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.
25
datasets available to search
ShareScore release 0.9.0
Dataset results
25 results for “Interpretable deep learning”
cigKast: A data of 3D synthetic seismic volumes with labeled paleokarsts for deep-learning-based paleokarst interpretation
<p>cigKarst is a dataset created by the <a href="http://cig.ustc.edu.cn/">Computational Interpretation Group (CIG)</a> for the deep-learning-based peleokarst interpretation in 3D seismic images, <a href="http://cig.ustc.edu.cn/xinming/list.htm" target="_blank" rel="noopener">Xinming Wu</a> is the main contributor to the dataset.</p> <p>This dataset contains 120 pairs of synthetic 3D seismic images and the corresponding label images with the ground truth of the paleokarst systems simulated in the seismic images. More detail of building this dataset is discussed in the paper published at the journal of JGR Solid Earth:</p> <p><strong>Wu, X.</strong>, S. Yan, J. Qi, and H. Zeng, 2020, Deep learning for characterizing paleokarst collapse features in 3D seismic images. <strong>JGR, Solid Earth</strong>, Vol. 125(9), 1-23, e2020JB019685. <a href="http://cig.ustc.edu.cn/_upload/tpl/05/cd/1485/template1485/papers/wu2020karst.pdf">[PDF]</a>. doi: 10.1029/2020JB019685</p> <p>Below are some brief description of the dataset:</p> <p>1) The "seismic.zip" contains 120 3D seismic images, each image is with the dimension of 256X256X256;</p> <p> 2) The "karst.zip" contains 120 3D label images of the karsts. Each label image is with the same dimension of 256X256X256. The values in a label image are set with ones in the karst areas while zeros elsewhere, which is why the compressed label images in the karst.zip is much smaller than the seismic images compressed in the seismic.zip</p>
CNN models and training, validation and test datasets for "PlotMI: interpretation of pairwise interactions and positional preferences learned by a deep learning model from sequence data"
<p>Convolutional neural network (CNN) models and their respective training, validation and test datasets used in manuscript:</p> <p>Tuomo Hartonen, Teemu Kivioja and Jussi Taipale, "PlotMI: interpretation of pairwise interactions and positional preferences learned by a deep learning model from sequence data"</p>
Interpretation results used in the paper "Real-Time Dual-Para FWI-Inv of GPR Data Based on Robust Deep Learning"
<p>We provide the updated synthetic data and inversion results used for all interpretations presented in the paper "Real-Time Dual-Parameter FWI Inversion of GPR Data Based on Robust Deep Learning."</p>
DeepAnnotation: A novel interpretable deep learning-based genomic selection model that integrates comprehensive functional annotations
<p>1. Update package, example dataset, and demo code of DeepAnnotation</p> <p>2. Update the transformed genotype data, the phenotype data, the comprehensive functional annotation data for Duroc prepared by RNAfold, DeepSEA, easyMF models, and the four types of input data for training DeepAnnotation model</p> <p>3. Add the conserved functional annotation</p> <p> </p>
"iDCNNPred: An interpretable deep learning model for virtual screening and identification of PI3Ka inhibitors against triple-negative breast cancer"
<p>In this study, we proposed a novel interpretable deep convolutional neural network prediction (iDCNNPred) system for classifying molecular bioactivity and identifying predictive potential inhibitors for the PI3Ka isoform protein. This system utilizes 2D molecular image representation as input features, instead of traditional molecular fingerprints or descriptors.</p> <p><strong>The datasets used for model construction, prediction and screening of chemical library are provided in this uploaded data in <a href="../api/records/10947610/draft/files/Molecular_image_Custom_DCNN_datasets.zip/content" target="_blank" rel="noopener noreferrer">Molecular_image_Custom_DCNN_datasets.zip</a> file for Custom-DCNN models and <a href="../api/records/10947610/draft/files/Molecular_image_pre_trained_datasets.zip/content" target="_blank" rel="noopener noreferrer">Molecular_image_pre_trained_datasets.zip</a> file for Pre-trained fine-tuned models. </strong><strong>The final run of models results given in file <a href="../api/records/10947610/draft/files/Custom_DCNN_Pre_trained_models.zip/content" target="_blank" rel="noopener noreferrer">Custom_DCNN_Pre_trained_models.zip</a></strong></p>
The impact of deep learning aid on the workload and interpretation accuracy of radiologists on chest computed tomography: a cross-over reader study.
<p>Data used to perform statistical analysis in "The impact of deep learning aid on the workload and interpretation accuracy of radiologists on chest computed tomography: a cross-over reader study.". </p>
Interpretable Deep Learning for Probabilistic MJO Prediction: CNN Forecasts
<p>This repository contains data produced for the paper "Interpretable Deep Learning for Probabilistic MJO Prediction" by A. Delaunay and H. M. Christensen (2021).</p> <p>>> mu_ens_XX.pt<br> contains the mean forecasts from each ensemble member at a lead time of XX days</p> <p>>> cov_alea_XX.pt<br> contains the aleatoric predictions of each ensemble member at a lead time of XX days</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>
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>
cigChannel: A large-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation
<h2>Assorted channel subset of the cigChannel dataset (V1.0)</h2> <h2>Expansion package of folded and faulted structures</h2> <div> <p>This version includes the last 100 samples (400 samples in total) of the assorted channel subset. Each sample features folded and faulted structures. Explanations of the uploaded zip files are listed below: </p> </div> <ul> <li>Assorted_Channel_Ip_xx-xx.zip: Seismic impedance volumes of sample No.xx to No.xx.</li> <li>Assorted_Channel_Label_xx-xx.zip: Binary-class label volumes of sample No.xx to No.xx, where the value 0 represents the background (non-channel areas) and 1 represents the channel.</li> <li>Assorted_Channel_Seismic_xx-xx.zip: Seismic (amplitude) volumes of sample No.xx to No.xx.</li> </ul> <h3>Portal to the assorted channel subset (main package, the first 300 samples):</h3> <ul> <li>Assorted channel subset: <a href="https://doi.org/10.5281/zenodo.11044512" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.11044512</a></li> </ul> <h3>Portals to the other subsets:</h3> <ul> <li>Submarine canyon subset: <a href="https://doi.org/10.5281/zenodo.11079950" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.11079950</a></li> <li>Meandering channel subset: <a href="https://doi.org/10.5281/zenodo.11078794" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.11078794</a></li> <li>Tributary channel network subset: <a href="https://doi.org/10.5281/zenodo.11073030" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.11073030</a></li> </ul>
Supplemental tables for 'Pan-microalgal dark proteome mapping via interpretable deep learning and synthetic chimeras'
<p>Distinguishing genuine microbial proteins from contaminants remains a major bottleneck in genomics, particularly for environmental and non-model organisms where conventional homology-based tools are slow, resource-intensive, and leave large fractions of the "dark proteome" unclassified. LA<sup>4</sup>SR offers a scalable, interpretable framework that classifies algal and bacterial proteins directly from translated sequence data, achieving near-complete recall while accelerating inference by ~ 10,000-fold relative to BLASTP. By revealing that internal sequence features alone can drive robust classification, LA4SR bypasses the need for complete gene models or perfect annotations—opening new opportunities for analyzing complex microbial communities and metagenomes. Interpretability methods further link emergent amino acid signatures to evolutionary and ecological features, highlighting the potential of language models not only to accelerate genomics workflows but also to uncover new biological insights.</p> <p> </p> <p><strong>Table S1 | External spreadsheet. </strong>This spreadsheet contains LA<sup>4</sup>SR performance metrics, technical performance estimations, and BLAST results and runtimes of genomes comprising the algal training data.<strong> </strong></p> <p><strong>Table S2 | External spreadsheet. </strong>Captum attributions for 100 sequences each of algal and bacterial origin obtained using the LayerIntegratedGradients function.</p> <p><strong>Table S3 | External spreadsheet. </strong>Influential motifs found with the DeepMotifMinerPro software introduced in this work (see Data S3).</p> <p><strong>Table S4 | External spreadsheet.</strong> LA4SR and Diamond BLAST results for data from new assemblies from seen species (Fig. S7), contaminated assemblies from unseen genera (Fig. S7), and clean assemblies from unseen genera (Fig. 8). For the LA4SR results for genome assemblies from unseen genera, the genomes were published after the model was trained, and the genera shown were not included in the training dataset. Newly sequenced genomes uploaded to NCBI SRA accession SUB14799921.</p> <p> </p> <p> </p>
Rapid Flood Simulation and Source Area Identification in Urban Environments via Interpretable Deep Learning
<p>Here is the data and original code for the paper titled <em>Rapid Flood Simulation and Source Area Identification in Urban Environments via Interpretable Deep Learning</em>. If you have any questions, please contact <a rel="noopener">202331470015@mail.bnu.edu.cn</a>.</p>
Rapid Flood Simulation and Source Area Identification in Urban Environments via Interpretable Deep Learning
<p>Here are the relevant data and preliminary code for the paper titled 'Rapid Flood Simulation and Source Area Identification in Urban Environments via Interpretable Deep Learning' for your reference. If you have any questions, please contact <a rel="noopener">202331470015@mail.bnu.edu.cn</a>.</p>
Dataset for Using deep learning interpretability to study the development of drawing behaviour in children
Open the record for dataset details and reuse information.
Interpretable deep learning reveals the sequence rules of Hippo signaling (RNA-Seq)
GEO Series GSE252462. Mus musculus. 9 samples. Type: Expression profiling by high throughput sequencing.
Usability and Clinical Effectiveness of an Interpretable Deep Learning Framework for Post-Hepatectomy Liver Failure Prediction
ClinicalTrials.gov study NCT06031818. IPD Sharing: UNDECIDED. Countries: 1. Publications: 0.
Interpretable deep learning reveals the sequence rules of Hippo signaling (ChIP-Seq)
GEO Series GSE252457. Mus musculus. 47 samples. Type: Genome binding/occupancy profiling by high throughput sequencing.
Interpreting regulatory mechanisms of Hippo signaling through a deep learning sequence model
GEO Series GSE252463. Mus musculus. 59 samples. Type: Expression profiling by high throughput sequencing; Genome binding/occupancy profiling by high throughput sequencing.
Interpretable deep learning reveals the sequence rules of Hippo signaling (ATAC-Seq)
GEO Series GSE252456. Mus musculus. 3 samples. Type: Genome binding/occupancy profiling by high throughput sequencing.
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.