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.
87
datasets available to search
ShareScore release 0.9.0
Dataset results
87 results for “Learning design”
Supporting user preferences in search-based product line architecture design using Machine Learning
<p>The Product Line Architecture (PLA) is one of the most important artifacts of a Software Product Line. PLA design requires intensive human effort as it involves several conflicting factors. In order to support this task, an interactive search-based approach, automated by a tool named OPLA-Tool, was proposed in a previous work. Through this tool the software architect evaluates the generated solutions during the optimization process. Considering that evaluating PLA is a complex task and search-based algorithms demand a high number of generations, the evaluation of all solutions in all generations cause human fatigue. In this work, we incorporated in OPLA-Tool a Machine Learning (ML) model to represent the architect in some moments during the optimization process aiming to decrease the architect's effort. Through the execution of a quanti-qualitative exploratory study it was possible to demonstrate the reduction of the fatigue problem and that the solutions produced at the end of the process, in most cases, met the architect’s needs.</p>
Machine learning-guided high throughput nanoparticle design
<p>Widefield microscopy high content images used for this study. Contains all the intermediate reports in excel result from image analysis and processing:</p> <ul> <li>00_Initial Dataset (DoE): contains all image data used to determine the labels for the first active learning cycle. Nano particle formulations were suggested using deisgn of experiments.</li> <li>01_ML_Iteration01 (Exploration): contains all image data used to determine the labels for the formulations suggested by the first active learning cycle</li> <li>02_ML_Iteration02 (Exploitation): contains all image data used to determine the labels for the formulations suggested by the second active learning cycle</li> <li>03_ML_Iteration03 (Exploration): contains all image data used to determine the labels for last (model validation) experiment. Includes the subsets of particles predicted with low and high uptake.</li> </ul>
Inverse Design of Octagonal Plasmonic Structure for Switching Using Deep Learning
<p>OctagonalRR_AOPS: Datasets for "<strong>Inverse Design of Octagonal Plasmonic Structure for Switching Using Deep Learning</strong>," (2024).</p>
The AI Economist: Taxation policy design via two-level deep reinforcement learning
<p>This dataset contains all raw experimental data for the paper "The AI Economist: Taxation Policy Design via Two-level Deep Multi-Agent Reinforcement Learning". </p> <p>The accompanying simulation, reinforcement learning, and data visualization code can be found at https://github.com/salesforce/ai-economist.</p> <p>For the one-step economy experiments, we provide:</p> <ul> <li> <p>training histories,</p> </li> <li> <p>configuration files (these experiments do not use phases), and</p> </li> <li> <p>final agent and planner models.</p> </li> </ul> <p>For the Gather-Trade-Build scenario, the data covers 6 spatial layouts: two Open-Quadrant (with 4 and 10 agents), and four Split-World maps with different configurations of the high-skilled and low-skilled agents. It also covers 4 tax policies (the AI Economist, Saez, free-market, and US federal). In addition, the AI Economist has been optimized for two social welfare functions: the product of equality and productivity, and inverse-income weighted utility. The Saez tax policy also uses estimated elasticities. </p> <p>Each experiment was repeated with different random seeds: 10 seeds for the Open-Quadrant scenarios, and 5 seeds for the Split-World scenarios. For each individual experiment, we provide: </p> <ul> <li> <p>Training histories (e.g. equality and productivity throughout training)</p> </li> <li> <p>the phase 1 and phase 2 configuration files, </p> </li> <li> <p>40 episode dense logs (the final 10 simulation logs across 4 environment replicas),</p> </li> <li> <p>phase 1 final agent models, and</p> </li> <li> <p>phase 2 final agent and planner models.</p> </li> </ul> <p>Finally, we include all data and results used to calibrate the Saez elasticity estimates and to estimate elasticity directly from a sweep over flat-rate tax policies:</p> <ul> <li> <p>training histories,</p> </li> <li> <p>the phase 1 and phase 2 configuration files, </p> </li> <li> <p>phase 1 final agent models, and</p> </li> <li> <p>phase 2 final agent and planner models.</p> </li> </ul>
Dataset for the Manuscript: Demonstration of optically-driven plasmonic nanomotors designed by deep learning networks
<p>This repository contains the data corresponding to the manuscript "Demonstration of the optically-driven plasmonic nanomotor designed by deep learning networks." It consists of 5 parts: Machine learning, Numerical analysis, Rotation measurement, Scattering measurement, and Supplementary information. The code for the machine learning algorithm is available at "https://github.com/mintaechung/Nanomotor_Predictor_Generator."</p> <p> </p> <ul> <li><strong>'Machine_learning.zip'</strong>: Correlation between optical torques calculated by SIE and predicted by trained CNN, Objective loss functions at the 1st iteration, and the torque distribution of the initial randomset and the output of the nanorotor generator after the 3rd iteration.</li> <li><strong>'Numerical_analysis.zip'</strong>: MATLAB codes to retrieve 'Moments', 'Field intensity distribution', 'Poynting vectors', and 'Torques'. </li> <li><strong>'Rotation_measurement.zip'</strong>: Raw videos, Intensity profiles of ROI, Rotation measurement results.</li> <li><strong>'Scattering_measurement.zip'</strong>: Scattering intensity measurement with reference light.</li> <li><strong>'Supplementary_Info.zip'</strong>: Random geometry generation, Optical torques of 6 blades, Expanded structure, Shrinkage, Polarization independence, Angular momentum, and Machine learning progress.</li> </ul>
A fast machine-learning-guided primer design pipeline for selective whole genome amplification
<p>Addressing many of the major outstanding questions in the fields of microbial evolution and pathogenesis will require analyses of populations of microbial genomes. Although population genomic studies provide the analytical resolution to investigate evolutionary and mechanistic processes at fine spatial and temporal scales – precisely the scales at which these processes occur – microbial population genomic research is currently hindered by the practicalities of obtaining sufficient quantities of the relatively pure microbial genomic DNA necessary for next-generation sequencing. Here we present swga2.0, an optimized and parallelized pipeline to design selective whole genome amplification (SWGA) primer sets. Unlike previous methods, swga2.0 incorporates active and machine learning methods to evaluate the amplification efficacy of individual primers and primer sets. Additionally, swga2.0 optimizes primer set search and evaluates strategies, including parallelization at each stage of the pipeline, to dramatically decrease program runtime from weeks to minutes. Here we describe the swga2.0 pipeline, including the empirical data used to identify primer and primer set characteristics, that improve amplification performance. Additionally, we evaluated the novel swga2.0 pipeline by designing primers sets that successfully amplify <em>Prevotella melaninogenica</em>, an important component of the lung microbiome in cystic fibrosis patients, from samples dominated by human DNA.</p>
Benchmarking Study of Deep Generative Models for Inverse Polymer Design: Reinforcement Learning
<p>Well-trained models and generation results for reinforcement learning part of <a href="https://github.com/ytl0410/Polymer-Generative-Models-Benchmark">ytl0410/Polymer-Generative-Models-Benchmark: Well-trained models and generative outcomes for the paper "Benchmarking Study of Deep Generative Models for Inverse Polymer Design" (github.com)</a></p>
Cone-Beam X-Ray CT Data Collection Designed for Machine Learning: Samples 38-42
<p>This upload contains samples 38 - 42 from the data collection described in</p> <p>Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", <em>Sci Data</em> <strong>6, </strong>215 (2019). <a href="https://doi.org/10.1038/s41597-019-0235-y">https://doi.org/10.1038/s41597-019-0235-y</a> or <a href="https://arxiv.org/abs/1905.04787">arXiv:1905.04787</a> (2019)</p> <p>Abstract:<br> "Unlike previous works, this open data collection consists of X-ray cone-beam (CB) computed tomography (CT) datasets specifically designed for machine learning applications and high cone-angle artefact reduction: Forty-two walnuts were scanned with a laboratory X-ray setup to provide not only data from a single object but from a class of objects with natural variability. For each walnut, CB projections on three different orbits were acquired to provide CB data with different cone angles as well as being able to compute artefact-free, high-quality ground truth images from the combined data that can be used for supervised learning. We provide the complete image reconstruction pipeline: raw projection data, a description of the scanning geometry, pre-processing and reconstruction scripts using open software, and the reconstructed volumes. Due to this, the dataset can not only be used for high cone-angle artefact reduction but also for algorithm development and evaluation for other tasks, such as image reconstruction from limited or sparse-angle (low-dose) scanning, super resolution, or segmentation."</p> <p>The scans are performed using a custom-built, highly flexible X-ray CT scanner, the FleX-ray scanner, developed by <a href="https://xre.be/">XRE nv</a>and located in the FleX-ray Lab at the <a href="https://www.cwi.nl/">Centrum Wiskunde & Informatica (CWI)</a> in Amsterdam, Netherlands. The general purpose of the FleX-ray Lab is to conduct proof of concept experiments directly accessible to researchers in the field of mathematics and computer science. The scanner consists of a cone-beam microfocus X-ray point source that projects polychromatic X-rays onto a 1536-by-1944 pixels, 14-bit flat panel detector (Dexella 1512NDT) and a rotation stage in-between, upon which a sample is mounted. All three components are mounted on translation stages which allow them to move independently from one another.</p> <p>Please refer to the paper for all further technical details.</p> <p>The complete data set can be found via the following links: <a href="https://doi.org/10.5281/zenodo.2686725">1-8</a>, <a href="https://doi.org/10.5281/zenodo.2686970">9-16</a>, <a href="https://doi.org/10.5281/zenodo.2687386">17-24</a>, <a href="https://doi.org/10.5281/zenodo.2687634">25-32</a>, <a href="https://doi.org/10.5281/zenodo.2687896">33-37</a>, <a href="https://doi.org/10.5281/zenodo.2688111">38-42</a></p> <p>The corresponding Python scripts for loading, pre-processing and reconstructing the projection data in the way described in the paper can be found on <a href="https://github.com/cicwi/WalnutReconstructionCodes">github</a></p> <p>For more information or guidance in using these dataset, please get in touch with</p> <ul> <li>henri.dersarkissian [at] gmail.com</li> <li>Felix.Lucka [at] cwi.nl</li> </ul>
Cone-Beam X-Ray CT Data Collection Designed for Machine Learning: Samples 33-37
<p>This upload contains samples 33 - 37 from the data collection described in</p> <p>Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", <em>Sci Data</em> <strong>6, </strong>215 (2019). <a href="https://doi.org/10.1038/s41597-019-0235-y">https://doi.org/10.1038/s41597-019-0235-y</a> or <a href="https://arxiv.org/abs/1905.04787">arXiv:1905.04787</a> (2019)</p> <p>Abstract:<br> "Unlike previous works, this open data collection consists of X-ray cone-beam (CB) computed tomography (CT) datasets specifically designed for machine learning applications and high cone-angle artefact reduction: Forty-two walnuts were scanned with a laboratory X-ray setup to provide not only data from a single object but from a class of objects with natural variability. For each walnut, CB projections on three different orbits were acquired to provide CB data with different cone angles as well as being able to compute artefact-free, high-quality ground truth images from the combined data that can be used for supervised learning. We provide the complete image reconstruction pipeline: raw projection data, a description of the scanning geometry, pre-processing and reconstruction scripts using open software, and the reconstructed volumes. Due to this, the dataset can not only be used for high cone-angle artefact reduction but also for algorithm development and evaluation for other tasks, such as image reconstruction from limited or sparse-angle (low-dose) scanning, super resolution, or segmentation."</p> <p>The scans are performed using a custom-built, highly flexible X-ray CT scanner, the FleX-ray scanner, developed by <a href="https://xre.be/">XRE nv</a>and located in the FleX-ray Lab at the <a href="https://www.cwi.nl/">Centrum Wiskunde & Informatica (CWI)</a> in Amsterdam, Netherlands. The general purpose of the FleX-ray Lab is to conduct proof of concept experiments directly accessible to researchers in the field of mathematics and computer science. The scanner consists of a cone-beam microfocus X-ray point source that projects polychromatic X-rays onto a 1536-by-1944 pixels, 14-bit flat panel detector (Dexella 1512NDT) and a rotation stage in-between, upon which a sample is mounted. All three components are mounted on translation stages which allow them to move independently from one another.</p> <p>Please refer to the paper for all further technical details.</p> <p>The complete data set can be found via the following links: <a href="https://doi.org/10.5281/zenodo.2686725">1-8</a>, <a href="https://doi.org/10.5281/zenodo.2686970">9-16</a>, <a href="https://doi.org/10.5281/zenodo.2687386">17-24</a>, <a href="https://doi.org/10.5281/zenodo.2687634">25-32</a>, <a href="https://doi.org/10.5281/zenodo.2687896">33-37</a>, <a href="https://doi.org/10.5281/zenodo.2688111">38-42</a></p> <p>The corresponding Python scripts for loading, pre-processing and reconstructing the projection data in the way described in the paper can be found on <a href="https://github.com/cicwi/WalnutReconstructionCodes">github</a></p> <p>For more information or guidance in using these dataset, please get in touch with</p> <ul> <li>henri.dersarkissian [at] gmail.com</li> <li>Felix.Lucka [at] cwi.nl</li> </ul>
Cone-Beam X-Ray CT Data Collection Designed for Machine Learning: Samples 25-32
<p>This upload contains samples 25 - 32 from the data collection described in</p> <p>Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", <em>Sci Data</em> <strong>6, </strong>215 (2019). <a href="https://doi.org/10.1038/s41597-019-0235-y">https://doi.org/10.1038/s41597-019-0235-y</a> or <a href="https://arxiv.org/abs/1905.04787">arXiv:1905.04787</a> (2019)</p> <p>Abstract:<br> "Unlike previous works, this open data collection consists of X-ray cone-beam (CB) computed tomography (CT) datasets specifically designed for machine learning applications and high cone-angle artefact reduction: Forty-two walnuts were scanned with a laboratory X-ray setup to provide not only data from a single object but from a class of objects with natural variability. For each walnut, CB projections on three different orbits were acquired to provide CB data with different cone angles as well as being able to compute artefact-free, high-quality ground truth images from the combined data that can be used for supervised learning. We provide the complete image reconstruction pipeline: raw projection data, a description of the scanning geometry, pre-processing and reconstruction scripts using open software, and the reconstructed volumes. Due to this, the dataset can not only be used for high cone-angle artefact reduction but also for algorithm development and evaluation for other tasks, such as image reconstruction from limited or sparse-angle (low-dose) scanning, super resolution, or segmentation."</p> <p>The scans are performed using a custom-built, highly flexible X-ray CT scanner, the FleX-ray scanner, developed by <a href="https://xre.be/">XRE nv</a>and located in the FleX-ray Lab at the <a href="https://www.cwi.nl/">Centrum Wiskunde & Informatica (CWI)</a> in Amsterdam, Netherlands. The general purpose of the FleX-ray Lab is to conduct proof of concept experiments directly accessible to researchers in the field of mathematics and computer science. The scanner consists of a cone-beam microfocus X-ray point source that projects polychromatic X-rays onto a 1536-by-1944 pixels, 14-bit flat panel detector (Dexella 1512NDT) and a rotation stage in-between, upon which a sample is mounted. All three components are mounted on translation stages which allow them to move independently from one another.</p> <p>Please refer to the paper for all further technical details.</p> <p>The complete data set can be found via the following links: <a href="https://doi.org/10.5281/zenodo.2686725">1-8</a>, <a href="https://doi.org/10.5281/zenodo.2686970">9-16</a>, <a href="https://doi.org/10.5281/zenodo.2687386">17-24</a>, <a href="https://doi.org/10.5281/zenodo.2687634">25-32</a>, <a href="https://doi.org/10.5281/zenodo.2687896">33-37</a>, <a href="https://doi.org/10.5281/zenodo.2688111">38-42</a></p> <p>The corresponding Python scripts for loading, pre-processing and reconstructing the projection data in the way described in the paper can be found on <a href="https://github.com/cicwi/WalnutReconstructionCodes">github</a></p> <p>For more information or guidance in using these dataset, please get in touch with</p> <ul> <li>henri.dersarkissian [at] gmail.com</li> <li>Felix.Lucka [at] cwi.nl</li> </ul>
Cone-Beam X-Ray CT Data Collection Designed for Machine Learning: Samples 17-24
<p>This upload contains samples 17 - 24 from the data collection described in</p> <p>Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", <em>Sci Data</em> <strong>6, </strong>215 (2019). <a href="https://doi.org/10.1038/s41597-019-0235-y">https://doi.org/10.1038/s41597-019-0235-y</a> or <a href="https://arxiv.org/abs/1905.04787">arXiv:1905.04787</a> (2019)</p> <p>Abstract:<br> "Unlike previous works, this open data collection consists of X-ray cone-beam (CB) computed tomography (CT) datasets specifically designed for machine learning applications and high cone-angle artefact reduction: Forty-two walnuts were scanned with a laboratory X-ray setup to provide not only data from a single object but from a class of objects with natural variability. For each walnut, CB projections on three different orbits were acquired to provide CB data with different cone angles as well as being able to compute artefact-free, high-quality ground truth images from the combined data that can be used for supervised learning. We provide the complete image reconstruction pipeline: raw projection data, a description of the scanning geometry, pre-processing and reconstruction scripts using open software, and the reconstructed volumes. Due to this, the dataset can not only be used for high cone-angle artefact reduction but also for algorithm development and evaluation for other tasks, such as image reconstruction from limited or sparse-angle (low-dose) scanning, super resolution, or segmentation."</p> <p>The scans are performed using a custom-built, highly flexible X-ray CT scanner, the FleX-ray scanner, developed by <a href="https://xre.be/">XRE nv</a>and located in the FleX-ray Lab at the <a href="https://www.cwi.nl/">Centrum Wiskunde & Informatica (CWI)</a> in Amsterdam, Netherlands. The general purpose of the FleX-ray Lab is to conduct proof of concept experiments directly accessible to researchers in the field of mathematics and computer science. The scanner consists of a cone-beam microfocus X-ray point source that projects polychromatic X-rays onto a 1536-by-1944 pixels, 14-bit flat panel detector (Dexella 1512NDT) and a rotation stage in-between, upon which a sample is mounted. All three components are mounted on translation stages which allow them to move independently from one another.</p> <p>Please refer to the paper for all further technical details.</p> <p>The complete data set can be found via the following links: <a href="https://doi.org/10.5281/zenodo.2686725">1-8</a>, <a href="https://doi.org/10.5281/zenodo.2686970">9-16</a>, <a href="https://doi.org/10.5281/zenodo.2687386">17-24</a>, <a href="https://doi.org/10.5281/zenodo.2687634">25-32</a>, <a href="https://doi.org/10.5281/zenodo.2687896">33-37</a>, <a href="https://doi.org/10.5281/zenodo.2688111">38-42</a></p> <p>The corresponding Python scripts for loading, pre-processing and reconstructing the projection data in the way described in the paper can be found on <a href="https://github.com/cicwi/WalnutReconstructionCodes">github</a></p> <p>For more information or guidance in using these dataset, please get in touch with</p> <ul> <li>henri.dersarkissian [at] gmail.com</li> <li>Felix.Lucka [at] cwi.nl</li> </ul>
Cone-Beam X-Ray CT Data Collection Designed for Machine Learning: Samples 9-16
<p>This upload contains samples 9 - 16 from the data collection described in</p> <p>Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", <em>Sci Data</em> <strong>6, </strong>215 (2019). <a href="https://doi.org/10.1038/s41597-019-0235-y">https://doi.org/10.1038/s41597-019-0235-y</a> or <a href="https://arxiv.org/abs/1905.04787">arXiv:1905.04787</a> (2019)</p> <p>Abstract:<br> "Unlike previous works, this open data collection consists of X-ray cone-beam (CB) computed tomography (CT) datasets specifically designed for machine learning applications and high cone-angle artefact reduction: Forty-two walnuts were scanned with a laboratory X-ray setup to provide not only data from a single object but from a class of objects with natural variability. For each walnut, CB projections on three different orbits were acquired to provide CB data with different cone angles as well as being able to compute artefact-free, high-quality ground truth images from the combined data that can be used for supervised learning. We provide the complete image reconstruction pipeline: raw projection data, a description of the scanning geometry, pre-processing and reconstruction scripts using open software, and the reconstructed volumes. Due to this, the dataset can not only be used for high cone-angle artefact reduction but also for algorithm development and evaluation for other tasks, such as image reconstruction from limited or sparse-angle (low-dose) scanning, super resolution, or segmentation."</p> <p>The scans are performed using a custom-built, highly flexible X-ray CT scanner, the FleX-ray scanner, developed by <a href="https://xre.be/">XRE nv</a>and located in the FleX-ray Lab at the <a href="https://www.cwi.nl/">Centrum Wiskunde & Informatica (CWI)</a> in Amsterdam, Netherlands. The general purpose of the FleX-ray Lab is to conduct proof of concept experiments directly accessible to researchers in the field of mathematics and computer science. The scanner consists of a cone-beam microfocus X-ray point source that projects polychromatic X-rays onto a 1536-by-1944 pixels, 14-bit flat panel detector (Dexella 1512NDT) and a rotation stage in-between, upon which a sample is mounted. All three components are mounted on translation stages which allow them to move independently from one another.</p> <p>Please refer to the paper for all further technical details.</p> <p>The complete data set can be found via the following links: <a href="https://doi.org/10.5281/zenodo.2686725">1-8</a>, <a href="https://doi.org/10.5281/zenodo.2686970">9-16</a>, <a href="https://doi.org/10.5281/zenodo.2687386">17-24</a>, <a href="https://doi.org/10.5281/zenodo.2687634">25-32</a>, <a href="https://doi.org/10.5281/zenodo.2687896">33-37</a>, <a href="https://doi.org/10.5281/zenodo.2688111">38-42</a></p> <p>The corresponding Python scripts for loading, pre-processing and reconstructing the projection data in the way described in the paper can be found on <a href="https://github.com/cicwi/WalnutReconstructionCodes">github</a></p> <p>For more information or guidance in using these dataset, please get in touch with</p> <ul> <li>henri.dersarkissian [at] gmail.com</li> <li>Felix.Lucka [at] cwi.nl</li> </ul>
Cone-Beam X-Ray CT Data Collection Designed for Machine Learning: Samples 1-8
<p>This upload contains samples 1 - 8 from the data collection described in</p> <p>Henri Der Sarkissian, Felix Lucka, Maureen van Eijnatten, Giulia Colacicco, Sophia Bethany Coban, Kees Joost Batenburg, "A Cone-Beam X-Ray CT Data Collection Designed for Machine Learning", <em>Sci Data</em> <strong>6, </strong>215 (2019). <a href="https://doi.org/10.1038/s41597-019-0235-y">https://doi.org/10.1038/s41597-019-0235-y</a> or <a href="https://arxiv.org/abs/1905.04787">arXiv:1905.04787</a> (2019)</p> <p>Abstract:<br> "Unlike previous works, this open data collection consists of X-ray cone-beam (CB) computed tomography (CT) datasets specifically designed for machine learning applications and high cone-angle artefact reduction: Forty-two walnuts were scanned with a laboratory X-ray setup to provide not only data from a single object but from a class of objects with natural variability. For each walnut, CB projections on three different orbits were acquired to provide CB data with different cone angles as well as being able to compute artefact-free, high-quality ground truth images from the combined data that can be used for supervised learning. We provide the complete image reconstruction pipeline: raw projection data, a description of the scanning geometry, pre-processing and reconstruction scripts using open software, and the reconstructed volumes. Due to this, the dataset can not only be used for high cone-angle artefact reduction but also for algorithm development and evaluation for other tasks, such as image reconstruction from limited or sparse-angle (low-dose) scanning, super resolution, or segmentation."</p> <p>The scans are performed using a custom-built, highly flexible X-ray CT scanner, the FleX-ray scanner, developed by <a href="https://xre.be/">XRE nv</a>and located in the FleX-ray Lab at the <a href="https://www.cwi.nl/">Centrum Wiskunde & Informatica (CWI)</a> in Amsterdam, Netherlands. The general purpose of the FleX-ray Lab is to conduct proof of concept experiments directly accessible to researchers in the field of mathematics and computer science. The scanner consists of a cone-beam microfocus X-ray point source that projects polychromatic X-rays onto a 1536-by-1944 pixels, 14-bit flat panel detector (Dexella 1512NDT) and a rotation stage in-between, upon which a sample is mounted. All three components are mounted on translation stages which allow them to move independently from one another.</p> <p>Please refer to the paper for all further technical details.</p> <p>The complete data set can be found via the following links: <a href="https://doi.org/10.5281/zenodo.2686725">1-8</a>, <a href="https://doi.org/10.5281/zenodo.2686970">9-16</a>, <a href="https://doi.org/10.5281/zenodo.2687386">17-24</a>, <a href="https://doi.org/10.5281/zenodo.2687634">25-32</a>, <a href="https://doi.org/10.5281/zenodo.2687896">33-37</a>, <a href="https://doi.org/10.5281/zenodo.2688111">38-42</a></p> <p>The corresponding Python scripts for loading, pre-processing and reconstructing the projection data in the way described in the paper can be found on <a href="https://github.com/cicwi/WalnutReconstructionCodes">github</a></p> <p>For more information or guidance in using these dataset, please get in touch with</p> <ul> <li>henri.dersarkissian [at] gmail.com</li> <li>Felix.Lucka [at] cwi.nl</li> </ul>
Appraise the immunogenicity of designed antibody using deep learning
<p>Appraise the immunogencity of designed antibody using deep learning</p> <p>Link to deep learning model: <a href="https://gitlab.developers.cam.ac.uk/ch/sormanni/abnativ">Yusuf Hamied Department of Chemistry / Sormanni Lab / AbNatiV · GitLab (cam.ac.uk)</a></p> <p>Python code: run_abnativ_humanness_score.py</p> <p>Dataset: antibody_affinity_protein_sabdab_vhvl_immunebuilder_outfiles_nomissing_h.fasta</p> <p>Example output: *res_scores.csv and *seq_scores.csv</p>
KuafuPrimer: Machine learning facilitates the design of 16S rRNA gene primers with minimal bias in bacterial communities
<p>KuafuPrimer is a machine learning-aided method that learns community characteristics from several samples to design 16S rRNA gene primers with minimal bias for microbial communities. It is built on <strong>Python 3.9.0</strong>, <strong>Pytorch 1.12.0</strong>. Here are some large size files required to run KuafuPrimer, and users need to download and put them in correct directories before running the program.</p> <ol> <li>Silva_ref_data.zip: processed files of silva dataset that should be put in <code>Model_data/Silva_ref_data/</code>.</li> <li>DeepAnno16_publicated_model.zip: parameters of the trained DeepAnno16 model that should be put in <code>Model_data/DeepAnno16_publicated_model/</code> .</li> </ol> <p>For more information, please refer to https://github.com/zhanghaoyu9931/KuafuPrimer.</p>
Ab initio design of microbial communities from large-scale seed pools using deep learning and rapid ptimization
<h4>This repository contains the full results of our paper: <strong><em>Ab initio</em> design of microbial communities from large-scale seed pools using deep learning and rapid ptimization.</strong></h4> <p>Authors: Xiaoqing Jiang#, Jiaheng Hou#, Haoyu Zhang#, Jinyuan Guo, Shaohua Gu, Yulin Liao, Xinrun Yang, Peter X. Geng, Yiyan Zhou, Qian Guo, Chunhui Wang, Mo Li, Alexandre Jousset, Zhong Wei*, and Huaiqiu Zhu*</p> <p>The results including:</p> <p><strong>(1)</strong> <strong>GEM.tar.gz</strong>: The eBiota-GEM dataset, containing 21,514 Genome-Scale Metabolic Models (GEMs) constructed using CarveMe based on RefSeq complete genomes.</p> <p><strong>(2) Baterial_evaluation.tar.gz</strong>: The evaluation of the ability to uptake substrates and secret productions for all 21,514 GEMs.</p> <p><strong>(3) Community_results.tar.gz</strong>: The results calculated from eBiota-GEM includes various combinations for two-bacterial consortia, covering strain IDs, substrates, products, yields, dual-bacterial growth, single-bacterial growth, co-occurrence predictions, interactions and total production.</p> <p><strong>(4) DeepCooc_files.tar.gz</strong>: The parameter files of DeepCooc, required by eBiota platform.</p>
STL files: Modeling and design of heterogeneous hierarchical bioinspired spider web structures using deep learning and additive manufacturing
<p>STL files for paper titled modeling and design of heterogeneous hierarchical bioinspired spider web structures using deep learning and additive manufacturing</p>
Dataset and scripts for publication "Property design of extruded magnesium-gadolinium alloys through machine learning"
<p>Data and scripts accompanying publication "Property design of extruded magnesium-gadolinium alloys through machine learning"</p>
Towards a practical framework to "ethics by design" data sharing and machine learning applications
<p>Responsible AI and data-driven applications can only be developed when teams integrate the ethical principles directly into the development process. An important prerequisite is the involvement of a diverse group of stakeholders who build and are affected by AI and data systems. We present a practical framework that helps teams build trustworthy AI systems and data strategies by combining expertise and training from philosophy, law, machine learning and design.</p>
Inverse folding for antibody sequence design using deep learning
<p>Model weights of the <a href="https://arxiv.org/abs/2310.19513">AbMPNN model (arXiv:2310.19513)</a> presented at the <a href="https://icml-compbio.github.io/">2023 ICML Workshop on Computational Biology</a>, and csv files with the split between train, test and validation across the <a href="https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab/">SAbDab</a> and <a href="https://zenodo.org/record/7258553">ImmuneBuilder</a> datasets.</p><p>This model is based on <a href="https://www.biorxiv.org/content/10.1101/2022.06.03.494563v1">ProteinMPNN</a> and can be run using the corresponding code: <a href="https://github.com/dauparas/ProteinMPNN">https://github.com/dauparas/ProteinMPNN</a>.</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.