Loading...
Loading...
Medical imaging (X-ray, CT, MRI), electronic health records, clinical trials, ECG/EEG, pathology
13,136 datasets
SATraj-OS is a large-scale dataset of graphical user interface (GUI) interaction trajectories for Computer-Using Agents (CUAs). The dataset is designed for both capability learning and safety training of agents that perform tasks like browsing websites, editing documents, and managing files. It was created by AI45Research and last updated on Hugging Face in April 2026.
JiaLong Wang's dataset contains plasma metabolomic and lipidomic profiles from a discovery cohort of 75 osteoporosis patients and 140 healthy controls, with validation in an independent cohort of 20 patients and 42 controls. Ultra-performance liquid chromatography-mass spectrometry (UPLC-MS) was used for non-targeted analysis, and random forest modeling was applied to identify differential metabolites. The data supports the development and validation of a diagnostic model for osteoporosis.
1488 successful agent rollouts from the moonshot/kimi-k2.5 model on the seta-env-v2 terminal-agent benchmark were distilled into this supervised fine-tuning dataset. The dataset, created by camel-ai and last updated on 2026-04-14, is tokenized with the Qwen/Qwen3-8B chat template and intended for AREAL FSDPLMEngine SFT training. Each row preserves the full per-trial diagnostic record from the build pipeline.
MERRA-2 provides a global atmospheric reanalysis from 1980 to the present with a latency of about three weeks. This collection, M2TMNPRAD, contains monthly mean assimilations of radiation diagnostics, such as cloud fraction for radiation and air temperature tendencies due to longwave and shortwave radiation, across 42 pressure levels. It is produced by NASA's Global Modeling and Assimilation Office using the Goddard Earth Observing System Model version 5.12.4.
MERRA-2 provides a 3D monthly mean assimilation of cloud diagnostics across 42 pressure levels, including updraft areal fraction and in-cloud liquid water mass. This dataset is produced by NASA's Global Modeling and Assimilation Office using the GEOS model and covers the period from 1980 to the present, with a latency of approximately three weeks.
MERRA-2 provides a global atmospheric reanalysis from 1980 to present, updated with a latency of approximately three weeks. This monthly mean collection includes meteorology diagnostics such as air temperature at multiple levels, wind components, sea level pressure, and total precipitable water vapor. It is produced by NASA's Global Modeling and Assimilation Office using the GEOS version 5.12.4 model.
MERRA-2 tavgM_2d_lnd_Nx provides monthly mean land surface diagnostics from NASA's global atmospheric reanalysis. The dataset covers 1980 to the present and is produced by NASA's Global Modeling and Assimilation Office using the GEOS model. Data latency is approximately three weeks after the end of each month.
M2TMNXINT is a monthly mean collection of vertically integrated water and energy diagnostics from NASA's MERRA-2 global atmospheric reanalysis. The dataset covers the period from 1980 to the present, produced by NASA's Global Modeling and Assimilation Office (GMAO) using the GEOS 5.12.4 model. Data has a latency of approximately three weeks after the end of each month.
MERRA-2 M2TMNXGLC provides monthly mean assimilated land ice surface diagnostics on a 0.625 x 0.5 degree global grid. NASA's Global Modeling and Assimilation Office (GMAO) produces this data using the GEOS model, covering the period from 1980 to the present with approximately three weeks latency.
MERRA-2 M2TMNXADG provides monthly mean, time-averaged 2D data on assimilated aerosol diagnostics. NASA's Global Modeling and Assimilation Office produced this dataset using the GEOS model, covering the period from 1980 to the present with approximately three weeks latency.
MERRA-2 instM_2d_int_Nx provides instantaneous, monthly mean, 2-dimensional vertically integrated atmospheric diagnostics from NASA's global reanalysis. The dataset covers the period from 1980 to the present, produced by NASA's Global Modeling and Assimilation Office using the GEOS model. It includes variables such as kinetic energy, virtual potential temperature, and total precipitable water components.
MERRA-2 provides a global atmospheric reanalysis from 1980 to the present, updated with a latency of about three weeks. NASA's Global Modeling and Assimilation Office produced this dataset using the Goddard Earth Observing System Model version 5.12.4. It consists of monthly mean assimilations of single-level meteorological diagnostics.
3385 point-like or extended X-ray sources were detected in the first 5.5 square degrees surveyed by the XMM-Newton Large-Scale Structure project. The catalog, created by NASA HEASARC in February 2008, provides main parameters like position, count rate, and source extent with associated likelihood values. Additional data products, including X-ray images and optical thumbnails, are available from the Milan XMM-LSS database.
FIB-SEM and X-ray micro-tomographic images of a wettability-altered carbonate rock sample before and after dissolution with reactive CO2-saturated brine at reservoir pressure and temperature conditions. The data were acquired by the British Geological Survey to investigate CO2 storage in depleted oil fields with oil-wet or mixed-wet conditions. A novel procedure of injecting oil after reactive transport revealed previously unidentified ghost regions of partially-dissolved rock grains.
Three repeat medical X-ray CT experiments at different flow rates capture steady-state core floods in a heterogeneous Bentheimer rock sample. The data includes raw and upscaled scans, MATLAB processing files for 3D saturation upscaling, and analytical model files for comparison with experimental results. The dataset was created by the British Geological Survey and last updated on 2026-04 09.
STHELAR (Spatial Transcriptomics and H&E histology for Large-scale Annotation Resource) is a multi-tissue dataset integrating high-resolution spatial transcriptomics data with Hematoxylin & Eosin (H&E) whole slide images. It provides detailed segmentation masks and cell-type annotations for developing models that predict cell types directly from histology. The dataset was authored by FelicieGS and a version containing 587,555 images was last updated on 2026-04-02.
A single-case medical report details a 39-year-old patient with a 14.3 cm ulcerated triple-negative breast cancer. The report, authored by Jie Tan and uploaded to figshare in March 2026, describes a multimodal treatment approach combining transarterial chemoembolization (TACE) with systemic nab-paclitaxel and the PD-1 inhibitor Toripalimab, resulting in a pathological complete response.
A 1.8 MB DOCX file published on figshare under CC-BY-4.0 license by David B. Langley, last updated March 17, 2026. The dataset likely contains tabular data related to the binding interactions between IGHV4–34 antibodies and foreign and self-glycans, providing insights into autoimmune cold agglutinin disease.
A 752 KB document authored by David B. Langley and last updated on March 17, 2026. It presents structural insights into the binding mechanism of IGHV4-34 antibodies to self and foreign glycans, focusing on the role of a hydrophobic patch in framework region 1. The analysis connects findings from HIV envelope glycoprotein studies to autoimmune conditions like cold agglutinin disease.
A survey of 127 psychotherapists with experience in eating disorder treatment, conducted by Armin Hartmann. The dataset captures therapist perspectives on patient characteristics, symptoms, and therapeutic challenges for cases they considered 'normal' and 'difficult'. The data was last updated on March 17, 2026.