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.
13,064
datasets available to search
ShareScore release 0.9.0
Dataset results
13,064 results for “predictions”
Calorimeter Dataset for NTK Predictions
Open the record for dataset details and reuse information.
Dataset supporting "Predictable Patterns of Seasonal Atmospheric River Variability Over North America During Winter"
<p>A dataset containing selected outputs from real time forecasts and hindcasts produced by the Seamless System for Prediction and Earth System Research (SPEAR). Variables in the dataset include atmospheric river frequency, surface temperature, 500 hPa geopotential height and precipitation. The period covers 1991 through 2023 averaged seasonally in the months December through February. Forecasts initialized in a given month "MM" are stored in subdirectories and files with the indicator "iMM," where MM varies from 03 to 12 (March through December). A pair of python scripts demonstrating average predictability time analysis are also included. This data is associated with the study "Predictable Patterns of Seasonal Atmospheric River Variability over North America during Winter," by Clark et al. </p>
FIGURE 4. Predicted secondary structure for D1–D1 in Aliterella shaanxiensis (Aliterellaceae), a new coccoid cyanobacterial species from China
FIGURE 4. Predicted secondary structure for D1–D1′ helix of 16S–23S rRNA intergenic spacer of three Aliterella strains. (a) A. antarctica CENA408T; (b) A. atlantica CENA595T; (c) A. shaanxiensis FACHB–2293.
FIGURE 5. Predicted secondary structure for Box-B in Aliterella shaanxiensis (Aliterellaceae), a new coccoid cyanobacterial species from China
FIGURE 5. Predicted secondary structure for Box-B helix of 16S–23S rRNA intergenic spacer of three Aliterella strains. (a) A. antarctica CENA408T; (b) A. atlantica CENA595T; (c) A. shaanxiensis FACHB–2293.
Predicted protein-protein interactions of the human tyrosine kinase Lck by AF2Complex
<p>Structural models and Supplementary data described in the publication:</p> <p>Predicting protein interactions of the kinase Lck critical to T cell modulation</p> <p>Structure (Cell Press), 2024</p> <p>Reference Authors: Mu Gao and Jeffrey Skolnick</p> <p><br>screening_results -- Virtual PPI screening results of the protein kinase Lck (SH3-SH2 domains as the bait).<br>predicted structural models.zip -- Compressed structural models described in the publication.<br>af2c_input_features -- Input features used to predict protein complex models with AF2Complex. </p>
Data for "Completing the speciation cycle: Ecological niches and traits predict local species coexistence in birds across the globe"
<p>These are files to replicate all analyses in our article:</p> <p>A data file in xlsx format.</p> <p>A phylogeny in nexus format.</p> <p>An R code for analyses.</p>
Data for National carbon footprint estimations of an electrified internet of energy with circular economy under future EV market share prediction in China
<p>This dataset is created for National carbon footprint estimations of an electrified internet of energy with circular economy under future EV market share prediction in China.</p> <p>The dataset includes the energy demand for buildings of each province in China, the Centralized and Distributed PV-battery system design of each province in China, The EV and ICEV carbon emission comparison of each province in China, the electricity price in China, The Carbon footprint and NPV calculation of current and future building-transportation system in China.</p>
Hydrograph and Recession Flows Predictions Simulations using Deep Learning: Watershed Uniqueness and Objective Functions
<p>This resource contains the results presented in the paper titled 'Hydrograph and Recession Flows Simulations using Deep Learning: Watershed Uniqueness and Objective Functions' by Abhinav Gupta and Sean McKenna.<span><span><br></span></span></p> <p>'</p>
Trained Surface Layer Models and Metrics for "Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications"
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>
Datasets for predicting river bakline using ML and ArcGIS
<p>These datasets are used for predicting the Padma River bankline using different machine learning models, where ArcGIS was integrated. The coordinates of the river bankline were recorded at every 400 meters for different years, using offsets of 400 meters. The coordinates, years, and locations served as input variables for the models.</p>
Exploring zero-shot structure-based protein fitness prediction
<p>This repository contains data used in Exploring zero-shot structure-based protein fitness<br>prediction.</p> <p>Directions to use this data can be found on <a href="https://github.com/gitter-lab/benchmarking-structure-based-models">our GitHub repository</a>.</p> <ol> <li><code>experimental_struct_artifacts</code> contains the experimentally determined structures for ProteinGym assays used in our analysis along with the reference file needed to generate ESM inverse folding predictions for these structures in ProteinGym.</li> <li><code>results</code> contains the prediction results obtained by running SSEmb on the 216 ProteinGym assays being considered in this study.</li> <li><code>test.tar.gz</code> contains all the structures from ProteinGym as well as MSAs generated using mmseqs2. To use this directory: <ul> <li>Setup SSEmb as directed in its <a href="https://github.com/KULL-Centre/_2023_Blaabjerg_SSEmb">repository</a></li> <li>Download this file and extract it in the data folder.</li> </ul> </li> </ol> <p> </p> <p> </p>
Data for "Understanding the drivers and predictability of record low Antarctic sea ice in austral winter 2023"
<p>Data for Figures 1 - 5 in "Understanding the drivers and predictability of record low Antarctic sea ice in austral winter 2023". Includes data for: CESM2-Nudge, ERA5, CESM2-REFORECAST-2023, CESM2-FORECAST-2024, and CESM2-NO-ENSO-NUDGE.</p>
Alphafold2_ab_initio iterative predictions for folding intermediate identification
<p>Iterative structure predictions for protein PDB ids starts from 6.</p>
Alphafold2_ab_initio iterative predictions for folding intermediate identification
<div>PDB ids start from 5 and 7.</div> <div> <div> <p> </p> </div> </div>
Alphafold2_ab_initio iterative predictions for folding intermediate identification
<p><span>Iterative structure predictions for protein PDB ids starts from 2.</span></p>
Dataset for the paper 'Predicting mechanical properties of polycrystalline nanopillars by interpretable machine learning'
<div> <div>This dataset contains the data produced for the above paper. The dataset consists of:</div> <div> </div> <div>- input nanopillars before deformation (molecular_dynamics/nanopillars)</div> <div>- stress-strain curves acquired by deforming the nanopillars (molecular_dynamics/stress_strain_curves)</div> <div>- weights of the CNNs trained to predict mechanical properties of the nanopillars (machine_learning/train_CNN)</div> <div>- Grad-CAM fields of the predictions (machine_learning/train_CNN)</div> <br> <div>Codes used for creating and analyzing the dataset are available at https://github.com/tekoivisto/nanopillar-ML</div> </div>
Morphological heart age from CTA: Predictions, Performance and Saliency Maps
<p>This data distribution contains regression results for age prediction from computed tomography angiography images from the SCAPIS dataset, as well as proof-of-concept experiments concerning the prediction of known volumetric features estimated through segmentation of the images.</p> <p>Each sub-folder represents one experiment.</p> <p>For each experiment (sex-stratified), there is a csv file '0.csv'<br>with the following structure</p> <p>Row 1: subject id1, subject id2, subject id3, ...<br>Row 2: reference value1, reference value2, reference value3, ...<br>Row 3: predicted value1, predicted value2, predicted value3, ...</p> <p>There is also a file 'results_summary.txt' which provides a text output of the quality measures corresponding to each experiment:<br>Mean Absolute Error (MAE)<br>R^2 (R2)<br>Pearson correlation (r_p)<br>Spearman correlation (r_s)<br>Intraclass Correlation Coefficient (ICC)</p> <p>The following sub-folders/experiments contain saliency maps:<br>- main (the main experiment with PCA from the whole heart)<br>- main_linear (the main experiment without PCA from the whole heart)<br>- poc_lvv (proof-of-concept: left ventricle volume)<br>- poc_rvv (proof-of-concept: right ventricle volume)<br>- poc_lav (proof-of-concept: left atrium volume)<br>- poc_rav (proof-of-concept: right atrium volume)<br>- poc_myov (proof-of-concept: myocardium volume)<br>- poc_av (proof-of-concept: aorta volume)</p> <p>The feature subsets use the following encoding (for the feature subset experiments, the path contains the numbers representing the included features):<br>1: Median Density<br>2: Median Volume<br>3: Stddev Density<br>4: Stddev Volume</p> <p>Ethics:<br>The subjects/images are all anonymized, with a chronological age rounded to whole months.</p> <p>Ethics approval was obtained from the Swedish Ethical Review Authority (Dnr 2022-07308-01) to conduct this research study related to human subjects, with associated sex and age information. All subjects provided informed written consent for their collected data to be used for research and for that research to be published. The study adheres to the Declaration of Helsinki. SCAPIS has been approved as a multicentre trial by the ethics committee at Umea University and adheres to the Declaration of Helsinki.</p>
Utilizing DNA pooling to predict cancer eye, ocular squamous cell carcinoma, in Hereford cattle
<p>Files include genotypes and dye intensity data from BovineHD bead array from a small closed population of Hereford cattle. 42 animals are individually genotyped and 10 pools of 50 animals are genotyped. Random regression of individual dye intensity data were regressed on pool data to estimate genetic connections between animals and pools. Covariances among animals for pool contributions were also estimated.</p>
Popularity Prediction in Anime with Deep Learning (with dataset)
<p>In the japanese anime industry, predicting whether an upcoming product will be popular is crucial. This paper introduces one of the most comprehensive free datasets for predicting anime popularity using only features accessible before huge investments, relying solely on freely available internet data and adhering to rigorous standards based on real-life experiences. To explore this dataset and its potential, a deep neural network architecture incorporating GPT-2 and ResNet-50 is proposed. The model achieved a best mean squared error (MSE) of 0.011, significantly surpassing a benchmark with traditional methods of 0.412, and a best root-square (R2) score of 0.187, outperforming the benchmark of −30.795. The aim of this study is to explore the scope and impact of features available before huge investments in relation to anime popularity. For that reason, and complementing the MSE and R2 metrics, Pearson and Spearman correlation coefficients are used. The best results, with Pearson at 0.436 and Spearman at 0.431, along with a well-fitted learning curves, suggests that while these features are relevant, they are not decisive for determining anime popularity and they likely interacts with additional features accessible after further investments. This is one of the first multimodal approaches to address this kind of tasks, aiming to support an entertainment industry by helping to avoid financial failures and guide successful production strategies.</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.