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.
86
datasets available to search
ShareScore release 0.9.0
Dataset results
86 results for “cell annotation”
scRNA-seq atlases for 3 Caenorhabditis species - annotated cell datasets
<p>Annotated datasets (monocle3 objects) of scRNA-seq data for <em>C. elegans</em>, <em>C. briggsae</em> and <em>C. tropicalis</em> L2 nematodes. The datasets are published together with the manuscript "Divergence in neuronal signaling pathways despite conserved neuronal identity among <em>Caenorhabditis</em> species".</p> <p><a href="https://doi.org/10.1016/j.cub.2025.05.036" target="_blank" rel="noopener">https://doi.org/10.1016/j.cub.2025.05.036</a></p> <p>Files deposited include cell datasets for all sequenced cells ("all_cds") and datasets for all cells annotated as neurons ("neu_cds"). </p> <p><em>C. elegans</em> strain - N2.</p> <p><em>C. briggsae</em> strain - AF16.</p> <p><em>C. tropicalis</em> strain - NIC203.</p>
An annotated high-content fluorescence microscopy dataset with EGFP-Galectin-3-stained cells and manually labelled outlines
<p>Here we present a benchmarking dataset of fluorescence microscopy images with EGFP-Galectin-3-stained cells together with annotations of their outlines. Images were randomly selected from an RNA interference screen with a modified U2OS osteosarcoma cell line, acquired on a Thermo Fischer CX7 high-content imaging system at 20x magnification. </p> <p>The dataset contains 60 images showing over 2000 labelled nuclear objects in total, which is sufficiently large to train well-performing neural networks for instance or semantic segmentation. It is pre-split into training, development and test set, each in a zip file. The dataset should be referred to as Aitslab_bioimaging2.</p> <p>For most of the images, nuclear staining and annotations have been published previously in the dataset Aitslab_bioimaging1 (https://doi.org/10.5281/zenodo.6657260). The conversion script to produce the png images from the C01 images was published together with this dataset.</p>
scGPT: End-to-End Protocol for Fine-tuned Retina Cell Type Annotation
<h1>Abstract</h1> <p>Single-cell research faces challenges in accurately annotating cell types at high resolution, especially when dealing with large-scale datasets and rare cell populations. To address this, foundation models like scGPT offer flexible, scalable solutions by leveraging transformer-based architectures. This protocol provides a comprehensive guide to fine-tuning scGPT for cell-type classification in single-cell RNA sequencing (scRNA-seq) data. We demonstrate how to fine-tune scGPT on a custom retina dataset, highlighting the model’s efficiency in handling complex data and improving annotation accuracy achieving 99.5% F1-score. This protocol automates key steps, including data preprocessing, model fine-tuning, and evaluation. This protocol enables researchers to efficiently deploy scGPT for their own datasets. The provided tools, including a command-line script and Jupyter Notebook, simplify the customization and exploration of the model, proposing an accessible workflow for users with minimal Python and Linux knowledge. The protocol offers an off-the-shell solution of high-precision cell-type annotation using scGPT for researchers with intermediate bioinformatics.</p>
Brightfield images of cells and spheroids in wells annotated with bounding boxes
<p>The images in this dataset show cells in different developmental stages upon forming spheroids. They can go through several developmental sages: Starting from cells, they turninto compacted objects and then into spheroids. Ultimately, they can die and disintegrate. The objects are annotated with bounding boxes that carry these respective labels. The dataset in its current form can be upload to an OMERO server using the omero-cli-transfer package - simply download the zip file, log into your omero server and use the `omero transfer unpack` command as shown on the <a href="https://github.com/ome/omero-cli-transfer">omero-cli-transfer documentation</a>.</p> <p>The dataset can be used to train object detection models such as a <a href="https://docs.ultralytics.com/models/yolov8/">yolo classifier </a>- the linked repository provides a tutorial on how to do so.</p>
Large-scale annotated dataset for cochlear hair cell detection and classification
<p>Our sense of hearing is mediated by cochlear hair cells, of which there are two types organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains 5 - 15 thousand terminally differentiated hair cells, and their survival is essential for hearing as they do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. Machine learning can be used to automate the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, rat, guinea pig, pig, primate, and human cochlear tissue, from normal conditions and following <i>in-vivo</i> and <i>in-vitro</i>ototoxic drug application. The dataset includes over 107,000 hair cells which have been manually identified and annotated as either inner or outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair-cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to give other hearing research groups the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease. </p><p>Associated code is provided here: https://github.com/indzhykulianlab/hcat-data</p>
Datasets for CASSL: A cell-type annotation method for single cell transcriptomics data using semi-supervised learning
<p>This repository contains datasets used in the project CASSL: A cell-type annotation method for single cell transcriptomics data using semi-supervised learning. This project aims at learning cell annotations for missing cell labels via NMF and recursive k-Means clustering.</p>
Annotated images from yeast cell lifespans - Training & Test sets - DetecDiv (id01)
<p>This dataset has been generated by manual annotation from timelapse images of yeast cells dividing using the DetecDiv software (see below).</p> <p>It contains ~250 000 images from 250 cellular lifespans (each lifespan is made of between 700 and 1000 images). Each image is classified between 6 classes: "1. unbudded", "2. small", "3. large", "4. dead", "5. empty", "6. clog", according to the subfolder of the image.</p> <p>Besides, this folder also contains a .mat file containing 250 timeseries of classes corresponding to the lifespan of the 200 cells.</p> <p> </p> <p>The dataset used for training (200 cellular lifespans) is in the folder /trainingset, while the dataset used for testing (50cellular lifespans) is in the folder /testset</p> <p>It has been used to train the network <a href="https://doi.org/10.5281/zenodo.5553862">doi.org/10.5281/zenodo.5553862</a> from the software DetecDiv: <a href="https://github.com/gcharvin/DetecDiv">github.com/gcharvin/DetecDiv</a></p> <p><a href="https://biorxiv.org/content/10.1101/2021.10.05.463175v1">biorxiv.org/content/10.1101/2021.10.05.463175v1</a></p> <p> </p> <p><strong>Data type</strong>: 3D microscopy images (3 stacks brightfield) (.tif) + annotation (.mat)</p> <p><strong>Microscopy data type</strong>: Brightfield images with 3 stacks, each stack representing a color of RGB.</p> <p><strong>Imaging</strong>: 20x 0.45 NA brightfield, 6.5µm*6.5µm sCMOS</p> <p><strong>Cell type</strong>: Budding yeast wild type cell (BY4742)</p> <p><strong>File format</strong>: .tif (16-bit RGB, 1 color per z-stack) + .mat</p> <p><strong>Image size</strong>: 60x60x1 (Pixel size: x,y: 325 nm, 3*z: 3*1325 nm)</p> <p> </p> <p><strong>Author(s)</strong>: Théo, ASPERT</p> <p><strong>Contact email</strong>: theo.aspert@gmail.com</p> <p><strong>Affiliation</strong>: IGBMC, Université de Strasbourg</p> <p><strong>Funding bodies</strong>: This work was supported by the Agence Nationale pour la Recherche, the grant ANR-10-LABX-0030-INRT, a French State fund managed by the Agence Nationale de la Recherche under the frame program Investissements d'Avenir ANR-10-IDEX-0002-02.</p>
Annotation of the non-canonical translatome reveals that CHO cell microproteins are a new class of therapeutic antibody drug product impurity
<p>3,681 novel Chinese hamster proteoforms (derived from uORFs, ouORFs and ORFs encoded on NCBI annotated non-coding RNAs).</p>
Cell specificity of human regulatory annotations and their genetic effects on gene expression
<p>Processed data for the manuscript: Cell specificty of regulatory annotations and their genetics effects on gene expression.</p> <p>The code to generate these data is included in the zip-file: regulatoryAnnotations_comparisons-master.zip</p> <p>and at GitHub: https://github.com/ParkerLab/regulatoryAnnotations_comparisons</p> <p>Individual dataset information:</p> <p>numberOfSegments.dat.gz: Number of segments in each annotation</p> <p>lengthDistributionOfSegments.dat.gz: Length distribution of segments in each annnotation</p> <p>genomeCoverage.dat.gz: Total genome coverage of regions in each annoation</p> <p>overlapFraction.dat.gz: Basepair level overlap between two pairs of annotations</p> <p>annotations_chromatinStateOverlap.dat.gz: Overlap of annotations with chromatin states</p> <p>information.fourcells_enhancer.dat.gz: Information content of the mean enhancer chromatin posterior probability for annotation segments across four cell types</p> <p>information.fourcells_promoter.dat.gz: Information content of the mean promoter chromatin posterior probability for annotation segments across four cell types</p> <p>gwas_enrichment_stats.txt.gz: Enrichment of GWAS SNPs in annotations</p> <p>GTEx_v7.ESI_medianTPM_min0.15.dat.gz : ESI for genes across 50 tissues</p> <p>gtexv7_lcleqtl.enrichment.dat.gz: Enrichment of GTEx v7 LCL eQTL in annotations</p> <p>gtexv7_lcleqtl.binned_lclESI.enrichment.dat.gz: Enrichment of GTEx v7 LCL eQTL binned by lclESI in annotations</p> <p>K562.gtexv7_bloodeqtl.fdr0.1.prune0.8.maf0.2.ld0.99.annotations.dat.gz: GTEx v7 blood eQTL effect sizes in K562 annotations </p> <p>GM12878.gtexv7_lcleqtl.fdr0.1.prune0.8.maf0.2.ld0.99.annotations.dat.gz: GTEx v7 LCL eQTL effect sizes in GM12878 annotations</p> <p>GM12878.dsqtl.prune0.8.maf0.2.ld0.99.annotations.dat.gz : GM12878 DNase QTL effect sizes in GM12878 annotations</p> <p>GM12878.allelicBiasResults.FracRef.downsampled30.annotations.withMAF.dat.gz: GM12878 ATAC-seq allelic bias effect sizes in GM12878 annotations </p> <p> <br> <br> <br> </p>
Quantitative phase microscopy timelapse dataset of PNT1A, DU-145 and LNCaP cells with annotated caspase 3,7-dependent and independent cell death
<p>Time-lapse dataset of prostatic cell lines (DU-145, PNT1A, LNCaP) exposed to cell death-inducing compounds (staurosporine, doxorubicin) and black phosphorus. The time-lapse dataset is annotated as follows: (1) cell masks and cell numbers, (2) by cell death type and timepoint of death in the attached xlsx file. This dataset is supplementary to the article:</p> <p>Vicar, T., Raudenska, M., Gumulec, J. <em>et al.</em> The Quantitative-Phase Dynamics of Apoptosis and Lytic Cell Death. <em>Sci Rep</em> <strong>10, </strong>1566 (2020). <a href="https://doi.org/10.1038/s41598-020-58474-w">https://doi.org/10.1038/s41598-020-58474-w</a></p> <p>Correlative fluorescence microscopy is in a separate dataset <a href="https://doi.org/10.5281/zenodo.4531900">10.5281/zenodo.4531900</a></p> <p>Code is available at <a href="https://github.com/tomasvicar/CellDeathDetect">https://github.com/tomasvicar/CellDeathDetect</a></p> <p><strong>Methods</strong></p> <p><em>Cell culture and cultured cell conditions</em><br> LNCaP cell line was established from a lymph node metastase of the hormone-refractory patient and contains a mutation in the AR gene. This mutation creates a promiscuous AR that can bind to different types of steroids. LNCaP cells are AR-positive, PSA-positive, PTEN-negative and harbor wild-type p53 {Skjoth, 2006 #150; Mitchell, 2000 #149}. PNT1A is immortalized non-tumorigenic epithelial cell line. PNT1A cells harbour wild-type p53. However, SV40 induced T-antigen expression inhibits the activity of p53. This cell line had lost the expression of androgen receptor (AR) and prostate-specific antigen (PSA) (Raudenska, 2019). DU-145 cell line is derived from the metastatic site in the brain and contains P223L and V274F mutations in p53. This cell line is PSA and AR-negative and androgen independent (Chappell, 2012). All cell lines used in this study were purchased from HPA Culture Collections (Salisbury, UK). and were cultured in RPMI-1640 medium with 10 % FBS. The medium was supplemented with antibiotics (penicillin 100 U/ml and streptomycin 0.1 mg/ml). Cells were maintained at 37°C in a humidified (60%) incubator with 5% CO2 (Sanyo, Japan).</p> <p><em>Correlative time-lapse quantitative phase-fluorescence imaging</em></p> <p>QPI and fluorescence imaging were performed by using multimodal holographic microscope Q-PHASE (TESCAN, Brno, Czech Republic). To determine the amount of caspase-3/7 product accumulation, cells were loaded with 2 µM CellEventTM Caspase-3/7 Green Detection Reagent (Life Technologies, Carlsbad, CA, USA) according to the manufacturer’s protocol and visualized using FITC 488 nm filter. To detect the cells with a loss of plasma membrane integrity, cells were stained with 1 ug/ml propidium iodide (Sigma Aldrich Co., St. Louis, MO, USA) and visualized using TRITC 542 nm filter. Nuclear morphology and chromatin condensation were analyzed using Hoechst 33342 nuclear staining (ENZO, Lausen, Switzerland) and visualized using DAPI 461 nm filter. Cells were cultivated in Flow chambers μ-Slide I Lauer Family (Ibidi, Martinsried, Germany). To maintain standard cultivation conditions (37°C, humidified air (60%) with 5% CO2) during time-lapse experiments, cells were placed in the gas chamber H201 - for Mad City Labs Z100/Z500 piezo Z-stages (Okolab, Ottaviano NA, Italy). To image enough cells in one field of view, lens Nikon Plan 10/0.30 were chosen. For each cell line and each treatment, seven fields of view were observed with the frame rate 3 mins/frame for 24 or 48 h respectively. Holograms were captured by CCD camera (XIMEA MR4021 MC-VELETA), fluorescence images were captured using ANDOR Zyla 5.5 sCMOS camera. Complete quantitative phase image reconstruction and image processing were performed in Q-PHASE control software. Cell dry mass values were derived according to {Prescher, 2005 #177} and {Park, 2018 #178} from the phase (eq. (1)), where m is cell dry mass density (in pg/μm2), φ is detected phase (in rad), λ is wavelength in μm (0.65 μm in Q-PHASE), and α is specific refraction increment (≈0.18 μm3/pg). All values in the formula except the Phi are constant. Phi (Phase) is the value measured directly by the microscope. Integrated phase shift through a cell is proportional to its dry mass, which enables studying changes in cell mass distribution (Park et al., 2018).</p> <p><strong>File description</strong></p> <p>There are three archives included for particular cell lines:</p> <ul> <li>QPI_annotated_timelapse_DU145.zip for DU-145 cells</li> <li>QPI_annotated_timelapse_PNT1A.zip for PNT1A cells</li> <li>QPI_annotated_timelapse_LNCaP.zip for LNCaP cells</li> </ul> <p>The archive includes of following files:</p> <ul> <li><strong>Tiff with time-lapse</strong> quantitative phase image (32-bit files 600x600px with values in pg/um2 with framerate 1 frame/3minutes with 1.59 px/um), named <em>QPI_cellline_treatment_FOV.tiff</em></li> <li><strong>Tiff file with segmentation</strong> mask for particular cells named <em>mask_cellline_treatment_FOV.tiff</em></li> <li><strong>xlsx table</strong> with cell death type (1 for apoptosis, 2 for necrosis, 3 for ambiguous/surviving) and time of death for representative cell number from mask, named <em>labels_cellline_treatment_FOV.xlsx</em></li> </ul> <p>file naming has following conventions:</p> <ul> <li>cell names: DU145, PNT1A, LNCaP for particular cell line</li> <li>treatments: st, bp, do for staurosporine, black phosphorus and doxorubicin</li> <li>fields of view: 1 to 7</li> </ul> <p>e.g. QPI_DU145_st_4.tif, mask_DU145_st_4.tif, labels_DU145_st_4.xlsx</p> <p>Note that correlative fluorescence images are available at <a href="https://doi.org/10.5281/zenodo.4531900">10.5281/zenodo.4531900</a></p>
spindle cell variant diffuse large B-cell lymphoma (NGS annotation file; high confidence calls) hematolrep-2136295
<p>Diffuse large B-cell lymphoma with spindle cell morphology is a rare variant. We present the case of a 74-year-old male who initially presented with a right supraclavicular (lymph) node enlargement. Histological analysis showed a proliferation of spindle-shaped cells with narrow cytoplasms. An immunohistochemical panel was used to exclude other tumors, such as melanoma, carcinoma, and sarcoma. The lymphoma was characterized by a cell-of-origin subtype of germinal center B-cell-like (GCB) based on Hans’ classifier (CD10-negative, BCL6-positive, and MUM1-negative); EBER negativity, and the absence of BCL2, BCL6, and MYC rearrangements. Mutational profiling using a custom panel of 168 genes associated with aggressive B-cell lymphomas confirmed mutations in ACTB, ARID1B, DUSP2, DTX1, HLA-B, PTEN, and TNFRSF14. Based on the LymphGen 1.0 classification tool, this case had an ST2 subtype prediction. The immune microenvironment was characterized by moderate infiltration of M2-like tumor-associated macrophages (TMAs) with positivity of CD163, CSF1R, CD85A (LILRB3), and PD-L1; moderate PD-1 positive T cells, and low FOXP3 regulatory T lymphocytes (Tregs). Immunohistochemical expression of PTX3 and TNFRSF14 was absent. Interestingly, the lymphoma cells were positive for HLA-DP-DR, IL-10, and RGS1, which are markers associated with poor prognosis in DLBCL. The patient was treated with R-CHOP therapy, and achieved a metabolically complete response.</p> <p>Carreras J, Kikuti YY, Miyaoka M, Hiraiwa S, Tomita S, Ikoma H, Kondo Y, Ito A, Nagase S, Miura H, Roncador G, Colomo L, Hamoudi R, Campo E, Nakamura N. Mutational Profile and Pathological Features of a Case of Interleukin-10 and RGS1-Positive Spindle Cell Variant Diffuse Large B-Cell Lymphoma. <em>Hematology Reports</em>. 2023; 15(1):188-200. https://doi.org/10.3390/hematolrep15010020</p>
Single cell annotations in 3D bacterial biofilms of Vibrio cholerae
<p>This repository contains the data to reproduce the study `Single-cell segmentation in bacterial biofilms with optimized convolutional neural networks enables tracking of cell lineages and measurements of growth rates` by Jelli, Ohmura, Netter, et al. It contains the following four subfolders:</p> <p> </p> <p>- `training-data-from-experimentally-acquired-images`: the dataset that was created to train segmentation models<br> - `trained-models`: contains five models trained on the trainind dataset to be used for predictions<br> - `segmentation-predictions-for-different-species`: segmentations based on a trained model on biofilms of different species<br> - `training-data-synthetic`: Synthetic microscope images and their corresponding label images together with scripts to create the data</p>
Filtered and annotated SNV and indel variants in the PC3 and LNCaP human prostate cancer cell lines
<p>150bp paired-end reads (insert size 350bp) were obtained using the Illumina HiSeqX sequencer. Samtools v1.3.1 mpileup and bcftools were used to interrogate indexed BAM files, from whole-genome reads aligned to human reference genome GRCh38 build 82, and generate a VCF (Variant Call Format) file of single nucleotide variants (SNVs) and short indel variants. Variants private, or unique to a particular cell line, or shared by both were next identified. Variants (likely to be common germline variants) present in HapMap, 1000 genomes phase 3 (2,504 human genomes), and the National Heart Lung and Blood Institute’s Exome Sequencing Project (ESP) (bundled variant data file available at https://goo.gl/mEogvD) were excluded. Variant files (VCF) were filtered using SnpSift with the following parameters: 'QUAL \textgreater= 200 \&\& DP \textgreater= 30', where QUAL denotes minimum variance confidence and DP total depth threshold. Filtered variants were annotated using SnpEff v4.3g. Please see https://github.com/sciseim/PCaWGS for associated scripts.</p> <p> </p>
Supplementary data for ENACT: End-to-End Analysis and Cell Type Annotation for Visium High Definition (HD) Slides
<p>This project contains the datasets used to evaluate and reproduce the results of ENACT (End-to-End Analysis and Cell Type<br>Annotation for Visium HD Slides). The dataset consists of:</p> <ul> <li>a sample Visium HD sample of human colorectal cancer, courtesy of 10X Genomics (<a href="https://www.10xgenomics.com/datasets/visium-hd-cytassist-gene-expression-libraries-of-human-crc">Visium HD Spatial Gene Expression Library, Human Colorectal Cancer (FFPE) - 10x Genomics</a>). All credit goes to 10X Genomics.</li> <li>configuration files to be used to reproduce the results provided in the ENACT publication, </li> <li>evaluation plots used in the ENACT publication, and</li> <li>results obtained after running ENACT on the human colorectal cancer sample using the four bin-to-cell assignment methods (naive, weighted_by_area, weighted_by_transcript, and weighted_by_cluster) and the three cell annotation methods (Sargent, CellAssign, CellTypist)</li> </ul> <p>Additionally, results from running ENACT on the following three public VisiumHD samples are provided to showcase ENACT’s tissue-agnostic nature:</p> <div> <div> <div> <ul> <li> <p><a href="https://www.10xgenomics.com/datasets/visium-hd-cytassist-gene-expression-human-lung-cancer-post-xenium-expt">Human Lung FFPE</a> sample from a subject with Adenocarcinoma (age and gender unspecified),</p> </li> <li> <p><a href="https://www.10xgenomics.com/datasets/visium-hd-cytassist-gene-expression-human-tonsil-fresh-frozen">Human Tonsil Fresh Frozen</a> sample from a 21 year old male subject with Reactive Follicular Hyperplasia,</p> </li> <li> <p><a href="https://www.10xgenomics.com/datasets/visium-hd-cytassist-gene-expression-human-breast-cancer-fresh-frozen">Human Breast Fresh Frozen</a> sample from a 58 year old female subject with Ductal Carcinoma in Situ (DCIS).</p> </li> </ul> </div> </div> </div> <p> </p>
Annotated images from yeast cell lifespans - Testset- DetecDiv (id01)
<p>This dataset has been generated by manual annotation from timelapse images of yeast cells dividing using the DetecDiv software (see below).</p> <p>It contains ~ 35 000 images from 50 cell lifespans (each lifespan is made of between 700 and 1000 images). Each image is classified between 6 classes: "1. unbudded", "2. small", "3. large", "4. dead", "5. empty", "6. clog", according to the subfolder of the image.</p> <p>Besides, this folder also contains a .mat file containing 50 timeseries of classes corresponding to the lifespan of the 250 cells.</p> <p>It is related to the trained network <a href="https://doi.org/10.5281/zenodo.5553862">doi.org/10.5281/zenodo.5553862</a> from the software DetecDiv: <a href="https://github.com/gcharvin/DetecDiv">github.com/gcharvin/DetecDiv</a></p> <p><a href="https://biorxiv.org/content/10.1101/2021.10.05.463175v1">biorxiv.org/content/10.1101/2021.10.05.463175v1</a></p> <p> </p> <p><strong>Data type</strong>: 3D microscopy images (3 stacks brightfield) (.tif) + annotation (.mat)</p> <p><strong>Microscopy data type</strong>: Brightfield images with 3 stacks</p> <p><strong>Imaging</strong>: 20x 0.45 NA brightfield, 6.5µm*6.5µm sCMOS</p> <p><strong>Cell type</strong>: Budding yeast wild type cell (BY4742)</p> <p><strong>File format</strong>: .tif (16-bit RGB, 1 color per z-stack) + .mat</p> <p><strong>Image size</strong>: 60x60x1 (Pixel size: x,y: 325 nm, 3*z: 3*1325 nm)</p> <p> </p> <p><strong>Author(s)</strong>: Théo, ASPERT</p> <p><strong>Contact email</strong>: theo.aspert@gmail.com</p> <p><strong>Affiliation</strong>: IGBMC, Université de Strasbourg</p> <p><strong>Funding bodies</strong>: This work was supported by the Agence Nationale pour la Recherche, the grant ANR-10-LABX-0030-INRT, a French State fund managed by the Agence Nationale de la Recherche under the frame program Investissements d'Avenir ANR-10-IDEX-0002-02.</p>
Fully annotated Human Breast carcinoma cells for 3D segmentation training
<p>Fully annotated dataset for training of 3D segmentation models. We provide the Raw image patches in the Raw directory and instance segmentation labels in the RealMask directory, the semantic segmentation masks are provided in the BinaryMask directory. Manually curated from originally published dataset over here: http://celltrackingchallenge.net/3d-datasets/ by team at Kapoorlabs.</p>
HT1080WT cells embedded in 3D collagen type I matrices - manual annotations for cell instance segmentation and tracking
<p>Human fibrosarcoma HT1080WT (ATCC) cells at low cell densities embedded in 3D collagen type I matrices [1]. The time-lapse videos were recorded every 2 minutes for 16.7 hours and covered a field of view of 1002 pixels × 1004 pixels with a pixel size of 0.802 μm/pixel The videos were pre-processed to correct frame-to-frame drift artifacts, resulting in a final size of 983 pixels × 985 pixels pixels.</p> <p><em>Hasini Jayatilaka, Anjil Giri, Michelle Karl, Ivie Aifuwa, Nicholaus J Trenton, Jude M Phillip, Shyam Khatau, and Denis Wirtz. EB1 and cytoplasmic dynein mediate protrusion dynamics for efficient 3-dimensional cell migration. FASEB J., 32(3):1207–1221, 2018. ISSN 0892-6638. doi: 10.1096/fj.201700444RR.</em></p> <p>Further information about how to use this data is given in <a href="http://github.com/esgomezm/microscopy-dl-suite-tf">https://github.com/esgomezm/microscopy-dl-suite-tf</a></p> <p><strong>This dataset is provided together with the following preprint and if you use it, we would like to kindly ask you to cite it properly:</strong></p> <p><a href="https://arxiv.org/abs/2112.08817">Estibaliz Gómez-de-Mariscal, Hasini Jayatilaka, Özgün Çiçek, Thomas Brox, Denis Wirtz, Arrate Muñoz-Barrutia, *Search for temporal cell segmentation robustness in phase-contrast microscopy videos*, arXiv 2021 (arXiv:2112.08817)</a></p>
Annotated timeseries from yeast cell lifespans - Training and Test sets - DetecDiv (id03)
<p>This dataset represents timeseries lables of cell divisions, to train & test a classifier to detect cell-cycle slowdown.<br> It has been generated by manual annotation from yeast cells lifespans using the DetecDiv software (see below).</p> <p>It is made of 1 file containing :</p> <ul> <li>Groundtruth Input data (Xdata): 250 timeseries of classes "1. unbudded", "2. small", "3. large", "4. dead", "5. empty", "6. clog" which are outputs from the <a href="https://doi.org/10.5281/zenodo.5553862">doi.org/10.5281/zenodo.5553862</a> network</li> <li>Groundtruth outputdata (Ydata): 250 timeseries of classes "1. pre-slowdown", "2. post-slowdown", which have been annotated manually.</li> </ul> <p>The indexes from the Xdata correspond to that of the Ydata. Timeseries from 1->200 were used as training while 201->250 were used as validation.</p> <p>It is related to the trained network <a href="https://https://doi.org/10.5281/zenodo.5553829">doi.org/10.5281/zenodo.5553829</a> from the software DetecDiv: <a href="https://github.com/gcharvin/DetecDiv">github.com/gcharvin/DetecDiv</a></p> <p><a href="http://biorxiv.org/content/10.1101/2021.10.05.463175v1">biorxiv.org/content/10.1101/2021.10.05.463175v1</a></p> <p> </p> <p><strong>Data type</strong>: Vector timeseries (.mat) (250xF with F the number of frames, between 700 and 1000).</p> <p><strong>File format</strong>: .mat</p> <p><strong>Author(s)</strong>: Théo, ASPERT</p> <p><strong>Contact email</strong>: theo.aspert@gmail.com</p> <p><strong>Affiliation</strong>: IGBMC, Université de Strasbourg</p> <p><strong>Funding bodies</strong>: This work was supported by the Agence Nationale pour la Recherche, the grant ANR-10-LABX-0030-INRT, a French State fund managed by the Agence Nationale de la Recherche under the frame program Investissements d'Avenir ANR-10-IDEX-0002-02.</p> <p> </p>
Annotated pixels from brightfield images from yeast cell in microfluidic traps - Training and Test sets - DetecDiv (id02)
<p>This dataset has been generated by manual segmentation from timelapse images of yeast cells dividing using the DetecDiv software (see below).</p> <p>It contains ~1950 raw images (folder "images") associated with their mask (folder "labels") with 3 classes of pixels according to their value on the mask image, "1. background", "2. mother", "3. other".</p> <p>A splitSets.mat indicates which images have been used for training or for testing.</p> <p>It is related to the trained network <a href="https://doi.org/10.5281/zenodo.5553851">doi.org/10.5281/zenodo.5553851</a> from the software DetecDiv: github.com/gcharvin/DetecDiv</p> <p><a href="https://biorxiv.org/content/10.1101/2021.10.05.463175v1">biorxiv.org/content/10.1101/2021.10.05.463175v1</a></p> <p>-------------------------------------------------------</p> <p><strong>Data type</strong>: 2D microscopy images (brightfield) (.tif) + mask image (.tif)</p> <p><strong>Microscopy data type</strong>: Brightfield images</p> <p><strong>Imaging</strong>: 20x 0.45 NA brightfield, 6.5µm*6.5µm sCMOS</p> <p><strong>Cell type</strong>: Budding yeast wild type cell (BY4742)</p> <p><strong>File format</strong>: .tif (16-bit RGB, 1 color per z-stack) + .mat</p> <p><strong>Image size</strong>: Brightfield: 60x60x1 (Pixel size: x,y: 325 nm) // Mask: 60x60x1 (Pixel size: x,y: 325 nm), 3 pixel values (one per class).</p> <p><strong>Author(s)</strong>: Théo, ASPERT</p> <p><strong>Contact email</strong>: theo.aspert@gmail.com</p> <p><strong>Affiliation</strong>: IGBMC, Université de Strasbourg</p> <p><strong>Funding bodies</strong>: This work was supported by the Agence Nationale pour la Recherche, the grant ANR-10-LABX-0030-INRT, a French State fund managed by the Agence Nationale de la Recherche under the frame program Investissements d'Avenir ANR-10-IDEX-0002-02.</p>
Data accompanying MetaChrom and "Annotating functional effects of non-coding variants in neuropsychiatric cell types by Deep Transfer Learning"
<p>This is the data accompanying the paper " Annotating functional effects of non-coding variants in neuropsychiatric cell types by Deep Transfer Learning" and the GitHub repository https://github.com/bl-2633/MetaChrom. </p> <p><strong>/data/bed_files/ </strong>contains the unprocessed bed file used in analysis</p> <p><strong>/data/seq_data/</strong> contains processed data from the bed files with corresponding partition and labels for each sequence segment.</p> <p><strong>/trained_model/MetaChrom_model/</strong> contains the pre-trained MetaChrom model on neural developmental context</p> <p><strong>/trained_models/MetaFeat_model/ </strong>contains the MetaFeat model used in training</p> <p><strong>/tool/</strong> contains files and software necessary for the processing pipeline.</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.