Find research datasets worth reusing

Goat-CNN: A Lightweight Convolutional Neural Network for Pose-Independent Body Condition Score Estimation in Goats

<p>Here we introduce the dataset utilized in our published paper entitled "<a href="https://www.sciencedirect.com/science/article/pii/S2666154324002114">Goat-CNN: A Lightweight Convolutional Neural Network for Pose-Independent Body Condition Score Estimation in Goats</a>".</p> <p>Contained within the "bcs" folder are all the videos collected for this study. Each video file is named with a format denoting its respective details. The first number signifies the sequence of collection, the second denotes the ear tag, and the final figure represents the body condition score (BCS) value.</p> <p>For example: "1_158734_2.50" indicates the first sampling of an animal with the ear tag "158734" and a BCS value of "2.50".</p> <p>Additionally, we provide two Python scripts in this repository. The first script, "Video2Frame.py", facilitates the splitting of videos into individual frames. The second script, "Frames2npy.py", converts these frames into two numpy-friendly files with the extension ".npy". These files contain both the images ("X_train_bcs300.npy") and their corresponding labels ("Y_train_bcs300.npy").</p> <p>Furthermore, for the convenience of swift experimentation, we have included the desired .npy files within the repository.</p> <p>To load these files into your Python environment, you can use the following code snippet:</p> <div> <div>th4figs = '/content/drive/MyDrive/compag_2023/'</div> <br> <div>path4images = "/content/drive/MyDrive/CodeRefarm/datasets/BCS/X_train_bcs300.npy"</div> <div>Xtrain = np.load(path4images)</div> <br> <div>path4labels = "/content/drive/MyDrive/CodeRefarm/datasets/BCS/Y_train_bcs300.npy"</div> <div>Ytrain = np.load(path4labels).astype(float)</div> <br> <div>print("X train : ", Xtrain.shape)</div> <div>print("Y train : ", Ytrain.shape)</div> <div> <div> <div> <div> <div> <div> <div> </div> </div> <div> </div> </div> </div> </div> </div> <div> <div> <div> <div> <div> <div> <div> <div> <pre>X train : (5332, 300, 300, 3) Y train : (5332,)<br> </pre> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div>

opencc-zeroMay 2024View details →

dryad40/100

Benefits and limits of phasing alleles for network inference of allopolyploid complexes

<p>Accurately reconstructing the reticulate histories of polyploids remains a central challenge for understanding plant evolution. Although phylogenetic networks can provide insights into relationships among polyploid lineages, inferring networks may be hindered by the complexities of homology determination in polyploid taxa. We use simulations to show that phasing alleles from allopolyploid individuals can improve phylogenetic network inference under the multispecies coalescent by obtaining the true network with fewer loci compared to haplotype consensus sequences or sequences with heterozygous bases represented as ambiguity codes. Phased allelic data can also improve divergence time estimates for networks, which is helpful for evaluating allopolyploid speciation hypotheses and proposing mechanisms of speciation. To achieve these outcomes in empirical data, we present a novel pipeline that leverages a recently developed phasing algorithm to reliably phase alleles from polyploids. This pipeline is especially appropriate for target enrichment data, where depth of coverage is typically high enough to phase entire loci. We provide an empirical example in the North American <em>Dryopteris </em>fern complex that demonstrates insights from phased data as well as the challenges of network inference. We establish that our pipeline (PATÉ: Phased Alleles from Target Enrichment data) is capable of recovering a high proportion of phased loci from both diploids and polyploids. These data may improve network estimates compared to using haplotype consensus assemblies by accurately inferring the direction of gene flow, but statistical non-identifiability of phylogenetic networks poses a barrier to inferring the evolutionary history of reticulate complexes.</p>

dryad40/100

Data from: Pleiotropy alleviates the fitness costs associated with resource allocation trade-offs in immune signaling networks

<p>Many genes and signaling pathways within plant and animal taxa drive the expression of multiple organismal traits. This form of genetic pleiotropy instigates trade-offs among life-history traits if a mutation in the pleiotropic gene improves the fitness contribution of one trait at the expense of another. Whether or not pleiotropy gives rise to conflict among traits, however, likely depends on the resource costs and timing of trait deployment during organismal development. To investigate factors that could influence the evolutionary maintenance of pleiotropy in gene networks, we developed an agent-based model of co-evolution between parasites and hosts. Hosts comprise signaling networks that must faithfully complete a developmental program while also defending against parasites, and trait signaling networks could be independent or share a pleiotropic component as they evolved to improve host fitness. We found that hosts with independent developmental and immune networks were significantly more fit than hosts with pleiotropic networks when traits were deployed asynchronously during development. When host genotypes directly competed against each other, however, pleiotropic hosts were victorious regardless of trait synchrony because the pleiotropic networks were more robust to parasite manipulation, potentially explaining the abundance of pleiotropy in immune systems despite its contribution to life history trade-offs.</p>

opencc-zeroMay 2024View details →

openmit-licenseMay 2024View details →

Dataset and Model Weights for Plasma Sheet Model Graph Network Simulator

<p>This repository contains the simulation data and pre-trained Graph Neural Network (GNN) models produced in [1].</p> <p>Two *.zip files are provided:</p> <ul> <li>data.zip - contains the datasets of train/test simulations produced using the Sheet Model algorithm [1, 2]</li> <li>models.zip - contains the GNN model weights (<em>*.</em>pkl<em>) </em>+ relevant training information and model parameters <em>(*.</em>yml<em> and *</em>.txt)</li> </ul> <p>Dataset subfolders are named according to dataset/{'train' or 'test'}/{number of sheets}/{boundary condition}/. Each subfolder contains multiple simulations and a single info.yml file with relevant information regarding the overall setup. For each i-th simulation the following files are provided:</p> <ul> <li>x_{i}.npy - array with sheet trajectories (#time-steps, #sheets)</li> <li>v_{i}.npy - array with sheet velocities (#time-steps, #sheets)</li> <li>x_eq_{i}.npy - array with sheet equilibrium positions (#time-steps, #sheets)</li> </ul> <p> Model sub-folders are named according to :</p> <ul> <li>models/{time step}/{seed} - default architecture (preferred)</li> <li>models/{time step}/{'collisions', 'nosent' or 'equivariant'}/{seed} - alternative (less performing) architectures mentioned in the paper appendices.</li> </ul> <p>For each model we provide:</p> <ul> <li>params_best.pkl - model weights that performed the best during training on the validation set</li> <li>params_final.pkl - model weights at the end of training</li> <li>model_cfg.yml - GNN architecture metadata</li> <li>train_cfg.yml - training configuration metadata</li> <li>train_data.yml - training dataset metadata</li> <li>loss.txt - training and validation loss per epoch</li> <li>loss_i.txt - training loss per gradient update step</li> </ul> <h3>Source Code</h3> <p>The source code used to produce the data, train, and test the models can be found at: <a href="https://github.com/diogodcarvalho/gns-sheet-model">https://github.com/diogodcarvalho/gns-sheet-model</a></p> <h3>References</h3> <p>[1] D. D. Carvalho, D. R. Ferreira, L. O. Silva, "Learning the dynamics of a one-dimensional plasma model with graph neural networks<em>", Mach. Learn.: Sci. Technol. 5 025048 </em>(2024)</p> <p>[2] J. Dawson, "One‐Dimensional Plasma Model"<em>, The Physics of Fluids</em> 5.4 (1962): 445-459.</p> <p> </p>

dryad40/100

Physics-informed neural networks (PINNs) with unsaturated water flow models for inverse analysis of soil hydraulic parameters of layered soil profiles

<p>Information about the spatial distribution of soil hydraulic parameters is necessary for the accurate prediction of soil water flow and coupled movement of chemicals and heat at the field scale using a process-based model. Physics-informed neural networks (PINNs), which can provide physical constraints in deep learning to obtain a mesh-free solution, can be used to inversely estimate the soil hydraulic parameters from less and noisy training data. Previous studies using PINNs have successfully estimated soil hydraulic parameters for homogeneous soil but estimating such parameters of layered soil profiles where the interface depth and the parameters are unknown still has some difficulties. The objective of this study was to develop PINNs to inversely estimate the distribution of soil hydraulic parameters, such as saturated hydraulic conductivity and <em>α</em> and <em>n</em>, of the Mualem-van Genuchten model directly within layered soil profiles by predicting changes in pressure head from training data based on simulation results at given depths during infiltration. The impact of factors affecting PINNs performance, such as the weights assigned to each component of the loss function, the time range used in error computations, and the number of samples used to assess physical constraint was investigated. By assigning a larger weight to the physical constraint and excluding the earlier stage of infiltration in the loss function, the changes in pressure head and the three soil hydraulic parameter distributions within the layered soil profiles were successfully estimated. The developed PINNs can be further applied to more complex soils and can be improved.</p>

opencc-zeroMay 2024View details →

Conformer datasets for "Equivariant Graph Neural Networks for Toxicity Prediction"

<p>Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain.</p> <p>PAPER</p> <p>https://pubs.acs.org/doi/full/10.1021/acs.chemrestox.3c00032</p> <p>CODE and MODELS:</p> <p>The conformer data sets and trained toxicity models will be published upon acceptance of this work. The code has been made available at <a href="https://github.com/jule-c/ET-Tox">https://github.com/jule-c/ET-Tox</a>, and the processed data as well as pretrained models for training and testing can be downloaded from <a href="../record/7942946">https://zenodo.org/record/7942946</a>. We can provide the full list of conformers as XYZ files upon request.</p>

Growing up with nutritional stress leads to peripheral social network positions, independent of 'personality'

<p>Variables:</p> <p>BirdID: unique identifier of individuals</p> <p>Day: numerical, day of testing</p> <p>Room: physical Location of aviary, arbitrary numbering</p> <p>Group: numerical. Each group consists of one sex. </p> <p>Degree, Strength, EC, CV: social network variables. When precluded by a "D"; calculated using duration-based networks. When precluded by "F"; calculated using frequency-based networks. </p> <p>Sex: 1 = female, 2 = male</p> <p>DT: developmental treatment. Easy or Hard </p> <p>GenDad & GenMom: unique identifier. Genetic father or mother. </p> <p>DS, GP, PC1NO, PC1exp, Immobility: personality scores from Gerritsma et al., 2023. When precluded by "s", they are standardized ((x - mean) / sd). </p> <p>Broodsize: numerical, natal broodsize. </p> <p>nestID: unique identifier for nest, arbitrary numbering. </p> <p>Aviary: aviary in which individual was born. Arbitrary numbering. </p> <p>Groupday: combination of day and group. First day of first group would be 11. Tenth day of first group would be 101. </p> <p>Sexmc: mean-centered sex (sex-avg(sex)). </p> <p>Broodsizemc: mean-centered brood size. </p> <p>logTI: log10(immobility)</p> <p>DT3: numerical representation of DT. 1 = hard, 0 = easy. </p>

Dataset for training SENMAP, a automatic tool to curate LTR-retrotransposons using convolutional neural networks

<p>Transposable elements (TEs) are specific structures of the genome of species, which can move from one location to another. For that reason, they can cause mutations or changes that can be negative, such as the appearance of diseases, or beneficial, such as participating in fundamental roles in the evolution of genomes and genetic diversity. Long Terminal Repeat retrotransposons (LTR-RT) are the most abundant in plant species, hence the importance of studying these structures in particular. Over the time, these elements can suffer changes called nested insertions, which can inactivate or modify the functioning of the element, for that they are no longer consider as intact element and cannot be used for identification and classification studies. We create a dataset containing 56,442 LTR-RTs targed as "non-intact" elements and 49,215 considered as "intact". </p> <p>We formated the sequences IDs in order to keep relevant information as the superfamily and the lineage, as well as the category (Negative for "non-intact" and Positive for "intact" elements). </p> <p> This dataset (the npy files obtained from the fasta file) was used for training SENMAP, a convolutional neural network architecture to obtain intact LTR-RT sequences in plant genomes, which is composed by four convolutional layers, LeakyReLU as activation function and BinaryFocalLoss as loss function. Achieving an F1-score percentage of 91.37% with test data, identifying low quality sequences rapidly and efficiently, contributing to curate libraries of LTR retrotransposons of plants genomes published in large-scale sequencing projects due to the post-genomic era.</p>

opencc-by-4.0Feb 2022View details →

Real-Time Adaptation of an Artificial Neural Network for Transfemoral Amputees Using a Powered Prosthesis

<p>This dataset contains the data used in our manuscript titled "Real-Time Adaptation of an Artificial Neural Network for Transfemoral Amputees Using a Powered Prosthesis". Data structure is explained in the README.txt file located at the top-level of the dataset.</p> <p>Please contact corresponding author Richard B. Woodward for any questions.</p>

Impacts of centralized control on mixed traffic network performance: A strategic games analysis

<p>This dataset contains the data that were used to assess the proposed framework within the context of the case study in the paper entitled "Impacts of centralized control on mdaixed traffic network per-formance: A strategic games analysis".</p>

Code and Data for the Study "A User-Centric Model of Connectivity in Street Networks"

<p>This resource contains the code and results used in the paper:</p> <p>Corcoran, P. and R. Lewis (Pending) “A User-Centric Model of Connectivity in Street Networks”</p> <p>Please consult <strong>UserGuide.pdf</strong> for further information. </p>

Robust quantum dots charge autotuning using neural network uncertainty - Output data

<p>Outputs of the model training and the offline autotuning experiments presented in the paper: "<em>Robust quantum dots charge autotuning using neural network uncertainty</em>".</p> <p>For convenience, the results are splitted in several zipped files:</p> <ul> <li><strong>run_outputs_light.zip</strong>: contains only settings and results text files (sufficient for compiling result tables).</li> <li><strong>run_outputs_full_scan.zip</strong>: contains complete scan of the diagrams (for qualitative analyse)</li> <li><strong>run_outputs_part<N>.zip</strong>: contains all autotuning simulation output, grouped by seed (images and video output types might vary between seeds)</li> </ul> <p>Each folder in the zipped files represent a run that includes:</p> <ul> <li>log file</li> <li>plots / images</li> <li>run settings</li> <li>performance results</li> <li>pytorch model parameters</li> </ul> <p>See README.txt for more information about the file strucutre.</p>

Network-wide Emissions Estimation Using the Macroscopic Fundamental Diagram

<p>This is the dataset for the NCST project of Network-wide Emissions Estimation Using the Macroscopic Fundamental Diagram.</p> <p>Estimation of emissions and energy consumption using MOVES (Motor Vehicle Emission Simulator) model is cumbersome for large-scale network and intractable for real-time analysis and control purposes. This project aims to develop a simplified method for estimation of emissions and energy consumption in large-scale networks using the macroscopic fundamental diagram (MFD). In the proposed method, the network will be divided up into a number of homogeneous regions and the emissions and energy consumption from all links inside each region will be approximated by MFD-based variables in the MOVES model. Later, the developed method will be used to propose real-time traffic control policies optimizing the network-wide emissions and energy consumption.</p>

Data Set for the Journal Article "Heron: Visualizing and Controlling Chemical Reaction Explorations and Networks"

<p>This data archive contains all data newly created in the following publication:</p> <p>Charlotte H. Müller, Miguel Steiner, Jan P. Unsleber, Thomas Weymuth, Moritz Bensberg, Katja-<br>Sophia Csizi, Maximilian Mörchen, Paul L. Türtscher, and Markus Reiher, "Heron: Visualizing and<br>Controlling Chemical Reaction Explorations and Networks", in preparation.</p> <p>The directory contents are as follows:</p> <ul> <li>steered_eschenmoser.tar.xz: Dump of the database created during the steered exploration</li> <li>steered_exploration_protocol_chemoton_3.1.json: Protocol used for the steered exploration</li> </ul>

Self Consistent Recurrent Neural Network for Path Dependent Deformation

<p>Data and Machine Learning codes for the paper:</p> <ul> <li>Title<strong> : Self Consistent Recurrent Neural Network for Path Dependent Deformation</strong></li> </ul> <p><strong>Abstract</strong> : Current neural network (NN) structures can learn patterns from data points with historical dependence. Specifically, in natural language processing (NLP), sequential learning has transitioned from recurrence-based architectures to transformer-based architectures. However, it is not known in advance which NN architectures will perform best on datasets containing deformation history due to mechanical loading. Thus, this study ascertains the appropriateness of 1D-convolutional, recurrent, and transformer-based architectures for predicting material failure based on the earlier states in the form of deformation history. Following this investigation, the crucial issues arising from the mathematical computation process of the best-performing NN architectures and the physical properties of the deformation paths are examined in detail. Additionally, we propose a novel and adaptable RNN approach to address the fundamental challenges of truncation and consistency related to obtaining estimations that are compatible with the natural physical properties of deformation paths. This study will serve as a foundation for localization estimation and pave the way for future endeavors to propose further solutions to encountered challenges.</p>

opencc-by-4.0Dec 2023View details →

Data & code repository for the article "A network toxicology approach for mechanistic modelling of nanomaterial hazard and adverse outcomes"

<p>This repository contains the relevant data and code supporting the study "A network toxicology approach for mechanistic modelling of nanomaterial hazard and adverse outcomes". </p> <p>In detail the following data sources have been included:</p> <ul> <li>the relevant code and supporting data (code_to_upload.zip and supporting_data.zip);</li> <li>supplementary materials of the paper, including: <ul> <li>individual enrichment results of the 93 exposures to the 31 ENMs (enrichments_results.zip);</li> <li>comparison between the mechanism of action retrieved from differentially expressed genes and network modelling (network_comparison_results.zip);</li> <li>overrepresented network edges in categories of networks (overrepresented_structures.zip)</li> </ul> </li> </ul>

opencc-by-4.0Dec 2023View details →

Supplementary Materials: The molecular landscape of premature aging diseases defined by multilayer network exploration

<p>This dataset contains supplementary materials related to study "The molecular landscape of premature aging diseases defined by<br>multilayer network exploration" (Beust C., Valdeolivas A., Baptista A., Brière G., Lévy N., Ozisik O., Baudot A.)</p> <p>Supplementary Figures:  <br>Supplementary Figure S1: Clustering of the premature aging disease communities obtained with 50 iterations of  itRWR  <br>Supplementary Figure S2: Clustering of the premature aging disease communities obtained with 150 iterations of  itRWR  <br>Supplementary Figure S3: Clustering of the premature aging disease communities obtained with 100 iteration of  itRWR, with a cutoff value at 0.5 on the dendrogram  </p> <p>Supplementary Tables:  <br>Supplementary Table S1: Premature Aging HPO phenotypes  <br>Supplementary Table S2:Tthe 67 PA diseases and their 132 associated genes from ORPHANET  <br>Supplementary Table S3: Number of nodes, edges, and densities of the 4 network layers composing the multilayer  biological network  <br>Supplementary Table S4: Parameters used for MultiXrank  </p> <p>Supplementary Files:  <br>Supplementary File S1: Csv file containing the enrichment analysis results computed using the genes associated with  physiological aging  <br>Supplementary File S2: Excel file containing the gene nodes belonging to each of the 67 communities  <br>Supplementary File S3: Excel file containing the gene nodes belonging to each cluster (i.e., the union of the genes belonging to the set of communities composing the cluster)  <br>Supplementary File S4: Csv file containing the diseases belonging to each cluster  <br>Supplementary File S5: Excel file containing the enrichment of clusters using lists of physiological aging genes  <br>Supplementary File S6: Csv file containing the lists of genes differentially expressed in human blood, skin, brain, muscle and breast during aging, from the study of Irizar et al.  <br>Supplementary File S7: Excel file containing the enrichment analysis results of the 67 communities, using GO Biological Processes and Cellular Components, and Reactome pathways functional annotations  <br>Supplementary File S8: Excel file containing the enrichment analysis results of the 6 clusters, using GO Biological Processes and Cellular Components, and Reactome pathways functional annotations. The last 2 columns contain  the seed nodes of the cluster annotated for the corresponding function and their corresponding diseases. <br>Supplementary File S8bis: Excel file containing the enrichment analysis results of the 8 clusters obtained with an alternative cutoff of 0.5 in the dendrogram, using GO Biological Processes and Cellular Components, and Reactome pathways functional annotations.<br>Supplementary File S9: Excel file containing enrichment analysis results of the 6 clusters, using HPO phenotypes  </p> <p>Supplementary Text:  <br>Supplementary Text S1: Comparison with alternative network exploration strategies, including classical (non- iterative) Random Walk with Restart, Multilayer network partitioning, and computation of network distances with shortest paths.</p> <p> </p> <p> </p>

opencc-zeroJun 2024View details →

Dataset: Gilat Satellite Networks Ltd. (GILT) Stock Performance

This dataset provides historical stock market performance data for specific companies. It enables users to analyze and understand the past trends and fluctuations in stock prices over time. This information can be utilized for various purposes such as investment analysis, financial research, and market trend forecasting.

opencc-zeroJun 2024View details →

Dataset: Extreme Networks, Inc. (EXTR) Stock Performance