Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
1,943
datasets available to search
ShareScore release 0.9.0
Dataset results
1,943 results for “machine learning”
Preprocessed C# Source Codes for Machine Learning
<p>The dataset comes from the HackerRank site, 329,937 C# source codes of 22 tasks were collected and all verified by unit tests.</p> <p>During the download process, source codes received only a unique serial number instead of the user name who solved the task and stored inside the 'task_name/origin' folder. After collecting the data, a new database was created, which included cleaned-up versions of the source codes ('task_name/cleaned' folders contains). Finally, a third set of data was extracted from this cleaned-up version, where a delimiter was inserted before and after each elementary expression to support easy processing and analysis processes ('task_name/reduced' folders contains). Inside the 'task_name' folder three csv files, which contain the equality checking result. The compressed folder also contains a vector space (and related files) made from the reduced data set. These four files are directly in the main folder.</p>
3D nanostructural characterisation of grain boundaries in atom probe data utilising machine learning techniques
<p>This repository contains supplementary data to the simulations in our paper</p> <p>"3D nanostructural characterisation of grain boundaries in atom probe data utilising machine learning techniques"</p> <p><strong>APTTipCarvingExecutable.tar.gz</strong><br> Contains the production state of the tip synthesis tool source code and compilation</p> <p><strong>TAPSimExecutable.tar.gz</strong><br> Contains the production state of the TAPSim simulation tool source code and compilation</p> <p><strong>scripts.zip</strong><br> Contains tiny shell scripts we used to execute the simulations</p> <p><strong>Two production simulations were performed.</strong><br> Both use the same tip bicrystal geometry but different orientations:<br> <strong>SimID.31054 is the one we discuss in the paper, it has the experimentally measured orientations</strong><br> SimID.31053 is an exemplary simulation with two different crystal orientations</p> <p><strong>For both SimID results five TAR archives exist:</strong><br> TAPSimDetectorHits* contains the main result, the simulated detector hit positionsBiCarving*<br> TAPSimTrajectories* contains all ion trajectories<br> TAPSimInput* contains supplementary results of the TAPSim field evaporation simulation<br> BiCarving* contains the settings and results of the synthesis, the XML file inside the archive details the orientations<br> Meshgen* contains the results of the meshing process prior to the TAPSim simulation</p> <p> </p>
Supplementary File S2 for the publication 'Predicting Bacterial Virulence Factors - Evaluation of Machine Learning and Negative Data Strategies' by Rentzsch, R et al.
<p>Supplementary File S2 for the publication 'Predicting Bacterial Virulence Factors - Evaluation of Machine Learning and Negative Data Strategies' by Robert Rentzsch, Carlus Deneke, Andreas Nitsche, and Bernhard Y. Renard</p>
Compound activity classes from ChEMBL for machine learning analysis
<p>Ten activity classes are provided that were extracted from ChEMBL version 24 for machine learning studies. Compounds are given in SMILES representations. The following selection criteria were applied. Compounds were required to be tested in a direct binding assay against a single human protein with a ChEMBL assay confidence score of 9. In addition, K<sub>i</sub> measurements had to be available. If multiple K<sub>i</sub> values were available for a compound and did not fall within the same order of magnitude, the compound was not selected. Furthermore only compounds with (mean) pK<sub>i</sub> of at least 5 were considered. Moreover, activity classes had to contain at least 200 compounds belonging to at least 50 computationally determined analog series. The 10 deposited classes consist of 243 to 955 compounds and 57 to 216 analog series.</p>
The codrep machine learning on source code competition, the raw diff
<p>CodRep is a machine learning competition on source code data. It is carefully designed so that anybody can enter the competition, whether professional researchers, students or independent scholars, without specific knowledge in machine learning or program analysis. In particular, it aims at being a common playground on which the machine learning and the software engineering research communities can interact.</p> <p> </p> <p>This dataset provides the raw diffs that we collected, that are used for generating the prediction tasks. See more info at https://github.com/KTH/CodRep-competition.</p>
2D Ising model Monte Carlo configurations for the paper Entropy from Machine Learning
<p>Monte Carlo configurations for the 2D Ising model on a periodic 20x20 lattice used in the paper <em>Entropy from Machine Learning.</em></p> <p>Contains:</p> <ul> <li>20000 configurations for each temperature in the range T=1.0 to T=4.0 in 0.1 intervals</li> <li>40000 configurations at T=Tc</li> <li>README.md file with information about reading into Python</li> </ul> <p>See repository <a href="https://github.com/rmldj/ml-entropy">github.com/rmldj/ml-entropy.</a></p>
Machine learning pipeline to train toxicity prediction model of FunTox-Networks
<p>Machine Learning pipeline used to provide toxicity prediction in FunTox-Networks</p> <p>01_DATA # preprocessing and filtering of raw activity data from ChEMBL<br> - Chembl_v25 # latest activity assay data set from ChEMBL (retrieved Nov 2019)<br> - filt_stats.R # Filtering and preparation of raw data<br> - Filtered # output data sets from filt_stats.R<br> - toxicity_direction.csv # table of toxicity measurements and their proportionality to toxicity</p> <p>02_MolDesc # Calculation of molecular descriptors for all compounds within the filtered ChEMBL data set<br> - datastore # files with all compounds and their calculated molecular descriptors based on SMILES<br> - scripts<br> - calc_molDesc.py # calculates for all compounds based on their smiles the molecular descriptors<br> - chemopy-1.1 # used python package for descriptor calculation as decsribed in: https://doi.org/10.1093/bioinformatics/btt105</p> <p>03_Averages # Calculation of moving averages for levels and organisms as required for calculation of Z-scores<br> - datastore # output files with statistics calculated by make_Z.R<br> - scripts<br> -make_Z.R # script to calculate statistics to calculate Z-scores as used by the regression models<br> <br> 04_ZScores # Calculation of Z-scores and preparation of table to fit regression models<br> - datastore # Z-normalized activity data and molecular descriptors in the form as used for fitting regression models<br> - scripts<br> -calc_Ztable.py # based on activity data, molecular descriptors and Z-statistics, the learning data is calculated</p> <p>05_Regression # Performing regression. Preparation of data by removing of outliers based on a linear regression model. Learning of random forest regression models. Validation of learning process by cross validation and tuning of hyperparameters.</p> <p>- datastore # storage of all random forest regression models and average level of Z output value per level and organism (zexp_*.tsv)<br> - scripts<br> - data_preperation.R # set up of regression data set, removal of outliers and optional removal of fields and descriptors<br> - Rforest_CV.R # analysis of machine learning by cross validation, importance of regression variables and tuning of hyperparameters (number of trees, split of variables)<br> - Rforest.R # based on analysis of Rforest_CV.R learning of final models</p> <p>rregrs_output<br> # early analysis of regression model performance with the package RRegrs as described in: https://doi.org/10.1186/s13321-015-0094-2</p>
Machine learning classification of archaea and bacteria identifies novel predictive genomic features
<p>Dataset used for the classification analysis of archaea and bacteria based on 77 genomic features calculated using GBRAP (GenBank Retrieving, Analyzing and Parsing) tool (Vischioni, C. et al. Gbrap: a tool to retrieve, parse and analyze genbank files of viral and bacterial species. bioRxiv 2021–09 (2021)).</p>
Machine Learning Framework for High-Resolution Air Temperature Downscaling Using LiDAR-Derived Urban Morphological Features
<p>This dataset supports the study titled <em>"Machine Learning Framework for High-Resolution Air Temperature Downscaling Using LiDAR-Derived Urban Morphological Features"</em>, published in <em>Urban Climate</em> (<a href="https://doi.org/10.1016/j.uclim.2024.102102" target="_new" rel="noopener">DOI: 10.1016/j.uclim.2024.102102</a>).</p> <p> </p> <p><strong>Content Overview:</strong></p> <ul> <li> <p><strong>Building Label Data for Footprint Detection</strong>:</p> <ul> <li><em>Amsterdam_BDG_Label.rar</em></li> <li><em>MiamiDade_BDG_Label.rar</em></li> </ul> <p>These are the label datasets used for training the building detection segmentation models. They have been instrumental in accurately detecting building footprints in Amsterdam.</p> </li> <li> <p><strong>Amsterdam_3D_Buildings.rar</strong>: CityGML file of 3D building models for Amsterdam, derived from LiDAR data and U-Net3+ model.</p> </li> </ul> <ul> <li> <p><strong>Morphological Features.rar</strong>: Contains urban morphological features (in raster format) extracted from LiDAR data used in the study.</p> </li> <li> <p><strong>Training and Test Data for Air Temperature Estimation</strong>:</p> <ul> <li><em>Train_Test_AvgTemp_Amsterdam.rar</em></li> <li><em>Train_Test_MaxTemp_Amsterdam.rar</em></li> <li><em>Train_Test_MinTemp_Amsterdam.rar</em></li> </ul> <p>This dataset includes training and testing data for estimating air temperatures in three scenarios: average daily temperature, minimum daily temperature, and maximum daily temperature for the city of Amsterdam.</p> </li> </ul>
MD simulations files for: Enhanced Sampling of Biomolecular Slow Conformational Transitions Using Adaptive Sampling and Machine Learning
<div>Colvar files and related python scripts of Ala2 and Ala10 simulations.</div>
A machine learning model reveals expansive downregulation of ligand-receptor interactions enhancing lymphocyte infiltration in melanoma with developed resistance to Immune Checkpoint Blockade
<p>Data repository containing the data to reproduce the results and findings that are published in:</p> <p>Sahni, S., Wang, B., Wu, D. <em>et al.</em> A machine learning model reveals expansive downregulation of ligand-receptor interactions that enhance lymphocyte infiltration in melanoma with developed resistance to immune checkpoint blockade. <em>Nat Commun</em> <strong>15</strong>, 8867 (2024). https://doi.org/10.1038/s41467-024-52555-4</p>
Supplementary Tables for "A 3.3-Million-Year Record of Antarctic Iceberg Rafted Debris and Ice Sheet Evolution Quantified by Machine Learning"
<p>Supplementary Tables for "A 3.3-Million-Year Record of Antarctic Iceberg Rafted Debris and Ice Sheet Evolution Quantified by Machine Learning"</p> <p> </p> <p><strong>Table Captions:</strong></p> <p><strong>Table S1.</strong> Site U1537 Age Model Tie Points from Weber et al. (2022) and Reilly et al. (2021)</p> <p><strong>Table S2. </strong>Site U1537 Age Model used in this study, applying both the age tie points from Weber et al. (2022) and Reilly et al. (2021)</p> <p><strong>Table S3. </strong>Hole U1538A correlation to the Dove Basin Stack from Bailey et al. (2022), and the addition of the U1538 splice CCSF-A depth to the Dove Basin CCSF-A</p> <p><strong>Table S4. </strong>Site U1538 splice table used in this study, note the continuation down Hole A after Core 14H</p> <p><strong>Table S5. </strong>New top core section offsets for Site U1536 cores added to the Reilly et al. (2021) extended splice table</p> <p><strong>Table S6. </strong>New top core section offsets for Site U1537 cores added to Reilly et al. (2021) extended splice table</p> <p><strong>Table S7. </strong>Comparison of Convolutional Neural Network IRD counts to shipboard eye counts of IRD at Site U1536</p> <p><strong>Table S8. </strong>Site U1537 CNN IRD Counts per 50 cm bins</p> <p><strong>Table S9. </strong>Site U1536 IRD Fluxes Per 5 kyr Quantified by a Convolutional Neural Network (0-3.3 Ma)</p> <p><strong>Table S10. </strong>Site U1537 IRD Fluxes Per 5 kyr Quantified by a Convolutional Neural Network (0-3.3 Ma)</p> <p><strong>Table S11. </strong>Site U1536 IRD Fluxes Per 1 kyr Quantified by a Convolutional Neural Network (0-1.2 Ma)</p> <p><strong>Table S12. </strong>Site U1537 IRD Fluxes Per 1 kyr Quantified by a Convolutional Neural Network (0-1.2 Ma)</p> <p><strong>Table S13. </strong>Site U1538 IRD Fluxes Per 1 kyr Quantified by a Convolutional Neural Network (0-1.2 Ma)</p>
Supplementary data for: Graphene Microelectrode Arrays, 4D Structured Illumination Microscopy, and a Machine Learning Spike Sorting Algorithm Permit the Analysis of Ultrastructural Neuronal Changes During Neuronal Signalling in a Model of Niemann-Pick Disease Type C
<p>Supplementary example data for the work presented in "<em>Graphene Microelectrode Arrays, 4D Structured Illumination Microscopy, and a Machine Learning Spike Sorting Algorithm Permit the Analysis of Ultrastructural Neuronal Changes During Neuronal Signalling in a Model of Niemann-Pick Disease Type C</em>". </p> <p><strong>Abstract: </strong></p> <p>Simultaneously recording network activity and ultrastructural changes of the synapse is essential for advancing our understanding of the basis of neuronal functions. However, the rapid millisecond-scale fluctuations in neuronal activity and the subtle sub-diffraction resolution changes of synaptic morphology pose significant challenges to this endeavour. Here, we use specially designed graphene microelectrode arrays (G-MEAs), which are compatible with high spatial resolution imaging across various scales as well as permit high temporal resolution electrophysiological recordings to address these challenges. Furthermore, alongside G-MEAs, we have developed an easy-to-implement machine learning algorithm to efficiently process the large datasets collected from MEA recordings. We demonstrate that the combined use of G-MEAs, machine learning (ML) spike analysis, and four-dimensional (4D) structured illumination microscopy (SIM) enables monitoring the impact of disease progression on hippocampal neurons which have been treated with an intracellular cholesterol transport inhibitor mimicking Niemann-Pick disease type C (NPC), and show that synaptic boutons, compared to untreated controls, significantly increase in size, leading to a loss in neuronal signalling capacity.</p> <p> </p>
Code and Data for "A machine learning approach for estimating snow depth across the European Alps from Sentinel-1 imagery"
<p>Here we share the data and code for “A machine learning approach for estimating snow depth across the European Alps from Sentinel-1 imagery”</p> <p>Corresponding author: Devon Dunmire devon.dunmire@kuleuven.be</p> <p>‘model_training’ - contains script to train the ML model, and training data sets from (1) in-situ snow measurement sites (training_data.p) and (2) photogrammetry snow depth maps (map_training_data.p)</p> <p>‘Cross_val_predictions’ contains model predictions for our cross-validation of all the in-situ snow measurement sites</p> <p>‘run_model’ contains the trained model (final_model_xg.pkl) and scripts to retrieve snow depth with our ML model.</p> <p>‘SD_*’ zip folders contains daily ML snow depth output over the European Alps for each snow year from Sept. 1 2015 - Apr. 30 2023. Data from multiple orbits is averaged.</p> <p>Naming convention: ‘S1_ml_SD_{yyyymmdd}_.nc’</p>
Training data composition determines machine learning generalization and biological rule discovery
<p>Github: https://github.com/csi-greifflab/negative-class-optimization</p> <p>Preprint: https://www.biorxiv.org/content/10.1101/2024.06.17.599333v1</p>
Trade-offs Between Performance Efficiency and Costs While Using Function as a Service for Machine Learning Tasks: A Systematic Literature Review
<p>This repository contains all artifacts that were used for the systematic literature review (SLR) related to a the cost and performance trade-offs when Function as a Service (FaaS) for machine learning (ML) tasks.</p> <p>We selected and analyzed 65 papers and publications that were optained via Scopus. The study took place in 2024 from January to August 2024.</p>
Una rivista ad accesso aperto, senza costi per gli autori e di alta qualità: la storia del "Journal of Machine Learning Research". [Video]
<p>«Times have changed. Articles now circulate easily via the Internet, but unfortunately MLJ publications are under restricted access. […] In summary, our resignation from the editorial board of MLJ reflects our belief that journals should principally serve the needs of the intellectual community, in particular by providing the immediate and universal access to journal articles that modern technology supports, and doing so at a cost that excludes no one.» Questa lettera di dimissioni, firmata dalla maggioranza degli editor della rivista Machine Learning (Kluwer ), sancì la nascita del Journal of Machine Learning Research, una rivista open access, subito accreditatasi tra le più qualificate sedi di pubblicazione per le ricerche nel settore del machine learning. Una vicenda che risale al 2000, ma che, ad anni di distanza, non cessa di far discutere. Come quando nel 2011 Kent Anderson (Scholarly Kitchen) mise in dubbio la sostenibilità di riviste open access e senza costi per gli autori. «In my field (computer science) one of the most prominent journals is entirely free and open access (Journal of Machine Learning Research)» fu la secca replica di Yann LeCun. Ne nacque una discussione, proseguita sul blog di Stuart Shieber, che appare emblematica sotto diversi aspetti e di cui proveremo a riassumere i punti salienti.</p>
Result dataset for the paper "Determining Research Priorities Using Machine Learning"
<p>The dataset needed by the paper software to run the notebooks.</p>
Input Dataset for "Determining Reseach Priorities Using Machine Learning" Paper
<p>Input dataset. Used by LDA and other scripts to create the result dataset. Journal data harvested from ADS in 2020 (so it will be different if again harvested in present day given that new papers are being added for various years by ADS staff).</p>
Evaluating Machine Learning Models for Supernova Gravitational Wave Signal Classification
<p>This dataset contains gravitational wave (GW) data used in our research work <a href="https://doi.org/10.1088/2632-2153/ada33a" target="_blank" rel="noopener">Abylkairov et al. (2024)</a>. The first 10,000 columns represent the gravitational wave strain <em>D · h</em> [cm] for the corresponding time values ranging from -993 ms to 6.9 ms, with a step size of 0.1 ms. The zero time refers to the time of core bounce. Each row within these first 10,000 columns corresponds to 864 different gravitational wave signals.</p> <p>Columns 10,001 to 10,005 contain the following additional parameters:</p> <ul> <li><strong>T/|W|</strong>: The rotational parameter.</li> <li><strong>GR_or_GREP</strong>: Binary indicator for the signal type, where 0 denotes GR and 1 denotes GREP.</li> <li><strong>EOS</strong>: The equation of state (EOS) model, where 0 corresponds to SFHo, 1 to LS220, 2 to HSDD2, and 3 to GShenFSU2.1.</li> <li><strong>f_peak</strong>: The peak frequency [Hz].</li> <li><strong>D Delta h</strong>: <em>D · ∆h</em> [cm].</li> </ul> <p>For each row (representing a single gravitational wave signal), these parameters provide information about the signal's rotational parameter, type (GR or GREP), EOS model, peak frequency, and <em>D · ∆h</em>.</p> <p><strong>Note</strong>: In the f_peak calculation procedure, we truncated the GW signal at 4.5 ms after the end of the core bounce (see <a href="https://doi.org/10.1103/PhysRevD.95.063019">Richers et al. (2017)</a> for details).</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.