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.
13,064
datasets available to search
ShareScore release 0.9.0
Dataset results
13,064 results for “predictions”
Fig. 3 in Predicting size at first sexual maturity from length/weight relationship: a case study with an Amazonian catfish
Fig. 3. Length/weight relationship of female Auchenipterichthys longimanus. A and C represent Huxley regular length/ weight relationship and its distribution of proportional residuals. B and D represent polyphasic length/weight relationship its and distribution of proportional residuals.
DPCstruct Classification of AlphaFold2-Predicted Protein Structures
<p>This dataset contains DPCstruct domain classifications for protein structures predicted by AlphaFold2, as presented in the paper "Unsupervised Domain Classification of AlphaFold2-Predicted Protein Structures."</p> <p>DPCstruct was applied to a non-redundant set of the AlphaFold Database v4.0, known as Foldseek Clusters, which includes approximately 15 million representative proteins, as described in the work by <a href="https://doi.org/10.1038/s41586-023-06510-w">Barrio-Hernandez et al.</a></p> <p>This repository provides the results of our classification, along with all the data related to the analyses presented in our study. DPCstruct algorithm can be found at <a href="https://github.com/RitAreaSciencePark/DPCstruct">https://github.com/RitAreaSciencePark/DPCstruct</a> together with examples on how to use it.</p> <p><strong>FILES DESCRIPTION:</strong></p> <ul> <li><strong>dpcstruct_classification.tsv: </strong>List of domains identified by DPCstruct and their corresponding metacluster. Columns: Metacluster ID, Protein Uniprot ID, domain start, domain end.</li> <li><strong>mcs_reps.fasta:</strong> For each metacluster, two representative domains were selected: one representing the center of the cluster and the other being the domain with the highest pLDDT score. If these are the same, only one domain is included as the representative. This file contains the list of representative domains and their sequences in FASTA format.</li> <li><strong><span>mcs_reps_pdbs.zip: </span></strong>Contains a PDB file for each representative domain. The filename is structured as 'proteinID_metacluster.pdb'.</li> <li><strong>mcs_properties.tsv:</strong> Set of properties per metacluster, including: <ul> <li><strong>mcID:</strong> Metacluster ID.</li> <li><strong>size:</strong> Number of domains.</li> <li><strong>len_aa:</strong> Average length of domains (number of amino acids).</li> <li><strong>len_std:</strong> Standard deviation of domain lengths.</li> <li><strong>len_ratio:</strong> Ratio of len_std to len_aa.</li> <li><strong>plddt:</strong> Average predicted LDDT as reported by AlphaFold2.</li> <li><strong>disorder:</strong> Average intrinsic disorder score calculated with AIUPred.</li> <li><strong>alntmscore:</strong> Pairwise alignment TM-score between domains, averaged over all pairs.</li> <li><strong>tmscore:</strong> Pairwise alignment TM-score between domains, averaged over all pairs, using the maximum between TM-score normalized by query or target.</li> <li><strong>lddt:</strong> Pairwise LDDT score, averaged over all pairs.</li> <li><strong>prob:</strong> Pairwise probability of homology according to SCOPe, as reported by Foldseek.</li> <li><strong>pident:</strong> Pairwise percentage identity, averaged over all pairs.</li> </ul> </li> <li><span><strong>annotated_[cath|scop]_qc[x]_t[x]_l[x].tsv:</strong> </span>For each fold in [CATH|SCOP], we provide the best matching DPCstruct domain, if available, along with the structural alignment information as reported by Foldseek. A fold is considered annotated if its alignment values meet or exceed the following thresholds: <ul> <li>qc: query coverage.</li> <li>t: template modelling score of the alignment.</li> <li>l: lddt score of the alignment.</li> </ul> </li> <li><strong>dpcstruct_consistency.tsv:</strong> Consistency of DPCstruct metaclusters with respect to Pfam 36.0 labels. Note that we consider a Pfam label to overlap with a DPCstruct domain even if it shares just one amino acid, which is why some metaclusters have many labels. In such cases, we only display 5 representative labels.</li> <li><strong>pfam_consistency.tsv:</strong> Consistency of Pfam Clans with respecto to DPCstruct labels.</li> </ul> <p><strong>Note:</strong> All 'tsv' files contain a header as the first row.</p> <p>If there is any doubt regarding the data or there is something missing please contact us: </p> <p>federico.barone@areasciencepark.it</p>
Black Soldier Fly detection, phenotyping and sex prediction dataset
<p>BSF_Larvae for training the detection and segmentation model consists of 321 images with over 5000 larvae instances. </p> <p>Single_Larvae_data consists of 1608 single larvae images for the measurement of body weight, length and width of the individual larva. </p> <p>The Larvae size excel sheet contains the size and sex data corresponding to the individual larva. </p> <p>The Larvae sex classification dataset includes images cropped from the Single_Larvae_data for sex classification.</p>
UniSpec: Deep Learning for Predicting the Full Range of Peptide Fragment Ion Series to Enhance the Proteomics Data Analysis Workflow
<p>UniSpec is a comprehensive DL spectrum predictor that can predict the intensity of the entire HCD MS/MS fragment ion series, going beyond existing tools limited to b/y ion series. </p> <p>All datasets developed for UniSpec model are shared on Zenodo as part of the UniSpec publication, "UniSpec: Deep Learning for Predicting Comprehensive Peptide Fragment Ion Series to Improve Peptide-Spectrum Matches from Shotgun Proteomics Experiments".</p> <p>This includes UniSpec datasets, downstream evaluation and analysis, and application case studies.</p> <p>1. pre-processed training, evaluation and testing data for machine learning;</p> <p> UniSpec-Datasets.7z, Readme_UniSpecDatasets.txt</p> <p>2. Streamlined input datasets based on the fragmentation dictionary;</p> <p> Streamlined_inputdatasets.7z, Readme_Streamlined_inputdatasets.txt</p> <p>3. Predictions on the validation and test sets;</p> <p> UniSpecPred_Validation-Test.7z, Readme_Predictons_ValidationTest.txt</p> <p>4. Evaluation by comparison with Prosit;</p> <p> a. Predictions: prosit_and_unispec_predictions.7z, Readme_prosit_and_unispec_predictions.txt</p> <p> b. Cosine similarity scores: prosit_vs_unispec_CS.7z, Readme_prosit_vs_unispec_CS.txt</p> <p>5. CSS for Different HCD Fragment Ion Series;</p> <p> CS_for_ion_splits.tsv</p> <p>6. Application 1: PSM rescoring;</p> <p> PSM rescoring_zipfiles.7z, PSM rescoring_readme.txt</p> <p>7. Application 2: In-silico spectral library search </p> <p> in-silico_librarysearch.7z, in-silico_librarysearch_readme.txt</p> <p> </p>
Sample data for "Classification Modeling for Hazardous Rip Current Prediction" Notebook
<p>This sample dataset is used in the notebook "Classification Modeling for Hazardous Rip Current Prediction" to demonstrate the application of using machine learning to identify hazardous rip current. The notebook is available in the NOAA Center for Artificial Intelligence GitHub Learning Journey repository (https://github.com/noaa-ncai/learning-journey). The full dataset is available via NOAA.</p>
Prediction of Humpback Whale Sighting Zones based on Environmental Factors using Tree-based Algorithms
<p>This is the datased used in the paper: Prediction of Humpback Whale Sighting Zones based on Environmental Factors using Tree-based Algorithms</p>
Predicted UV-to-Radio SEDs of little red dots: AGN and SF
<p>Predicted Dust SEDs for JWST's Little Red Dots<br>17-Sep-2024</p> <p>Here are the average UV through radio spectral energy distributions predicted for the LRD population from Figure 2 of Casey et al. (2024b, https://arxiv.org/abs/2407.05094, ApJL in press). There are two SEDs: one predicting the emission is due to AGN and one that it is due to star-formation. Wavelength is given as log10 of rest-frame wavelength in microns. Flux density is log10 Fnu in mJy. Email cmcasey.astro@gmail.com with questions.</p>
Winter Precipitation-Type Models for "Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications"
<p>This contains trained model weights, scalers, and evaluation metrics for the winter precipitation-type models trained as part of the paper "Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications". </p>
Predicting Partial Atomic Charges in Metal-Organic Frameworks: An Extension to Ionic MOFs
<p>This dataset is associated with the study <em>"Predicting Partial Atomic Charges in Metal-Organic Frameworks: An Extension to Ionic MOFs."</em> Detailed instructions for installation, usage, and example scripts for the PACMOF2 models can be found on our GitHub <a href="https://github.com/snurr-group/pacmof2">repository</a>.</p> <div> <div> <div> <div> <p>The dataset includes the following files:</p> <ul> <li><strong>DDEC6_data.zip</strong>: Contains the crystal structures of MOFs with DDEC6 partial charges.</li> <li><strong>PACMOF2_prediction_cifs.zip</strong>: Contains the crystal structures of MOFs with DDEC6 charges as predicted by the PACMOF2 models.</li> <li><strong>PACMOF2_ionic.gz</strong>: A machine learning model designed to predict charges in ionic MOFs with a non-zero formal charge.</li> <li><strong>PACMOF2_neutral.gz</strong>: A machine learning model designed to predict charges in neutral MOFs.</li> </ul> <p>For more details about each file, please refer to the accompanying <code>README.md</code> file.<br><br><br>Updates: <br>- September 2024 (version 1.0.1): Added README.md file.</p> </div> </div> </div> </div>
Data for publication "The Thermosphere was Poorly Predictable not Only During but also Before and After the Starlink Storm on 3-4 February 2022"
<p>This dataset are used to plot figures in the article "The Thermosphere was Poorly Predictable not Only During but also Before and After the Starlink Storm on February 3-4, 2022". Data files in CSV (comma-separated values) format contain modeling and observational values. Modeling values obtained from the Field Line Interhemispheric Plasma (FLIP) model and Arctic MERRA-2 Wind model. Observational values consist the ionosonde measurments, planetary geomagnetic (Kp) and solar activity indices (F10.7), variations of the solar wind parameters. Data files contain data for the period from February 1 to 9, 2022 and from December 21 to 23, 2021. </p>
Alphafold2 and AlphaFold-Multimer Predicted Interactions of Soybean Proteins with Macrophomina phaseolina Effectors reveals putative protease inhibitors and SUSS effectors.
<p> </p> <ul> <li> <p><strong>Kunitz Monomer Prediction</strong>:</p> <ul> <li><strong>Data</strong>: Analysis of soybean Kunitz proteins.</li> <li><strong>Details</strong>: Detected on the apoplast at 3 days post-infection with <em>Macrophomina phaseolina</em>.</li> <li><strong>File</strong>: <code>KUNITZ_monomers_outputdir.zip</code></li> </ul> </li> <li> <p><strong>Uncharacterized M. phaseolina Protein Monomer Prediction</strong>:</p> <ul> <li><strong>Data</strong>: Predictions for uncharacterized proteins.</li> <li><strong>Details</strong>: Detected on the apoplast at 3 days post-infection.</li> <li><strong>File</strong>: <code>uncharacterised_proteins_SUSS_effectoroutputdir.zip</code></li> </ul> </li> </ul> <ul> <li> <p><strong>Positive Validation Set</strong>:</p> <ul> <li><strong>Data</strong>: Experimental verification of protein-inhibitor pairs.</li> <li><strong>Details</strong>: Pairs include experimentally verified interactions, specifically proteins and inhibitors, but lack resolved crystal structures.</li> <li><strong>File</strong>: <code>existing_non_existinpairs_Validation_outputdir.zip</code></li> </ul> </li> </ul> <ul> <li> <p><strong>Soybean Serine Protease-Kunitz Interaction</strong>:</p> <ul> <li><strong>Data</strong>: Interactions between soybean serine proteases and Kunitz proteins.</li> <li><strong>Details</strong>: Analyzed in the apoplastic space at 3 days post-infection.</li> <li><strong>File</strong>: <code>glycine max_Serine protease_Vs_Gmaxkunitz_outputdir.zip</code></li> </ul> </li> </ul> <ul> <li> <p><strong>Cysteine Protease without Pro-domain-MoErs-like effector Interaction</strong>:</p> <ul> <li><strong>Data</strong>: Interactions involving cysteine proteases.</li> <li><strong>Details</strong>: Rice RD21 and soybean cysteine proteases with pro-domains removed interacting with <em>MoErs1</em> and <em>MoErs1</em>-like M.phaseolina effectors.</li> <li><strong>File</strong>: <code>AF2-Multimer_RD21&GmaxCproteases_MoERS1_screening_outputdir.zip</code></li> </ul> </li> </ul> <ul> <li> <p><strong>Fungal Serine Protease-Kunitz Interaction</strong>:</p> <ul> <li><strong>Data</strong>: Interactions between <em>Macrophomina phaseolina</em> serine proteases and soybean Kunitz proteins.</li> <li><strong>Details</strong>: Evaluated in the apoplastic space at 3 days post-infection.</li> <li><strong>File</strong>: <code>fungalSerineprotease_Vs_Gmax_kunitzoutputdir.zip</code></li> </ul> </li> <li> <p><strong>Negative Validation Set</strong>:</p> <ul> <li><strong>Data</strong>: Known non-interacting pairs.</li> <li><strong>Details</strong>: Non-interacting pairs of serine proteases-chitinases that are not resolved as crystal structures</li> <li><strong>File</strong>: <code>Gmax_Serineprotease_Vs_Gmaxchitinases_Validation_outputdir.zip</code></li> </ul> </li> </ul>
Supplementary Data: Data Imbalance in Drug Response Prediction: Multi-Objective Optimization Approach in Deep Learning Setting
Open the record for dataset details and reuse information.
Dataset - Papyrus - A large scale curated dataset aimed at bioactivity predictions
<p><strong>Fixed version of additional_files:</strong></p> <p><strong>- In the previous version of 05.6_additional_files</strong> the data type of some descriptors was assigned incorrectly</p> <p><strong>- In this fixed version </strong>data types are correct </p> <p>This repository contains version 05.6 of the Papyrus dataset, an aggregated dataset of small molecule bioactivities, as described in the article "Papyrus - A large scale curated dataset aimed at bioactivity predictions" doi.org/10.1186/s13321-022-00672-x.</p> <p>Changes compared to version 05.5</p> <p>- applied small molecule filter that filters out compounds with a MW < 200 or > 800, heavy metal containing compounds and mixtures</p> <p>- include TID column which contains information on the original protein identifier</p>
Pre-existing natural variations of adult neurogenesis and anxiety predict hierarchical social status of inbred male mice.
<p>CVS files and image files of all data presented in the correcponding figures. </p>
Data for "Using physics-informed neural networks to predict the lifetime of laser powder bed fusion processed 316L stainless steel under multiaxial low-cycle fatigue loading"
<p>Title of dataset: Data for "Using physics-informed neural networks to predict the lifetime of laser powder bed fusion processed 316L stainless steel under multiaxial low-cycle fatigue loading".</p> <p>Name/institution/contact information: Dr. Michal Bartošák, Czech Technical University in Prague - Faculty of Mechanical Engineering, email: michal.bartosak@fs.cvut.cz.</p> <p>Date of data collection: The data were collected between 2021 and 2024.</p> <p>File name structure: The data consists of two files: "316L_fatigue_and_defects.xls," which contains fatigue lifetime data and defect characteristics, and an associated description file, "read_me.txt."</p> <p>See "https://doi.org/10.1016/j.ijfatigue.2024.108608" for the associated article and a detailed description of the methods.</p>
Supplementary data and code for "Predicting anthropogenic food supplementation from individual tracking data"
<p><span>This repository contains data and R-Scripts to reproduce the results presented in the paper “</span><span>Predicting anthropogenic food supplementation from individual tracking data</span><span>” published in Ibis. Please note that some data (basemap of Switzerland, forests, buildings) are publicly available from </span><span><a href="https://map.geo.admin.ch/"><span>https://map.geo.admin.ch/</span></a></span><span> and are therefore not provided here. The abstract of the article is as follows: </span><span>Many wildlife species consume food or refuse provided by humans. To understand the effect of anthropogenic food subsidies on wildlife populations, we first need to quantify where and when individuals can access such food sources. The red kite <em>Milvus milvus</em> is an opportunistic raptor species and uses both inadvertent and deliberate food subsidies provided by citizens. Here we present a new approach using GPS-tracking data to predict where anthropogenic food subsidies likely occur. We tracked 497 individuals with solar-powered GPS transmitters over an average of 3.2 (range 1 – 9) breeding seasons in Switzerland, and combined these data with locations of 125 known feeding sites obtained through interviews. We used two sequential random forest models, at both individual movement and population levels, to predict where anthropogenic food subsidies were attended by red kites. The first model classified locations that were frequently and regularly revisited, and successfully predicted 85% of locations that were within 50 m of an externally validated feeding site. These predicted locations were aggregated in 500 m grid cells to calculate the proportion of individuals and locations associated with predicted food subsidy. A second model related the presence of known food subsidies to the aggregated predictions. In our study area, 80% of known anthropogenic food provision locations could be correctly identified using red kite tracking data, but data sparsity beyond the core range of tracked individuals limits predictions of anthropogenic food subsidies at larger geographic scales. Nonetheless, biologging data can identify ephemeral food sources, and facilitate an assessment of the importance of anthropogenic food subsidies on the fitness of individuals in tracked populations.</span></p>
A3D Model Organism Database (A3D-MODB): a database for proteome aggregation predictions in model organisms
<p>The unified and integrated metadata accompanied by referencing identifiers from the A3D database is available for download in CSV format.</p> <p>Aleksandra E Badaczewska-Dawid, Aleksander Kuriata, Carlos Pintado-Grima, Javier Garcia-Pardo, Michał Burdukiewicz, Valentín Iglesias, Sebastian Kmiecik, Salvador Ventura, A3D Model Organism Database (A3D-MODB): a database for proteome aggregation predictions in model organisms, <em>Nucleic Acids Research</em>, Volume 52, Issue D1, 5 January 2024, Pages D360–D367, <a href="https://doi.org/10.1093/nar/gkad942">https://doi.org/10.1093/nar/gkad942</a></p>
Evaluating mesoscale model predictions of diurnal speedup events in the Altamont Pass Wind Resource Area of California
<p>This dataset contains input files for the Weather Research and Forecasting (WRF) model related to the manuscript "Evaluating mesoscale model predictions of diurnal speedup events in the Altamont Pass Wind Resource Area of California," to be submitted to the <em>Journal of Applied Meteorology and Climatology</em> by Arthur, et al. Included are:</p> <ul> <li><strong>namelist.wps</strong>: used by the WRF preprocessing system (WPS) to configure the model domain and initial/boundary conditions</li> <li><strong>Vtable.HRRR</strong>: used by WPS to process data from the High-Resolution Rapid Refresh (HRRR) model for WRF initial/boundary conditions</li> <li><strong>namelist.input.mynn</strong>: used to run the MYNN PBL simulation</li> <li><strong>namelist.input.3dpbl</strong>: used to run the 3D PBL simulation</li> <li><strong>windturbines.txt</strong>: used to define the location and type of wind turbines included in the simulations</li> <li><strong>wind-turbine-*.tbl</strong>: used to define the parameters of each turbine type (see Table 1 in Arthur et al.) <ul> <li><strong>1</strong>: NREL 1.7MW, H=80m, D=103m</li> <li><strong>2</strong>: NREL 2.3MW, H=80m, D=107m</li> <li><strong>3</strong>: NREL 2.3MW, H=80m, D=116m</li> <li><strong>4</strong>: Vestas V47 0.66MW, H=60m, D=47m</li> <li><strong>5</strong>: Bonus B54 1.0MW, H=55m, D=54m</li> </ul> </li> </ul> <p>This work was prepared by LLNL under Contract DE-AC52-07NA27344.</p>
Quantification of Fatty Acids in Hemp Seeds (Cannabis sativa L.) and Yield Prediction Using Machine Learning for Soxhlet and Ultrasound Extraction Methods
<p>This study focuses on the quantification of fatty acids present in hemp seeds (Cannabis sativa L.) cultivated in the Ecuadorian Andes using Soxhlet and ultrasound extraction methods. The aim is to evaluate and compare the extraction efficiency of these two techniques. Furthermore, machine learning models are applied to predict extraction yields based on experimental conditions. Using locally cultivated seeds provides valuable insights into the influence of regional agro-climatic conditions on the chemical composition. The integration of predictive algorithms offers a novel approach to optimizing the extraction process, enhancing both precision and efficiency. The findings could contribute to developing sustainable extraction methods for high-value bioactive compounds in the food and pharmaceutical industries.</p>
Aberrant gene expression prediction benchmark based on GTEx v8
<p>This repository contains the aberrant gene expression prediction benchmark data as well as the necessary expected gene expression across tissues and tissue-specific isoform contribution scores for AbExp prediction.<br> </p> <p>The aberrant gene expression prediction benchmark data (aberrant_expression_prediction_benchmark.parquet) contains the following columns:</p> <ul> <li>individual: GTEx individual</li> <li>gene: Ensembl gene identifier</li> <li>tissue: GTEx tissue</li> <li>tissue_type: GTEx tissue type</li> <li>mu: OUTRIDER-estimated expected gene expression</li> <li>theta: OUTRIDER-estimated gene dispersion</li> <li>counts: Raw gene expression count</li> <li>normalized_counts: OUTRIDER-normalized gene expression count</li> <li>l2fc: log2 fold change between observed and expected gene expression count</li> <li>zscore: z-score of gene expression, obtained by quantile-mapping the OUTRIDER-estimated distribution to the standard normal distribution</li> <li>nominal_pvalue: OUTRIDER-estimated <em>p</em>-value of being an expression outlier</li> <li>FDR: FDR-adjusted <em>p</em>-value of being an expression outlier</li> <li>is_in_benchmark: Whether this observation is part of the aberrant gene expression prediction benchmark</li> <li>is_underexpressed_outlier: Whether this observation is an underexpression outlier at FDR < 5%. This is the benchmark prediction label.</li> </ul> <p><br>The isoform proportions table (gtex_v8_isoform_proportions.tsv) contains the following columns:</p> <ul> <li>gene: Ensembl gene identifier</li> <li>tissue_type: GTEx tissue type</li> <li>tissue: GTEx tissue</li> <li>transcript: Ensembl transcript identifier</li> <li>mean_transcript_proportions: mean transcript proportions across individuals in GTEx v8</li> <li>median_transcript_proportions: median transcript proportions across individuals in GTEx v8</li> <li>sd_transcript_proportions: standard deviation of transcript proportions across individuals in GTEx v8</li> </ul> <p><br>The expected gene expression table (gtex_v8_expected_expression.tsv) contains the following columns:</p> <ul> <li>gene: Ensembl gene identifier</li> <li>tissue_type: GTEx tissue type</li> <li>tissue: GTEx tissue</li> <li>gene_is_expressed: Whether the gene is expressed in the tissue</li> <li>median_expression: median OUTRIDER-estimated expected gene expression (mu) across individuals</li> <li>expression_dispersion: OUTRIDER-estimated gene dispersion (theta)</li> </ul>
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.