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.
20
datasets available to search
ShareScore release 0.9.0
Dataset results
20 results for “generative deep models”
Data from: "Deep Generative Modeling of Periodic Variable Stars Using Physical Parameters"
<p>This dataset was used for the training of a conditioned Variational Autoencoder that generates physically informed light curves of periodic variable stars. The light curves correspond to data obtained from The Optical Gravitational Lensing Experiment (<a href="https://ui.adsabs.harvard.edu/abs/1992AcA....42..253U/abstract">OGLE</a>), while ancillary information was obtained from the Gaia Data Release 2 (<a href="https://ui.adsabs.harvard.edu/link_gateway/2016A&A...595A...1G/doi:10.1051/0004-6361/201629272">GAIA DR2</a>). This repository contains the preprocessed OGLE light curves and the GAIA measurements corresponding to each cross-matched source. We also provided a subsample of cross-matched sources that were carefully validated following several steps described in the companion article (paper reference).</p> <p>This dataset is realized in tandem with the corresponding <a href="https://github.com/jorgemarpa/PELS-VAE">GitHub</a> and <a href="https://arxiv.org/abs/2005.07773">article</a>.</p> <p> </p> <p> </p>
scGraph2Vec: a deep generative model for gene embedding augmented by Graph Neural Network and single-cell omics data
<p>This repository contains the training data and source code to reproduce the results of our paper:<br>scGraph2Vec: a deep generative model for gene embedding augmented by Graph Neural Network and single-cell omics data</p> <p>More description can be also found in GitHub (https://github.com/LPH-BIG/scGraph2Vec).</p>
Candidate compounds from the design of covalent Bruton's tyrosine kinase (BTK) inhibitors via focused deep generative modeling
<pre>A total of 1491 candidate inhibitors for covalent inhibition of BTK are deposited as SMILES strings together with 34 known covalent BTK inhibitors used to guide generative computational design. The study will be reported in a publication in Molecules under the authors' names.</pre>
Deep Generative Model Samples
<p>This dataset contains the main results of <em>Deep Generative Models for Galaxy Image Simulations</em> (Lanusse et al. 2020).</p> <p>It consists of tuples of postage stamps of HST/ACS COSMOS galaxies, corresponding parametric light profiles, and samples from a Deep Generative Model conditioned on size, magnitude, and redshift of the corresponding real galaxies. For each tuple, the dataset also contains morphological statitics computed on each stamp.</p> <p>The details of the creation of this dataset and how to use it to reproduce the plots of the paper can be found at https://github.com/McWilliamsCenter/deep_galaxy_models .</p>
Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery
<p>Understanding transcriptional responses to chemical perturbations is central to drug discovery, but exhaustive experimental screening of diseasecompound combinations is unfeasible. To overcome this limitation, here we introduce PRnet, a perturbation-conditioned deep generative model that predicts transcriptional responses to novel chemical perturbations that have never experimentally perturbed at bulk and single-cell levels. Evaluations indicate that PRnet outperforms alternative methods in predicting responses across novel compounds, pathways, and cell lines. PRnet enables gene-level response interpretation and in-silico drug screening for diseases based on gene signatures. PRnet further identifies and experimentally validates novel compound candidates against small cell lung cancer and colorectal cancer. Lastly, PRnet generates a large-scale integration atlas of perturbation profiles, covering 88 cell lines, 52 tissues, and various compound libraries. PRnet provides a robust and scalable candidate recommendation workflow and successfully recommends drug candidates for 233 diseases. Overall, PRnet is an effective and valuable tool for gene-based therapeutics screening.</p>
Deep learning generates custom-made logistic regression models for explaining how breast cancer subtypes are classified
<p>Breast cancer is the most frequently found cancer in women and the one most often subjected to genetic analysis. Nonetheless, it has been causing the largest number of women's cancer-related deaths. PAM50, the intrinsic subtype assay for breast cancer, is beneficial for diagnosis and stratified treatment but does not explain each subtype's mechanism. Nowadays, deep learning can predict the subtypes from genetic information more accurately than conventional statistical methods. However, the previous studies did not directly use deep learning to examine which genes associate with the subtypes. Ours is the first study on a deep-learning approach to reveal the mechanisms embedded in the PAM50-classified subtypes. We developed an explainable deep learning model called a point-wise linear model, which uses a meta-learning approach to generate a custom-made logistic regression model for each sample. Logistic regression is familiar to physicians and medical informatics researchers, and we can use it to analyze which genes are important for subtype prediction. The custom-made logistic regression models generated by the point-wise linear model for each subtype used the specific genes selected in other subtypes compared to the conventional logistic regression model: the overlap ratio is less than twenty percent. And analyzing the point-wise linear model's inner state, we found that the point-wise linear model used genes relevant to the cell cycle-related pathways. The results of this study suggest the potential of our explainable deep learning to play a vital role in cancer treatment.</p>
Benchmarking Study of Deep Generative Models for Inverse Polymer Design: Reinforcement Learning
<p>Well-trained models and generation results for reinforcement learning part of <a href="https://github.com/ytl0410/Polymer-Generative-Models-Benchmark">ytl0410/Polymer-Generative-Models-Benchmark: Well-trained models and generative outcomes for the paper "Benchmarking Study of Deep Generative Models for Inverse Polymer Design" (github.com)</a></p>
Data for HydrAMP - a deep generative model for antimicrobial peptide discovery
<ul> <li>data- training data for peptides < 25 AA (16.8 MB)</li> <li>models - checkpoints of HydrAMP, PepCVAE, and Basic models for every training epoch (466 MB)</li> <li>results - dumped generation results for every model. Required for running comparison notebooks (832 MB)</li> <li>wheels - custom TensorFlow packages (1 GB)</li> </ul> <p> </p>
DynamicBind: Predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model.
<p>test and training data.</p>
Data to publication "The performance of deep generative models for learning joint embeddings of single-cell multi-omics data"
<p>Joint embedding data to publication "The performance of deep generative models for learning joint embeddings of single-cell multi-omics data"</p> <p>Code available at https://github.com/MTreppner/multiomics_dgms</p>
Supplemental materials for AaceGEN: Attention Guided Adversarial Code Example Generation for Deep Code Models
Open the record for dataset details and reuse information.
Benchmarking Study of Deep Generative Models for Inverse Polymer Design: Generation Results
Open the record for dataset details and reuse information.
Deep Neural Models for Medical Concept Normalization in User-Generated Texts
<p>PsyTar folds used for experiments in the paper "Deep Neural Models for Medical Concept Normalization in User-Generated Texts" to be published at ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Student Research Workshop. </p> <p>All other datasets used in the paper can be found in the following places:</p> <p>Cadec random: https://zenodo.org/record/55013#.XPE1MC1eN24<br> Cadec custom: https://yadi.sk/d/GZoWm1wBxzyW_w</p> <p>SMM4H dataset: in the paper "Data and systems for medication-related text classification and concept normalization from Twitter: insights from the Social Media Mining for Health (SMM4H) - 2017 shared task"<br> <br> Bibtex:</p> <p>@inproceedings{miftahutdinov2019,<br> title = "Deep Neural Models for Medical Concept Normalization in User-Generated Texts",<br> author = "Miftahutdinov, Zulfat and Tutubalina, Elena",<br> booktitle = "Proceedings of {ACL} 2019, Student Research Workshop",<br> month = jul,<br> year = "2019",<br> address = "Florence, Italy",<br> publisher = "Association for Computational Linguistics",<br> }</p>
Supplemental Material for 'Deep Generative Models of Protein Structure Uncover Distant Relationships Across a Continuous Fold Space' and DeepUrfold
<p>Data provided for the paper Draizen, EJ, Veretnik, S, Mura, C, and Bourne, PE. "Deep Generative Models of Protein Structure Uncover Distant Relationships Across a Continuous Fold Space." <em>Nature Communications</em>, Aug. 2024.</p> <div> </div> <p> </p>
Survey2Survey: A deep learning generative model approach for cross-survey image mapping
<p>During the last decade, there has been an explosive growth in survey data and deep learning techniques, both of which have enabled great advances for astronomy. The amount of data from various surveys from multiple epochs with a wide range of wavelengths, albeit with varying brightness and quality, is overwhelming, and leveraging information from overlapping observations from different surveys has limitless potential in understanding galaxy formation and evolution. Synthetic galaxy image generation using physical models has been an important tool for survey data analysis, while deep learning generative models show great promise. In this paper, we present a novel approach for robustly expanding and improving survey data through cross survey feature translation. We trained two types of neural networks to map images from the Sloan Digital Sky Survey (SDSS) to corresponding images from the Dark Energy Survey (DES). This map was used to generate false DES representations of SDSS images, increasing the brightness and S/N while retaining important morphological information. We substantiate the robustness of our method by generating DES representations of SDSS images from outside the overlapping region, showing that the brightness and quality are improved even when the source images are of lower quality than the training images. Finally, we highlight several images in which the reconstruction process appears to have removed large artifacts from SDSS images. While only an initial application, our method shows promise as a method for robustly expanding and improving the quality of optical survey data and provides a potential avenue for cross-band reconstruction.</p><p>------------</p><p>This repository contains the image files from Survey2Survey: a deep learning generative model approach for cross-survey image mapping. Please cite https://arxiv.org/abs/2011.07124 if you use this data in a publication. For more information, contact Brandon Buncher at buncher2(at)illinois.edu</p><p><strong>--- Directory structure ---</strong></p><p>tutorial.ipynb demonstrates how to load the image files (uploaded here as tarballs). Images were obtained from the SDSS DR16 cutout server (https://skyserver.sdss.org/dr16/en/help/docs/api.aspx) and DES DR1 cutout server (https://des.ncsa.illinois.edu/desaccess/</p><ul><li>./sdss_train/ and ./des_train/ contain the original SDSS and DES images used to train the neural network (Stripe82)</li><li>./sdss_test/ and ./des_test/ contain the original SDSS and DES images used for the validation dataset (Stripe82)</li><li>./sdss_ext/ contain images from the external SDSS dataset (SDSS images without a DES counterpart, outside Stripe82)</li><li>./cae and ./cyclegan contain images generated by the CAE and CycleGAN, respectively. train_decoded/ and test_decoded/ contain the reconstructions of the images from the training dataset and test dataset, respectively. external_decoded/ contain the DES-like image reconstructions of SDSS objects from the external dataset (outside Stripe82).</li></ul>
Model runs generated by publication "Re-evaluating 14 C dating accuracy in deep-sea sediment archives"
<p>Model runs generated by following publication:</p> <p>B.C. Lougheed, P. Ascough, A. Dolman, L. Löwemark and B. Metcalfe, 2020. “Re-evaluating 14C dating accuracy in deep-sea sediment archives.” Geochronology, doi:10.5194/gchron-2019-10</p> <p>Contains .mat files that can be opened by the Matlab / Octave environment.</p>
Datasets accompanying Deep generative AI models analyzing circulating orphan non-coding RNAs enable accurate detection of early-stage non-small cell lung cancer
<p>These datasets accompany the manuscript "Deep generative AI models analyzing circulating orphan non-coding RNAs enable accurate detection of early-stage non-small cell lung cancer".</p> <p>The datasets include:</p> <ul> <li> <p><code>metadata.tsv.gz</code> Phenotype information of the samples</p> </li> <li> <p><code>mirna_counts.tsv.gz</code> MicroRNA count matrix (for data normalization)</p> </li> <li> <p><code>oncrna_counts.tsv.gz</code> oncRNA count matrix</p> </li> <li> <p><code>orion/</code> Ensemble of Orion models</p> </li> </ul>
DeepStruc: Towards structure solution from pair distribution function data using deep generative models
<p>XYZ files, PDF dataset and XGB model to use MetalFinder which is one of the baseline models in the paper.</p>
Results of differential expression analysis for the manuscript "N-of-one differential gene expression without control samples using a deep generative model"
<p>Output files for the differential gene expression analysis in the manuscript "N-of-one differential gene expression without control samples using a deep generative model". The zip file contains three folders with the results for DESeq2 and the DGD (named NB-GMM in the folders).</p><p>- The folder False_positives_Fig4B contains the results presented in figure 4B of the manuscript. The file False_positive_single_vs_all.csv contains the results for the one-vs-all experiments. The file False_positive_5_vs_all.csv contains the results for the 5-vs-all experiments.</p><p>- The folder enrichment_plots contains the results presented in figure 4C of the manuscript. Each subfolder (e.g. Basal, HER2E, LumA, LumB) contain the differential expression analysis results for each breast cancer subtype.</p><p>- The folder fig5 contains the results presented in figure 5 of the manuscript. The results for each cancer are presented in a folder.</p>
Deep learning models for generation of precipitation maps based on NWP Data
<p>Numpy arrays used in the paper "Deep learning models for generation of precipitation maps based on NWP".</p> <p>trn = training set<br> vld = validation set<br> tst = test set<br> x = COSMO-DE-EPS ensemble statistics<br> y = high definition radar precipitation<br> t = time<br> c = COSMO-DE-EPS precipitation prediction</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.