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.
1,048
datasets available to search
ShareScore release 0.9.0
Dataset results
1,048 results for “interpreting”
Unpacking the "black box": improving ecological interpretation of regression based models
<p><strong>Aim</strong><br>Many tree species distribution models use black-box machine learning techniques that often neglect interpretative aspects and instead focus mainly on maximising predictive accuracy. In this study, we outline an interpretative modelling framework to gain better ecological insights while mapping abundance patterns of six North American species.</p> <p><strong>Location</strong><br>Continental United States and Canada</p> <p><strong>Methods</strong><br>We develop an innovative procedure using regression trees by stabilising variance and mapping dominant rules which we term 'optimized regression tree bagging for interpretation and mapping' (ORTBIM). We apply this technique to understand ecological features influencing the abundance patterns of three eastern (<em>Pinus</em> <em>strobus</em>, <em>Acer</em> <em>saccharum</em>, and <em>Quercus</em> <em>montana</em>), and three western (<em>Picea</em> <em>engelmannii</em>, <em>Pinus</em> <em>ponderosa</em>, and <em>Pseudotsuga</em> <em>menziesii</em>) tree species in North America. For these species, we assess and map the dominant climate-terrain interactions that partly determine abundance patterns in the eastern and western regions. In the process, we examine the role of varying responses and scales and explore finer-scale species climate-terrain niches and non-linear relationships.</p> <p><strong>Results</strong><br>Our study emphasizes the prominent role of elevation and heat-moisture variables in the west and the greater importance of seasonal precipitation and seasonal temperature in the east. The abundance patterns under future climate (SSP5–8.5) show climate-terrain habitats shifting northward and westward into Canada and Alaska for the eastern species, and predominantly north-westward for the western species.</p> <p><strong>Conclusion</strong><br>Our interpretative modelling framework can be used to gain a more comprehensive understanding of the abundance patterns across the full species range, to formulate better predictive models, and to facilitate improved management practices under climate change.</p>
land cover interpreted samples for the Amur River Basin in China
<p> 7755 training samples were derived by visually interpreting with eight land cover classes using the Landsat images from Google Earth Engine (GEE). </p>
Supplemental Data File for Resetting Archaeological Interpretations of Pre-Contact Indigenous Agriculture: Maize Isotopic Evidence from Three Ancestral Mohawk Iroquoian Villages
<p>Supplemental data tables for the paper "Resetting Archaeological Interpretations of Pre-Contact Indigenous Agriculture: Maize Isotopic Evidence from Three Ancestral Mohawk Iroquoian Villages" revised manuscript submitted for peer review.</p>
Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
<p>Retinoblastoma is a rare and aggressive form of childhood eye cancer that requires prompt diagnosis and treatment to prevent vision loss and even death. Deep learning models have shown promising results in detecting retinoblastoma from fundus images, but their decision-making process is often considered a "black box" that lacks transparency and interpretability. In this project, we explore the use of LIME and SHAP, two popular explainable AI techniques, to generate local and global explanations for a deep learning model based on InceptionV3 architecture trained on retinoblastoma and non-retinoblastoma fundus images. We collected and labeled a dataset of 400 retinoblastoma and 400 non-retinoblastoma images, split it into training, validation, and test sets, and trained the model using transfer learning from the pre-trained InceptionV3 model. We then applied LIME and SHAP to generate explanations for the model's predictions on the validation and test sets. Our results demonstrate that LIME and SHAP can effectively identify the regions and features in the input images that contribute the most to the model's predictions, providing valuable insights into the decision-making process of the deep learning model. In addition, the use of InceptionV3 architecture with spatial attention mechanism achieved high accuracy of 97\% on the test set, indicating the potential of combining deep learning and explainable AI for improving retinoblastoma diagnosis and treatment.</p>
An Interpretable Framework to Characterize Compound Treatments on Filamentous Fungi using Cell Painting and Deep Metric Learning
<p>This deposit contains:</p> <ul> <li>{train,test,val}.csv: Meta-data files</li> <li>images.tar.gz: Archive of images</li> <li>checkpoint.pth.tar: Model weights</li> <li>code.tar.gz: Code necessary to reproduce our experiments.</li> </ul>
Dataset for publication: "Using explainable machine learning to interpret the effects of policies on air pollution: COVID-19 lockdown in London"
<p>This online repository offers supplementary datasets supporting the findings in the research article titled "Using explainable machine learning to interpret the effects of policies on air pollution: COVID-19 lockdown in London," published in Environmental Science & Technology. The dataset contains air quality data from different monitoring sites in London between 2016 and 2020 and weather data for the same period. Additionally, the dataset incorporates 136 features relating to London's Middle Layer Super Output Areas (MSOAs) in the year 2019, which can be used to identify the key factors contributing to the heterogeneous changes in air quality levels at different spatial locations during the pandemic. Please refer to the metadata file for detailed data sources and descriptions. </p>
Quantitative interpretation of the physical processes associated with the interannual variation of South Asian summer monsoon
<p>This is the CFRAM-A data of "Quantitative interpretation of the physical processes associated with the interannual variation of South Asian summer monsoon". The data includes 10 years: 1997, 1999, 2000, 2001, 2008, 2009, 2013, 2015, 2018, and 2019. Each year includes two "nc" data, one is the partial temperature, the other is the total temperature.</p>
Data from: Past population control biases interpretations of contemporary genetic data: implications for future invasive Sitka black-tailed deer management in Haida Gwaii
<p>Invasive species management practices often include genetic analyses to better inform decision-making and resource allocation. Yet, past management actions may artificially bias recovered patterns of genetic variation; for example, a population bottleneck caused by contemporary culling may mirror some patterns associated with historical isolation. Here, we aimed to disentangle the impacts of past management activities from natural processes for Sitka black-tailed deer (<em>Odocoileus</em> <em>hemionus</em> <em>sitkensis</em>), an invasive species that has been repeatedly culled on two islands, SGang Gwaay and Reef, within the Haida Gwaii archipelago (Canada). We applied a recently developed Genotyping-in-Thousands by sequencing panel to contemporary (e.g., blood, serum, tissue, muscle, feces) and archived deer samples, the latter collected prior to management activity within the system (c. 1997–1998), which allowed us to contextualize conflicting patterns of isolation and connectivity previously observed on SGang Gwaay and Reef. Successful genotyping (92.6%) and population genetic analysis of 292 individuals at 236 SNPs revealed signals of historical isolation on SGang Gwaay and Reef, provided evidence of a founder effect during initial colonization, and indicated an absence of ongoing gene flow. Furthermore, our spatiotemporal analyses consistently supported a priori predictions associated with bottlenecks within post-cull populations, such as within-island loss of genetic variation, elevated within-island kinship, and increased levels of among-island genetic differentiation. These findings are promising for future management of deer on SGang Gwaay and Reef, suggesting that eradications on these islands may be durable. More broadly, our work highlights the importance of understanding management history before interpreting contemporary population genetic data.</p>
Zip archive containing datasets described in the manuscript entitled "Distribution-agnostic Deep Learning Enables Accurate Single‐Cell Data Recovery and Transcriptional Regulation Interpretation"
<p>The datasets used in the manuscript entitled "Distribution-agnostic Deep Learning Enables Accurate Single‐Cell Data Recovery and Transcriptional Regulation Interpretation". These datasets encompass all the experiments conducted in the manuscript, including simulation experiments, downsampling experiments, clustering, differential expression analysis, enrichment analysis, trajectory inference, batch correction, and clinical case discovery.</p> <p>The open-source software is available at https://github.com/XuYuanchi/Bis.</p>
Real-Time Delphi data: How to identify and interpret weak signals of change in the forest bioeconomy
<p>Data from: Mauno, T., Catelo, F., Bengston, D.N., Pykäläinen, J. & Hujala, T. 2023. How to identify and interpret weak signals of change in the forest bioeconomy. Forest Policy and Economics. <a href="https://doi.org/10.1016/j.forpol.2023.103075?_gl=1*a2eeob*_ga*NDE0MDgzOTYwLjE2OTY0ODY2MTY.*_ga_NY8L5SJPMB*MTY5NjQ5NDIxNi4yLjEuMTY5NjUwMTI0Mi4wLjAuMA..">https://doi.org/10.1016/j.forpol.2023.103075</a></p> <p>This exploratory study sought to understand how to identify and interpret weak signals of change that may have an impact on the forest bioeconomy. An international panel of experts in the forest bioeconomy and in foresight provided their views through a two-stage Real-Time Delphi method which utilized the multiple rounds of traditional Delphi and the instantaneous feedback of the Real-Time Delphi method.</p> <p>The Real-Time Delphi exercise was conducted in two stages through the eDelphi software (edelphi.org); the first stage was focused on <em>Changes</em> and the second on <em>Weak Signals</em>. For the Real-Time Delphi exercise, two expert matrices (forest bioeconomy matrix and futures & foresight matrix) were prepared with the aim of obtaining diverse expertise to participate in the study.</p> <p>The first stage was conducted during a 10-day period in early September 2022 (Sep 5, 2022 – Sep 14, 2022). The second stage was also conducted during a 10-day period later in September 2022 (Sep 21, 2022 – Sep 30, 2022). A total of 11 (6 forest bioeconomy experts and 5 futures research and foresight specialists) participated in both eDelphi stages.</p> <p>This dataset includes: (i) completed Real-Time Delphi stages (including anonymized answers and discussions of 11 participants) (ii) questions for both Real-Time Delphi stages, and (iii) anonymized expert matrices (forest bioeconomy matrix and futures & foresight matrix)</p> <p>For more information, please contact the corresponding author (data controller): Tuomas Mauno (University of Eastern Finland), tuomas.mauno@uef.fi</p>
Study to Establish Image Interpretation Criteria for 18F Fluciclovine PET in Detecting Recurrent Brain Metastases (PURSUE)
ClinicalTrials.gov study NCT04410367. IPD Sharing: NO. Countries: 1. Publications: 1.
Visualizations to Improve Pain Communication Between Patients, Interpreters, and Providers
ClinicalTrials.gov study NCT04975789. IPD Sharing: NO. Countries: 1. Publications: 1.
Web-based Interpretation Training For Anxiety
ClinicalTrials.gov study NCT02382003. IPD Sharing: Not stated. Countries: 1. Publications: 1.
Hostile Interpretation Bias Training to Treat Irritability
ClinicalTrials.gov study NCT03592368. IPD Sharing: NO. Countries: 1. Publications: 3.
Atrial Fibrillation (AF) and Electrocardiogram (EKG) Interpretation Project ECHO
ClinicalTrials.gov study NCT05890274. IPD Sharing: YES. Countries: 1. Publications: 3.
Effects of Maternal Interpretation Biases on Child Anxiety and Related Responses
ClinicalTrials.gov study NCT02095340. IPD Sharing: Not stated. Countries: 1. Publications: 4.
Interpretation Training to Reduce Anxiety: Evaluating Technology-based Delivery Models and Methods to Reduce Attrition
ClinicalTrials.gov study NCT03498651. IPD Sharing: YES. Countries: 1. Publications: 1.
Satisfaction of Limited English-Proficient Patients With Phone Interpretation Services Compared to In-Person Interpreters: A Randomized Controlled Trial
ClinicalTrials.gov study NCT03470194. IPD Sharing: Not stated. Countries: 1. Publications: 1.
Interpreting morphological adaptations associated with viviparity in the Tsetse fly (Glossina morsitans) by three-dimensional analysis
Open the record for dataset details and reuse information.
The influence of the statistical significance of results and spin on readers’ interpretation of the results in an abstract for a hypothetical clinical trial: A randomized trial
Open the record for dataset details and reuse information.
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.