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.
261
datasets available to search
ShareScore release 0.9.0
Dataset results
261 results for “protein prediction”
Protein Subcellular localization prediction data used in the article entitled "MSclassifier: Median-Supplement model-based Classification tool for automated knowledge discovery"
<p>This repository contains data used to obtain results from a 5-fold cross-validation testing of how MSclassifier and other packages accurately predict protein subcellular localization in the software article entitled "MSclassifier: median-supplement model-based classification tool for automated knowledge discovery." The data used in the software article is derived from data generated in "G. K. Acquaah-Mensah, S. M. Leach, and C. Guda, Predicting the subcellular localization of human proteins using machine learning and exploratory data analysis, Genomics Proteomics Bioinformatics, 4(2):120-133, 2006, <a href="https://doi.org/10.1016/S1672-0229(06)60023-5">https://doi.org/10.1016/S1672-0229(06)60023-5</a>"</p>
Predicted Secreted Proteins for the Citrus Stem-End Rot Fungal Pathogen Lasiodiplodia theobromae CITRA15
<p>Lasiodiplodia theobromae (L. theobromae) belongs to a diverse genus of fungal pathogens associated with perennial tropical fruit plants worldwide. In citrus, L. theobromae causes stem-end rot (SER), a damaging postharvest disease that is aggravated when trees are also infected with the citrus greening bacterium, a Candidatus Liberibacter asiaticus. Due to the latent infection of L. theobromae during the preharvest stage, it is also difficult to control by chemical and physical treatment. We sequenced and assembled the first genome of isolate CITRA15 of L. theobromae obtained from citrus, providing a resource for future research on postharvest and preharvest disease management of citrus and other fruit crops and diagnostics. Here we want to share a set of i) 10,496 predicted coding gene sequences (cds) and ii) 10,496 predicted proteins and ii) 1,016 predicted secreted proteins using SignalP v2.0 and TMHMM v2.0.</p> <p> </p>
Accurate and Cost-Effective NMR Chemical Shift Predictions for Proteins using Molecules-in-Molecules Fragmentation-Based Method
<p>Files and coordinates associated with the paper titled 'Accurate and Cost-Effective NMR Chemical Shift Predictions for Proteins using Molecules-in-Molecules Fragmentation Based Method. '</p>
Data from: Contemporary evolution of sea urchin gamete-recognition proteins: experimental evidence of density-dependent gamete performance predicts shifts in allele frequencies over time
Species whose reproductive strategies evolved at one density regime might be poorly adapted to other regimes. Field and laboratory experiments on the sea urchin Strongylocentrotus franciscanus examined the influences of the two most common sperm bindin alleles, which differ at two amino acid sites, on fertilization success. In the field experiment, the Arginine/Glycine (RG) genotype performed best at low densities and the Glycine/Arginine (GR) genotype at high densities. In the lab experiment, the RG genotype had a higher affinity with available eggs, whereas the GR genotype was less likely to induce polyspermy. These sea urchins can reach 200 years of age. The RG allele dominates in old sea urchins, whereas younger sea urchins have near equal RG and GR allele frequencies. A latitudinal cline in RG and GR genotypes is consistent with longer survival of sea urchins in the north and with predominance of RG genotypes in older individuals. The oldest sea urchins were likely conceived at low densities, before sea-urchin predators, like sea otters, were overharvested and sea urchin densities exploded off the west coast. Contemporary evolution of gamete-recognition proteins might allow species to adapt to shifts in abundances and reduces the risk of reproductive failure in altered populations.
Data from: Antibody responses to Plasmodium vivax Duffy binding and erythrocyte binding proteins predict risk of infection and are associated with protection from clinical malaria
Background. The Plasmodium vivax Duffy Binding Protein (PvDBP) is a key target of naturally acquired immunity. However, the functional receptor-binding region II of PvDBP (PvDBPII) is highly polymorphic. The natural acquisition of antibodies to different variants of PvDBPII, including AH, O, P and Sal1 alleles, the central region III-V, and P. vivax Erythrocyte Binding Protein region II (PvEBPII) and their associations with risk of clinical P. vivax malaria are not well understood. Methodology. Total IgG and IgG subclasses 1, 2, and 3 that recognize four alleles of PvDBPII (AH, O, P, and Sal1), PvDBPIII-V and region II of PvEBP (PvEBPII) were measured in samples collected from a cohort of Papua New Guinean (PNG) children of aged 1-3 years living in a highly endemic area of PNG. The levels of binding inhibitory antibodies (BIAbs) to PvDBPII (AH, O, and Sal1) were also tested in a subset of children. The association of presence of IgG with age, cumulative exposure (measured as the product of age and malaria infections during follow-up, i.e. molFOB) and prospective risk of clinical malaria were evaluated. Results. Increase in antigen-specific total IgG, IgG1, and IgG3 with age and cumulative exposure was only observed for PvDBPII AH and PvEBPII. High total IgG responders and IgG3 specific responses to the predominant PvDBPII AH allele, were associated with decreased incidence of clinical P. vivax episodes (aIRR=0.56-0.68, P=<0.001-0.021 ). High total IgG and IgG1 to PvEBPII correlated more strongly with protection against clinical vivax malaria compared with those of all PvDBPII variants (aIRR=0.38, P<0.001). Antibodies to PvDBPII AH and PvEBPII showed evidence of an additive effect, with a joint protective association of 70%. The six children with high levels of Binding Inhibitory Antibodies (BIAbs) to PvDBPII and high strain-transcending blocking ability (i.e. >80%) tended to have less clinical diseases (IRR=0.45, P=0.083). Conclusion. Antibodies to the key parasite invasion ligands PvDBPII and PvEBPII are good correlates of protection against P. vivax malaria in PNG. This further strengthens the rationale for inclusion of PvDBPII in a recombinant subunit vaccine for P. vivax malaria and highlights the need for further functional studies to determine the potential of PvEBPII as a component of a subunit vaccine for P. vivax malaria.
GAABind: A Geometry-Aware Attention-Based Network for Accurate Protein-Ligand Binding Pose and Binding Affinity Prediction
<p>The preprocessed dataset for paper "GAABind: A Geometry-Aware Attention-Based Network for Accurate Protein-Ligand Binding Pose and Binding Affinity Prediction" with associated code at https://github.com/Mercuryhs/GAABind.</p><p>The dataset files are saved as .pkl file for the convenience of use.</p><p><strong>Paper Abstract</strong>:</p><p>Protein-ligand interactions are increasingly profiled at high-throughput, playing a vital role in lead compound discovery and drug optimization. Accurate prediction of binding pose and binding affinity constitutes a pivotal challenge in advancing our computational understanding of protein-ligand interactions. However, inherent limitations still exist, including high computational cost for conformational search sampling in traditional molecular docking tools, and the unsatisfactory molecular representation learning and intermolecular interaction modeling in deep learning-based methods. Here we propose a geometry-aware attention-based deep learning model, GAABind, which effectively predicts the pocket- ligand binding pose and binding affinity within a multi-task learning framework. Specifically, GAABind comprehensively captures the geometric and topological properties of both binding pockets and ligands, and employs expressive molecular representation learning to model intramolecular interactions. Moreover, GAABind proficiently learns the intermolecular many-body interactions and simulates the dynamic conformational adaptations of the ligand during its interaction with the protein through meticulously designed networks. We trained GAABind on the PDBbindv2020 and evaluated it on the CASF2016 dataset, the results indicate that GAABind achieves state-of-the-art performance in binding pose prediction and shows comparable binding affinity prediction performance. Notably, GAABind achieves a success rate of 82.8% in binding pose prediction, and the Pearson correlation between predicted and experimental binding affinities reaches up to 0.803. Additionally, we assessed GAABind's performance on the SARS-CoV-2 main protease cross-docking dataset. In this evaluation, GAABind demonstrates a notable success rate of 76.5% in binding pose prediction and achieves the highest Pearson correlation coefficient in binding affinity prediction compared with all baseline methods.</p>
Sequence/simulation data for Direct Prediction of Intrinsically Disordered Protein Conformational Properties From Sequence
<p>This is a DOI-linked deposition of sequence/biophysical properties pairs used in the associated paper by Lotthammer et al:</p><p>Lotthammer, J. M.<strong>*</strong>, Ginell, G. M.<strong>*</strong>, Griffith, D.<strong>*</strong>, Emenecker, R. J. & Holehouse, A. S. <br>Direct Prediction of Intrinsically Disordered Protein Conformational Properties From Sequence.<br><i><strong>Nature Methods</strong></i> (<i>in press</i>), (2023).</p><p> </p>
DynamicBind: Predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model.
<p>test and training data.</p>
Benchmark dataset for protein function prediction that integrates various protein information
<p>This research was funded by the National Science Centre in Poland (grant number 2021/41/N/ST6/01919)</p>
Datasets associated with the manuscript Protein Condensate Atlas from predictive models of heteromolecular condensate composition
<p>Datasets associated with the manuscript "Protein Condensate Atlas from predictive models of heteromolecular condensate composition".</p>
Source data for manuscript(De novo protein design with a denoising diffusion network independent of pre-trained structure prediction models)
<p>This respository contains the source data for figure and supplementary figure in manuscript(SCUBA-D).</p>
Source data for manuscript(De novo protein design with a denoising diffusion network independent of pre-trained structure prediction models)
<p>This respository contains the source data for figure and supplementary figure in manuscript(SCUBA-D).</p>
Data for DualNetGO: A Dual Network Model for Protein Function Prediction via Effective Feature Selection
<p>Data used in the paper, including annotation files, graph embeddings from TransformerAE, and protein attributes for both human and mouse, and for cafa3 data. Extract and place them in the <em>data </em>folder.</p>
predicted_protein_complex_structures_datasets
Open the record for dataset details and reuse information.
Supplementary materials used for the research to predict phase separation in protein chains
<p>This is a collection of all the data, codes and metadata that were used for the research titled: 'Sequence based prediction of protein phase separation into disordered condensates using machine learning'.</p>
The 'dark matter' of protein variants carries a distinct DNA signature and predicts damaging variant effects
<p>Data generated for the manuscript "The 'dark matter' of protein variants carries a distinct DNA signature and predicts damaging variant effects".</p> <p> </p> <p>Please consult the README file for detailed description of data files included in this dataset.</p>
A strategy to validate protein function predictions in vitro - accompanying data
<p>This repository contains the ProteinCartography analyses that accompany the pub "<a href="https://doi.org/10.57844/arcadia-cae9-96c4">A strategy to validate protein function predictions <em>in vitro</em></a><a href="https://doi.org/10.57844/arcadia-cae9-96c4">."</a> These proteins were selected from a list of the 200 most studied human proteins in the Protein Data Bank (PDB) which was published in <a href="https://onlinelibrary.wiley.com/doi/10.1002/pro.4038">Liu and Buck, 2021</a>. </p> <p>Each analysis was done using <a href="https://github.com/Arcadia-Science/ProteinCartography/releases/tag/v0.5.0">v0.5.0</a> of ProteinCartography using the standard configuration parameters. Each analysis is in its own zipped file corresponding to the protein name. The zipped files contain inputs, configuration files, all the structures, and all ProteinCartography results. Additionally, for a handful of the proteins, we ran a scaled-up version of ProteinCartography asking for 10,000 hit proteins instead of the standard. These are also included with the file prefix "Scaled-up_". </p> <p>Finally, we've decided to move forward with 2 protein families for validation of our tool, ProteinCartography. These protein families are <a href="https://doi.org/10.57844/arcadia-1e5d-e272">deoxycytidine kinase</a> and <a href="https://doi.org/10.57844/arcadia-74ad-345f">Ras GTPase</a>. For more about these two protein families, visit the mentioned pubs! </p>
Spatio-temporal learning from molecular dynamics simulations for protein-ligand binding affinity prediction
<p>This Zenodo repository provides comprehensive resources for the paper titled "Spatio-temporal learning from molecular dynamics simulations for protein-ligand binding affinity prediction" published on <a href="https://academic.oup.com/bioinformatics/article/41/8/btaf429/8238154">Bioinformatics</a>. We created a dataset of 63,000 molecular dynamics simulations by performing 10 simulations of 10 ns on 6,300 complexes. Neural networks were developed to learn from this data in order to predict the binding affinities of protein-ligand complexes. The implementation of these neural networks are available on <a href="https://github.com/ICOA-SBC/MD_DL_BA" target="_blank" rel="noopener">github</a>. Our collection includes training/benchmark datasets, trained statistical models, and results on test sets (CSV & PDF files).</p> <p> </p> <p><strong>Training/benchmark datasets:</strong></p> <p>Training, validation and test sets are provided to train and evaluate the following neural networks:</p> <ul> <li>Pafnucy, Proli and Densenucy without MD data augmentation (dataset file names contain "initial")</li> <li>Pafnucy, Proli and Densenucy with MD data augmentation (dataset file names contain "MDDA")</li> <li>Pafnucy with/without MD data augmentation and Proli and Densenucy with MD data augmentation were also evaluated on the fep test set (test set file name contain "fep")</li> <li>Timenucy and Videonucy using spatiotemporal learning methods (dataset file names contain "4D")</li> <li>Pafnucy without MD data augmentation and on a reduced training set (dataset file names contain "reduced")</li> </ul> <p>For each training methodology (MD data augmentation and spatiotemporal learning), we provide the data for the whole complex, only the ligand or only the protein. Additionally for spatiotemporal learning, we provide the data with only the ligand using the tracking mode.</p> <p> </p> <p><strong>Statistical models:</strong></p> <p>We provide the models trained with Pafnucy, Proli, Densenucy, Timenucy and Videonucy. Each models were trained in 10 replicates. </p> <p>For Pafnucy, Proli, Densenucy, we provide the models trained with random and systematic rotations, as well as with or without MD data augmentation.</p> <p>For Proli, Densenucy, Timenucy and Videonucy, we provide the models trained on the whole complex, only the ligand or only the protein.</p> <p>For Pafnucy we also provide the models trained on the reduced set (5932 complexes).</p> <p> </p> <p><strong>Results on test sets (CSV & PDF files):</strong></p> <p>We provide the predictions on the PDBbind v.2016 core set.</p> <ul> <li>For spatiotemporal learning methods (Timenucy and Videonucy), there are predictions for only 83 complexes, as we did not perform simulations on the whole test set.</li> <li>For models trained with MD DA, predictions were carried on the crystallographic structures as well as on the frames extracted from the simulations performed on the test set (augmented test).</li> </ul> <p>Results on the FEP dataset are also provided for Pafnucy, Proli and Densenucy.</p> <p> </p> <p>The Raw MD data (~4.5 To) are stored, and can be visualized/downloaded, on the <a href="https://mdposit.mddbr.eu/#/browse?search=MDBind">MDDB</a>.</p> <p>This work was performed using HPC resources from GENCI-IDRIS (Grant 2021-A0100712496 & 2022-AD011013521) and CRIANN (Grant 2021002).</p>
AlphaFold2 predicted structures of ThsA and ThsB proteins
<p>This Zenodo record contains the AlphaFold2 models described in the manuscript: Structural characterization of macro domain-containing Thoeris antiphage defense systems</p>
Fueling ab initio folding with oceanic metagenomics enables structure and function predictions of new protein families
<p>Code and protein sequence database to construct multiple sequence alignment from Tara Ocean data.</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.