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”
Genetic architecture and polygenic risk score prediction of degenerative suspensory ligament desmitis (DSLD) in the Peruvian Horse
<p class="MsoNormal"><strong>Introduction</strong>: Spontaneous rupture of tendons and ligaments is common in several species including humans. In horses, degenerative suspensory ligament desmitis (DSLD) is an important acquired idiopathic disease of a major energy-storing tendon-like structure. DSLD risk is increased in several breeds, including the Peruvian Horse. Affected horses have often been used for breeding before the disease is apparent. Breed predisposition suggests a substantial genetic contribution, but heritability and genetic architecture of DSLD have not been determined.</p> <p class="MsoNormal"><strong>Methods</strong>: To identify genomic regions associated with DSLD, we recruited a reference population of 183 Peruvian Horses, phenotyped as DSLD cases or controls, and undertook a genome-wide association study (GWAS), a regional window variance analysis using local genomic partitioning, a signatures of selection (SOS) analysis, and polygenic risk score (PRS) prediction of DSLD risk. We also estimated trait heritability from pedigrees.</p> <p class="MsoNormal"><strong>Results</strong>: Heritability was estimated in a population of 1,927 Peruvian horses at 0.22±0.08. After establishing a permutation-based threshold for genome-wide significance, 151 DSLD risk single nucleotide polymorphisms (SNPs) were identified by GWAS. Multiple regions of enriched local heritability were identified across the genome, with strong enrichment signals on chromosomes 1, 2, 6, 10, 13, 16, 18, 22, and the X chromosome. With SOS analysis, there were 66 genes with a selection signature in DSLD cases that was not present in the control group that included the <em>TGFB3</em> gene. Pathways enriched in DSLD cases included proteoglycan metabolism, extracellular matrix homeostasis, and signal transduction pathways that included the hedgehog signaling pathway. The best PRS predictive performance was obtained when we fitted 1% of top SNPs using a Bayesian Ridge Regression model which achieved the highest mean of R<sup>2</sup> on both the probit and logit liability scales, indicating a strong predictive performance.</p> <p><strong>Discussion</strong>: We conclude that within-breed GWAS of DSLD in the Peruvian Horse has further confirmed that moderate heritability and a polygenic architecture underlies the trait and identified multiple DSLD SNP associations in novel tendinopathy candidate genes influencing disease risk. Pathways enriched with DSLD risk variants include ones that influence glycosaminoglycan metabolism, extracellular matrix homeostasis, and signal transduction pathways.</p>
Deep model predictive control of gene expression in thousands of single cells
<p>Experimental data, training datasets, and trained models for our study on deep model predictive control of gene expression in bacteria. This data can be used to reproduce our results and figures.</p> <p>See our preprint here: <a href="https://www.biorxiv.org/content/10.1101/2022.10.28.514305">biorxiv.org/content/10.1101/2022.10.28.514305</a></p> <p>And our code repository here: <a href="https://gitlab.com/dunloplab/deepcellcontrol">gitlab.com/dunloplab/deepcellcontrol</a></p> <p><strong>Contents:</strong></p> <ul> <li><em>datasets.zip</em>: Formatted experimental data used to train and validate fluorescence forecasting models.</li> <li><em>experiments.zip:</em> Processed data for all control experiments.</li> <li><em>misc.zip</em>: Files necessary to reproduce some figures or to exactly reproduce some of our results.</li> <li><em>models.zip</em>: Trained neural network models and associated files.</li> </ul>
Mutation Effect Prediction of Proteins using RoseTTAFold
<p>Deep mutational scanning datasets used for 'Mutation Effect Prediction of Proteins using RoseTTAFold'. </p> <p>Target MSAs, RF predicted PDBs and experimental values (csvs) are provided. Results published and referenced in paper are also provided.</p>
Is my model fit for purpose? Validating a population model for predicting freshwater fish responses to flow management
<p>Models based on ecological processes ("process-explicit models") are often used to predict ecosystem responses to environmental changes or management scenarios. However, models are imperfect and need to be validated, ideally by testing their assumptions and outputs against independent empirical data sets. Examples of validation of process-explicit models are rare. Recently, stochastic population models have been developed to predict the likely responses (over 10-120 years) of a riverine fish (golden perch, Macquaria ambigua) to flow management in the Murray-Darling Basin (MDB) in eastern Australia, one of the world's most regulated river basins. Declines of golden perch (and other species) are a direct consequence of altered hydrology, and managers require information to predict how fish will respond to possible future hydrological conditions to guide the substantial investments in flow management. Here, we use two independent field data sets to validate our population model. We compared model predictions to observed trends to ask: (1) how do predicted population sizes and growth rates compare to observed data? (2) does the correlation between predicted and observed population sizes and growth rates vary among populations? (3) does the correlation between predicted and observed population sizes and growth rates vary across observed hydrological conditions? and (4) how do modelled and observed fish movement rates compare? We found reasonable correlations between fish population sizes and growth rates as predicted by the model and observed in independent data sets for several populations (Aim 1) but the strength of these correlations varied among populations (Aim 2) and hydrological conditions (Aim 3). Predicted and observed fish movement rates were strongly correlated (Aim 4). Population models are frequently used in conservation decision-making but are rarely validated. We demonstrate that: (1) validation can identify model strengths and weaknesses; (2) observed data sets often have inherent limitations that can preclude robust validations; (3) validation is likely be more common if appropriate observed data sets are available; and (4) validation should consider the purpose of modelling. Wider consideration of these messages would contribute to more critical examinations of models so they can be most appropriately used in conservation decision-making.</p>
Ensemble of optimised machine learning algorithms for predicting surface soil moisture content at global scale (v1.0)
<p>This study investigates the estimation of daily SSM using eight optimised ML algorithms and ten ensemble models (constructed via model bootstrap aggregating techniques and five-fold cross-validation). The algorithmic implementations were trained and tested using the international soil moisture network (ISMN) data collected from 1722 stations distributed across the World. </p>
Sarcopenia index predicts short-term prognosis of head and neck squamous cell carcinoma
<p>Dataset of "Sarcopenia index predicts short-term prognosis of head and neck squamous cell carcinoma"</p>
Data from: Phenotypic drought stress prediction of European beech (Fagus sylvatica) by genomic prediction and remote sensing
<p><span>Current climate change species response models usually do not include evolution. We integrated remote sensing with population genomics to improve phenotypic response prediction to drought stress in the key forest tree species European beech (<em>Fagus sylvatica</em> L.). We used whole-genome sequencing of pooled DNA from natural stands along an ecological gradient from humid-cold to warm-dry climate. We phenotyped stands for leaf area index (LAI) and moisture stress index (MSI) for the period 2016–2022. We predicted this data with matching meteorological data and a newly developed genomic population prediction score in a Generalised Linear Model. Model selection showed that the addition of genomic prediction decisively increased the explanatory power. We then predicted the response of beech to future climate change under evolutionary adaptation scenarios. A moderate climate change scenario would allow persistence of adapted beech forests, but not worst-case scenarios. Our approach can thus guide mitigation measures, such as allowing natural selection or proactive evolutionary management.</span></p>
Figure 18: Theoretical Prediction of Meropenem Resistance in Pseudomonas aeruginosa (2020-2030)
<p><strong>Figure 18: Theoretical Prediction of Meropenem Resistance in Pseudomonas aeruginosa (2020-2030) </strong></p>
Figure 8: Theoretical Prediction of Oxacillin Resistance in Staphylococcus Aureus 2020-2030
<p><strong>Figure 8: Theoretical Prediction of Oxacillin Resistance in Staphylococcus Aureus 2020-2030 </strong></p> <p> </p>
Figure 6: Theoretical Prediction of Ampicillin Resistance in Enterococcus faecium (2020-2030)
<p><strong>Figure 6: Theoretical Prediction of Ampicillin Resistance in Enterococcus faecium (2020-2030)</strong></p> <p> </p>
Accurate TCR-pMHC Interaction Prediction Using a BERT-based Transfer Learning Method
<p>The datasets used for the TABR-BERT. For the complete training and testing code of TABR-BERT, see <a href="https://github.com/Freshwind-Bioinformatics/TABR-BERT">Freshwind-Bioinformatics/TABR-BERT: TABR-BERT: an Accurate and Robust BERT-based Transfer Learning Model for TCR-pMHC Interaction Prediction (github.com)</a>.</p>
Test-time training for deep MS/MS spectrum prediction improves peptide identification
<p>In bottom-up proteomics, peptide-spectrum matching is critical for peptide and protein identification. Recently, deep learning models have been used to predict tandem mass spectra of peptides, with the similarity scores of predicted and experimental spectra being integrated into peptide-spectrum matching. These models follow the supervised learning paradigm, which trains a general model using paired peptides and spectra from standard datasets and uses the model for prediction on experimental data. However, this approach can lead to inaccurate predictions due to differences between the training data and the experimental data, such as sample types, enzyme specificity, and instrument calibration. To address this issue, we proposed a Test-Time Training paradigm that adapts the pre-trained model to experimental data-specific models, namely PepT3. PepT3 results in a 10-40\% increase in peptide identification, depending on the distinctness of training and experimental data. Intriguingly, PepT3 improves the identification of tumor-specific neo-epitopes when applied to a complex patient-derived immunopeptidomic sample, with two-thirds of these neo-epitopes predicted to bind to the patient's human leukocyte antigen isoforms</p>
Data and results for "Germline-encoded specificities and the predictability of the B cell response"
<p>Data and results for Vieira et al., <a href="https://www.biorxiv.org/content/10.1101/2022.09.16.508315v4">Germline-encoded specificities and the predictability of the B cell response</a></p> <p>Code for the analyses is available at <a href="https://github.com/cobeylab/v_gene_selection/">https://github.com/cobeylab/v_gene_selection/</a></p> <p> </p>
Predicting plant species climate preferences on the basis of mechanistic traits
<p>Improved estimation of climate niches is critical, given climate change. Plant adaptation to climate depends on their physiological traits and their distributions, yet traits are rarely used to inform the estimation of species climate niches, and the power of a trait-based approach has been controversial, given the many ecological factors and methodological issues that may result in decoupling of species' traits from their native climate. For 107 species across six ecosystems of California, we tested the hypothesis that mechanistic leaf and wood traits can robustly predict the mean of diverse species' climate distributions, when combining methodological improvements from previous studies, including standard trait measurements and sampling plants growing together at few sites. Further, we introduce an approach to quantify species' trait-climate mismatch. We demonstrate a strong power to predict species' mean climate from traits. As hypothesized, the prediction of species' mean climate is stronger (and mismatch lower) when traits are sampled for individuals closer to species' mean climates. Improved resolution of species' climate niches based on mechanistic traits can importantly inform conservation of vulnerable species under the threat of climatic shifts in upcoming decades.</p>
Predicting educators' curiosity towards VR technologies
<p>Dataset about the curiosity of learning more about VR technology usage in education..</p>
Data from: Maximum stem diameter predicts liana population demography
<p>Determining population demographic rates is fundamental to understanding differences in species life-history strategies and their capacity to coexist. Calculating demographic rates, however, is challenging and requires long-term, large-scale censuses. Body size may serve as a simple predictor of demographic rate; can it act as a proxy for demographic rate when those data are unavailable? We tested the hypothesis that maximum body size predicts species' demographic rate using repeated censuses of the 77 most common liana species on the Barro Colorado Island, Panama (BCI) 50-ha plot. We found that maximum stem diameter does predict species' population turnover and demography. We also found that lianas on BCI can grow to the enormous diameter of 635 mm, indicating that they can store large amounts of carbon and compete intensely with tropical canopy trees. This study is the first to show that maximum stem diameter can predict plant species' demographic rates and that lianas can attain extremely large diameters. Understanding liana demography is particularly timely because lianas are increasing rapidly in many tropical forests, yet their species-level population dynamics remain chronically understudied. Determining per-species maximum liana diameters in additional forests will enable systematic comparative analyses of liana demography and potential influence across forest types.</p>
Data files and taxonomic classifiers for Pseudomonas syringae classification and virulence factor prediction
<p>PSSC.tree : core-genome tree of 2,161 high quality <em>Pseudomonas syringae</em> genomes</p> <p>metadata.csv: A CSV file containing taxonomic data, type strain designations, phylogroups as assigned in this study, LIN clusters assigned for classification purposes, presence/absence of key virulence factors, and metadata found in each genome’s Biosample record for all genomes found in PSSC.tree</p> <p>CLASSIFIER_xxx: QIIME 2 classifier artifacts trained on amplicons generated from primer sets indicated in file name</p> <p>xxx_VFOC.JSON: HMMER results for T3SS and effectors and WHOP genes, structured with both genome and gene product accession numbers as primary key, depending on file</p> <p> </p> <p> </p>
PRESCOTT/ESCOTT/iGEMME mutational effect predictions of all single point mutations for about 3000 proteins
<p>PRESCOTT/ESCOTT/iGEMME mutational effect predictions of all single point mutations for about 3000 proteins</p> <p>This dataset contains four tgz files:</p> <p> </p>
Harnessing genotype-phenotype nonlinearity to accelerate biological prediction
<p><strong>Description:</strong></p> <p>We are sharing phenotypic data sets used in the pub <a href="http://doi.org/10.57844/arcadia-5953-995f">“Harnessing genotype-phenotype nonlinearity to accelerate biological prediction”</a>. Contained within are a set of publicly available empirical phenotype data sets, synthetic phenotypes we generated, and the output of an autoencoder model trained on them.</p> <p>Walkthroughs for all analyses using these data are available on <a href="http://doi.org/10.5281/zenodo.8371249">GitHub</a>.</p> <p><strong>Files: </strong></p> <ul> <li><strong>“ail_cleaned_phenos.RDS”:</strong> .RDS file of mouse phenotypes from Bogue et al. 2015</li> <li><strong>“all_autoencoder_phenotype_predictions.csv“:</strong> .csv file containing accuracy statistics for all phenotype-phenotype autoencoder models analyzed in the pub</li> <li><strong>“arapheno_cleaned_phenos.RDS“:</strong> .RDS file of Arabidopsis phenotypes from Exposito-Alonso et al. 2019</li> <li><strong>“autoencoder_phenos.zip“:</strong> directory of synthetic phenotype sets used to train the autoencoder models</li> <li><strong>“dgrp_cleaned_phenos.RDS”:</strong> .RDS file of DGRP fruit fly phenotypes compiled from multiple sources, originally reported in Mackay et al. 2012</li> <li><strong>“jax_cleaned_phenos.RDS”:</strong> .RDS file of mouse phenotypes from Gonzales et al. 2018</li> <li><strong>“nematode_cleaned_phenos.RDS”:</strong> .RDS file of nematode phenotypes from Snoek et al. 2019</li> <li><strong>“phen_pleio_int_01_0_1.pk”:</strong> pickle of all synthetic phenotypes analyzed in the pub</li> <li><strong>“yeast_cleaned_phenos.RDS”:</strong> .RDS file of yeast phenotypes from Bloom et al. 2019</li> </ul> <p>A full description of how the synthetic phenotypes and autoencoder predictions were generated is available in the associated <a href="http://doi.org/10.57844/arcadia-5953-995f">pub</a>.</p>
ESM-1v predictions for human uniprot IDs
<p>Pathogenicity predictions of single amino acid substitutions calculated using the ESM-1v language model.</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.