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.
171
datasets available to search
ShareScore release 0.9.0
Dataset results
171 results for “Performance prediction”
Do the predicted suitability scores from species distribution models correlate with species performance on-ground?
Open the record for dataset details and reuse information.
Data from: Behavioural hypervolumes of spider communities predict community performance and disbandment
Open the record for dataset details and reuse information.
Data from: Divergence in pollen performance between Clarkia sister species with contrasting mating systems supports predictions of sexual selection
Open the record for dataset details and reuse information.
Data from: Variation in host plant usage and diet breadth predict sibling preference and performance in the neotropical tortoise beetle Chelymorpha alternans (Coleoptera: Chrysomelidae: Cassidinae)
Open the record for dataset details and reuse information.
Data from: Towards a predictive framework for biocrust mediation of plant performance: a meta-analysis
Open the record for dataset details and reuse information.
Performance Curves for better Performance Predictions of Parallel Applications in Multicore Environments
<p><br> Model-based performance prediction for parallel applications on architectural models suffers from significant inaccuracies. <br> A major reason is that current model-based performance prediction approaches consider CPU speed as a single metric for multicore performance. </p> <p>Thus, in this paper, we investigate performance-influencing factors for multicore environments, execute extensive experiments to determine their impact on the performance, and extract performance curves for characteristic behaviours.</p> <p>As a result, we present a set of performance curves to software engineers which enables them to increase the performance prediction power in an easy to use manner. <br> Further, we evaluate the approach using 13 SPEC Benchmarks and could show that our approach reduces the prediction error by up to 60% and increases the accuracy by up to 98% for certain scenarios. </p>
Identification and validation of 174 COVID‑19 vaccine candidate epitopes reveals low performance of common epitope prediction tools
<p>Datasets used in "Identification and validation of 174 COVID‑19 vaccine candidate epitopes reveals low performance of common epitope prediction tools"</p> <p>sars-cov-2_predicted.csv</p> <p>SARS-CoV-2 peptides predicted to be binders to 11 HLA alleles by the NetMHC suite tools, these selected peptides have been measured in a stability assay revealing SARS-CoV-2 epitopes (assay results can be found at: https://www.immunitrack.com/free-coronavirus-report-for-download/). </p> <p>tools_predictions_binders.xlsx</p> <p>File containing all predictions for tools tested in the benchmark (note that not all tools use same measure). List of binders (epitopes) with IEDB links and T cell studies overlap.</p>
Data from: Evaluating predictive performance of statistical models explaining wild bee abundance in a mass-flowering crop
<p>Wild bee populations are threatened by current agricultural practices in many parts of the world, which may put pollination services and crop yields at risk. Loss of pollination services can potentially be predicted by models that link bee abundances with landscape-scale land-use, but there is little knowledge on the degree to which these statistical models are transferable across time and space. This study assesses the transferability of models for wild bee abundance in a mass-flowering crop across space (from one region to another) and across time (from one year to another). The models used existing data on bumblebee and solitary bee abundance in winter oilseed rape fields, together with high-resolution land-use crop-cover and semi-natural habitats data, from studies conducted in five different regions located in four countries (Sweden, Germany, Netherlands, and the UK), in three different years (2011, 2012, 2013). We developed a hierarchical model combining all studies and evaluated the transferability using cross-validation. We found that both the landscape-scale cover of mass-flowering crops and permanent semi-natural habitats, including grasslands and forests, are important drivers of wild bee abundance in all regions. However, while the negative effect of increasing mass-flowering crops on the density of the pollinators is consistent between studies, the direction of the effect of semi-natural habitat is variable between studies. The transferability of these statistical models is limited, especially across regions, but also across time. Our study demonstrates the limits of using statistical models in conjunction with widely available land-use crop-cover classes for extrapolating pollinator density across years and regions, likely in part because input variables such as cover of semi-natural habitats poorly capture variability in pollinator resources between regions and years.</p>
Data from: Predicting classifier performance with limited training data: applications to computer-aided diagnosis in breast and prostate cancer
Clinical trials increasingly employ medical imaging data in conjunction with supervised classifiers, where the latter require large amounts of training data to accurately model the system. Yet, a classifier selected at the start of the trial based on smaller and more accessible datasets may yield inaccurate and unstable classification performance. In this paper, we aim to address two common concerns in classifier selection for clinical trials: (1) predicting expected classifier performance for large datasets based on error rates calculated from smaller datasets and (2) the selection of appropriate classifiers based on expected performance for larger datasets. We present a framework for comparative evaluation of classifiers using only limited amounts of training data by using random repeated sampling (RRS) in conjunction with a cross-validation sampling strategy. Extrapolated error rates are subsequently validated via comparison with leave-one-out cross-validation performed on a larger dataset. The ability to predict error rates as dataset size increases is demonstrated on both synthetic data as well as three different computational imaging tasks: detecting cancerous image regions in prostate histopathology, differentiating high and low grade cancer in breast histopathology, and detecting cancerous metavoxels in prostate magnetic resonance spectroscopy. For each task, the relationships between 3 distinct classifiers (k-nearest neighbor, naive Bayes, Support Vector Machine) are explored. Further quantitative evaluation in terms of interquartile range (IQR) suggests that our approach consistently yields error rates with lower variability (mean IQRs of 0.0070, 0.0127, and 0.0140) than a traditional RRS approach (mean IQRs of 0.0297, 0.0779, and 0.305) that does not employ cross-validation sampling for all three datasets.
Data Set for Predicting the Performance of ATL Model Transformations Based on Generated Models
<p>Predicting the execution time of model transformations can help to understand how a transformation reacts to a given input model without creating and transforming the respective model.</p> <p>In our previous data set (https://doi.org/10.5281/zenodo.8385957), we have documented our experiments in which we predict the performance of ATL transformations using predictive models obtained from training linear regression, random forest and support vector regression. As input for the prediction, our approach uses a characterization of the input model. In these experiments, we only used data from real models.</p> <p>However, a common problem is that transformation developers do not have enough models available to use such a prediction approach. Therefore, in a new variant of our experiments, we investigated whether the three considered machine learning approaches can predict the performance of transformations if we use data from generated models for training. We also investigated whether it is possible to achieve good predictions with smaller training data. The dataset provided here offers the corresponding raw data, scripts, and results.</p> <p>A detailed documentation is available in documentaion.pdf.</p>
Selected studies of the Artificial Intelligence Algorithms to Predict College Students academic performance: a Systematic Mapping Study
Open the record for dataset details and reuse information.
Precomputed predictions used in "Assessment of variant effect predictors unveils variants difficulty as a critical performance indicator"
Open the record for dataset details and reuse information.
Figure 2 in Maxent modeling for predicting potential distribution of goitered gazelle in central Iran the effect of extent and grain size on performance of the model
Figure 2. Jackknifing test of variable importance in the development of the uncorrelated model at 250-m resolution. Blue bars indicate the gain achieved when including that predictor only. Green gray bars show how much the total gain is diminished without the given predictor. Red bar indicate the gain achieved when including all predictors.
Data from: Validation of the GARD™skin assay for assessment of chemical skin sensitizers – ring trial results of predictive performance and reproducibility
Proactive identification of chemicals with skin sensitizing properties is a key toxicological endpoint within chemical safety assessment. In order to meet recent legislations and increase animal welfare, considerable efforts have been made to develop non-animal approaches to replace current animal testing. Genomic Allergen Rapid Detection (GARD™) is a state-of-the-art technology platform, the most advanced application of which is the assay for assessment of skin sensitizing chemicals, GARD™skin. The methodology is based on a dendritic cell (DC)-like cell line, thus mimicking the mechanistic events leading to initiation and modulation of downstream immunological responses. Induced transcriptional changes are measured following exposure to test chemicals, providing a detailed evaluation of cell activation. These changes are associated with the immunological decision-making role of DCs in vivo and include among other phenotypic modifications, up-regulation of co-stimulatory molecules, induction of cellular and oxidative stress pathways and xenobiotic responses. Here, results from an inter-laboratory ring trial of GARD™skin, conducted in compliance with OECD guidance documents and comprising a blinded chemical test set of 28 chemicals, are summarized. The assay was found to be transferable to naïve laboratories, with an inter-laboratory reproducibility of 92.0%. The within-laboratory reproducibility ranged between 82.1-88.9%, while the cumulated predictive accuracy across the three laboratories was 93.8%. Based on these and previously published data, it is concluded that GARD™skin is a robust and reliable method for the identification of skin sensitizing chemicals and suitable for use as a stand-alone assay. These data form the basis for the regulatory validation of GARD™skin.
Clinging performance on natural substrates predicts habitat use in anoles and geckos
<p>1. For arboreal lizards, the ability to cling or adhere to the substrate is critical for locomotion during prey capture, predator escape, thermoregulation, and social interactions. Thus, selection on traits related to clinging is likely strong. </p> <p>2. Correlations between morphology, performance, and habitat use have been documented in arboreal lizards, providing a framework for using functional traits to predict habitat use in the field.</p> <p>3. We tested the hypothesis that clinging performance predicts habitat use in an actively assembling community of introduced lizards in Hawaiʻi comprised of anoles (<i>Anolis carolinensis, A. sagrei</i>) and day geckos (<i>Phelsuma laticauda</i>).</p> <p>4. We measured morphological traits (toepad area and lamellae number) and tested clinging performance on two artificial and eight natural substrates in the lab. We measured habitat use in 10 m x 10 m outdoor enclosures where habitat availability was controlled and the lizard species assemblage was manipulated to reflect all species combinations. The enclosure experiment generated more than 9,000 habitat use observations from 360 lizards.</p> <p>5. Morphological traits that predict performance in <i>Anolis </i>were not predictive in <i>Phelsuma</i>, indicating that direct measures of performance are necessary for comparisons between the genera.</p> <p>6. Measuring clinging performance on multiple substrates provided key insights into patterns of habitat use. While all three species performed best on an artificial smooth substrate (acrylic), performance on natural substrates predicted which texture (rough vs. smooth) was most often used by each species. </p> <p>7. Performance predicted perch height use: species with the greatest clinging performance (<i>A. carolinensis </i>and <i>P. laticauda</i>) across substrates perched twice as high as <i>A. sagrei</i>.</p> <p>8. We did not observe habitat shifts in the height or texture of perches used by any species in response to experimental manipulation of the lizard species assemblage.</p> <p>9. Our results highlight the inextricable link between ecology, morphology, and performance, the importance of measuring functional traits in ecologically-relevant ways, and the potential for resource partitioning to be influenced by differences in the ability to attach to different substrates. </p>
Students' chronotype predicts performance in a Brazilian full-time middle school
<p>The performance, whether satisfactory or unsatisfactory, achieved in day-to-day tasks may vary according to several environmental synchronizers, such as 24-hour light-dark cycle. For instance, the human performance on physical and/or cognitive demanding activities achieve its best during day, when body temperature reaches a circadian peak. Moreover, individual differences in the circadian peaks in temperature along with individuals’ timing of sleep is referred to as chronotype. Here, we aimed to answer if in a Brazilian full-time school of early start time (a) the chronotypes affect the students’ performance; (b) there are differences between the students’ performance according to their chronotypes. We expected to find (a) a positive effect of the morning chronotype on the students’ performance, particularly in subjects that take place in early morning; (b) while a negative effect of the evening chronotype in that same period. To address the effect of the chronotype on the students’ scholar performance we build a Generalized Linear Mixed Model (GLMM). Results show that the students’ chronotype affects both their subjective and school-declared performance. In sum, we add evidence for the effect that individual chronotypes have on the students’ performance in a Brazilian full-time middle school. Our results shows that evening-type students are expected to have an increase of 0.038 (p = <0.05) log counts on their performance in Portuguese classes compared to other chronotypes. Results also support the hypothesis that the students’ performance is partially because of their chronotype. Distinctive features of the studied Brazilian full-time middle school are discussed.</p>
Data for CASP15 performance benchmarking of the state-of-the-art protein structure prediction methods
<p>CASP15 performance benchmarking of the state-of-the-art protein structure prediction methods</p>
Prediction of Outcome of Non Invasive Ventilation COPD Patients by Assessment of Diaphragmatic Performance
ClinicalTrials.gov study NCT06143150. IPD Sharing: Not stated. Countries: 0. Publications: 3.
The Accuracy of the Performance and Placement Test for Predicting Supraglottic Airway Device (SAD) Position in the Hypopharynx as Confirmed With Video Laryngoscopy
ClinicalTrials.gov study NCT03643029. IPD Sharing: YES. Countries: 0. Publications: 2.
Comparison of Frailty Screening Performance and Predictive Validity of Adverse Health Outcomes in Breast Cancer Patients Using Frailty Screening Tools
ClinicalTrials.gov study NCT06467149. IPD Sharing: NO. Countries: 1. Publications: 0.
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.