landscape, the management of research outputs, including data licensing and copyright, is of utmost importance. This 1.5-hour training provided a forum for participants to learn more about open licensing and copyright. It also aimed to equip participants with the knowledge and best practices they need to effectively navigate the complexities of CC licensing and copyright when using and generating research outputs such as scholarly publications, datasets, and white papers.<br><br>By the end of the workshop, participants developed an understanding of the basic principles of copyright, how it works, and where it applies. Participants are now able to describe the benefits of open licensing and the basics of how Creative Commons licenses work, have a deeper understanding of how research outputs interact with copyright and open licensing, and know where to find additional information and resources.</p> <p>To access a stream of this video with variable resolution, please <a href="https://share.vidyard.com/watch/5vMMsxsZK6q48yNHsDTkPe" target="_blank" rel="noopener">visit this link</a>.</p>
PhageHostLearn - training and test data
<p>This Zenodo repository contains all the training and test data necessary to reproduce the analyses in our manuscript "<strong>P</strong><strong>rediction of <em>Klebsiella</em> phage-host specificity at the strain level</strong>", including raw genome sequences, processed phage RBPs and <em>Klebsiella</em> K-loci sequences and the phage-host interaction data.</p>
OpenAlex Topic Classification v1 Model Artifacts and Training Data
<p>This is all data used to train the topic classification model and also the model artifacts to deploy the model. Please see the github repo for more information:</p> <p>https://github.com/ourresearch/openalex-topic-classification</p>
Training data for 'Long non-coding RNAs (lncRNAs) annotation with FEELnc' tutorial (Galaxy Training Material)
<p>Data needed for the 'Long non-coding RNAs (lncRNAs) annotation with FEELnc' tutorial (Galaxy Training Material).<br>The assembly was generated following the 'Genome assembly using PacBio data' tutorial.<br>The annotation was generated following the 'Genome annotation with Funannotate ' tutorial.</p> <p>The bam file is RNASeq SRR8534859_1.fastq.gz and SRR8534859_2.fastq.gz mapping on the genome assembly.</p>
Data from: How many specimens make a sufficient training set for automated three dimensional feature extraction?
<p>Deep learning has emerged as a robust tool for automating feature extraction from 3D images, offering an efficient alternative to labour-intensive and potentially biased manual image segmentation methods. However, there has been limited exploration into the optimal training set sizes, including assessing whether artificial expansion by data augmentation can achieve consistent results in less time and how consistent these benefits are across different types of traits. In this study, we manually segmented 50 planktonic foraminifera specimens from the genus Menardella to determine the minimum number of training images required to produce accurate volumetric and shape data from internal and external structures. The results reveal unsurprisingly that deep learning models improve with a larger number of training images with eight specimens being required to achieve 95% accuracy. Furthermore, data augmentation can enhance network accuracy by up to 8.0%. Notably, predicting both volumetric and shape measurements for the internal structure poses a greater challenge compared to the external structure, due to low contrast differences between different materials and increased geometric complexity. These results provide novel insight into optimal training set sizes for precise image segmentation of diverse traits and highlight the potential of data augmentation for enhancing multivariate feature extraction from 3D images. </p>
TA B L E 1 Summary of model fit, based on the area under the curve (AUC) of the receiver operating characteristic (ROC) for training data, and the most important bioclimatic variables in past, present, and future (2070) Maxent models of 13 bat species included in this study. in Southern Africa's Great Escarpment as an amphitheater of climate-driven diversification and a buffer against future climate change in bats
TA B L E 1 Summary of model fit, based on the area under the curve (AUC) of the receiver operating characteristic (ROC) for training data, and the most important bioclimatic variables in past, present, and future (2070) Maxent models of 13 bat species included in this study.
STEMMUS SCOPE emulator train test example data of 2014
<div> <div>The "csv" file contains land-atmosphere variables and latent heat flux (LEtot) simulated by STEMMUS-SCOPE (soil-plant model), version 1.5.0, see GitHub repository <a href="https://github.com/EcoExtreML/STEMMUS_SCOPE" target="_blank" rel="noopener">STEMMUS-SCOPE</a>. The data spreads over 19 Fluxnet sites and for the year 2014 with hourly intervals. For more information see <a href="https://research-software-directory.org/projects/ecoextreml" target="_blank" rel="noopener">EcoExtreML project</a>.</div> <br> <div>This data was used as training data pairs to develop an emulator using a random forests regression algorithm, the "onnx" file. The target variable is "latent heat flux (LEtot)" and features are land-atmosphere variables. For more information about the emulator, see GitHub repository <a href="https://github.com/EcoExtreML/Emulator" target="_blank" rel="noopener">STEMMUS-SCOPE Emulator</a>.</div> <div> </div> <div>The model and data are used to create a tutorial on applying an explainability method, for example, Kernel SHAP using the package <a href="https://dianna.readthedocs.io/en/latest/" target="_blank" rel="noopener">DIANNA</a>. For more information see <a href="https://www.esciencecenter.nl/projects/deep-insight-and-neural-networks-analysis-dianna/" target="_blank" rel="noopener">Deep Insight and Neural Network Analysis (DIANNA) project</a>.</div> </div>
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.