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.
43
datasets available to search
ShareScore release 0.9.0
Dataset results
43 results for “graph learning”
Graph Machine Learning Dataset SOA-SW
<p><strong>SOA-SW</strong> is a heterogeneous graph machine learning dataset based on the RDF knowledge graph <a href="doi.org/10.5281/zenodo.10299132">SemOpenAlex-SemanticWeb</a>.</p><p>SOA-SW contains six node types - works (95,575 nodes), authors (19,970 nodes), concepts (38,050 nodes), sources (10,739 nodes), institutions (5,846 nodes), and publishers (786 nodes), and seven edge types. </p><p>Each node has rich semantic node features as node representation (content-based and topology-based node features are available).</p><p>More information can be found in the README.txt and on <a href="https://github.com/davidlamprecht/AutoRDF2GML">https://github.com/davidlamprecht/AutoRDF2GML.</a></p><p> </p><p><strong>soa-sw-homogeneous-author</strong> only models the co-author network of SOA-SW.</p><p>It is a homogeneous graph containing the author node type (19,970 nodes) and the edge type author- author.</p><p>The authors' content-based features (nodes-nld) are based on the titles and abstracts of the authors' works (128-dimensional SciBERT embeddings).</p>
HAPPY: a deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images
<p>These two zipped folders contain all data necessary to train, validate and reproduce results from the paper.</p> <p>Unzipping the files will create 6 folders. Data from folders with the same name across both zips should be combined into one folder. The 'annotations' folder contains all ground truth annotations for training all three deep learning models. The 'datasets' folder contains images for training the nuclei localisation and cell classification models. The 'embeddings' folder contains cell embedding vectors and nuclei coordinates from two slides used to create nodes to train the graph tissue classification model. The 'graph_splits' folder contains regions defining the validation and test splits for the graph model. The 'slides' folder contains a sample region of a whole slide image as a .tiff file for running the inference demo. The 'trained_models' folder contains trained weights for each of the three models.</p> <p>Further instructions for dataset use and creation of custom datasets are available in the GitHub readme: https://github.com/Nellaker-group/happy.</p>
Datasets for "Physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data"
<div> <p>Datasets used for implementing the <a href="https://github.com/huankoh/PSICHIC">PSICHIC</a> experiments shown in the <a href="https://doi.org/10.1101/2023.09.17.558145">manuscript</a>.</p> <p> </p> </div>
Graph Machine Learning Dataset AIFB (AIFB-GML)
<p>AIFB-GML is a comprehensive, heterogeneous graph machine learning dataset derived from the <a href="https://figshare.com/articles/dataset/AIFB_DataSet/745364" target="_blank" rel="noopener">AIFB RDF knowledge graph</a>. This dataset integrates a variety of node types, including individuals (:person), research groups (:group), and scholarly publications (:publication).</p> <p>Developed using the innovative <a href="https://github.com/davidlamprecht/AutoRDF2GML" target="_new">AutoRDF2GML framework</a>, AIFB-GML is specifically formatted to facilitate graph-based tasks such as node classification and link prediction.</p>
Data for paper "Graph Deep Learning Model for Mapping Mineral Prospectivity"
<p>Four prospecting information, namely, NE- and NW- trending faults, Agno Batholithic pluton margins, and porphyry intrusive contacts for mineral prospectivity mapping in Baguio district, Philippines.</p>
Dataset & Code related to article 'Bilateral Adaptive Graph Convolutional Network on CT based COVID-19 Diagnosis with Uncertainty-Aware Consensus-Assisted Multiple Instance Learning'
<p>This record contains the 7768 lung masks <strong>manual annotations, implementation code, and pre-trained models</strong> related to the article 'Bilateral Adaptive Graph Convolutional Network on CT based COVID-19 Diagnosis with Uncertainty-Aware Consensus-Assisted Multiple Instance Learning'</p> <p>Also we include the visualised, selected top D reliable CT slices for all COVID-19 patients in the test dataset for better understanding. </p> <p>For the detailed usage of the data and code, please refer to https://github.com/smallmax00/BAGCN-Covid19</p> <p> </p>
OQM9HK: A Large-scale Graph Dataset for Machine Learning in Materials Science
<p>This is a large-scale graph dataset of materials science based on the Open Quantum Materials Database (OQMD) v1.5 .</p> <p><a href="https://storage.googleapis.com/rimcs_cgnn/oqm9hk_dataset_Sep_30_2022.pdf" target="_blank" rel="noopener">Technical Report</a></p> <p><a href="https://www.rimcs.co.jp" target="_blank" rel="noopener">RIMCS Website</a></p> <p><strong>Data Loading</strong></p> <p>A Python code example:</p> <pre><code>import sys sys.path.append('/your/path/to/data/OQM9HK_BEL') import OQM9HK bel_path='/your/path/to/data/OQM9HK_BEL' config = OQM9HK.load_config(path=bel_path) print(config['atomic_numbers']) split = OQM9HK.load_split(path=bel_path) print(len(split['train']), len(split['val']), len(split['test'])) graph_data = OQM9HK.load_graph_data(path=bel_path) name = next(iter(graph_data)) # Frist entry's name graph = graph_data[name] # Graph object print(graph.nodes) print(graph.edge_sources) print(graph.edge_targets) dataset = OQM9HK.load_targets(path=bel_path) # Pandas dataframe print(dataset) train_set = dataset.iloc[split['train']] val_set = dataset.iloc[split['val']] test_set = dataset.iloc[split['test']]</code></pre> <p> </p>
Graph Machine Learning Dataset LinkedMDB (LinkedMDB-GML)
<p>LinkedMDB-GML is a heterogeneous graph machine learning dataset based on the full RDF knowledge graph <a href="https://ceur-ws.org/Vol-538/ldow2009\_paper12.pdf" target="_blank" rel="noopener">LinkedMDB</a> (6.1 million RDF triples).</p> <p>LinkedMDB-GML contains node types, such as movies and related entities, such as actors and directors.</p> <p>LinkedMDB-GML was created with <a href="https://github.com/davidlamprecht/AutoRDF2GML" target="_blank" rel="noopener">AutoRDF2GML</a>.</p>
Spatial domains identification in spatial transcriptomics by domain knowledge-aware and subspace-enhanced graph contrastive learning
<p>We propose a graph contrastive learning framework, GRAS4T, which combines contrastive learning and subspace module to accurately distinguish different spatial domains by capturing tissue microenvironment through self-expressiveness of spots within the same domain. To uncover the pertinent features for spatial domain identification, GRAS4T employs a graph augmentation based on histological images prior, preserving information crucial for the clustering task. Experimental results on 8 ST datasets from 5 different platforms show that GRAS4T outperforms five state-of-the-art competing methods in spatial domain identification. Significantly, GRAS4T excels at separating distinct tissue structures and unveiling more detailed spatial domains. GRAS4T combines the advantages of subspace analysis and graph representation learning with extensibility, making it an ideal framework for ST domain identification.</p>
DrugBLIP: Exploring the Protein-Molecule Interaction Mechanisms with a Multi-task Learning Graph Transformer
Open the record for dataset details and reuse information.
Descriptor and Graph-based Molecular Representations in Prediction of Copolymer Properties using Machine Learning
<p>This dataset accompanies a study that investigates the use of machine learning (ML) approaches for predicting seven different physical properties of 140 binary copolymers. Two computational methods were employed: a random forest (RF) model based on molecular descriptors and a Graph Neural Network (GNN) using 2D polymer graphs. These methods were applied in both single- and multi-task settings to explore the strengths of each approach in capturing various polymer properties.</p> <p>The dataset includes two files:</p> <ol> <li> <p><strong>Dataset.xlsx</strong>: Contains the following information for each of the 140 copolymers:</p> <ul> <li>Polymer names</li> <li>SMILES notation of the monomers</li> <li>Fraction of monomers in each copolymer</li> <li>Simulated values (calculated using molecular dynamics simulation) and experimental values of various physical properties, including density, specific heat capacity at constant pressure ad volume ,radius of gyration, linear expansion coefficient, volume expansion coefficient, and bulk modulus .</li> </ul> </li> <li> <p><strong>Descriptors.xlsx</strong>: Provides the molecular descriptors calculated using PaDEL-Descriptor software, which were used as input for the RF model to predict polymer properties.</p> </li> </ol> <p>This work provides insight into the comparative strengths of descriptor- and graph-based representations in machine learning models for predicting material properties. It also highlights the importance of selecting appropriate molecular representations based on the nature of the properties being predicted.</p>
Linked Papers With Code: The Latest in Machine Learning as an RDF Knowledge Graph
<p><strong>Linked Papers With Code (LPWC)</strong> is an <strong>RDF knowledge graph </strong>that comprehensively models the research field of <strong>machine learning</strong>. It contains information about almost 400,000 machine learning <strong>publications</strong>, including the <strong>tasks</strong> addressed, the <strong>datasets</strong> utilized, the <strong>methods</strong> implemented, and the <strong>evaluations</strong> conducted, along with their <strong>results</strong>. The data set is based on <strong>Papers With Code</strong> and licensed under the CC BY-SA 4.0 license. Furthermore, we provide <strong>knowledge graph embeddings</strong> for entities and relations represented in LPWC.</p><p>More information can be found at <a href="https://linkedpaperswithcode.com/"><strong>https://linkedpaperswithcode.com/</strong></a> and in the ISWC'23 publication <a href="https://linkedpaperswithcode.com/"><strong>"</strong></a><a href="https://aifb.kit.edu/web/Inproceedings3993"><strong>Linked Papers With Code: The Latest in Machine Learning as an RDF Knowledge Graph".</strong></a></p>
Data for "Learning Collective Cell Migratory Dynamics from a Static Snapshot with Graph Neural Networks"
<p>This dataset contains snapshots of cell monolayers, represented as graphs, along with their corresponding average displacement measurements.</p>
Relevant Datasets and Software Used for Paper "KGML-xDTD: A Knowledge Graph-based Machine Learning Framework for Drug Treatment Prediction and Mechanism Description"
<p>This repository contains relevant datasets and software used in a paper "KGML-xDTD: A Knowledge Graph-based Machine Learning Framework for Drug Treatment Prediction and Mechanism Description". They are used to run the code of <em>KGML-xDTD </em>stored on <a href="https://github.com/chunyuma/KGML-xDTD">Github</a> and support the results of this paper.</p> <p><strong>About the datasets</strong></p> <p>1. <em>bkg_rtxkg2c_v2.7.3.tar.gz</em></p> <p>This tar.gz file contains three sub-folders: tsv_files, scripts, and relevant_dbs. The "tsv_files" sub-folder has the input files that the neo4j software uses. The "scripts" sub-folder contains a shell script with a relevant python script to construct the biomedical knowledge graph. The "relevant_dbs" sub-folder stores two auxiliary databases that <em>KGML-xDTD</em> needs to use. </p> <p>2. <em>indication_paths.yaml</em></p> <p>This file contains the <a href="https://sulab.github.io/DrugMechDB">DrugMechDB</a> MOA paths that we used to evaluate the predicted MOA paths by <em>KGML-xDTD. </em>It is downloaded from the official <a href="https://github.com/SuLab/DrugMechDB">GitHub repository</a> of DrugMechDB.</p> <p>3. <em>training_data.tar.gz</em></p> <p>This tar.gz file contains the processed training data of four data sources (e.g., <a href="https://mychem.info">MyChem</a>, <a href="https://lhncbc.nlm.nih.gov/ii/tools/SemRep_SemMedDB_SKR/SemMedDB_download.html">SemMedDB</a>, <a href="https://bioportal.bioontology.org/ontologies/NDFRT">NDF-RT</a>, <a href="https://unmtid-shinyapps.net/shiny/repodb/">RepoDB</a>) mentioned in the paper. These processed drug-disease pairs have been matched to the identifiers of biological entities used in our biomedical knowledge graph and respectively split into true positive (tp) sets and true negative (tn) sets. We also provide the names of these drug identifiers and disease identifiers under a sub-folder "translated _to_name".</p> <p><strong>About the software</strong></p> <p><em>neo4j-community-3.5.26.tar.gz</em></p> <p>This tar.gz is the Neo4j community version 3.5.26 downloaded from <a href="https://neo4j.com/download-center/#community">Neo4j Download Center</a>. Although the newer versions are available, due to their big changes in the Neo4j setting that are not compatible with our scripts on Github, we provide the version that we used in our research. If you would like to use the newer version, modifications to our script will be required to import the biomedical knowledge graph into your local Neo4j database with the new setting.</p>
Deep learning and knowledge graph powered drug combination discovery against infectious diseases
<p>The Datasets and source codes for paper "<strong>Deep learning and knowledge graph powered drug combination discovery against infectious diseases</strong>".</p>
Graph Contrastive Learning with Adversarial Structure Refinement (GCL-ASR)
Open the record for dataset details and reuse information.
Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning
Open the record for dataset details and reuse information.
Bottom-up Graph Representation Learning for Symbolic Expression Solving
Open the record for dataset details and reuse information.
Spatially resolved transcriptomics and graph-based deep-learning improve accuracy of routine CNS tumor diagnostics
<p><span>The diagnostic landscape of brain tumors has recently evolved to integrate comprehensive molecular markers alongside traditional histopathological evaluation. Foremost, genome-wide DNA methylation profiling and next generation sequencing (NGS) has become a cornerstone in classifying Central Nervous System (CNS) tumors, as recognized by its inclusion into the 2021 WHO classification. Despite its diagnostic precision, a limiting requirement for NGS and methylation profiling is sufficient DNA quality and quantity which restricts its feasibility, especially in cases with small biopsy samples or low tumor cell content, both frequent challenges in specimen of diffusely growing CNS lesions. Addressing these challenges, we demonstrate a application, namely <strong>NePSTA </strong>(<strong>Ne</strong>uro<strong>P</strong>athology <strong><em>S</em></strong><em>patial <strong>T</strong>ranscriptomic<strong> A</strong>nalysis</em>), which is capable of generating comprehensive morphological and molecular neuropathological diagnostics from single 5 µm tissue sections. Our framework employs 10x Visium spatial transcriptomics with graph neural networks for automated histological and molecular evaluations. Trained and evaluated across 130 patients with CNS malignancies and healthy donors across four medical centers, NePSTA<strong> </strong>integrates spatial gene expression data and inferred CNAs to predict tissue histology and methylation-based subclasses with high accuracy. Further, we demonstrate the ability to reconstruct immunohistochemistry and genotype profiling on single thin slides of minute tissue biopsies. Our approach has minimal tissue requirements, often inadequate for conventional molecular diagnostics, demonstrating the potential to transform neuropathological diagnostics and enhance tumor subtype identification with implications for fast and precise diagnostic work-up.</span></p>
MAG for Heterogeneous Graph Learning
<p>We provide an academic graph based on a snapshot of the <strong>Microsoft Academic Graph</strong> from <strong>26.05.2021.</strong> The Microsoft Academic Graph (MAG) is a large-scale dataset containing information about scientific publication records, their citation relations, as well as authors, affiliations, journals, conferences and fields of study. We acknowledge the Microsoft Academic Graph using the URI <a href="https://aka.ms/msracad">https://aka.ms/msracad</a>. For more information regarding schema and the entities present in the original dataset please refer to: <a href="https://docs.microsoft.com/en-us/academic-services/graph/reference-data-schema">MAG schema</a>. </p> <p><strong>MAG for Heterogeneous Graph Learning</strong><br> We use a recent version of MAG from May 2021 and extract all relevant entities to build a graph that can be directly used for heterogeneous graph learning (node classification, link prediction, etc.). The graph contains all English papers, published after 1900, that have been cited at least 5 times per year since the time of publishing. For fairness, we set a constant citation bound of 100 for papers published before 2000. We further include two smaller subgraphs, one containing <em>computer science</em> papers and one containing <em>medicine</em> papers. </p> <p><em><strong>Nodes and features</strong></em><br> We define the following nodes:</p> <ul> <li><strong>paper </strong>with mag_<em>id, graph_id, </em><em>normalized title</em>, <em>year of publication</em>, <em>citations </em>and a 128-dimension <em>title embedding </em>built using word2vec<br> No. of papers:<em> 5,091,690</em> (all), <em>1,014,769 </em>(medicine), <em>367,576 </em>(computer science);</li> <li><strong>author </strong>with mag_<em>id, graph_id, normalized name, citations</em><br> No. of authors: <em>6,363,201 </em>(all), <em>1,797,980 </em>(medicine), <em>557,078 </em>(computer science);</li> <li><strong>field </strong>with mag_<em>id, graph_id, level, citations </em>denoting the hierarchical level of the field where 0 is the highest-level (e.g. <em>computer science</em>)<br> No. of fields: <em>199,457 </em>(all), <em>83,970 </em>(medicine), <em>45,454 </em>(computer science);</li> <li><strong>affiliation </strong>with mag_<em>id, graph_id, citations</em><br> No. of affiliations: <em>19,421 </em>(all), <em>12,103 </em>(medicine), <em>10,139 </em>(computer science); </li> <li><strong>venue </strong>with mag_<em>id, graph_id, citations, type</em> denoting whether conference or journal<br> No. of venues: <em>24,608 </em>(all), <em>8,514 </em>(medicine), <em>9,893 </em>(computer science). </li> </ul> <p><em><strong>Edges</strong></em><br> We define the following edges:</p> <ul> <li><strong>author </strong><em>is_affiliated_with</em><strong> affiliation</strong><br> No. of author-affiliation edges: <em>8,292,253 </em>(all), <em>2,265,728 </em>(medicine), <em>665,931 </em>(computer science);</li> <li><strong>author </strong><em>is_first/last/other </em><strong>paper</strong><br> No. of author-paper edges: <em>24,907,473 </em>(all), <em>5,081,752 </em>(medicine), <em>1,269,485 </em>(computer science);</li> <li><strong>paper </strong><em>has_citation_to</em><strong> paper</strong><br> No. of author-affiliation edges: <em>142,684,074 </em>(all), <em>16,808,837 </em>(medicine), <em>4,152,804 </em>(computer science);</li> <li><strong>paper </strong><em>conference/journal_published_at</em><strong> venue</strong><br> No. of author-affiliation edges: <em>5,091,690 </em>(all), <em>1,014,769 </em>(medicine), <em>367,576 </em>(computer science);</li> <li><strong>paper </strong><em>has_field_L0/L1/L2/L3/L4</em><strong> field</strong><br> No. of author-affiliation edges: <em>47,531,366 </em>(all), <em>9,403,708 </em>(medicine), <em>3,341,395 </em>(computer science);</li> <li><strong>field</strong><em> is_in </em><strong>field</strong><br> No. of author-affiliation edges: <em>339,036 </em>(all), <em>138,304 </em>(medicine), <em>83,245 </em>(computer science);</li> </ul> <p>We further include a reverse edge for each edge type defined above that is denoted with the prefix <em>rev_ </em>and can be removed based on the downstream task. </p> <p><strong>Data structure</strong><br> The nodes and their respective features are provided as separate <em>.tsv</em> files where each feature represents a column. The edges are provided as a pickled python dictionary with schema:</p> <pre><code class="language-python">{target_type: {source_type: {edge_type: {target_id: {source_id: {time } } } } } }</code></pre> <p>We provide three compressed ZIP archives, one for each subgraph (all, medicine, computer science), however we split the file for the complete graph into 500mb chunks. Each archive contains the separate node features and edge dictionary.</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.