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.
38
datasets available to search
ShareScore release 0.9.0
Dataset results
38 results for “network attention”
Dataset of behavioral and neurophysiological data of a virtual sailing task published in: "Providing task instructions during motor training enhances performance and modulates attentional brain networks"
<p>Dataset belonging to the behavioral and neurophysiological data of the publication: "Providing task instructions during motor training enhances performance and modulates attentional brain networks". The two uploaded Zip files contain kinematic and electroencephalographic data of 36 participants for the Obstacle and HorizonTask.</p>
Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks
<p>Residue-residue distance information is useful for predicting tertiary structures of protein monomers or quaternary structures of protein complexes. Many deep learning methods have been developed to predict intra-chain residue-residue distances of monomers accurately, but few methods can accurately predict inter-chain residue-residue distances of complexes. We develop a deep learning method CDPred (i.e., Complex Distance Prediction) based on the 2D attention-powered residual network to address the gap. Tested on two homodimer datasets, CDPred achieves the precision of 60.94% and 42.93% for top L/5 inter-chain contact predictions (L: length of the monomer in homodimer), respectively, substantially higher than DeepHomo’s 37.40% and 23.08% and GLINTER’s 48.09% and 36.74%. Tested on the two heterodimer datasets, the top Ls/5 inter-chain contact prediction precision (Ls: length of the shorter monomer in heterodimer) of CDPred is 47.59% and 22.87% respectively, surpassing GLINTER’s 23.24% and 13.49%. Moreover, the prediction of CDPred is complementary with that of AlphaFold2-multimer.</p>
Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks
<p>Residue-residue distance information is useful for predicting tertiary structures of protein monomers or quaternary structures of protein complexes. Many deep learning methods have been developed to predict intra-chain residue-residue distances of monomers accurately, but few methods can accurately predict inter-chain residue-residue distances of complexes. We develop a deep learning method CDPred (i.e., Complex Distance Prediction) based on the 2D attention-powered residual network to address the gap. Tested on two homodimer datasets, CDPred achieves the precision of 60.94% and 42.93% for top L/5 inter-chain contact predictions (L: length of the monomer in homodimer), respectively, substantially higher than DeepHomo’s 37.40% and 23.08% and GLINTER’s 48.09% and 36.74%. Tested on the two heterodimer datasets, the top Ls/5 inter-chain contact prediction precision (Ls: length of the shorter monomer in heterodimer) of CDPred is 47.59% and 22.87% respectively, surpassing GLINTER’s 23.24% and 13.49%. Moreover, the prediction of CDPred is complementary with that of AlphaFold2-multimer.</p>
Dataset supplementing Marx, S., Gruenhage, G., Walper, D., Rutishauser, U., Einhäuser, W. (2015). Competition with and without priority control: linking rivalry to attention through winner-take-all networks with memory. Annals of the New York Academy of Sciences. 1339, 138-153.
<p>Data supplementing the paper Marx, S., Gruenhage, G., Walper, D., Rutishauser, U., Einhäuser, W. (2015). Competition with and without priority control: linking rivalry to attention through winner-take-all networks with memory. <em>Annals of the New York Academy of Sciences. 1339, </em>138-153. doi: 10.1111/nyas.12575 The files can be freely used for scientific purposes, provided this reference is appropriately cited.</p> <p>Files contain the behavioral data, the model can be found at https://doi.org/10.5281/zenodo.573026</p> <p> </p> <p>The following files are contained in this folder:</p> <p>dataExp1.mat contains the data of experiment 1</p> <p>The variables durationLeft and durationRight contain 5 x 6 x 6 cell arrays with the dominance durations for the left and right grating, respectively. Dimensions are subject x contrast level left x contrast level right.</p> <p><br> dataExp2.mat contains the data of experiment 2</p> <p>Variables buttonStart, buttonEnd and whichButton contain 3x4x5 (contrast levels x blank duration levels x subjects) cell arrays that contain the start time and end time of each button press, and which button (1/2) was pressed, respectively.</p> <p>Variables presStart and presEnd contain 3x4x5 (contrast levels x blank duration levels x subjects) cell arrays that contain start and end of each blank period. All time stamps refer to the onset of the first blanking trial (end of continuous presentation)</p> <p>Variable prevPerz contains the percept (button) that was pressed at the end of the continuous presentation period.</p> <p><br> figure3_human.m, figure4_human.m and figure6_human.m exemplify the usage of the data by re-plotting the figures containing human data of the aforementioned paper</p>
Flood water depth prediction with Convolutional Temporal Attention Networks
<p>SwissFlood dataset from Flood water depth prediction with Convolutional Temporal Attention Networks paper.</p>
Feature attention graph neural network for estimating brain age and identifying important neural connections in mouse models of genetic risk for Alzheimer's disease
<p>Connectome, traits and behavior data for APOE234 mice.</p> <ul> <li>1. connectome.zip: mouse brain structural connectivity matrices from diffusion MRI.</li> <li>2. FAGNN_Phenotype.csv: a sheet of trait information of mice used in the study.</li> </ul> <p>columns: winding numbers, total distance, normalized NE time, normalized NE distance, normalized NW time, normalized NW distance, normalized SE time, normalized SE distance, normlaized SW time, normalized SW distance, island latency to first entry, island entries, normalized thigmataxis time, and normalized thigmotaxis distance</p> <div>rows: 4 trials for each day from day 1 to day 5 with 1 probing test each at day 5 and day 8</div> <ul> <li>3. mouse_anatomy.csv: brain region information regarding the connectivity matrix.</li> <li>4. behavior.zip: behavioral data for each mouse from Morris Water Maze experiments.</li> </ul>
Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks
<p>Benchmark data sets of CDPred as described in</p> <p><strong>Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks</strong></p> <p>Zhiye Guo<sup>1</sup>, Jian Liu<sup>1</sup>, Jeffrey Skolnick<sup>2</sup>, Jianlin Cheng<sup>1*</sup></p> <p><sup>1 </sup>Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211</p> <p><sup>2 </sup>School of Biological Sciences, Georgia Institute of Technology, Atlanta, GA 30332-2000</p> <p>*Corresponding author (chengji@missouri.edu)</p> <p>There is four test dataset in this package, each test dataset contains four different folders and one list file. The <strong>afpred_pdb</strong> includes all the corresponding monomer structures predicted by alphafold. The <strong>cdpred_output </strong>includes the prediction results of our tool CDPred for each dataset. The <strong>pre_gen_a3m </strong>includes the multiple sequence alignments file used by CDPred to generate prediction results. And the <strong>true_pdb </strong>includes the fasta file for the test dataset and its heavy atom distance map (h_dist) and carbon alpha distance map (real_dist) that extract from the native structure.</p> <p>HomoTest1: The homodimer test dataset contains 28 targets collect from CASP_CAPRI 10-13</p> <p>HomoTest2: The homodimer test dataset contains 23 targets collect from CASP_CAPRI 13-14</p> <p>HeteroTest1: The heterodimer test dataset contains 9 targets collect from CASP_CAPRI13-14</p> <p>HeteroTest2: The heterodimer test dataset contains 55 targets collect from PDB bank 09-2021 to 11-2021</p>
Data from: Task-evoked metabolic demands of the posteromedial default mode network are shaped by dorsal attention and frontoparietal control networks
<p><span>External tasks evoke characteristic fMRI BOLD signal deactivations in the default mode network (DMN). However, for the corresponding metabolic glucose demands both decreases and increases have been reported. To resolve this discrepancy, functional PET/MRI data from 50 healthy subjects performing Tetris® were combined with previously published data sets of working memory, visual and motor stimulation. We show that the glucose metabolism of the posteromedial DMN is dependent on the metabolic demands of the correspondingly engaged task-positive networks. Specifically, the dorsal attention and frontoparietal network shape the glucose metabolism of the posteromedial DMN in opposing directions. While tasks that mainly require an external focus of attention lead to a consistent downregulation of both metabolism and the BOLD signal in the posteromedial DMN, cognitive control during working memory requires a metabolically expensive BOLD suppression. This indicates that two types of BOLD deactivations with different oxygen-to-glucose index may occur in this region. We further speculate that consistent downregulation of the two signals is mediated by decreased glutamate signaling, while divergence may be subject to active GABAergic inhibition. The results demonstrate that the DMN relates to cognitive processing in a flexible manner and does not always act as a cohesive task-negative network in isolation.</span></p>
Effect of Transcranial Magnetic Stimulation to the Frontoparietal Attention Network on Anxiety Potentiated Startle
ClinicalTrials.gov study NCT03027414. IPD Sharing: Not stated. Countries: 1. Publications: 4.
Data from: Task-evoked metabolic demands of the posteromedial default mode network are shaped by dorsal attention and frontoparietal control networks
Open the record for dataset details and reuse information.
Double attention recurrent convolution neural network for answer selection
<p>Answer selection is one of the key steps in many Question Answering (QA) applications. In this paper, a new deep model with two kinds of attention is proposed for answer selection: the Double Attention Recurrent Convolution Neural Network (DARCNN). Double attention means self-attention and cross-attention. The design inspiration of this model came from the Transformer in the domain of machine translation. Self-attention can directly calculate dependencies between words regardless of the distance. However, self-attention ignores the distinction between its surrounding words and other words. Thus, we design a decay self-attention that prioritizes local words in a sentence. In addition, cross-attention is established to achieve interaction between question and candidate answer. With the outputs of self-attention and decay self-attention, we can get two kinds of interactive information via cross-attention. Finally, using the feature vectors of the question and answer, elementwise multiplication is used to combine with them and multi-layer perceptron (MLP) is used to predict the matching score. Experimental results on four QA datasets containing Chinese and English show that DARCNN performs better than other answer selection models, thereby demonstrating the effectiveness of self-attention, decay self-attention and cross-attention in answer-selection tasks.</p>
GAABind: A Geometry-Aware Attention-Based Network for Accurate Protein-Ligand Binding Pose and Binding Affinity Prediction
<p>The preprocessed dataset for paper "GAABind: A Geometry-Aware Attention-Based Network for Accurate Protein-Ligand Binding Pose and Binding Affinity Prediction" with associated code at https://github.com/Mercuryhs/GAABind.</p><p>The dataset files are saved as .pkl file for the convenience of use.</p><p><strong>Paper Abstract</strong>:</p><p>Protein-ligand interactions are increasingly profiled at high-throughput, playing a vital role in lead compound discovery and drug optimization. Accurate prediction of binding pose and binding affinity constitutes a pivotal challenge in advancing our computational understanding of protein-ligand interactions. However, inherent limitations still exist, including high computational cost for conformational search sampling in traditional molecular docking tools, and the unsatisfactory molecular representation learning and intermolecular interaction modeling in deep learning-based methods. Here we propose a geometry-aware attention-based deep learning model, GAABind, which effectively predicts the pocket- ligand binding pose and binding affinity within a multi-task learning framework. Specifically, GAABind comprehensively captures the geometric and topological properties of both binding pockets and ligands, and employs expressive molecular representation learning to model intramolecular interactions. Moreover, GAABind proficiently learns the intermolecular many-body interactions and simulates the dynamic conformational adaptations of the ligand during its interaction with the protein through meticulously designed networks. We trained GAABind on the PDBbindv2020 and evaluated it on the CASF2016 dataset, the results indicate that GAABind achieves state-of-the-art performance in binding pose prediction and shows comparable binding affinity prediction performance. Notably, GAABind achieves a success rate of 82.8% in binding pose prediction, and the Pearson correlation between predicted and experimental binding affinities reaches up to 0.803. Additionally, we assessed GAABind's performance on the SARS-CoV-2 main protease cross-docking dataset. In this evaluation, GAABind demonstrates a notable success rate of 76.5% in binding pose prediction and achieves the highest Pearson correlation coefficient in binding affinity prediction compared with all baseline methods.</p>
Dataset for "MA-MGAN: Mixed Attention Markovian Generative Adversarial Network for Meteorological Downscaling"
<p>Dataset for "MA-MGAN: Mixed Attention Markovian Generative Adversarial Network for Meteorological Downscaling", including the training set and testing set used by the model, as well as the experimental results in the main text and supplementary Information.</p>
Networks of Swiss water governance issues. Studying fit between media attention and organizational activity
<p>Anonymized data and R code needed to replicate the analysis presented in the study "Networks of Swiss water governance issues. Studying fit between media attention and organizational activity" to be published in Society & Natural Resources.</p> <p>The study looks at how relations between Swiss water governance issues are portrayed in the media as compared to the way organizations involved in water governance reflect these relations in their activity.</p> <p>This is a paper output of the SNF funded project "Overlapping subsystems". Access to the complete, non-anonymized dataset is restricted.</p> <p>Study doi: tbd</p>
DMGAT: Predicting ncRNA-Drug resistance associations based on diffusion map and heterogeneous graph attention network
<p>Dataset for the paper: DMGAT: Predicting ncRNA-Drug resistance associations based on diffusion map and heterogeneous graph attention network</p>
Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics [Dataset]
<p>Supplementary data for 'Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics'. </p>
Our processed LoveDA dataset for "LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images"
<p>Our processed LoveDA dataset is used for the paper "<a href="https://doi.org/10.7717/peerj-cs.1467">LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images</a>"</p>
Our processed CITY_OSM dataset for "LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images"
<p>Our processed CITY_OSM dataset is used for the paper "<a href="https://doi.org/10.7717/peerj-cs.1467">LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images</a>".</p>
A dataset of aerial images taken by UAV that we collected for "LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images"
<p>Our private dataset of UAV aerial imagery for paper "<a href="https://doi.org/10.7717/peerj-cs.1467">LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images</a>".</p>
The surgical instrument dataset in the paper A Lightweight Segmentation Network for Endoscopic Surgical Instruments Based on Edge Refinement and Efficient Self-Attention
<p>In the paper A Lightweight Segmentation Network for Endoscopic Surgical Instruments Based on Edge Refinement and Efficient Self-Attention, we collected and annotated the surgical instrument dataset.</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.