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.
9
datasets available to search
ShareScore release 0.9.0
Dataset results
9 results for “Geometric Deep Learning”
Classification of hierarchical text using geometric deep learning: the case of clinical trials corpus
<p>We consider the hierarchical representation of documents as graphs and use geometric deep learning to classify them into different categories. While graph neural networks can efficiently handle the variable structure of hierarchical documents using the permutation invariant message passing operations, we show that we can gain extra performance improvements using our proposed selective graph pooling operation that arises from the fact that some parts of the hierarchy are invariable across different documents. We applied our model to classify clinical trial (CT) protocols into completed and terminated categories. We use bag-of-words based as well as pre-trained transformer-based embeddings to featurize the graph nodes, achieving f1-scores $\simeq 0.85$ on a publicly available large scale CT registry of around 360K protocols. We further demonstrate how the selective pooling can add insights into the CT termination status prediction.</p>
Data from: Genome-scale annotation of protein binding sites via language model and geometric deep learning
<p>The dataset contains the training and test sets of protein binding sites with DNA, RNA, peptide, protein, ATP, HEM, Zn2+, Ca2+, Mg2+ and Mn2+. Each protein is associated with 3 lines indicating the protein name (PDB accession code and chain), sequence and residue labels (0 for non-binding and 1 for binding), respectively. The ESMFold-predicted structures are also provided.</p>
Geometric deep learning improves generalizability of MHC-bound peptide predictions
<p>Full dataset and trained models from the manuscript "<strong>Geometric deep learning improves generalizability of MHC-bound peptide predictions</strong>".</p> <p>"outputs_and-BA_data.zip" contains the networks' outputs for each cross-validation experiment and a "full_dataset.csv" containing the initial BA data.<br>Note: this file has been updated (2024/11/26) due to errors in generating some of the previous csvs. In the earlier version, both MLP and CNN outputs reported were wrong. The correct values are now reported in the updated csvs.</p> <p>"trained_models.zip" contains all the trained models parameters</p> <p>"propedia_ssl.zip" contains all the 3D models from propedia used to train the 3D-SSL</p> <p>"pdb.zip" contains 3D models generated in PANDORA and used to train CNN, GNN and EGNN. It amounts to 145665 .pdb files, one for each human binding affinity entry from the initial dataset from O'Donnell et al. The list of entries used to actually train networks after filtering can be found in outputs_and-BA_data.zip", in the "full_dataset.csv" file. </p> <p> </p> <p>CHANGELOG v4:</p> <p>- In outputs_and-BA-data.zip, updated CNN_AlleleClustered_test_crossval.csv and CNN_shuffled_test_crossval.csv. These file had the wrong IDs paired with the network outputs.The IDs and labels are now consistent with the outputs.</p> <p>- Updated reference from the preprint to the published article. </p> <p> </p>
GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts
<p>The following contains the datasets described in the paper: GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts, and the associated code can be found at https://github.com/Graph-COM/GDL_DS.</p>
GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts (Dataset 2)
<p>The following contains the datasets described in the paper: <strong>GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts</strong>, and the associated code can be found at <a href="https://github.com/Graph-COM/GDL_DS">https://github.com/Graph-COM/GDL_DS</a>. </p>
Chemperium database for: Geometric Deep Learning for Molecular Property Predictions with Chemical Accuracy Across Chemical Space
<p>The dataset and trained models for the submitted manuscript "Geometric Deep Learning for Molecular Property Prediction with Chemical Accuracy Across Chemical Space"</p> <p>The trained models can be used in combination with the predict module in github.com/mrodobbe/chemperium. More information in README.md.</p> <p><em>When using these datasets, refer directly to the manuscript: https://doi.org/10.1186/s13321-024-00895-0 </em></p>
Assemblies generated in the manuscript "Geometric deep learning framework for de novo genome assembly"
<p>Assemblies evaluated in the manuscript "Geometric deep learning framework for de novo genome assembly". All the assemblies were generated by us, except CHM13.ONT.Flye-2.9.fa.gz which was generated by <a href="https://www.nature.com/articles/s41587-019-0072-8">Kolmogorov et al. (2019)</a>.</p>
SpatPPI: a geometric deep learning model for predicting protein-protein interactions involving intrinsically disordered regions
Open the record for dataset details and reuse information.
A Deep Learning-Based and Fully Automated Pipeline for Thoracic Aorta Geometric Analysis and Planning for Endovascular Repair from Computed Tomography
<p>Full dataset of segmentations for both the thoracic artery and the proximal pulmonary arteries (format: standard NIfTI, nii) from Saitta S, Sturla F, Caimi A, Riva A, Palumbo MC, Nano G, Votta E, Corte AD, Glauber M, Chiappino D, Marrocco-Trischitta MM, Redaelli A. A Deep Learning-Based and Fully Automated Pipeline for Thoracic Aorta Geometric Analysis and Planning for Endovascular Repair from Computed Tomography. J Digit Imaging. 2022 Jan 26. doi: 10.1007/s10278-021-00535-1. Epub ahead of print. PMID: 35083618.</p> <p>Abstract</p> <p>Feasibility assessment and planning of thoracic endovascular aortic repair (TEVAR) require computed tomography (CT)-based analysis of geometric aortic features to identify adequate landing zones (LZs) for endograft deployment. However, no consensus exists on how to take the necessary measurements from CT image data. We trained and applied a fully automated pipeline embedding a convolutional neural network (CNN), which feeds on 3D CT images to automatically segment the thoracic aorta, detects proximal landing zones (PLZs), and quantifies geometric features that are relevant for TEVAR planning. For 465 CT scans, the thoracic aorta and pulmonary arteries were manually segmented; 395 randomly selected scans with the corresponding ground truth segmentations were used to train a CNN with a 3D U-Net architecture. The remaining 70 scans were used for testing. The trained CNN was embedded within computational geometry processing pipeline which provides aortic metrics of interest for TEVAR planning. The resulting metrics included aortic arch centerline radius of curvature, proximal landing zones (PLZs) maximum diameters, angulation, and tortuosity. These parameters were statistically analyzed to compare standard arches vs. arches with a common origin of the innominate and left carotid artery (CILCA). The trained CNN yielded a mean Dice score of 0.95 and was able to generalize to 9 pathological cases of thoracic aortic aneurysm, providing accurate segmentations. CILCA arches were characterized by significantly greater angulation (p = 0.015) and tortuosity (p = 0.048) in PLZ 3 vs. standard arches. For both arch configurations, comparisons among PLZs revealed statistically significant differences in maximum zone diameters (p < 0.0001), angulation (p < 0.0001), and tortuosity (p < 0.0001). Our tool allows clinicians to obtain objective and repeatable PLZs mapping, and a range of automatically derived complex aortic metrics.</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.