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.
19
datasets available to search
ShareScore release 0.9.0
Dataset results
19 results for “protein embeddings”
Embeddings from protein language models predict conservation and variant effects
<p>For this work, we used protein language model representations (embeddings) to predict sequence conservation without multiple sequence alignments (MSAs). Embeddings alone predicted residue conservation almost as accurately from single sequences as ConSeq using MSAs (two-state Matthew Correlation Coefficient – MCC - for ProtT5 embeddings of 0.596±0.006 vs. 0.608±0.006 for ConSeq).</p> <p><strong><em>ConSurf10k</em>- Dataset for the development of ProtT5cons:</strong> The method (ProtT5cons) predicting residue conservation used <em>ConSurf-DB </em>(Ben Chorin et al. 2020). This resource provided sequences and conservation for 89,673 proteins. For all, experimental high-resolution three-dimensional (3D) structures were available in the Protein Data Bank (PDB) (Berman et al. 2000). As standard-of-truth for the conservation prediction, we used the values from ConSurf-DB generated using HMMER (Mistry et al. 2013), CD-HIT (Fu et al. 2012), and MAFFT-LINSi (Katoh and Standley 2013) to align proteins in the PDB (Burley et al. 2019). For proteins from families with over 50 proteins in the resulting MSA, an evolutionary rate at each residue position is computed and used along with the MSA to reconstruct a phylogenetic tree. The ConSurf-DB conservation scores ranged from 1 (most variable) to 9 (most conserved). The PISCES server (Wang and Dunbrack 2003) was used to redundancy reduce the data set such that no pair of proteins had more than 25% pairwise sequence identity. We removed proteins with resolutions >2.5Å, those shorter than 40 residues, and those longer than 10,000 residues. The resulting data set (ConSurf10k) with 10,507 proteins (or domains) was randomly partitioned into training (9,392 sequences), cross-training/validation (555) and test (519) sets.</p> <p>Uploaded data:</p> <ul> <li>ConSuf10k_PDBid_seq_cons.fasta: fasta file with PDBid, sequence and conservation annotation</li> <li>consurf10k_test_ids.txt: txt file with id's of test set</li> <li>consurf10k_train_ids.txt: txt file with id's of train set</li> <li>consurf10k_val_ids.txt: txt file with id's of cross-validation set</li> </ul>
Protein language model embeddings and predictions for the fly proteome (FlyBase)
<p>Residue and sequence embeddings of the fly (drosophila melanogaster) proteome (FlyBase for organism drosophila melanogaster, downloaded on 2022.03.01) computed using bio_embeddings (bioembeddings.com) using the ProtT5 embedder at full precision (https://www.biorxiv.org/content/10.1101/2020.07.12.199554v3). To open the embeddings file, please see <a href="https://github.com/sacdallago/bio_embeddings/blob/develop/notebooks/open_embedding_file.ipynb">this notebook</a>. The embeddings will be indexed by numbers according to the mapping file (mapping_file.csv) in this dataset. All following results will share the same mapping (for instance, to access the variation prediction results, by accessing index "0", you will query results for the sequence "FBpp0304622").</p> <p>Additionally:</p> <p>- Sequence-level predictions of subcellular localization in 10 classes using LA (https://www.biorxiv.org/content/10.1101/2021.04.25.441334v1)</p> <p>- Residue-level three state secondary structure prediction (alpha, sheet or other) using models reported in the ProtTrans paper (https://www.biorxiv.org/content/10.1101/2020.07.12.199554v3)</p> <p>- Residue-level prediction of conservation (in 9 states) and of variation effect (from 0 [no-effect] to 1 [effect]) using VESPAl (https://doi.org/10.1007/s00439-021-02411-y)</p> <p> </p> <p>Files included:</p> <p>- dmel-all-translation-r6.44.fasta --> FASTA-formatted sequences of drosophila melanogaster from FlyBase</p> <p>- mapping_file.csv --> A CSV file mapping the identifiers used in the following files (from 0 to 30737) to the identifiers in the FlyBase fasta file (dmel-all-translation-r6.44.fasta).</p> <p>- DSSP3_fly_ProtT5Sec.fasta --> Secondary structure predictions in three states for each residue of each protein in dmel-all-translation-r6.44.fasta. "H" stands for Helix; "E" stands for Sheet; "C" stands for Other.</p> <p>- subcell_fly_LA_ProtT5.csv --> Subcellular location (10 states) and memrane-boundness (2 states) for each protein in dmel-all-translation-r6.44.fasta</p> <p>- embeddings_file.h5 --> per-residue embeddings of sequences in dmel-all-translation-r6.44.fasta. Each dataset in the .h5 file represents a protein sequence and contains a matrix of length Lx1024, with L being the length of the protein sequence. Datasets are indexed using integers. The original sequence identifier (from the FASTA header) can be accessed through the "original_id" attribute. See https://docs.bioembeddings.com/v0.2.0/notebooks/open_embedding_file.html for information on how to open the file.</p> <p>- reduced_embeddings_file.h5 --> per-sequence embeddings of sequences in dmel-all-translation-r6.44.fasta (obtained by mean-pooling the residue-embeddings along the length dimension of the protein sequence). Each dataset in the .h5 file represents a protein sequence and contains a vector of size 1024 (meaning, each sequence has the same dimension).</p> <p>- conspred_probs.h5 --> per-sequence conservation probability (softmax) prediction of sequences in dmel-all-translation-r6.44.fasta in 9 classes. Each dataset in the .h5 file represents a protein sequence and contains a matrix of length 9xL, with L being the length of the protein sequence, and 9 being the predicted conservation class (index 0 = very variable; index 8 = very conserved)</p> <p>- vespal_SAVeffect_fly.zip --> zipped .h5 file of per-sequence variation predictions of sequences in dmel-all-translation-r6.44.fasta on a scale from 0 (neutral) to 1 (effect). -1 indicates WT substitution. Each dataset in the .h5 file represents a protein sequence and contains a matrix of length 20xL, with L being the length of the protein sequence, and 20 being the predicted variation score for each residue substitution (AAs in the following order: "<strong>ALGVSREDTIPKFQNYMHWC</strong>" . Meaning that index 0 = substitution of the residue to "A", index = 1 substitution to residue "L", aso.)</p>
Dataset for the article "Cost-effective Potential for Accurate Polarizable Embedding Calculations in Protein Environments"
<p>This dataset contains additional material related to the article: "Cost-effective Potential for Accurate Polarizable Embedding Calculations in Protein Environments". Final version of the article is available at <a href="https://doi.org/10.1021/acs.jctc.9b00616">https://doi.org/10.1021/acs.jctc.9b00616</a> (paywall). A preprint is freely available at <a href="https://doi.org/10.26434/chemrxiv.8126912">https://doi.org/10.26434/chemrxiv.8126912</a>. See <em>readme.md</em> for further description.</p>
Protein language model embeddings and predictions of the human proteome
<p>Residue and sequence embeddings of the human proteome (SwissProt for organism Human, downloaded on 2021.06.09) computed using bio_embeddings (bioembeddings.com) using the ProtT5 embedder at full precision (https://www.biorxiv.org/content/10.1101/2020.07.12.199554v3).</p> <p>Additionally:</p> <p>- Sequence-level predictions of subcellular localization in 10 classes using LA (https://www.biorxiv.org/content/10.1101/2021.04.25.441334v1)</p> <p>- Residue-level three state secondary structure prediction (alpha, sheet or other) using models reported in the ProtTrans paper (https://www.biorxiv.org/content/10.1101/2020.07.12.199554v3)</p> <p> </p> <p>Files included:</p> <p>- human.fasta --> FASTA-formatted sequences of human from SwissProt</p> <p>- DSSP3_human_ProtT5Sec.fasta --> Secondary structure predictions in three states for each residue of each protein in human.fasta. "H" stands for Helix; "E" stands for Sheet; "C" stands for Other.</p> <p>- subcell_human_LA_ProtT5.csv --> Subcellular location (10 states) and memrane-boundness (2 states) for each protein in human.fasta</p> <p>- embeddings_file.h5 --> per-residue embeddings of sequences in human.fasta. Each dataset in the .h5 file represents a protein sequence and contains a matrix of length Lx1024, with L being the length of the protein sequence. Datasets are indexed using integers. The original sequence identifier (from the FASTA header) can be accessed through the "original_id" attribute. See https://docs.bioembeddings.com/v0.2.0/notebooks/open_embedding_file.html for information on how to open the file</p> <p>- reduced_embeddings_file.h5 --> per-sequence embeddings of sequences in human.fasta (obtained by mean-pooling the residue-embeddings along the length dimension of the protein sequence). Each dataset in the .h5 file represents a protein sequence and contains a vector of size 1024 (meaning, each sequence has the same dimension).</p>
Text-fig. 9. Lusitanispermum choffatii gen. et sp. nov. seeds from the Early Cretaceous Famalicão locality (sample 025), Portugal; Synchrotron radiation X-ray tomographic microscopy (SRXTM, orthoslices). a) Longitudinal orthoslice (yz0769) through the median plane of the seed (S174345) showing expanded exotestal cells (ex, arrow head) in the hilar region and well-preserved cellular nutritive tissue with an embedded tiny embryo (asterisk markes the margin of the embryo); note well-developed mesotesta (me) on the raphal side of seed. b) Longitudinal orthoslice (yz0750) in the median plane showing detail of micropylar part of seed with well-preserved exotesta (ex) and mesotesta (me) and tiny embryo with two rudimentary cotyledons (asterisks mark the margin of the cotyledons); note numerous granular bodies in the cellular nutritive tissue that are probably the remains of protein and lipid bodies. c) Transverse orthoslice (xy0311) through seed below hilum showing the bulging exotesta (arrow heads) (S174472); note that the exotestal cells in this region have thinner walls (arrows). d) Transverse orthoslice (xy0900) through the middle of a seed showing the uneven thickening of the anticlinal walls of the exotestal cells (ex), which are thicker towards the outside and very thin towards the inside; note also mesotesta (me) and the well-preserved cellular nutritive tissue (S174472). Scale bars = 500 µm (a, d); 250 µm (b, c). in Extinct Taxa Of Exotestal Seeds Close To Austrobaileyales And Nymphaeales From The Early Cretaceous Of Portugal
Text-fig. 9. Lusitanispermum choffatii gen. et sp. nov. seeds from the Early Cretaceous Famalicão locality (sample 025), Portugal; Synchrotron radiation X-ray tomographic microscopy (SRXTM, orthoslices). a) Longitudinal orthoslice (yz0769) through the median plane of the seed (S174345) showing expanded exotestal cells (ex, arrow head) in the hilar region and well-preserved cellular nutritive tissue with an embedded tiny embryo (asterisk markes the margin of the embryo); note well-developed mesotesta (me) on the raphal side of seed. b) Longitudinal orthoslice (yz0750) in the median plane showing detail of micropylar part of seed with well-preserved exotesta (ex) and mesotesta (me) and tiny embryo with two rudimentary cotyledons (asterisks mark the margin of the cotyledons); note numerous granular bodies in the cellular nutritive tissue that are probably the remains of protein and lipid bodies. c) Transverse orthoslice (xy0311) through seed below hilum showing the bulging exotesta (arrow heads) (S174472); note that the exotestal cells in this region have thinner walls (arrows). d) Transverse orthoslice (xy0900) through the middle of a seed showing the uneven thickening of the anticlinal walls of the exotestal cells (ex), which are thicker towards the outside and very thin towards the inside; note also mesotesta (me) and the well-preserved cellular nutritive tissue (S174472). Scale bars = 500 µm (a, d); 250 µm (b, c).
Silica in Silico: a Molecular Dynamics Characterization of the Early Stages of Protein Embedding for Atom Probe Tomography
<p>The .zip archive contains the trajectories of all the simulations performed and analysed within the manuscript. The water molecules were removed for control systems.</p>
Protein Function Embeddings: First Beta Release of Datasets
<p>This release corresponds to the datasets generated from a thesis work that explores how information for protein functions can be exploited through embeddings so that the produced information can be used to improve protein function annotations. The underlying hypothesis here is that any pair of proteins with high sequence similarity will also share a similar biological function which would be reflected by the corresponding protein embeddings. The comparison and evaluation of this is done using two text-driven embedding approaches: Word2doc2Vec and Hybrid-Word2doc2Vec.</p>
Cell type matching across species using protein embeddings and transfer learning
<p>TACTiCS is a method to transfer and align cell types in cross-species data. This repository contains the protein sequences, protein embeddings, count matrices and trained models for human, mouse and marmoset.</p>
Coarse-grained simulations of lipid membranes with various concentrations of embedded proteins
<p>Membranes with a polydisperse set of proteins with lipid/protein ratios of 50 (lp50), 75 (lp75), 100 (lp100), 200 (lp200), and 400 (lp400) are simulated for 100 µs. The protein–protein interactions are scaled down to prevent excessive aggregation. </p> <p>For all simulated lipid/protein ratio, a trajectory (.xtc) file is stored every 10 ns. Note that water beads and ions have been removed for a smaller file size. All beads, including solvent ones, are present in initial and final structures (.gro). Energy terms are stored every 1 ns (.edr). Simulation run input files (.tpr) and checkpoint files (.cpt) enable the rerunning or continuation of the simulations. Topology (.top) and index (.ndx) files for each system are also provided.</p> <p>The topology files for scaled protein–protein interactions work as follows: The bead types of the proteins in their topology files (.itp) are changed to those with a 'p', for example P4–>P4p. The interactions between normal beads are listed in martini_v2.2_standard.itp, while the interactions among 'p' beads as well as the cross terms between 'p' beads and normal beads are given in martini_v2.2_scaled_80.itp. The force constant of the elastic network was increased to enable an integration time step of 20 fs.</p> <p>The lipid head groups are gently restrained in the direction normal to the membrane to prevent excessive fluctuations and they hence simulate the presence of an actin cytoskeleton.</p> <p>The simulation parameters, common for all systems, are listed in the file md.mdp. </p> <p>All files are compatible with Gromacs 5.0.</p> <p>The results extracted from these simulations are presented in the paper</p> <p>M. Javanainen, H. Martinez-Seara, R. Metzler, and I. Vattulainen; Diffusion of Integral Membrane Proteins in Protein-Rich Membranes. J. Phys. Chem. Lett., 2017, 8 (17), pp 4308–4313, DOI: 10.1021/acs.jpclett.7b01758</p> <p>The Martini topologies are obtained form http://cgmartini.nl</p>
Protein domain embedding
<p>CATH and ECOD structure embedding computed with a <a href="https://github.com/BorgwardtLab/PST">Protein Language Model</a>. These two datasets were compiled to develop AI/ML methods for structure comparison (Guzenko 2020). Protein structures from both datasets are independent and can be used as training and testing data for ML methods. </p>
Embeddings from FLIP: benchmark tasks in fitness landscape inference for proteins
<p>ESM-1b embeddings used in FLIP. </p>
A joint embedding of protein sequence and structure enables robust variant effect predictions
Open the record for dataset details and reuse information.
Inverse design of viral infectivity-enhancing peptide fibrils from continuous protein-vector embeddings
<p>The Tables S3 - S5 are a supplement for the article "Inverse design of viral infectivity-enhancing peptide fibrils from continuous protein-vector embeddings" uploaded as a Preprint in ChemRxiv DOI: 10.26434/chemrxiv-2023-1kqm3</p>
Developing biomarkers incorporating high throughput RNA, DNA, small RNA sequencing and protein expression in Inflammatory Bowel Disease using formalin-fixed, paraffin-embedded (FFPE) tissue samples
GEO Series GSE221161. Homo sapiens. 203 samples. Type: Expression profiling by high throughput sequencing.
A joint embedding of protein sequence and structure enables robust variant effect predictions
<p>Data related to the GitHub repository KULL-Centre/_2023_Blaabjerg_SSEmb, which is also stored on Zenodo here: <span><span><a href="../doi/10.5281/zenodo.13765792" target="_blank" rel="noopener noreferrer">https://zenodo.org/doi/10.5281/zenodo.13765792</a>.</span></span></p>
Data from: Fit for genomic and proteomic purposes: sampling the fitness of nucleic acid and protein derivatives from formalin fixed paraffin embedded tissue
Open the record for dataset details and reuse information.
Cross-modality and self-supervised protein embedding for compound–protein affinity and contact prediction
Open the record for dataset details and reuse information.
Semi-Quantification of Her2/Neu Protein Expression in Formalin Fixed, Paraffin-Embedded Normal and Neoplastic Tissue
ClinicalTrials.gov study NCT02654444. IPD Sharing: Not stated. Countries: 0. Publications: 0.
RtmR is a membrane-embedded RRM-family RNA-binding protein that regulates biofilm formation
GEO Series GSE301959. Aliivibrio fischeri. 2 samples. Type: Other.
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.