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.
54
datasets available to search
ShareScore release 0.9.0
Dataset results
54 results for “neural structures”
Fast and long-term super-resolution imaging of ER nano-structural dynamics in living cells using a neural network
<p>Datasets acquired and generated for the manuscript "Fast and long-term super-resolution imaging of ER nano-structural dynamics in living cells using a neural network". The datasets include test, training and time series datasets each containing the raw data and the predicted data where it applies. </p>
Charting nanocluster structures via convolutional neural networks
<p>The repository contains a notebook for the training of the autoencoder for the RDFs for structural classification. The notebook describes the procedure going from RDFs calculation to clustering of the reduced space. In the folder are contained Au147 structures, together with the associated pretrained AE, the 3D chart and the different clustering performed varying mean shift bandwidth.</p> <p>Files:</p> <p>- ChartAu147.ipynb: notebook</p> <p>- Configurations: directory with the dataset divided according to the CNA classification of the structures, xyz format with no headers, every 147 lines is a single structure</p> <p>- Libraries: directory with functions imported in the notebook</p> <p>- Precomputed: directory with the precomputed outputs</p> <p> - rdfs.npy: preocmputed RDFs of the data stored in configurations, npy format to load with NumPy</p> <p> - labels.npy: CNA labels of the RDFs, npy format to load with NumPy</p> <p> - model_au147.pth: pretrained model for au147</p> <p> - scaler_au147.pkl: minmax scaler of the RDFs</p> <p> - chart_3d.dat: 3d space generated via the encoder on the au147 dataset</p> <p> - ae_reconstructions.npy: reconstructions of the rdfs of the model (model_au147.pth)</p> <p> - MSscanbw: pretrained mean shift clustering with different bandwidths, the file "clus_vs_bw.dat" reports the number of clusters associated to each bandwidth</p>
HEroBM: a deep equivariant graph neural network for high-fidelity backmapping from coarse-grained to all-atom structures
<p><span>Molecular simulations play a pivotal role in chemistry, biology, and material sciences, enabling the</span><br><span>study of complex dynamic properties within systems. Coarse-grained (CG) techniques have emerged</span><br><span>as indispensable tools in this domain, facilitating the sampling of large-scale systems and extending</span><br><span>simulation timescales by simplifying system representation. However, CG approaches involve a trade-</span><br><span>off: they sacrifice atomistic details that may be crucial for understanding the underlying processes.</span><br><span>To address this challenge, a recommended strategy is to identify key CG conformations and employ</span><br><span>backmapping methods to retrieve atomistic coordinates. Currently, rule-based methods often yield</span><br><span>suboptimal geometries and rely on energy relaxation, resulting in less-than-optimal outcomes. In</span><br><span>contrast, machine learning techniques offer higher accuracy but may lack transferability between</span><br><span>systems or be tied to specific CG mappings. In this study, we present HEroBM, a dynamic and scalable</span><br><span>method that utilizes deep equivariant graph neural networks and a hierarchical approach to achieve</span><br><span>high-resolution backmapping. HEroBM is capable of handling any type of CG mapping, providing a</span><br><span>versatile and efficient protocol for reconstructing atomistic structures with high accuracy. Grounded</span><br><span>in local principles, HEroBM spans the entire chemical space and can be applied across systems of</span><br><span>varying composition and sizes. We demonstrate the versatility of our framework through a range of</span><br><span>biological systems, including a complex real-case scenario. Here, our end-to-end backmapping approach</span><br><span>accurately generates atomistic coordinates for a G protein-coupled receptor bound to an organic small</span><br><span>molecule within a cholesterol/phospholipid bilayer. The high-fidelity HEroBM backmapping enables</span><br><span>researchers to effortlessly transition between CG and all-atom simulations, opening unprecedented</span><br><span>avenues for molecular investigations.</span></p>
NoSyms: A neural network approach to detecting data structures in raw memory
<p>This data was used for a experiments with graph convolutional neural networks for memory forensics as part of a bachelor thesis (included as pdf).<br> <br> Abstract:<br> <br> This work presents a neural network based approach for data structure detection in raw memory that does not require an entirely matching description of the target data structure. Instead, it’s merely necessary to provide multiple descriptions of data structures similar to the target as training data in the form of debugging symbols. The core contribution of this work is a formal description and implementation of encoding data structure definitions as well as raw memory contents such that they can be processed by graph convolutional neural networks. A description and implementation of a neural network meant to detect data structures in the memory contents of a Linux Kernel demonstrates the practical applicability of the described approach.<br> <br> The Code is available on GitHub <a href="https://github.com/NiklasBeierl/nosyms">https://github.com/NiklasBeierl/nosyms</a>.<br> <br> nokaslr_dump is the qemu memory snapshot used to test the model.<br> nokaslr.raw is the "raw" form of the snapshot as produced by Volatility 3's layerwriter plugin.<br> symbols-training-data contains the Volatility symbol JSON files from which training data was derived.<br> nokaslr_pointers.csv lists the kernel space pointers in the snapshot and<br> nokaslr_tasks.csv lists task structs in the snapshot. Both were extracted via a Volatility plugins that are included in the GitHub Repo.<br> vmlinux-5.4.0-58-generic.json is the symbol file for the kernel the snapshot was taken from.<br> other-symbols.zip contains symbol files I generated vor various other kernels but did not end up using, use at your own discretion.</p>
Deep neural networks and humans both benefit from compositional language structure
<p>This dataset holds the results generated in the paper:</p> <p>Deep neural networks and humans both benefit from compositional language structure</p> <p>by L. Galke, Y. Ram, and L. Raviv.</p>
Robust Method for Property Prediction via Artificial Neural Networks: Incorporating Key Structural Features for Carbon Dioxide – Ionic Liquid Mixtures
<p>This Dataset comprises two sub-sets of information:</p> <ul> <li>Database and Results of the work present in the paper "Robust Method for Property Prediction via Artificial Neural Networks: Incorporating Key Structural Features for Carbon Dioxide – Ionic Liquid Mixtures" published in The Journal of Physical Chemistry B (https://doi.org/10.1021/acs.jpcb.4c04432).</li> <li>Sample of the code used, in order to reproduce any of the results presented above. This can be found in the previous version of this Dataset (v1.0 https://zenodo.org/records/11216901)</li> </ul> <p> </p> <p>Regarding the sample code, an example for all ANN Models used in this work is provided. This includes the three models used:</p> <ol> <li>One based only on Critical Properties of Ionic Liquids (CRT Model)</li> <li>One based only on Structural Properties of Ionic Liquids (STR Model)</li> <li>One combination of the previous models, taking into account both Critical and Structural Properties (COMB Model)</li> </ol> <p>In this manner, it is possible to observe the differences between the performance of the different models, either through statiscal analysis or using graphical representation. This allows for the benchmarking to be done in a more concise way.</p>
Data for "Unfolding the structural stability of nanoalloys via symmetry-constrained genetic algorithm and neural network potential"
<p><strong>PtNi_alloy_eam.db</strong> is the dataset (ase.db object) consisting of 55982 intially sampled Pt-Ni alloy structures with EAM energies and forces.</p> <p><strong>PtNi_alloy_dft.db</strong> is the dataset (ase.db object) consisting of the final 6828 resampled Pt-Ni alloy structures with DFT energies and forces calculated by VASP. This is the training set for the NNP, and could be very useful for fitting other machine learning models.</p> <p><strong>PtNi_nanoalloy_vertices_nnp.db</strong> is the dataset (ase.db object) consisting of all the vertices (stable structures) on the convex hulls obtained from NNP-based SCGA runs on 36 Pt-Ni nanoalloy systems. The energies are given by the NNP. Additional information such as mixing energy, motif and symmetry axis are also saved in the dataset and can be queried by the 'data' keyword. An xyz format trajectory of these stable structures is also uploaded.</p> <p>All the input files and scripts for hybrid MC-MD simulations, QBC resampling, DFT calculations, NNP training, NNP-based SCGA runs and convex hull analysis are provided in <strong>inputs_and_scripts.zip</strong>.</p>
Database of small molecule X-ray absorption spectra, featurized structures, and neural network ensembles
<p>Companion data for arXiv preprint <em>Uncertainty-aware predictions of molecular X-ray absorption spectra using neural network ensembles</em> (<a href="https://arxiv.org/abs/2210.00336">https://arxiv.org/abs/2210.00336</a>), by Animesh Ghose, Mikhail Segal, Fanchen Meng, Zhu Liang, Mark S. Hybertsen, Xiaohui Qu, Eli Stavitski, Shinjae Yoo, Deyu Lu & Matthew R. Carbone.</p> <p><strong>Included</strong></p> <ul> <li>*-XANES-*.tar.bz2: raw input/output files for all molecular simulations used in the work. These inputs and outputs correspond to the structural data in the QM9 dataset.</li> <li>ml_ready.tar.bz2: machine learning-ready data (featurized spectra). Used as input to the neural network ensembles.</li> <li>XANES-220712-ACSF-*.tar.bz2: neural network ensembles used in this work.</li> </ul> <p><strong>Notes</strong></p> <ul> <li>The FEFF9 code [J. J. Rehr, J. J. Kas, F. D. Vila, M. P. Prange, and K. Jorissen, <em>Phys. Chem. Chem. Phys.</em> <strong>12</strong>, 5503 (2010)] was used to generate all X-ray absorption near-edge structure (XANES) spectra.</li> <li>All molecular structures were sourced from the QM9 database [R. Ramakrishnan, P. O. Dral, M. Rupp, and O. A. Von Lilienfeld, <em>Sci. Data</em> <strong>1</strong>, 1 (2014)].</li> </ul> <p><strong>Funding</strong></p> <p>This research is based upon work supported by the U.S. Department of Energy, Office of Science, Office Basic Energy Sciences, under Award Number FWP PS-030. This research also used theory and computational resources of the Center for Functional Nanomaterials, which is a U.S. Department of Energy Office of Science User Facility, and the Scientific Data and Computing Center, a component of the Computational Science Initiative, at Brookhaven National Laboratory under Contract No. DE-SC0012704.</p>
Dataset from the paper entitled "Complex structure of molten FLiBe (2 LiF – BeF2) examined by experimental neutron scattering, X-ray scattering, and deep neural network-based molecular dynamics"
<p>Dataset from the paper entitled "Complex structure of molten FLiBe (2 LiF – BeF2) examined by experimental neutron scattering, X-ray scattering, and deep neural network-based molecular dynamics". These data include experimental total scattering measurements and molecular dynamics simulations on the molten structure of FLiBe. </p>
Neural structure of a sensory decoder for motor control
<p>Data associated with 'Neural structure of a sensory decoder for motor control.' Egger, SW and Lisberger, SG. <em>Nature Communications</em>, 2022.</p>
Figure 5. ANN Structure 4.-Impact of Ethnic Group on Human Emotion Recognition Using Backpropagation Neural Network
<p>For classification purpose of the emotions, we use ANN of supervised learning based on<br> backpropagation algorithm. Backpropagation neural network architecture is used with its standards<br> learning function with 28 inputs representing the extracted features and 6 outputs representing 6<br> emotions, happy, sad, angry, fear, shame and disgust. the emotions. We have also a hidden layer<br> with 16 nodes selected after various trails to obtain the best results. The used ANN is depicted in<br> Figure 5.</p>
BRAIN Journal-High Performance Data mining by Genetic Neural Network-Figure 4. Structural Crossover
<p>Guided crossover operator is based on the two point separation from parents are selected<br> Left and right parts of them are related to each other by the condition to be meaningful With this<br> new child of his parents is that. But a new generation of the random choice to have reached this<br> stage. The crossover rate is fixed for our algorithm.</p>
BRAIN Journal-High Performance Data mining by Genetic Neural Network-Figure 3. The Structure of Neural Network
<p>A neural network (NN), in the case of artificial neurons called artificial neural<br> network (ANN) or simulated neural network (SNN), is an interconnected group of natural<br> or artificial neurons that uses a mathematical or computational model for information<br> processing based on a connectionist approach to computation. In most cases an ANN is an adaptive<br> system that changes its structure based on external or internal information that flows through the<br> network[9].<br> In more practical terms neural networks are nonlinear statistical data modelling or decision<br> making tools. They can be used to model complex relationships between inputs and outputs or<br> to find patterns in data.<br> Two neurons neural network active in memory (ON or 1) or disable (Off or 0), and each<br> edge (synapses or connections between nodes) is a weight. Edges with positive weight, stimulate or<br> activate next active node, and edges with negative weight, disable or inhibit the next connected<br> node (if it is active) ones.</p>
Figure 1. Brain Structure-Classification of Human Emotion from Deap EEG Signal Using Hybrid Improved Neural Networks with Cuckoo Search
<p>EEG data have collected from<br> desirable subjects. Each and every EEG signal has different kind of bands like Alpha, Beta,<br> Gamma, Theta, and Delta. Each band stores the particular information about the emotions. Alpha<br> band (8-13 Hz) which located in Frontal Occipital, Beta band (13-30 Hz) which located in Frontal<br> Central, Gamma band (30-100 Hz), Theta band (4- 7 Hz) which located in Midline Temp, Delta<br> band (0-4Hz) which located in Frontal Lobe. Before processing the EEG signal and extracting these<br> bands, preprocess the signal and reduce the noise. The basic brain figure is shown in below.</p>
Neural Networks for Structure-Informed Prediction of Formation Energy (employed in SIPFENN)
<p>pySIPFENN Documentation: <a href="https://pysipfenn.org">pysipfenn.org</a></p> <p>pySIPFENN GitHub: <a href="https://github.com/PhasesResearchLab/pySIPFENN">git.pysipfenn.org</a></p> <p>Original SIPFENN Paper: <a href="https://doi.org/10.1016/j.commatsci.2022.111254">10.1016/j.commatsci.2022.111254</a></p> <p> </p> <p>Network Changelog:</p> <p>V 0.10 - All models moved to the open ONNX format for improved interchangeability; NN30 neural network similar to NN20 but accepting the new KS2022 feature vector; Python code migrated to public GitHub repository.</p> <p>V 0.9 - Python code updated to the release version; paper published</p> <p>V 0.8 - Python code (beta) to run models included</p> <p>V 0.7 - Original upload of development models </p> <p> </p> <p>Selected works with SIPFENN alongside DFT and experiments:</p> <p>- <a href="https://doi.org/10.1016/j.actamat.2021.117448">10.1016/j.actamat.2021.117448</a></p> <p>- <a href="https://doi.org/10.1038/s41598-021-03578-0">10.1038/s41598-021-03578-0</a></p> <p> </p> <p>SIPFENN Abstract (original publication, 2021):</p> <p>In recent years, numerous studies have employed machine learning (ML) techniques to enable orders of magnitude faster high-throughput materials discovery by augmentation of existing methods or as standalone tools. In this paper, we introduce a new neural network-based tool for the prediction of formation energies based on elemental and structural features of Voronoi-tessellated materials. We provide a self-contained overview of the ML techniques used. Of particular importance is the connection between the ML and the true material-property relationship, how to improve the generalization accuracy by reducing overfitting, and how new data can be incorporated into the model to tune it to a specific material system.<br> <br> In the course of this work, over 30 novel neural network architectures were designed and tested. This lead to three final models optimized for (1) highest test accuracy on the Open Quantum Materials Database (OQMD), (2) performance in the discovery of new materials, and (3) performance at a low computational cost. On a test set of 21,800 compounds randomly selected from OQMD, they achieve mean average error (MAE) of 28, 40, and 42 meV/atom respectively. The second model provides better predictions on materials far from ones reported in OQMD, while the third reduces the computational cost by a factor of 8.<br> <br> We collect our results in a new open-source tool called SIPFENN (Structure-Informed Prediction of Formation Energy using Neural Networks). SIPFENN not only improves the accuracy beyond existing models but also ships in a ready-to-use form with pre-trained neural networks and a user interface. </p> <p> </p> <p>Contacts:</p> <p>- Adam Krajewski: ak@psu.edu</p> <p>- Prof. Zi-Kui Liu: zxl15@psu.edu</p>
Bugsplainer: Explaining Software Bugs Leveraging Code Structures in Neural Machine Translation
<p>Software bugs claim approximately 50% of development time and cost the global economy billions of dollars. Once a bug is reported, the assigned developer attempts to identify and understand the source code responsible for the bug and then corrects the code. Over the last five decades, there has been significant research on automatically finding or correcting software bugs. However, there has been little research on automatically explaining the bugs to the developers, which is essential but a highly challenging task. In this paper, we propose Bugsplainer, a transformer-based generative model, that generates natural language explanations for software bugs by learning from a large corpus of bug-fix commits. Bugsplainer can leverage structural information and buggy patterns from the source code to generate an explanation for a bug. Our evaluation using three performance metrics shows that Bugsplainer can generate understandable and good explanations according to Google's standard, and can outperform multiple baselines from the literature. We also conduct a developer study involving 20 participants where the explanations from Bugsplainer were found to be more accurate, more precise, more concise and more useful than the baselines.</p>
Neural representations of events arise from temporal community structure
Open the record for dataset details and reuse information.
Supplementary data for article 'Estimating and abstracting the 3D structure of feline bones using neural networks on X-ray (2D) images'
<p>3D DICOM volumes (CT scans) of feline femora, PNGs generated from them as DRRs using MeVisLab, and STLs generated from the DICOM volumes with MIMICS or MeshLab. Software to work with these files can be found at http://doi.org/10.5281/zenodo.3829423</p>
Forecasting of the Geomagnetic Activity for the Next 3 Days Utilizing Neural Networks Based on Parameters Related to Large-scale Structures of the Solar Corona
<p>These are supplementary data for the paper "Forecasting of the Geomagnetic Activity for the Next 3 Days Utilizing Neural Networks Based on Parameters Related to Large-scale Structures of the Solar Corona". They are:</p> <ul> <li>Python code to forecast Kp index</li> <li><span>Code to construct a nerual network model</span></li> </ul>
Training and validation datasets for "Three-Dimensional Implicit Structural Modeling Using Convolutional Neural Network"
<p>This is training and validation datasets used in manuscript "Three-Dimensional Implicit Structural Modeling Using Convolutional Neural Network". In this manuscript, we propose an efficient deep learning method using a Convolutional Neural Network (CNN) to predict a scalar field from sparse structural data associated with multiple distinct stratigraphic layers and faults. The CNN architecture is beneficial for the flexible incorporation of empirical geological knowledge when trained with numerous and realistic structural models that are automatically generated from a data simulation workflow. It also presents an expressive characteristic of integrating various types of structural constraints by optimally minimizing a hybrid loss function to compare predicted and reference structural models, opening new opportunities for further improving geological modeling. </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.