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”
Data sets and machine learning models for: Machine learning from quantum chemistry to predict experimental solvent effects on reaction rates
<p>The datasets and final machine learning model files for the manuscript "Machine learning from quantum chemistry to predict experimental solvent effects on reaction rates". Citation should refer directly to the manuscript:</p> <ul> <li>Chung, Y.; Green, W. H. Machine learning from quantum chemistry to predict experimental solvent effects on reaction rates. <em>Chemical Science </em><strong>2024,</strong> doi: <a href="https://doi.org/10.1039/D3SC05353A">10.1039/D3SC05353A</a></li> </ul> <p>To use the machine learning models, please refer to the sample files and instructions on <a href="https://github.com/yunsiechung/chemprop/tree/RxnSolvKSE_ML">https://github.com/yunsiechung/chemprop/tree/RxnSolvKSE_ML</a>. </p> <p>Detailed information can be found in README.md file.</p> <p><br><strong>Details on the files</strong></p> <p>In the pretraining and finetuning set csv files, each column represents:</p> <ol> <li>rxn_smiles: atom-mapped reaction SMILES</li> <li>solvent_smiles: solvent SMILES</li> <li>ddGsolv: solvation free energy of activation of a reaction-solvent pair at 298K in kcal/mol (main prediction target)</li> <li>ddHsolv: solvation enthalpy of activation of a reaction-solvent pair at 298K in kcal/mol (main prediction target)</li> <li>dGsolv_reactant: solvation free energy of reactant(s) at 298K in kcal/mol (additional feature)</li> <li>dGsolv_product: solvation free energy of product(s) at 298K in kcal/mol (additional feature)</li> <li>dHsolv_reactant: solvation enthalpy of reactant(s) at 298K in kcal/mol (additional feature)</li> <li>dHsolv_product: solvation enthalpy of product(s) at 298K in kcal/mol (additional feature)</li> </ol> <p><strong>Data sets under 'RxnSolvKSE_dataset_v1.1.zip'</strong></p> <ul> <li>pretraining_set: contains the dataset used for pre-training <ul> <li>all_data: contains all calculated data <ul> <li>pretraining_rxn_solvent_ddGsolv_ddHsolv_with_features_all.csv: contains both main prediction targets and additional feature for reaction-solvent pairs</li> <li>pretraining_solvent_info.csv: list of all solvents</li> <li>pretraining_unique_rxn.csv: list of all reactions, both forward and reverse directions</li> </ul> </li> <li>chosen_500k_data: contains the chosen 500k data <ul> <li>pretraining_rxn_solvent_ddGsolv_ddHsolv_500k.csv: contains main prediction targets for reaction-solvent pairs</li> <li>pretraining_features_react_prod_dGsolv_dHsolv_500k.csv: contains additional features for reaction-solvent pairs</li> <li>train_test_split: contains the 5-fold random split training and test sets.</li> </ul> </li> </ul> </li> <li>finetuning_set: contains the dataset used for fine-tuning <ul> <li>all_data: contains all calculated data <ul> <li>finetuning_rxn_solvent_ddGsolv_ddHsolv_with_features_all.csv: constains both main prediction targets and additional features for reaction-solvent pairs. The rxn_key column indicates whether the reaction is bimolecular hydrogen abstraction (bihabs), unimolecular hydrogen migration (intrahabs), or radical addition to a multiple bond (raddition). The 'fwd' and 'rev' each indicate forward and reverse reactions.</li> <li>finetuning_solvent_info.csv: list of all solvents</li> <li>finetuning_unique_rxn.csv: list of all reactions, both forward and reverse directions</li> </ul> </li> <li>chosen_data: contains chosen data <ul> <li>finetuning_rxn_solvent_ddGsolv_ddHsolv_chosen.csv: contains main prediction targets for reaction-solvent pairs</li> <li>finetuning_features_react_prod_dGsolv_dHsolv_chosen.csv: contains additional features for reaction-solvent pairs</li> </ul> </li> </ul> </li> <li>experimental_set: contains the experimental rate constant data used to test the model. The original experimental data can be found at <a href="../record/7747557">https://zenodo.org/record/7747557</a>. <ul> <li> expt_rxn_atom_mapped_smiles.csv: contains the atom-mapped reaction SMILES used for the experimental data.</li> <li>expt_data_collected.xlsx: contains all experimental data and detailed information</li> <li>expt_rxn_solv_smiles_with_features_all.csv: contains the computed additional features for the experimental reaction-solvent pairs.</li> </ul> </li> </ul> <p><strong>Machine learning model files under 'RxnSolvKSE_ML_model_files.zip'</strong></p> <ul> <li>Contains the Chemprop machine learning model files for predicting ddGsolv and ddHsolv for a reaction-solvent pair. It takes atom-mapped reaction SMILES and solvent SMILES as inputs.</li> <li>To use these ML models, please refer to the sample files and instructions on <a href="https://github.com/yunsiechung/chemprop/tree/RxnSolvKSE_ML">https://github.com/yunsiechung/chemprop/tree/RxnSolvKSE_ML</a></li> </ul>
Machine Eye for Defects: Machine Learning-Based Solution to Identify and Characterize Topological Defects in Textured Images of Nematic Materials
<p><strong>Our paper has been published on Phys. Rev. Res. (doi: 10.1103/PhysRevResearch.6.013259)</strong></p> <p><strong>Our preprint paper is also avilable at arXiv(https://arxiv.org/abs/2310.06406), here is the abstract of our paper:</strong></p> <p>Topological defects play a key role in the structures and dynamics of liquid crystals (LCs) and other ordered systems. There is a recent interest in studying defects in different biological systems with distinct textures. However, a robust method to directly recognize defects and extract their structural features from various traditional and nontraditional nematic systems remains challenging to date. Here we present a machine learning solution, termed Machine Eye for Defects (MED), for automated defect analysis in images with diverse nematic textures. MED seamlessly integrates state-of-the-art object detection networks, Segment Anything Model, and vision transformer algorithms with tailored computer vision techniques. We show that MED can accurately identify the positions, winding numbers, and orientations of ±1/2 defects across distinct cellular contours, sparse vector fields of nematic directors, actin filaments, microtubules, and simulation images of Gay–Berne particles. MED performs faster than conventional defect detection method and can achieve over 90% accuracy on recognizing ±1/2 defects and their orientations from vector fields and experimental tissue images. We further demonstrate that MED can identify defect types that are not included in the training data, such as giant-core defects and defects with higher winding number. Remarkably, MED can provide correct structural information about ±1 defects. As such, MED stands poised to transform studies of diverse ordered systems by providing automated, rapid, accurate, and insightful defect analysis.</p> <p> </p> <p><strong>Repository Organization</strong></p> <p><strong>Trained Models.zip</strong></p> <p>This directory is integral for model deployment and houses all relevant pre-trained models.</p> <ul> <li><strong>plus_vit_vecUV.pt</strong>: Pre-trained model for the Plus Transformer variant.</li> <li><strong>minus_vit_theR.pt</strong>: Pre-trained model for the Minus Transformer variant.</li> <li><strong>nanodet-plus-m_416-halfenhance</strong>: A sub-directory containing all files associated with the trained Nanodet-Plus model.</li> <li><strong>configs</strong>: Configuration files for training procedures.</li> </ul> <p><strong>Training Data.zip</strong></p> <p>This directory contains all datasets used for the training of Nanodet-Plus, Plus Transformer, and Minus Transformer models.</p> <p><strong>Code.zip</strong></p> <p>This directory features the implementation details and example use-cases showcased in Figure 2 and Figure 3c of our associated paper. The directory also includes code corresponding to the specific versions of Nanodet-Plus and SAM models cited in our study.</p> <ul> <li><strong>nanodet</strong>: Code in this folder is adapted from <a href="https://github.com/RangiLyu/nanodet">RangiLyu/nanodet</a> (https://github.com/RangiLyu/nanodet). We have included the exact version used for compatibility.</li> <li><strong>segment_anything</strong>: Code sourced from <a href="https://github.com/facebookresearch/segment-anything">Facebook Research's segment-anything</a> (https://github.com/facebookresearch/segment-anything). The specific version used is included for compatibility.</li> <li><strong>Fig2</strong>: Code for predicting topological defects in tissue cell images, citing the following reference: T. B. Saw et al., Nature 544, 212 (2017).</li> <li><strong>Fig3c</strong>: Code for predicting topological defects in microtubules images, citing the following reference: M. Golden et al., Sci. Adv. 9, eabq6120 (2023).</li> </ul> <p><strong>Initialization Steps</strong></p> <p>Before executing any code, please ensure the following:</p> <ul> <li>All files in the <strong>Trained Models</strong> directory must be available.</li> <li>Download the checkpoint <strong>sam_vit_l_0b3195.pth</strong> from <a href="https://github.com/facebookresearch/segment-anything">Facebook Research's segment-anything</a>. (https://github.com/facebookresearch/segment-anything)</li> </ul> <p><strong>Acknowledgments</strong></p> <ul> <li><a href="https://github.com/RangiLyu/nanodet">RangiLyu/nanodet</a> (https://github.com/RangiLyu/nanodet)</li> <li><a href="https://github.com/facebookresearch/segment-anything">Facebook Research's segment-anything</a> (https://github.com/facebookresearch/segment-anything)</li> </ul> <p>For further inquiries or issue reporting, you may contact us via email.</p> <p><strong>Contact Information</strong>: <a href="mailto:hrenae@connect.ust.hk">hrenae@connect.ust.hk</a></p>
Spatial Modeling of Groundwater Potential in the North of Minas Gerais, Brazil: An Integrated Approach Using Machine Learning and Environmental Data
<p>This database is associated with the article published in the Revista Brasileira de Cartografia (RBC), entitled: Spatial Modeling of Groundwater Potential in the North of Minas Gerais, Brazil: An Integrated Approach Using Machine Learning and Environmental Data. This database contains the Groundwater flow rasters and the covariates used in spatial modeling. This database is associated with the article published in the Revista Brasileira de Cartografia (RBC), entitled: Spatial Modeling of Groundwater Potential in the North of Minas Gerais, Brazil: An Integrated Approach Using Machine Learning and Environmental Data. This database contains the Groundwater flow rasters and the covariates used in spatial modeling.</p>
Dataset for "Enabling Machine Learning Models in Alarm Fatigue Research: Creation of a Large Relevance-annotated Oxygen Saturation Alarm Data Set"
<p>Chromik and Flint et al. (2024) (under review) propose an algorithm that uses clinical alarm logs, an annotation guideline (Klopfenstein et al. 2023), and routinely collected intensive care data to create a data set of relevance-annotated oxygen saturation alarms. We provide the algorithm's source code and data set of annotated oxygen saturation alarms as supplementary material to the publication.</p> <ul> <li>The algorithm's implementation is open-source and can be re-used on similar data sets.</li> <li>Our implementation used airway management data mappings to identify airway devices (AD), ventilation devices (VD), and ventilation modes (VM). These mappings can be found here: <a href="../doi/10.5281/zenodo.7511031">https://zenodo.org/doi/10.5281/zenodo.7511031</a></li> <li>The data set suggests that the majority of oxygen saturation alarms in the intensive care unit is non-actionable.</li> <li>We are the first to provide such an extensive data set of annotated oxygen saturation alarms.</li> </ul>
Machine learning-based q-RASAR approach for the in silico identification of novel multi-target inhibitors against Alzheimer's disease
<p>In the present research, we propose a novel approach, termed the Machine Learning (ML)-Based q-RASAR (quantitative read-across structure-activity relationship) method, for the identification of potential multi-target inhibitors against AD. The q-RASAR effectively combines the principles of both read-across and 2D QSAR approaches. As a result, it is imperative to take into account similarity-related aspects in the process of developing q-RASAR models. In this investigation, we have implemented ML-based q-RASAR modeling against seven major targets (AChE, BuChE, BACE1, 5-HT6, CDK-5 enzymes, Amyloid precursor protein, and Tau aggregation) of AD using the initially selected features in 2D QSAR models for the identifications of novel multitarget inhibitors. The models were individually used to check the applicability domain of a pool of 407270 natural products (NPs) obtained from the COCONUT database (<a href="https://coconut.naturalproducts.net/download">https://coconut.naturalproducts.net/download</a>) and provided prioritized compounds for experimental detection of their performance as anti-Alzheimer's drugs. Furthermore, we have also developed the q-RASAAR (quantitative read-across structure-activity-activity relationship) and selectivity-based q-RASAR models to explore the most important features contributing to the dual inhibition against the respective targets. Furthermore, we have applied seven distinct machine learning algorithms to enhance the predictive abilities of q-RASAR and q-RASAAR models. Moreover, we have also developed the univariate q-RASAR model, with the RA function as the primary independent variable. Moreover, molecular docking experiments have been conducted to gain insights into the atomic-level molecular interactions between ligands and enzymes. These observations are then juxtaposed with the structural characteristics obtained from models that elucidate the mechanistic aspects of binding events. These proposed models may serve as valuable tools for pinpointing crucial molecular attributes when designing potential drugs for Alzheimer's therapy through the rational design of multi-target inhibitors.</p>
Calibration of a pedestrian ingress model based on CCTV surveillance data using machine learning methods: data and code
<p>The package includes a dataset of trajectories obtained from a real-time pedestrian traffic detector at the vaccination centre and the code needed to validate the analyses described in the paper entitled Calibration of a pedestrian ingress model based on CCTV surveillance data using machine learning methods. Version 1.0.1 is a patch that corrects path to data.</p>
Machine learning suggests small size is a key determinant of plasmid host range
<p>Plasmids mediate gene exchange across taxonomic barriers through conjugation, shaping bacterial evolution for billions of years. While plasmid mobility can be harnessed for genetic engineering and drug-delivery applications, rapid plasmid-mediated spread of resistance genes has rendered most clinical antibiotics useless, posing an existential threat to human society. To solve this urgent problem, we must understand how plasmids spread across bacterial communities. Here, we applied machine-learning models to identify features that determine plasmid host range. We assembled an up-to-date dataset of more than thirty thousand bacterial plasmids, separated them into 1125 clusters, and assigned a distribution possibility score, which takes host distribution of each taxonomic rank and the sampling bias of the existing sequencing data into account, for each cluster. Using this score and an optimized plasmid feature pool, we built a model stack consisting of DecisionTreeRegressor, EvoTreeRegressor, and LGBMRegressor as base models and LinearRegressor as a meta-learner. Our analysis reveals that a short sequence length is most important for successful plasmid spread, followed by P-loop NTPases, mobility factors, and <span>β</span>-lactamases. Ours and other recent results suggest that small plasmids broaden their range by evading host defenses and using alternative modes of transfer instead of autonomous conjugation.</p>
Construction of a Predictive Model of Gangrenous Cholecystitis Based on Machine Learning
ClinicalTrials.gov study NCT06399081. IPD Sharing: NO. Countries: 1. Publications: 3.
Developing and Evaluating a Machine-Learning Opioid Overdose Prediction & Risk-Stratification Tool in Primary Care
ClinicalTrials.gov study NCT06810076. IPD Sharing: NO. Countries: 1. Publications: 5.
Machine Learning to Predict Postoperative Pneumonia in Brain Tumor Patients
ClinicalTrials.gov study NCT07321262. IPD Sharing: UNDECIDED. Countries: 1. Publications: 15.
Machine Learning Assisted Differentiation of Low Acuity Patients at Dispatch
ClinicalTrials.gov study NCT04757194. IPD Sharing: YES. Countries: 1. Publications: 2.
Volatilome and Single-Lead Electrocardiogram Optimize Ischemic Heart Disease Diagnosis Using Machine Learning Models
ClinicalTrials.gov study NCT06181799. IPD Sharing: NO. Countries: 1. Publications: 8.
Clinical Performance Evaluation of the Artificial Intelligence (AI)/ Machine Learning (ML) Technologies Utilized by the Origin Medical EXAM ASSISTANT
ClinicalTrials.gov study NCT06952439. IPD Sharing: NO. Countries: 1. Publications: 15.
The Prediction of Recurrence Lumbar Disc Herniation At L5-S1 Level Through Machine Learning Models Based on Endoscopic Discectomy Via the Interlaminar Approach
ClinicalTrials.gov study NCT06833099. IPD Sharing: NO. Countries: 1. Publications: 20.
Diagnostic Accuracy of a Novel Machine Learning Algorithm to Estimate Gestational Age
ClinicalTrials.gov study NCT05433519. IPD Sharing: YES. Countries: 2. Publications: 1.
Appropriate Use of Blood Cultures in the Emergency Department Through Machine Learning
ClinicalTrials.gov study NCT06163781. IPD Sharing: YES. Countries: 1. Publications: 3.
Predicting amphibian intraspecific diversity with machine learning: Challenges and prospects for integrating traits, geography, and genetic data
Open the record for dataset details and reuse information.
Data from: Decipher soil organic carbon dynamics and driving forces across China using machine learning
Open the record for dataset details and reuse information.
Stable and accurate orbital-free density functional theory powered by machine learning
Open the record for dataset details and reuse information.
Data from: Machine learning identification of microhabitat features associated with occupancy of artificial nestboxes by hazel dormice (Muscardinus avellanarius) in a UK woodland site
Open the record for dataset details and reuse information.
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.