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.
136
datasets available to search
ShareScore release 0.9.0
Dataset results
136 results for “Diffusion models”
Sampled Structures from Diffusion Models for Protein SHAPES
<p>Data associated with SHAPES (Structural and Hierarchical Assessment of Proteins with Embedding Similarity)</p> <ul> <li><code>rmsd.tar.gz</code> : RMSD and TM scores of ESMFold predicted structures with original designed backbones.</li> <li><code>mpnn.tar.gz</code> : ProteinMPNN designed sequences.</li> <li><code>raster.tar.gz</code> : CATH and sampled structures annotated with the grid square label after rasterization. Also includes the specific structures which are displayed in the raster plots.</li> <li><code>dssp.tar.gz</code> : Secondary structure frequences computed by DSSP.</li> <li><code>samples.tar.gz</code> : All sampled structures.</li> </ul> <p>Due to size, the ESMFold predicted structures for eight ProteinMPNN-designed sequences per sampled backbone are not included.</p> <p> </p> <p>Code: <code>proteinshapes-main.zip</code></p>
Simulation results of the technology diffusion model for electrolysis capacity
<p>This upload contains the pre-run simulation output of the technology diffusion model for the article:</p> <p>Odenweller, A., Ueckerdt, F., Nemet, G. F., Jensterle, M., and Luderer, G.: "Probabilistic feasibility space of scaling up green hydrogen supply".</p> <p>You may use the files to run the model code (available on GitHub) in reproduction mode, which reproduces all figures of the article without having to run the time-consuming simulation yourself. All files are provided in the rds format.</p> <p>Contents of this upload:</p> <ul> <li>01_conventional_growth_parameters.rds - Parameters of the distributions in the conventional growth case</li> <li>02_conventional_growth_sample.rds - Sample of the distributions in the conventional growth case</li> <li>03_conventional_growth_results.rds - Simulation results of model in the conventional growth case</li> <li>04_unconventional_growth_parameters.rds - Parameters of the distributions in the unconventional growth case</li> <li>05_unconventional_growth_sample.rds - Sample of the distributions in the unconventional growth case</li> <li>06_unconventional_growth_results.rds - Simulation results of model in the unconventional growth case</li> </ul>
Li diffusion modelling
<p>Data from Li diffusion modelling with QENS using different Li diffusion coeff sources</p>
Single-molecule tracking of Nodal and Lefty in live zebrafish embryos supports hindered diffusion model
<p><span>The hindered diffusion model postulates that the movement of a signaling molecule through an embryo is affected by tissue geometry and binding-mediated hindrance, but these effects have not been directly demonstrated <em>in vivo</em>. Here, we visualize extracellular movement and binding of individual molecules of the activator-inhibitor signaling pair Nodal and Lefty in live developing zebrafish embryos using reflected light-sheet microscopy. We observe that diffusion coefficients of molecules are high in extracellular cavities, whereas mobility is reduced and bound fractions are high within cell-cell interfaces. Counterintuitively, molecules nevertheless accumulate in cavities, which we attribute to the geometry of the extracellular space by agent-based simulations. We further find that Nodal has a larger bound fraction than Lefty and shows a binding time of tens of seconds. Together, our measurements and simulations provide direct support for the hindered diffusion model and yield insights into the nanometer-to-micrometer-scale mechanisms that lead to macroscopic signal dispersal.</span></p>
Pore network modeling as a new tool for determining gas diffusivity in peat
<p>The data and scripts are related to the manuscript “Pore network modeling as a new tool for determining gas diffusivity in peat” by Petri Kiuru, Marjo Palviainen, Arianna Marchionne, Tiia Grönholm, Maarit Raivonen, Lukas Kohl, and Annamari (Ari) Laurén submitted to Biogeosciences. The folder structure is similar to the one in the package “Peat macropore networks – new insights into episodic and hotspot methane emission” <a href="https://doi.org/10.5281/zenodo.6327112">https://doi.org/10.5281/zenodo.6327112</a>, and the remaining required data files can be found there.</p>
Fairness in Diffusion Recommender Models: Insights from an Empirical Study of DiffRec
<p>Dataset for the experiments of the paper submission `Fairness in Diffusion Recommender Models: Insights from an Empirical Study of DiffRec`. The included datasets are Foursquare Tokyo (FKTY), MovieLens 1M with all attributes and users (ML1M).</p>
A Unified Theoretical Framework for the Synergistic Integration of Transformers and Diffusion Models
<p>This paper introduces a novel, comprehensive theoretical framework for the synergistic integration of Transformer and Diffusion models, two paradigms that have independently revolutionized machine learning. We establish a fundamental correspondence between these models through a unified representation and a generalized dynamics equation, bridging the gap between their seemingly disparate architectures. Our key contributions include:</p> <p>(1) A unified mathematical formulation that encapsulates both Transformer and Diffusion processes;</p> <p>(2) A novel Diffusion-Enhanced Attention mechanism that incorporates Diffusion dynamics into Transformer attention;</p> <p>(3) Rigorous theoretical analyses including convergence guarantees, generalization bounds, and sample efficiency proofs for the integrated model.</p> <p>We provide detailed mathematical derivations and empirical validations across various tasks, demonstrating significant improvements over standalone models and existing hybrid approaches. This work lays the foundation for a new class of AI models that leverage the strengths of both paradigms, potentially leading to more powerful, efficient, and versatile AI systems. Our framework opens up new avenues for research in areas such as enhanced language modeling, advanced image generation, and multi-modal learning, paving the way for the next generation of AI technologies.</p>
His-MMDM: Multi-domain and Multi-omics Translation of Histopathology Images with Diffusion Models
<p>partab of His-MMDM: Multi-domain and Multi-omics Translation of Histopathology Images with Diffusion Models</p>
2000-2002 Dataset [1/7] for the models trained and tested in the paper 'Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy'
<p>This repository contains part 1/7 of the full dataset used for the models of the <a href="https://arxiv.org/abs/2406.13627">preprint</a> "Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy". </p> <p>This dataset comprises 3 years of normalized hourly data for both low-resolution predictors [16 km] and high-resolution target variables [2km] (2mT and 10-m U and V), from 2000-2002. Low-resolution data are preprocessed ERA5 data while high-resolution data are preprocessed VHR-REA CMCC data. Details on the performed preprocessing are available in the paper.</p> <p>This part 1/7 of the dataset also includes files related to metadata, static data, normalization, and plotting.</p> <p>To use the data, clone the corresponding <a href="https://github.com/DSIP-FBK/DiffScaler">repository</a>, unzip this zip file in the data folder, and download from Zenodo the other parts of the dataset listed in the related works.</p>
2009-2011 Dataset [4/7] for the models trained and tested in the paper 'Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy'
<p>This repository contains part 4/7 of the full dataset used for the models of the <a href="https://arxiv.org/abs/2406.13627">preprint</a> "Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy". </p> <p>This dataset comprises 3 years of normalized hourly data for both low-resolution predictors [16 km] and high-resolution target variables [2km] (2mT and 10-m U and V), from 2009-2011. Low-resolution data are preprocessed ERA5 data while high-resolution data are preprocessed VHR-REA CMCC data. Details on the performed preprocessing are available in the paper.</p> <p>To use the data, clone the corresponding <a href="https://github.com/DSIP-FBK/DiffScaler">repository</a>, unzip this zip file in the data folder, and download from Zenodo the other parts of the dataset listed in the related works.</p>
2012-2014 Dataset [5/7] for the models trained and tested in the paper 'Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy'
<p>This repository contains part 5/7 of the full dataset used for the models of the <a href="https://arxiv.org/abs/2406.13627">preprint</a> "Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy". </p> <p>This dataset comprises 3 years of normalized hourly data for both low-resolution predictors [16 km] and high-resolution target variables [2km] (2mT and 10-m U and V), from 2012-2014. Low-resolution data are preprocessed ERA5 data while high-resolution data are preprocessed VHR-REA CMCC data. Details on the performed preprocessing are available in the paper.</p> <p>To use the data, clone the corresponding <a href="https://github.com/DSIP-FBK/DiffScaler">repository</a>, unzip this zip file in the data folder, and download from Zenodo the other parts of the dataset listed in the related works.</p>
2015-2017 Dataset [6/7] for the models trained and tested in the paper 'Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy'
<p>This repository contains part 6/7 of the full dataset used for the models of the <a href="https://arxiv.org/abs/2406.13627">preprint</a> "Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy". </p> <p>This dataset comprises 3 years of normalized hourly data for both low-resolution predictors [16 km] and high-resolution target variables [2km] (2mT and 10-m U and V), from 2015-2017. Low-resolution data are preprocessed ERA5 data while high-resolution data are preprocessed VHR-REA CMCC data. Details on the performed preprocessing are available in the paper.</p> <p>To use the data, clone the corresponding <a href="https://github.com/DSIP-FBK/DiffScaler">repository</a>, unzip this zip file in the data folder, and download from Zenodo the other parts of the dataset listed in the related works.</p>
2006-2008 Dataset [3/7] for the models trained and tested in the paper 'Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy'
<p>This repository contains part 3/7 of the full dataset used for the models of the <a href="https://arxiv.org/abs/2406.13627">preprint</a> "Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy". </p> <p>This dataset comprises 3 years of normalized hourly data for both low-resolution predictors [16 km] and high-resolution target variables [2km] (2mT and 10-m U and V), from 2006-2008. Low-resolution data are preprocessed ERA5 data while high-resolution data are preprocessed VHR-REA CMCC data. Details on the performed preprocessing are available in the paper.</p> <p>To use the data, clone the corresponding <a href="https://github.com/DSIP-FBK/DiffScaler">repository</a>, unzip this zip file in the data folder, and download from Zenodo the other parts of the dataset listed in the related works.</p>
2003-2005 Dataset [2/7] for the models trained and tested in the paper 'Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy'
<p>This repository contains part 2/7 of the full dataset used for the models of the <a href="https://arxiv.org/abs/2406.13627">preprint</a> "Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy". </p> <p>This dataset comprises 3 years of normalized hourly data for both low-resolution predictors [16 km] and high-resolution target variables [2km] (2mT and 10-m U and V), from 2003-2005. Low-resolution data are preprocessed ERA5 data while high-resolution data are preprocessed VHR-REA CMCC data. Details on the performed preprocessing are available in the paper.</p> <p>To use the data, clone the corresponding <a href="https://github.com/DSIP-FBK/DiffScaler">repository</a>, unzip this zip file in the data folder, and download from Zenodo the other parts of the dataset listed in the related works.</p>
Masked Conditional Diffusion Model with GNN for Spatial Transcriptomics Data Imputation
Open the record for dataset details and reuse information.
Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
<p>We have provided some fine-tuned model checkpoints and datasets to help readers reproduce the experiments presented in the paper.</p>
Intravoxel incoherent motion model of diffusion weighted imaging and diffusion kurtosis imaging in differentiating of local colorectal cancer recurrence from scar/fibrosis tissue by multivariate logistic regression analysis
<p>We uploaded mean of diffusion coefficient (MD) and mean of diffusional Kurtosis values of 56 patients related to the manuscript: Fusco, Roberta, Vincenza Granata, Mario Sansone, Robert Grimm, Paolo Delrio, Daniela Rega, Fabiana Tatangelo, Antonio Avallone, Nicola Raiano, Giuseppe Totaro, Vincenzo Cerciello, Biagio Pecori, and Antonella Petrillo. 2020. "Intravoxel Incoherent Motion Model of Diffusion Weighted Imaging and Diffusion Kurtosis Imaging in Differentiating of Local Colorectal Cancer Recurrence from Scar/Fibrosis Tissue by Multivariate Logistic Regression Analysis" Applied Sciences 10, no. 23: 8609. https://doi.org/10.3390/app10238609</p>
On the importance of using event-specific wave pitch angle diffusion rates in modeling diffuse electron precipitation
<p>These are simulation results from running RAM-SCB and GLOW models. Two simulations were conducted. One uses diffusion coefficients derived based on statistical wave properties ("stat"), and the other uses coefficients from event-specific simultaneous wave properties ("event"). Data include the precipitating electron flux, wave diffusion coefficients, and height profiles of ionospheric electron density.</p>
Precise measurements of chromatin diffusion dynamics by modeling using Gaussian processes (Inter-Mito)
<p>Microscopy movies corresponding to interphase and mitotic cells in publication (add DOI when available).</p>
Precise measurements of chromatin diffusion dynamics by modeling using Gaussian processes (code)
<p>GP-FBM and GP-Tool codes and algorithms as in publication day. For updated version: https://github.com/guilmont/GP-Tool</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.