Find research datasets worth reusing

opencc-by-4.0Feb 2023View details →

In silico Antibody-Peptide Epitope prediction for Personalized cancer therapy publication data

In silico Antibody-Peptide Epitope prediction for Personalized cancer therapy publication data

opencc-by-4.0Feb 2023View details →

Predicted and reported column densities for the data set used in the characterization of the Orion Kleinmann-Low nebula

This dataset contains 172 molecular entries in the chemical inventory of the Orion Kleinmann-Low (Orion KL) used in as the data set used in the work that is currently under review: Scolati et al., "Explaining the Chemical Inventory of Orion KL through Machine Learning", (2023). The dataset was compiled using Herschel spectral line survey as well as ground observations using the IRAM 30 m telescope. The resulting list of molecules were used in the XCLASS fitting program described in <a href="https://iopscience.iop.org/article/10.1088/0004-637X/787/2/112">Crockett et al. (2014)</a>. The full dataset contains 64 unique molecules, including 18 isotoplogues, 9 deuterated, 8 vibrationally excited, and 9 molecules with multiple velocity components. The dataset is structured to provide each molecular entry with their corresponding SMILES string based representation, the beam size, rotational temperature, radial velocity, line width, as well as numerical codes to indicate physical environment within the source (i.e. hot core, compact ridge, etc.), and if the species is vibrationally excited or an isotopologue. The derived column densities reported in <a href="https://iopscience.iop.org/article/10.1088/0004-637X/787/2/112">Crockett et al. (2014) </a>are provided along with our machine learning model predictions (using the Gradient Boosting Regressor). Finally, a training vs testing tag was added to indicate which entries were split into the training and testing sets.

opencc-by-4.0Oct 2022View details →

Data and Code from "Structure-based prediction of Ras-effector binding affinities and design of 'branchegetic' interface mutations"

Data, data generation and data analysis for manuscript "Structure-based prediction of Ras-effector binding affinities and design of ‘branchegetic’ interface mutations", currently available as a preprint <a href="https://doi.org/10.1101/2022.09.04.506480">here</a>. Contains the following directories: <ul> <li>01_models: Contains all scripts for model generation and selection, as well as some of the generated and selected models. <ul> <li>01_inputs: The different inputs for the homology modelling pipeline. This includes AlphaFold single and complex templates, PDB templates and sequence alignments.</li> <li>02_validation: Model generation and initial selection for validation models, based on AF2 single models and PDB complex models.</li> <li>03_production1: Model generation and initial selection for Ras effector complexes, based on AF2 single models and PDB complex models.</li> <li>04_production2: Model generation and initial selection for Ras effector complexes, based on AF2 single models and AF2 complex models.</li> <li>05_selection_optics: Code and analysis for selection by unsupervised learning using OPTICS.</li> </ul> </li> <li>02_selected_models: The three representative models selected for each complex.</li> <li>03_affinity_prediction: Contains code and data for the prediction of binding affinities for Ras effector complexes.</li> <li>04_branch_pruning: Contains code and data for branch pruning analysis.</li> <li>05_systems_analysis: Contains code and data for the analysis of Ras effector systems based on affinities derived from affinity prediction and branch pruning analysis.</li> <li>06_visualization: Information on where in the raw data the panels for the figures in the manuscript can be found.</li> </ul>

opencc-by-4.0Dec 2022View details →

Data from: Thermal failure of diamond tools indicated by diamond degradation: Damage evaluation and property prediction on small image datasets

High temperature induced diamond degradation often leads to the failure of diamond tools. In this work, diamond samples holding different degrees of thermal damage were prepared by heating and sintering. The influence of diamond particle size and processing temperature was investigated through mechanical testing and micromorphology observation, meanwhile, a dataset containing 2870 SEM images showing diamonds with different degrees of degradation was constructed. By modification of VGG16 network, classification models and regression models were developed for thermal damage evaluation and sample property prediction. Training strategies including transfer learning and data augmentation were implemented and verified essential on the small dataset, where drop-out showed no positive effects. Two classification models (3-class and 65-class) were constructed and trained for damage evaluation. Visualized damage feature maps exported from Grad-CAM revealed the influential mechanism of thermal damage on diamonds, which proved the effectiveness of the classification models as well. Under the optimized training strategies, regression models were built for sample property prediction. The models towards toughness index, bending strength loss, relative density and Rockwell hardness were examined. Comparing the output results with real property values in test sets, the first two models matched well, and the latter two showed the opposite. It verified the validity of the regression models for property prediction as they were all established based on diamond damage image datasets. The loss in bending strength loss prediction model was smaller than that of toughness index, indicating bending strength easier to be shorten than impact toughness for diamond/metal composites suffering thermal impacts.

Streamflow Predictions using Machine Learning with Data Reformation

Streamflow Predictions using Machine Learning with Data Reformation

Multivariate prediction on wake-affected wind turbines using graph neural networks (Eurodyn) database

Database consisting of graphs generated using randomized layouts and PyWake simulations used in 'Multivariate prediction on wake-affected wind turbines using graph neural networks', contribution to Eurodyn 2023.

Plasmer: prediction results from other tools

Plasmer: prediction results from other tools

A Comparative Evaluation of Different Scores in Predicting Severity and Outcome in Acute Pancreatitis

This dataset is regarding my study which I conducted on 110 subjects.

Model weights and predictions for reproducible benchmarking experiments in MedMNIST v2

This data repository is associated with our <a href="https://github.com/MedMNIST/experiments">GitHub code</a> <ol> <li><code>weights_*.zip</code>: <ul> <li>PyTorch, AutoKeras and Google AutoML Vision are provided for MedMNIST2D.</li> <li>PyTorch and AutoKeras are provided for MedMNIST3D.</li> <li>If you are using PyTorch model weights, please note that the ResNet18_224 / ResNet50_224 models are trained with images resized to 224 x 224 by <code>PIL.Image.NEAREST</code>.</li> <li>Snapshots for <code>auto-sklearn</code> are not uploaded due to the embarrassingly large model sizes (lots of model ensemble).</li> </ul> </li> <li><code>predictions.zip</code>: We also provide all standard prediction files by PyTorch, auto-sklearn, AutoKeras and Google AutoML Vision, which works with <code>medmnist.Evaluator</code>. Each file is named as <code>{flag}_{split}_[AUC]{auc:.3f}_[ACC]{acc:.3f}@{run}.csv</code>, e.g., <code>bloodmnist_test_[AUC]0.997_[ACC]0.957@autokeras_3.csv</code>.</li> </ol>

Simulated metagenomic datasets used for determining the threshold score cutoff for taxa prediction using StrainIQ software

StrainIQ (Strain Identification and Quantification) is a novel tool that implements a new n-gram based algorithm for predicting and quantifying strain-level taxa from whole genome metagenomic sequencing data. To avoid the false positive prediction of by StrainIQ algorithm, we determined cutoff score for each site specific n-gram model called DSEM (DNA Signature Element Model) using positive and negative metagenomic datasets. The Figure2-datasets.zip has positive (from GI tract genomes) and negative (from non-GI tract genomes) simulated metagenomic datasets that were used for determining optimal cut-off based on GI tract DSEM. Please find the new link for this data at https://zenodo.org/record/8132164

Different forms of Scientific Literacy Predict Vaccine Hesitancy and COVID-19 Risk Perception

This is a data set that accompanies a manuscript that is yet to be published. The data set includes demographic information for 461 participants, and their responses to four surveys: one on scientific methodology, one on scientific facts, one on vaccine hesitiancy, and one on risk estimates related to COVID-19.

Vaginal microbial communities and combination efforts predict preterm birth in Chinese women

Elucidating the physiological and pathological characteristics of preterm birth is critical to the development of effective prediction and intervention strategies. Here, we present a nested case control study on 51 spontaneous preterm birth (sPTB) and 70 women who delivered at term. Systems-level analysis revealed bacterial compositions and functional differences between two distinct pregnancy outcomes. As expected, the vaginal environment with preterm birth was dominated by a more complex bacteria interaction network, and these interactions frequently exhibited opposite effects on different pregnancy outcomes. Furthermore, key species and combinations were identified to construct preterm birth prediction model. The final model contained three features generated from six bacteria (A. christensenii and L. crispatus; B. breve and S. anginosus; P. timonensis and L. fermentum) (AUROC = 0.942 for independent test). The AUROC value was 0.965 when white blood cell (WBC) and neutrophil (NEU) data were included. Collectively, our study provided a comprehensive characterization of the vaginal microbiome and revealed the potential utilization of bacteria in predicting the risk of preterm birth.

FIG. 4 in Bat activity rates do not predict bat fatality rates at wind energy facilities

FIG. 4. Bat activity rates measured before and after turbines were built at four wind energy facilities for high- and low-frequency bats during individual seasons. The dashed line indicates a 1:1 relationship between pre- and post-construction activity rates

FIG. 3 in Bat activity rates do not predict bat fatality rates at wind energy facilities

FIG. 3. Regression analysis for high-frequency bat activity rates (Panel A, n = 23) and low-frequency bat activity rates (Panel B, n = 24) recorded by raised microphones versus overall bat fatality rates at paired pre-construction and post-construction studies, grouped by U.S. Fish and Wildlife Service region

FIG. 2 in Bat activity rates do not predict bat fatality rates at wind energy facilities

FIG. 2. Regression analysis for overall bat activity rates recorded by ground microphones (n = 47) versus overall bat fatality rates at paired pre-construction and post-construction studies, grouped by U.S. Fish and Wildlife Service region

FIG. 1 in Bat activity rates do not predict bat fatality rates at wind energy facilities

FIG. 1. The number of paired pre-construction bat activity and post-construction bat fatality studies (first number) and paired post-construction bat activity and post-construction bat fatality studies (second number) used for regression analyses, organized by U.S. Fish and Wildlife Service region. The Mountain-Prairie region includes five studies from southern Alberta, Canada

Assesing gender differences for non-predictable Breakthrough Cancer Pain Phenomenon: a secondary analysis from IOPS-MS Study

IOPS-MS was a big multicentric study with the aim of characterizing BTcP in a large number of patients belonging to different settings and assessing possible factors influencing its development. Moreover, NP-BTcP topic was addressed elsewhere [https://doi.org/10.3390/cancers13164018]. One key difference is related to the hormonal (gender related characteristics) differences between men and women. For example, estrogen and progesterone can affect pain sensitivity, with some studies suggesting that women may be more sensitive to pain during certain stages of the menstrual cycle. Similarly, testosterone may have analgesic effects in men, which could contribute to differences in pain sensitivity between genders.

Characterizing Non-predictable Breakthrough Cancer Pain in frmale cancer patients: a secondary analysis from IOPS-MS study

IOPS-MS was a big multicentric study with the aim of characterizing BTcP in a large number of patients belonging to different settings and assessing possible factors influencing its development. Moreover, NP-BTcP topic was addressed elsewhere [https://doi.org/10.3390/cancers13164018]. The principal aim of this work is to characterize breast cancer (BC) patients compared with no-female-specific cancers (no-FSC). The importance of such focus lies on detecting main behavior of a hormone-dependent cancer type with respect to tumors which are not specific for women.

Prediction error, prior certainty, or belief updating: P3a component function in temporal Bayesian inference

Data for "Prediction error, prior certainty, or belief updating: P3a component function in temporal Bayesian inference"