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.
35
datasets available to search
ShareScore release 0.9.0
Dataset results
35 results for “foundation models”
Orthrus: Towards Evolutionary and Functional RNA Foundation Models
<p>Orthrus is a mature RNA model for RNA property prediction. It uses a Mamba encoder backbone, a variant of state-space models specifically designed for long-sequence data, such as RNA.</p> <p> </p> <p>Two versions of Orthrus are available:</p> <ul> <li>4-track base version: Encodes the mRNA sequence with a simplified one-hot approach.</li> <li>6-track large version: Adds biological context by including splice site indicators and coding sequence markers, which is crucial for accurate mRNA property prediction such as RNA half-life, ribosome load, and exon junction detection.</li> </ul> <p>This repository contains the annotations used to train Orthrus, as well as processed datasets used to evaluate Orthrus's ability to perform RNA property prediction. The datasets are taken from the following sources:</p> <ul> <li>Protein Subcellular Localization: Thul, P. J. et al. A subcellular map of the human proteome. Science 356 (2017).</li> <li>Mean Ribosome Load: Sugimoto, Y. & Ratcliffe, P. J. Isoform-resolved mRNA profiling of ribosome load defines interplay of HIF and mTOR dysregulation in kidney cancer. Nature Structural Molecular Biology 29, 871–880 (2022).</li> <li>RNA Halflife: Agarwal, V. & Kelley, D. R. The genetic and biochemical determinants of mRNA degradation rates in mammals. Genome Biol 23, 245 (2022).</li> <li>GO Molecular Function: Consortium, T. G. O. et al. The Gene Ontology knowledgebase in 2023. Genetics 224, iyad031 (2023).</li> </ul> <p>Dataset files encode sequence using a one-hot encoding using the vocabulary: [A, C, G, T].</p>
Data from "Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis"
<p>This dataset includes the collected geoscientific data of<strong> lunar images, seismic data, and DAS arrays</strong>.</p> <p>It can be used to test the foundation model adaptation in the geophysical domain.</p> <p>Below are some brief desription of the datasets:</p> <p>1) Lunar images for<strong> crater detection<a href="https://moon.bao.ac.cn/">[CAS]</a></strong> : 1000 are used for training and 199 for testing, each with a size of 1022x1022.</p> <p>2) Seismic data for <strong>geobody identification<a href="https://kaggle.com/competitions/tgs-salt-identification-challenge">[TGS]</a></strong> : 3000 are used for training and 1000 for testing, each with a size of 224x224.</p> <p>3) Seismic data for <strong>facies classification<a href="https://www.aicrowd.com/challenges/seismic-facies-identification-challenge">[SEAM]</a></strong> : 250 are used for training and 45 for testing, each with a size of 1006x782.</p> <p>4) Seismic data for <strong>deep fault detection </strong>: 1081 are used for training and 269 for testing, each with a size of 896x896.</p> <p>5) DAS arrays for <strong>seismic event detection<a href="../records/8270895">[Biondi]</a></strong> : 115 are used for training and 28 for testing, each with a size of 512x512.</p> <p><strong>Tips: All the images are “float32” and the labels are "int8".</strong></p> <p>The test code has been published on GitHub: <strong><a href="https://github.com/ProgrammerZXG/Cross-Domain-Foundation-Model-Adaptation/">Cross-Domain-Foundation-Model-Adaptation</a></strong>.</p>
A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks
<p>Training and testing samples used for BME-X model: testing_data.hdf5, training_data.hdf5</p> <p>Templates for histogram matching before model testing: Template_T?_*.???</p> <p>Testing image: test_24m.???</p>
Dataset and Checkpoints of MolEdit: In-silico 3D Molecular Editing through Physics-Informed and Peference-Aligned Generative Foundation Models
<p>This repository hosts the pre-trained checkpoints and data utilized for the development of MolEdit. The corresponding research paper, titled "<em>In-silico</em> 3D Molecular Editing through Physics-Informed and Peference-Aligned Generative Foundation Models" (an early version is preprinted at <a href="doi.org/10.26434/chemrxiv-2023-j2n6l-v2">doi:10.26434/chemrxiv-2023-j2n6l-v2</a>) and the corresponding GitHub repository of <a href="https://github.com/issacAzazel/MolEdit">MolEdit</a> details the application and validation of these checkpoints and data. For further information, please refer to the README.md file contained within this repository.</p>
a Foundational Model for Cardiovascular Disease Diagnosis and Prediction
ClinicalTrials.gov study NCT06591923. IPD Sharing: NO. Countries: 1. Publications: 0.
Retrospective Pathology Foundation Models
ClinicalTrials.gov study NCT07239297. IPD Sharing: NO. Countries: 1. Publications: 0.
Prospective Pathology Foundation Models
ClinicalTrials.gov study NCT07157618. IPD Sharing: NO. Countries: 1. Publications: 0.
Quantifying Radiation-Induced Skin Reactions: Establishing the Foundation for Future Prediction Models
ClinicalTrials.gov study NCT06029231. IPD Sharing: Not stated. Countries: 1. Publications: 0.
A Vision-Language Foundation Model for Brain Disease Diagnosis From Multimodal Data
ClinicalTrials.gov study NCT07126821. IPD Sharing: NO. Countries: 1. Publications: 0.
Foundation Model for Post-MI Cardiovascular Event Alert Using Huawei Watch
ClinicalTrials.gov study NCT07395648. IPD Sharing: Not stated. Countries: 0. Publications: 0.
Research on the Development and Application of a Preoperative Assessment Model for Transcatheter Mitral Valve Edge-to-Edge Repair Based on Visual Foundation Models
ClinicalTrials.gov study NCT07247890. IPD Sharing: NO. Countries: 0. Publications: 0.
Validation of Whole Body PET/CT Foundation Model
ClinicalTrials.gov study NCT07196995. IPD Sharing: Not stated. Countries: 0. Publications: 0.
Establishing a Controlled Human Infection Model for Influenza H3N2 as a Foundation for Pandemic Preparedness
ClinicalTrials.gov study NCT07305207. IPD Sharing: NO. Countries: 0. Publications: 0.
A visual–omics foundation model to bridge histopathology image with transcriptomics
GEO Series GSE293199. Homo sapiens. 1 samples. Type: Other.
A long context RNA foundation model for predicting transcriptome architecture
GEO Series GSE280041. Homo sapiens. 104 samples. Type: Expression profiling by high throughput sequencing.
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.