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.
1,433
datasets available to search
ShareScore release 0.9.0
Dataset results
1,433 results for “mask”
Tree mask for regions of Rondônia - Brazil
<p>Tree masks for three regions of Rondônia/Brazil: Ariquemes, Ouro Preto D'Oeste, and Rolim de Moura.</p>
Ocean basin mask for coordinated climate model experiments to explore tropical basin interaction
<p>This is a netcdf dataset containing a basin mask for distinguishing major ocean basins (Atlantic, Pacific, etc.). It has been simplified to for use with the TBI experiments coordinated by the CLIVAR Research Focus on Tropical Basin Interaction (https://www.clivar.org/research-foci/basin-interaction). The original data can be found at https://iridl.ldeo.columbia.edu/SOURCES/.NOAA/.NODC/.WOA09/.Masks/.basin/index.html?Set-Language=en</p>
IRHMapNet Radargram and Mask Patches Dataset.
<p><br># README: IRHMapNet Radargram and Mask Patches Dataset</p> <p>## Dataset Overview</p> <p>This dataset contains radargram patches and corresponding mask patches used for training and evaluating the **IRHMapNet** model. The dataset is designed for segmentation of internal reflection horizons (IRHs) from radio-echo sounding data. The data is organized into two directories: radargram patches (`grams_patches`) and mask patches (`masks_patches`), with each patch having dimensions of 512x512 pixels.</p> <p>### Contents</p> <p>- **grams_patches/**: Contains 600 `.csv` files representing radargram patches. Each file is a 512x512 matrix corresponding to a small section of the radargram image.<br>- **masks_patches/**: Contains 600 `.csv` files representing the ground-truth mask patches for segmentation. Each file is a 512x512 binary mask, where `1` indicates the presence of an internal reflection horizon (IRH), and `0` represents background or ice.</p> <p>## Data Format</p> <p>- The files in both directories are named consistently, with matching pairs of radargram and mask patches.<br> - Example: `grams_patches/patch_001.csv` corresponds to `masks_patches/patch_001.csv`.<br>- Each `.csv` file is a comma-separated values (CSV) file containing 512 rows and 512 columns.</p> <p>## Directory Structure</p> <p>```<br>DATA_IRHMapNet/<br>├── grams_patches/ # Radargram patches<br>│ ├── patch_001.csv<br>│ ├── patch_002.csv<br>│ └── ... (600 patches)<br>└── masks_patches/ # Mask patches (Ground truth)<br> ├── patch_001.csv<br> ├── patch_002.csv<br> └── ... (600 patches)<br>```</p> <p>## Usage Instructions</p> <p>1. **Loading the data**: Each `.csv` file can be loaded using standard CSV reading functions in Python, such as `numpy.loadtxt()` or `pandas.read_csv()`.<br> <br> Example in Python using `numpy`:<br> ```python<br> import numpy as np<br> radargram_patch = np.loadtxt('grams_patches/patch_001.csv', delimiter=',')<br> mask_patch = np.loadtxt('masks_patches/patch_001.csv', delimiter=',')<br> ```</p> <p>2. **Model training**: These patches are designed for input into a U-Net or similar convolutional neural network architectures for pixel-wise classification tasks. The radargram patches serve as input, and the mask patches provide the ground-truth labels for training.</p> <p>## License</p> <p>This dataset is made available under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. You are free to:</p> <p> Share — copy and redistribute the material in any medium or format.<br> Adapt — remix, transform, and build upon the material for any purpose, even commercially.</p> <p>You must give appropriate credit by citing the following publication:</p> <p>**Citation**: Moqadam, H., et al. (2024). Going deeper with deep learning: Automatically tracing internal reflection horizons in ice sheets. *Journal of Geophysical Research: Machine Learning and Computation*. DOI: [insert DOI]</p> <p>## Contact</p> <p>For questions or further information, please contact Hameed Moqadam at [hameed.moqadam@awi.de].<br> Data Curator: Hameed Moqadam<br> Annotator: Hameed Moqadam<br> Data Manager: Hameed Moqadam</p>
Focused learning by antibody language models using preferential masking of non-templated regions
<p><strong>Motivation.</strong> While existing antibody language models (AbLMs) excel at predicting germline residues, they often struggle with mutated and non-templated residues, which concentrate in the complementarity-determining regions (CDRs) and are crucial for determining antigen-binding specificity. Many of these models are trained using a masked language modeling (MLM) objective with uniform masking probabilities; however, antibody recombination is modular in nature, creating relatively distinct regions of high and low complexity (non-templated and templated, respectively). We sought to determine whether and to what extent AbLMs can improve when trained using an alternative masking strategy based on this observation.</p> <p><strong>Results.</strong> We developed a variation on MLM called <strong><em>Preferential Masking</em></strong>, which alters masking probabilities to amplify training signals from the CDR3. We pre-trained two AbLMs using either uniform or preferential masking and observed that the latter improves pre-training efficiency and residue prediction accuracy in the highly variable CDR3. Preferential masking also improves antibody classification by native chain pairing and binding specificity, suggesting improved CDR3 understanding and indicating that non-random, learnable patterns help govern antibody chain pairing. We further show that specificity classification is largely informed by residues in the CDRs, demonstrating that AbLMs learn meaningful patterns that align with immunological understanding.</p> <p><strong>Files. </strong>The following files are included in this repository:</p> <ul> <li><strong><em>uniform_250k.tar.gz</em></strong>: Model weights for the Uniform-250k model.</li> <li><strong><em>uniform_350k.tar.gz</em></strong>: Model weights for the Uniform-350k model.</li> <li><strong><em>preferential_250k.tar.gz</em></strong>: Model weights for the Preferential-250k model.</li> <li><strong><em>train-eval-test_cdr-mask.tar.gz</em></strong>: Datasets used to train all three models above. Compressed folder containing three files: <em>A_train.csv</em>, <em>A_eval.csv</em>, and <em>B_test.csv</em>. Each row contains a natively paired sequence with its corresponding label-encoded CDR mask, designed to align with the tokenized amino acid sequence. Sequences were obtained from <a href="https://doi.org/10.1038/s41586-022-05371-z">Jaffe et al.</a> and <a href="https://doi.org/10.1016/j.celrep.2024.114307">Hurtado et al</a>. These are referenced in the paper as Dataset A (<em>A_train.csv, A_eval.csv)</em>, and Dataset B (<em>B_test.csv</em>)<em>.</em></li> <li><strong><em>test-set_annotations.tar.gz</em></strong>: Unpaired annotations for all test set (Dataset B) sequences: <em>B_test-set_annotations.csv</em>. Used for Fig. 3 and Fig. 4D. Annotations can be mapped back to the paired sequences using their `sequence_id` and `locus` information.</li> <li><strong><em>pair_classification.tar.gz</em></strong>: Two classification datasets used to train the classifier models in Figure 4: <em>C_native-0_shuffled-1.csv</em> (Dataset C) and <em>D_native-0_shuffled-1.csv</em> (Dataset D). Dataset C sequences were obtained from <a href="https://doi.org/10.1038/s41586-022-05371-z">Jaffe et al.</a> and <a href="https://doi.org/10.1016/j.celrep.2024.114307">Hurtado et al</a> (Dataset B), and Dataset D sequences were obtained from <a href="https://doi.org/10.1038/s41590-022-01230-1">Phad et al</a> and data generated as part of this study.</li> <li><strong><em>CoV_classification.tar.gz</em></strong>: Classification dataset used to train the classifier models in Figure 5: <em>E_hd-0_cov-1.csv </em>(Dataset E). CoV antibody sequences were obtained from <a href="https://doi.org/10.1093/bioinformatics/btaa739">CoV-AbDAb</a>, and healthy donor sequences were obtained from <a href="https://doi.org/10.1038/s41590-022-01230-1">Phad et al</a>.</li> </ul> <p><strong>Code.</strong> All code used for model training, testing, and figure generation is available under the MIT license on <a href="https://github.com/brineylab/preferential-masking-paper">GitHub.</a></p> <p> </p>
Figure 27 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 27. Display by a female Maratus personatus in response to male courtship display. 1-2, Sequential frames from a video showing a female (at left) raising and turning her opisthosoma from side to side while facing away from a nearby male (arrows). 3-6, Male displaying to a female that has turned away and raised her opisthosoma.
Figure 26 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 26 (continued). Rapid movement of legs III was sometimes asynchronous during this bilateral display (45, 48-50, 53- 56, 59-62, 64).
Figure 26 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 26 (continued). Brief intervals of no movement (e.g., 41-42) alternated with very rapid movement or vibration of the extended legs (e.g., 35, 39, and 44).
Figure 26 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 26. Sequential (1-68, continued on next two pages) video frames (25FPS, exposure 20 msec/frame) showing a male Maratus personatus displaying to a female from one position. Here consecutive frames are arranged in rows. 2, Movement of legs III from a horizontal to a vertical orientation was recorded here in a single frame (estimated duration 20-40 msec). Note the constant movement of legs III from frame to frame, including 'floppy' flexion at the femuro-patellar joint (11, 18). During pauses between rapid leg movement, legs III were generally in one of three positions: near-horizontal, near-vertical, and intermediate (V-shaped position). There was little visible movement of the pedipalps during this sequence, as the pedipalps were held in a lower position to expose the black, glabrous clypeus and chelicerae.
Figure 20 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 20. Bilateral display positions by a male Maratus personatus. As the extended and elevated legs III are waved in a transverse plane, the distal segments (beyond the femur) are often 'flopped' relative to the axis of the leg, as shown here (1, 2). Legs III may also be waved in a near vertical position (4, 5), and brought together above the spider (3, 6). Bilaterally symmetric displays like these are usually seen when the male is in a stationary position facing the female, and not stepping from side to side.
Figure 19 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 19. Developmental stages of four different female Maratus personatus. Note the light (6) and dark (17) colour variation of penultimates (6th instar).
Figure 23 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 23. Sequential (1-32) video frames (25FPS, exposure 20 msec/frame) showing a male Maratus personatus stepping to either side and waving the leading leg LIII while facing a female. 1-3, Bilateral display from a fixed position in front of the female. 4-24, Unilateral display of the leading right leg III while stepping to the right. 25-30, Bilateral display in position. 31- 32, Unilateral display of the leading left leg III while stepping to the left.
Figure 17 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 17. Developmental stages of the holotype male Maratus personatus. 12, The penultimate male (6th instar) is readily identified by its expanded pedipalps, but still has white clypeal setae like those of the female. The carapace of the 3rd instar is about 1 mm wide.
Figure 2. Four different living adult male M. personatus. 3 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 2. Four different living adult male M. personatus. 3, The scales of this male have rubbed off, exposing the black cuticle of the dorsal opisthosomal plate. 9, The small chelicerae are black and glabrous, separated on either side from a marginal band of white setae.
Figure 16 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 16. Second instar Maratus personatus. After their first moult, these spiderlings emerge from the egg-sac (nest) with well-developed eyes and footpads, and a covering of setae that suggests the appearance of an adult female. 12, The adult female (left) is about 4 times the length of a second instar (~1.6 mm).
Figure 15 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 15. Development of first instar Maratus personatus. When these first emerge from the egg (1-3), they are little more than naked embryos, with short legs and unpigmented eyes that continue to grow and develop prior to the first moult. Some authors call these prelarvae. As these grow, pigment of the retinae, dorsal carapace, and opisthosoma appears, and the legs develop to the point that the spiderlings can move about in the egg sac. Although development is continuous during most of the first instar, the more developed pre-first moult spiderlings are sometimes called larvae.
Figure 10 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 10. Views of three different living female Maratus personatus. 5, In some individuals four distinct chevrons at the rear of the dorsal opisthosoma can be seen. In other individuals these are indistinct.
Figure 1 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 1. Views of the living adult male holotype for Maratus personatus. 5, From the front, deep blue scales surround the blue anterior eyes, offset by white setae of the eye region, above, and the pedipalps, below. 12, Like other Maratus, M. personatus has a dorsal opisthosomal plate with a distinct edge (arrow), as well as a triangular tuft of white colular setae.
Figure 8 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 8. Views of three different living female Maratus personatus. From above, these are mostly dark brown to black, with tracts of off-white or ivory scales on the sides of the carapace and opisthosoma. Two or more pairs of spots (scale patches) may be seen on the dorsal opisthosoma.
Figure 21 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 21. Bilateral (1-3, 5-12) and unilateral (4, 13-14) display positions by six different male Maratus personatus. When stepping from side to side (13-14), males raise and wave the leading leg III. Bilateral display may be brief, when the male is not stepping to one side or the other.
Figure 7 in Maratus personatus, a masked peacock spider from Cape Riche, Western Australia (Araneae: Salticidae: Euophryinae)
Figure 7. Medial to lateral view of the left pedipalp of six different male Maratus personatus. Separation of the inner and outer apex of the embolus can be seen in lateral views (distinctly in 5, less distinctly in 2, 6, 9, 13 and 18). General features, including the shape and relative size of the embolus, the presence of medial tegular sclerotization proximal to the embolus, the pedipalp of the male M. personatus is much like those of other Maratus.
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.