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”
Marine heatwave prediction using machine learning - Moana Project
<p>This datasets includes results of the PCA analysis used in the repository https://github.com/metocean/marineheatwave_ml_moana</p> <p> </p>
The dynamic matrix predicts population response to long-term experimental forest fragmentation
<div><strong>Context</strong></div> <div> </div> <div>Earth's forests are fragmented. Species' long-term persistence depends on their conservation in fragmented landscapes with remnants embedded in a matrix of human land use. This matrix influences species' persistence in fragments by determining their degree of isolation and the extent to which edge effects alter habitat. Matrix habitat is often dynamic, so its impact on persistence of remnant species changes over time.</div> <div> </div> <div><strong>Objectives</strong></div> <div> </div> <div>Previous research showed that the abundance response of predatory beetle species to matrix habitat predicted their response in fragments with a log-response ratio of about 0.5. When abundance declined in the matrix, there was a smaller but predictable decline in fragments. However, the predictive utility of a fragment:matrix log-response ratio needs testing with functionally different species, more detailed data, and a focus on mechanism.</div> <div> </div> <div><strong>Methods</strong></div> <div> </div> <div>In the Wog Wog habitat fragmentation experiment, we follow a detritivorous amphipod 27 years after forest fragmentation.</div> <div> </div> <div><strong>Results</strong></div> <div> </div> <div>The amphipod's response in habitat fragments was predicted by its response in the matrix with a log-response ratio of about 0.5, similar to predatory beetles. The amphipod's response was explained by its abiotic niche. The amphipod's short-term response did not predict its long-term response.</div> <div> </div> <div><strong>Conclusions</strong></div> <div> </div> <div>The log-response ratio might generalize across the invertebrate food web. For two groups within the Wog Wog experiment, a species' dynamic response in matrix habitat predicted its persistence in fragments. Future work should explore the generality of this finding. With knowledge of projected land use of matrix habitat, a species' matrix response could be used for management planning.</div>
Data from: The contributions of flower strips to wild bee conservation in agricultural landscapes can be predicted using pollinator habitat suitability models
<p>Sowing flower strips along field edges is a widely adopted method for conserving pollinating insects in agricultural landscapes. To maximize the effect of flower strips given limited resources, we need spatially explicit tools that can prioritize their placement, and for identifying plant species to include in seed mixtures.</p> <p>We sampled bees and plant species as well as their interactions in a semi-controlled field experiment with roadside/field edge pairs with/without a sown flower strip at 31 sites in Norway and used a regional spatial model of solitary bee species richness to test if the effect of flower strips on bee species richness was predictable from the modelled solitary bee species richness.</p> <p>We found that sites with flower strips were more bee species rich compared to sites without flower strips and that this effect was greatest in areas that the regional solitary bee species richness model had identified to be particularly important for bees. Spatial models revealed that even within small landscapes there were pronounced differences between field edges in the predicted effect of sowing flower strips.</p> <p>Of the plant species that attracted the most bee species, the majority mainly attracted bumblebees and only few species also attracted solitary bees. Considering both the taxonomic diversity of bees and the species richness of bees attracted by plants we suggest that seed mixes containing <em>Hieracium </em>spp. such as <em>Hieracium umbellatum </em>and <em>Pilosella officinarum</em>; <em>Taraxacum</em> spp; <em>Trifolium repens</em>;<em> Lotus corniculatus</em>; S<em>tellaria graminea</em>; and <em>Achillea millefolium</em> would provide resources for diverse bee communities in our region.</p> <p>Spatial prediction models of bee diversity can be used to identify locations where flower strips are likely to have the largest effect and can thereby provide managers with an important tool for prioritizing how funding for agri-environmental schemes such as flower strips should be allocated. Such flower strips should contain plant species that are attractive to both solitary and bumblebees, and do not need to be particularly plant species rich as long as the selected plants complement each other.</p>
Data from: Refuge-yeah or refuge-nah? Predicting locations of forest resistance and recruitment in a fiery world
<p>Climate warming, land use change, and altered fire regimes are driving ecological transformations that can have critical effects on Earth's biota. Fire refugia – locations that are disturbed less frequently or severely than their surroundings – may act as sites of relative stability during this period of rapid change by being resistant to fire and supporting post-fire recovery in adjacent areas. Because of their potential value to forest ecosystems, there is an urgent need to anticipate (1) where refugia are most likely to be found and (2) where they align with environmental conditions that support post-fire tree recruitment. Using biophysical predictors and patterns of burn severity from 1,180 recent fire events, we mapped the locations of potential fire refugia across upland conifer forests in the southwestern United States (US) (99,428 km2 of forest area), a region that is highly vulnerable to fire-driven transformation. We found that low pre-fire forest cover, flat slopes or topographic concavities, moderate weather conditions, spring-season burning, and areas affected by low- to moderate-severity fire within the previous 15 years were commonly associated with refugia. Based on current (i.e., 2021) conditions, we predicted that 67.6% and 18.1% of conifer forests in our study area would contain refugia under moderate and extreme fire weather, respectively. However, refugia were 36.4% (moderate weather) and 31.2% (extreme weather) more common across forests that experienced recent fires, as compared to recently unburned areas, supporting increased fire use during moderate weather and shoulder seasons to promote fire-resistant landscapes. When overlaid with models of tree recruitment, 23.2% (moderate weather) and 6.4% (extreme weather) of forests were classified as refugia with a high potential to support post-fire recruitment in the surrounding landscape. These locations may be disproportionately valuable for ecosystem sustainability, providing habitat for fire-sensitive species and maintaining forest persistence in an increasingly fire-prone world.</p>
Cold comfort: metabolic rate and tolerance to low temperatures predict latitudinal distribution in ants
<p class="MsoNormal"><span>Metabolic compensation has been proposed as a mean for ectotherms to cope with colder climates. For example, under the metabolic cold adaptation and the metabolic homeostasis hypotheses (MCA and MHH), it has been formulated that cold-adapted ectotherms should display both higher (MCA) and more thermally sensitive (MHH) metabolic rates (MRs) at lower temperatures. However, whether such compensation can truly be associated with distribution, and whether it interplays with cold-tolerance to support species' climatic niches, remains largely unclear despite broad ecological implications thereof. Here, we teased apart the relationship between MRs, cold-tolerance, and distribution, to test the MCA/MHH among 13 ant species. We report clear metabolic compensation effects, consistent with the MCA and MHH, where MR parameters strongly correlated with latitude and climatic factors across species' distributions. The combination of both cold-tolerance and MR further upheld the best predictions of species' climatic niches. To our knowledge, this is the first study showing that the association of metabolic data with cold-tolerance supports better predictive models of climatic temperature and distribution in social insects than models including cold-tolerance alone. </span><span>These results also highlight that adaptation to higher latitudes in ants involved adjustments of both cold-tolerance and MRs, <span>to</span><span> </span>allow this extremely successful group of insects to thrive under colder climates. </span></p>
Models and Data associated with: Single-cell gene expression prediction from DNA sequence at large contexts
<p>This archive holds trained models and associated data for the <a href="https://www.biorxiv.org/content/10.1101/2023.07.26.550634v1">manuscript</a>:<br> "Single-cell gene expression prediction from DNA sequence at large contexts"</p> <p>Structure:</p> <ul> <li>configs - example configs for the workflows to produce publication data </li> <li>data_* - pre-processed single cell data used for publication</li> <li>models_* - model checkpoints, hyperparameters and training progress in tensorboard logs</li> <li>preprocessing - additional data required to reproduce the pre-processing workflow</li> </ul> <p> </p> <p>"Copyright 2023 GlaxoSmithKline Research & Development Limited. All rights reserved."</p>
Prediction of Individual Autism Diagnostic Observation Schedule (ADOS) scores based on neural responses during live eye-to-eye contact
<p>Social difficulties are impactful in autism spectrum disorder (ASD), and links between these difficulties and underlying neural processes are active research questions. We present a multivariate classification method for neural data acquired from 36 participants during a live eye-to-eye contact task. Participants were either typically developed (TD) or diagnosed as ASD through gold-standard Autism Diagnostic Observation Schedule (ADOS) evaluation. We hypothesized multivariate classification could discriminate TD vs. ASD based on neural responses. Support vector machine (SVM) classification was able to discriminate between groups during the eye-contact interaction. In addition, it was found that underlying neural patterns contributing to binary classification also predicted measured ADOS scores with high correlation even though ADOS scores were not used for training. The correlation between observed and predicted ADOS scores was 0.72 (p < 0.002) for eye-to-eye contact. These findings suggest neural responses to live eye-to-eye contact are predictive of social symptomatology in ASD.</p>
Dataset of Numerical prediction of changes in atmospheric chemical compositions during a solar energetic particle event on Mars
<p>This dataset contains the input parameters and the simulated results used for figures in the paper "Numerical prediction of changes in atmospheric chemical compositions during a solar energetic particle event on Mars" by Y. Nakamura, F. Leblanc, N. Terada, S. Hiruba, I. Murata, H. Nakagawa, S. Sakai, S. Aoki, A. Piccialli, Y. Willame, L. Neary, A. C. Vandaele, K. Murase, and R. Kataoka.</p> <p>Detailed informations about the data files can be found in "README.txt".</p>
Improved Indian Ocean dipole seasonal prediction in the new generation of CMA prediction system
<p>Hindcast experiment Data for Liu et al. (2023), titled "Improved Indian Ocean dipole seasonal prediction in the new generation of CMA prediction system".</p>
The Magee 3 Equation Predicts Favorable Pathologic Response to Neoadjuvant Endocrine Therapy in Breast Cancer Patients
<p><strong>Supplementary Figure 1: </strong>Comparison between ROC curves of ME1, ME2, ME3, and MEm scores in a sample of breast cancer patients undergoing neoadjuvant endocrine therapy.</p> <p><strong>Supplementary Figure 2: </strong>ROC curves with their respective confidence intervals and AUC values in the sample of breast cancer patients, excluding those with clinical stage IA tumors. A: ME1. B: ME2. C: ME3. D: MEm.</p> <p><strong>Supplementary Figure 3:</strong> Comparison between ROC curves of ME1, ME2, ME3, and MEm scores in the sample of breast cancer patients undergoing neoadjuvant endocrine therapy (excluding those with clinical stage IA tumors).</p> <p> </p>
Datasets used in "Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications"
<p>The precipitation type (p-type) dataset (ptype.parquet) comprises observational weather reports sourced from the Meteorological Phenomena Identification Near the Ground (mPING) project, combined with corresponding numerical weather prediction data from the NOAA Rapid Refresh (RAP) model. These crowd-sourced mPING reports offer precipitation type labels (rain, snow, sleet, and freezing rain) across North America, while the RAP model provides atmospheric data, including temperature, humidity, and wind profiles, on pressure levels.</p> <p> </p> <p>The RAP data covers the contiguous United States (CONUS) from 2015 to 2022 on an hourly 13km grid. The mPING observations are matched to the nearest RAP grid cell and hour, allowing the two data sources to be merged into a labeled dataset suitable for classification tasks. </p> <p> </p> <p>The surface layer flux dataset (surface_layer.csv) contains high-frequency meteorological observations spanning from 2013 to 2015, collected at the Cabauw Experimental Site in the Netherlands. It includes measurements of various variables such as temperature, humidity, wind, radiation, and soil moisture, recorded every 10 minutes. The target output encompasses friction velocity, sensible heat, and latent heat.</p> <p><br> The code used for processing the datasets and training neural network models is available in the Miles-Guess repository (<a href="https://github.com/ai2es/miles-guess">https://github.com/ai2es/miles-guess</a>).</p>
Figure 1. Scatterplot of unstandardized predicted value of IHS4 and age split by sex.
<p>Unstandardized predicted value of IHS4 obtained from multiple linear regression with interaction between age and sex, adjusted for disease duration (b = 0.112, standard error = 0.055, p = 0.043).<br> IHS4: International hidradenitis suppurativa severity score system.</p>
Ensemble BLUP, Machine Learning, and Deep Learning Models Predict Maize Yield Better Than Each Model Alone.
<p>Data and scripts exploring ensembling strategies using the models developed in <a href="https://academic.oup.com/g3journal/advance-article/doi/10.1093/g3journal/jkad006/6982634">Kick et al., 2023</a> (see also <a href="https://zenodo.org/record/7401113">1</a>, <a href="https://zenodo.org/record/6916775">2</a>). Download all files to a single directory then run setup.sh or manually unzip using tar.</p> <p> </p> <table> <tbody> <tr> <td><strong>Filename</strong></td> <td><strong>Description</strong></td> </tr> <tr> <td>setup.sh</td> <td>Simple script that unzips zipped directories</td> </tr> <tr> <td>ext_data</td> <td>Reduced data from Kick et al. 2023</td> </tr> <tr> <td>ext_data_notebooks</td> <td>Contains python notebooks containing analysis and R markdown file containing visualization of results. Python and R data objects are written to allow results to be read in instead of re-generated.</td> </tr> <tr> <td>output</td> <td>Folder containing a placeholder file.</td> </tr> </tbody> </table> <p> </p> <p>This research used resources provided by the United States Department of Agriculture’s Agricultural Research Service (project number 5070-21000-041-000-D). The SCINet project of the USDA Agricultural Research Service (project number 0500-00093-001-00-D) was instrumental in the training of the models used in this work. In addition, we would like to acknowledge those presently and historically involved in generating data for the Genomes to Fields Initiative.</p> <p> </p> <p> </p> <p> </p>
Data Set for Enhanced Performance Prediction of ATL Model Transformations
<p>Model transformation languages are domain-specific languages, which are designed to comfortably define transformations. With the increasing use of transformations in various domains, the complexity and size of input models are also increasing. However, developers often lack suitable models for performance testing. We have therefore conducted experiments in which we predict the performance of model transformations based on characteristics of input models using machine learning approaches. In particular, we focused on how to predict the performance of transformations that also transform attributes whose values can have arbitrary size. This dataset contains our raw and processed input data, the scripts necessary to repeat our experiments, and the results we obtained.</p> <p>Our input data consists of the time measurements for six different transformations defined in the Atlas Transformation Language (ATL), as well as the collected characteristics of the real-world input models we used. In this data set, we provide the script that implements our experiments. We predict the execution time of ATL transformations using the machine learning approaches linear regression, random forests and support vector regression using a radial basis function kernel. We also investigate different sets of characteristics of input models as input for the machine learning approaches. These are described in detail in the provided documentation.pdf. The results of the experiments are provided as raw data in individual cvs files. Furthermore, we provide our Eclipse plugin, which collects the characteristics for a set of given models.</p> <p>A detailed documentation is available in documentaion.pdf.</p>
Functional traits and drought strategy predict leaf thermal tolerance
<p>Heat stress imposes an important physiological constraint on native plant species – one that will only worsen with human-caused climate change. Indeed, rising temperatures have already contributed to large-scale plant mortality events across the globe. These impacts may be especially severe in cities, where the urban heat island effect amplifies climate warming. Understanding how plant species will respond physiologically to rising temperatures and how these responses differ among plant functional groups is critical for predicting future biodiversity scenarios and making informed land management decisions. In this study, we evaluated the effects of elevated temperatures on a functionally and taxonomically diverse group of woody native plant species in a restored urban nature preserve in southern California using measurements of chlorophyll fluorescence as an indicator of leaf thermotolerance. Our aim was to determine if species' traits and drought strategies could serve as useful predictors of thermotolerance. We found that leaf thermotolerance differed among species with contrasting drought strategies, and several leaf-level functional traits were significant predictors of thermotolerance thresholds. Drought deciduous species with high specific leaf area, high rates of transpiration, and low water-use efficiency were the most susceptible to heat damage, while evergreen species with sclerophyllous leaves, high relative water content, and high water-use efficiency maintained photosynthetic function at higher temperatures. While these native shrubs and trees are physiologically equipped to withstand relatively high temperatures in this Mediterranean-type climate, hotter conditions imposed by climate change and urbanization may exceed the tolerance thresholds of many species. We show that leaf functional traits and plant drought strategies may serve as useful indicators of species' vulnerabilities to climate change, and this information can be used to guide restoration and conservation in a warmer world.</p>
Predicting school uptake of The Daily Mile in Northern Ireland- a data linkage study with School Census Data and Multiple Deprivation Measures
<p>The datasets for the research into the uptake of The Daily Mile in Northern Ireland- a data linkage study with School Census Data and Multiple Deprivation Measures. Questionnaires completed between 31st August 2022 and 16th December 2022. </p>
The Prognostic Value of COX-2 in Predicting Metastasis of Patients with Colorectal Cancer: A systematic review and meta analysis.
<p>The Prognostic Value of COX-2 in Predicting Metastasis of Patients with Colorectal Cancer: A systematic review and meta analysis.</p>
Alignment-based protein mutational landscape prediction: doing more with less
<div class="page"> <div class="layoutArea"> <div class="column"> <p>The wealth of genomic data has boosted the development of computational methods predicting the phenotypic outcomes of missense variants. The most accurate ones exploit multiple sequence alignments, which can be costly to generate. Recent efforts for democratizing protein structure prediction have overcome this bottleneck by leveraging the fast homology search of MMseqs2. Here, we show the usefulness of this strategy for mutational outcome prediction through a large-scale assessment of 1.5M missense variants across 72 protein families. Our study demonstrates the feasibility of producing alignment-based mutational landscape predictions that are both high-quality and compute-efficient for entire proteomes. We provide the community with the whole human proteome mutational landscape and simplified access to our predictive pipeline.</p> </div> </div> </div>
Lumped parameter liver simulation to predict acute hemodynamic alterations following partial resections (simulation data)
<p>This repository contains MATLAB .mat files containing simulation data reported in the manuscript "Lumped parameter liver simulation to predict acute hemodynamic alterations following partial resections" by Jeffrey Tithof, Timothy L. Pruett, and Joseph Sushil Rao (University of Minnesota). See the README file for details of which data set corresponds to which figure.</p>
Predictive neural computations in cerebellar circuits contribute to motor planning and faster behavioral responses in larval zebrafish
<p>This dataset contains raw and processed data along with jupyter notebooks to generate figures in Narayanan et al., 2023. Instructions for navigating through the dataset and for running the analysis codes are in README.pdf.</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.