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.
266
datasets available to search
ShareScore release 0.9.0
Dataset results
266 results for “Protein Modelling”
LigPCDS: Labeled Dataset of X-ray Protein Ligand Images in 3D Point Cloud and Validated Deep Learning Models
<p>The difference electron density from X-ray protein crystallography was used to create the first dataset of labeled ligand images in 3D point clouds, named <strong>LigPCDS</strong>. The dataset contain 244,226 entries of free organic ligands containing 3D representations labeled with two major labeling approaches: SP-based and AtomSymbol-based.</p> <p> </p> <p>The data from free organic molecules (non-covalent ligands) was retrieved from the Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB) in december 2019 with resolutions ranging from 1.5 to 2.2 Å. The ligand images (blobs) were interpolated from their calculated difference electron density map in a 3D grid-like bounding box, around their atomic positions, and stored in point clouds. These ligand grid representations were further processed to retrive the final ligands representation in 3D point clouds using a mask of the shape of the ligand. A grid spacing of 0.5 Å gave the best results. The density value of the grid points was used as feature. The labeling approach used the structure of the ligands to propose vocabularies of chemical classes based on the chemical atoms themselves and their cyclic substructures. These structure annotations were applied pointwise to the ligand 3D representations using an atomic sphere model. Four proposed vocabularies were validated by successfully training good performance deep learning models for the semantic segmentation of a stratified dataset from LigPCDS, using 78902 entries.</p> <p>The four validated deep learning models are: (i) the LigandRegion, composed by generic atoms of any type; (ii) the AtomCycle, composed by generic atoms outside cycles and generic cycles; (iii) the AtomC347CA56, composed by generic atoms outside cycles, not aromatic cycles of size 3 to 7 and aromatic cycles of size 5 and 6; and (iv) the AtomSymbolGroups, composed by the atoms symbols with groupings. The mean accuracy of these models in their cross-validation was between 49.7% <span lang="EN-GB">[-19.4,20.</span><span lang="EN-GB">2]</span> and 77.4% <span lang="EN-GB">[-11.7,12.1]</span> in terms of Intersection over Union (mIoU) metric and between 62.4% <span lang="EN-GB">[-18.8,19.</span><span lang="EN-GB">7]</span> and 87.0% <span lang="EN-GB">[-8.4,8.8]</span> in F1-score (mF1), confidence interval between squared brackets. The models i, ii and iii and the used labeled representations in 3D point cloud are contained in the SP-based record; and model iv and its used labeled representations are contained in the AtomSymbol-based record.</p> <p>The dataset and validated models may be used to tackle problems regarding known and unknown ligand building to drug discovery and fragment screening pipelines. </p> <p>The code used to create and validated the LigPCDS is available at the following repository: https://github.com/danielatrivella/np3_ligand</p> <p>This repository also contains the NP³ Blob Label application for ligand building using the validated deep learning models from LigPCDS.</p>
Project files provided as supporting information to the manuscript "Ligand-protein interactions in lysozyme investigated through a dual-resolution model"
<p><strong>README file for the project files provided as supporting information to the manuscript "Ligand-protein interactions in lysozyme investigated through a dual-resolution model"</strong></p> <p>February 12, 2020</p> <p>Authors: Raffaele Fiorentini, Kurt Kremer and Raffaello Potestio</p> <p>================================</p> <p>Overview</p> <p>The dataset is organised in three (compressed) subfolders (see the tree diagrams in each section):</p> <p>- annihilation<br> - decoupling<br> - density</p> <p>The figure deltaG_binding_ann_dec_comparison.png shows the results of binding free energy calculations comparing the values obtained both for annihilation and decoupling.</p> <p>The figure deltaG_binding_annih_gromacs_espp.png displays the results for Binding FE, comparing the values obtained in GROMACS and ESPResSo++.</p> <p>The README.pdf file contains detailed information about these folders and their content.</p> <p>================================</p> <p>The "annihilation" folder contains all results concerning the calculation of binding free energy in case of annihilation and it is divided in two parts: </p> <p>- complex<br> - ligand</p> <p>In "complex" are reported the results of Ligand-Protein FE both in ESPResSo++ and GROMACS. All simulations are fully-atomistic. </p> <p>In "ligand" are reported the results of ligand solvation free energy both in ESPResSo++ and GROMACS. All simulations are fully-atomistic. </p> <p>====</p> <p>The "decoupling" folder contains all results concerning the calculation of binding free energy in case of decoupling and it is divided in three parts: </p> <p>- complex-DualRes<br> - complex-FullyAT<br> - ligand</p> <p>In "complex-DualRes" are reported the results of Ligand-Protein FE only in ESPResSo++ (GROMACS cannot do decoupling). The system is simulated in Dual-Resolution. It is possible to find the trajectory files in the sub-directories "lambdaindex-0" and "lambdaindex-30".</p> <p>In "complex-fullyAT" are reported the results of Ligand-Protein FE only in ESPResSo++. The system simulated is fully-atomistic. It is possible to find the trajectory file in the sub-directories "lambdaindex-0" and "lambdaindex-30".</p> <p>In "ligand" are reported the results of ligand solvation free energy only in ESPResSo++. All simulations are fully-atomistic. It is possible to find the trajectory file in the sub-directories "lambdaindex-0" and "lambdaindex-20".</p> <p>====</p> <p>The "density" folder contains the data for the tuning of the c parameter of the steric repulsion among residues. This parameter is tuned so that the water density attains the value computed in all-atom simulations.</p>
Datasets for Supervised Learning Model Predicts Protein Adsorption to Carbon Nanotubes
<p>All used Datasets to pair with "Supervised Learning Model Predicts Protein Adsorption to Carbon Nanotubes" by Nicholas Ouassil*, Rebecca L. Pinals*, Jackson Travis Del Bonis-O'Donnell, Jeffrey W. Wang, and Markita P. Landry</p> <p>*Co-authors</p>
Input features of E. coli proteome for predicting and modeling protein-protein interactions with AF2Complex
<p>Input features to be used with AF2Complex for predicting protein-protein interactions among ~4400 E. coli proteins. A pickled feature file was generated by the feature data pipeline of AF2Complex for each E. coli protein. To reduce storage size, we limited up to 10,000 MSA sequences and up to 10 structural templates from the Protein Data Bank. The cutoff date for sequence libraries and the Protein Data Bank releases used for feature generation is no later than 11-30-2021.</p> <ul> <li>ecoli_af2c_fea.txt -- A list of all E coli protein with pre-generated input features</li> <li>af2c_fea_ecoli_220331_msa10ktem10.tar -- Input features named after the UniProt ID of each proteins. Note that after untar the tarball, you may use the gzipped feature pickle files directly with AF2Complex w/o gunzip.</li> </ul>
Data for "SeaMoon: from protein language models to continuous structural heterogeneity"
<p>Datasets used for development of SeaMoon: <br><a href="https://github.com/PhyloSofS-Team/seamoon">https://github.com/PhyloSofS-Team/seamoon</a>.</p> <p>This upload contains the following data:</p> <ul> <li><strong>precomputed_emb.tar.gz</strong> is a compressed archive containing the precomputed data used for training and testing the models of the SeaMoon method, in Torch <strong>.pt </strong>format. <br>The file prefixes consist of two IDs, "ID1_ID2_", identifying the <a href="https://github.com/PhyloSofS-Team/DANCE">DANCE</a> [1] protein conformational collection used for its generation. "ID1" represents the first member of the collection in alphabetical order, while "ID2" is the reference conformation for the structural alignment. The "ESM_data" or "ProstT5_data" suffixes designate the type of embeddings, generated by either ESM2 [2] or ProstT5 [3].<br>The dictionnary contains the following keys: <ul> <li><strong>emb:</strong> The per-residue embedding.</li> <li><strong>data: </strong>A tuple containing "ID2" (the reference), the amino acid sequence, and the coverage of the positions in the original DANCE collection.</li> <li><strong>eigvect:</strong> The eigenvectors of the covariance matrix of the "ID1_ID2" collection, centered on reference conformaton "D2".</li> <li><strong>eigval: </strong>The associated eigenvalues.</li> <li><strong>ref:</strong> The coordinates of the C-alpha atoms of the reference conformaton "ID2".</li> </ul> </li> <li><strong>train_list.txt, train_list_5ref.txt, val_list.txt </strong>and<strong> test_list.txt</strong> contain the identifiers of the samples used for training and evaluating the SeaMoon models. In the "5ref" setting, we used up to 5 reference conformations per collection. </li> </ul> <p>For details on SeaMoon see:</p> <div> <div>SeaMoon: Prediction of molecular motions based on language models</div> </div> <div>Valentin Lombard, Dan Timsit, Sergei Grudinin, Elodie Laine</div> <div>bioRxiv 2024.09.23.614585; doi: https://doi.org/10.1101/2024.09.23.614585</div> <div> </div> <div>For more information on data usage and generation please see <a href="https://github.com/PhyloSofS-Team/seamoon">https://github.com/PhyloSofS-Team/seamoon</a>.</div> <div> </div> <div>Abstract:</div> <p>How protein move and deform determines their interactions with the environment and is thus of utmost importance for cellular functioning. Following the revolution in single protein 3D structure prediction, researchers have focused on repurposing or developing deep learning models for sampling alternative protein conformations. In this work, we explored whether continuous compact representations of protein motions could be predicted directly from protein sequences, without exploiting nor sampling protein structures. Our approach, called SeaMoon, leverages protein Language Model (pLM) embeddings as input to a lightweight (~1M trainable parameters) convolutional neural network. SeaMoon achieves a success rate of up to 40% when assessed against ~1,000 collections of experimental conformations exhibiting a wide range of motions. SeaMoon capture motions not accessible to the normal mode analysis, an unsupervised physics-based method relying solely on a protein structure's 3D geometry, and generalises to proteins that do not have any detectable sequence similarity to the training set. SeaMoon is easily retrainable with novel or updated pLMs. </p> <p> </p> <p>[1] Lombard, V.; Grudinin, S.; Laine, E. Explaining Conformational Diversity in Protein Families through Molecular Motions. Scientific Data 2024, 11, 752.</p> <p>[2] Lin, Z.; Akin, H.; Rao, R.; Hie, B.; Zhu, Z.; Lu, W.; Smetanin, N.; Verkuil, R.; Kabeli, O.; Shmueli, Y.; Dos Santos Costa, A.; Fazel-Zarandi, M.; Sercu, T.; Candido, S.; Rives, A. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 2023, 379, 1123–1130.</p> <p>[3] Heinzinger, M.; Weissenow, K.; Sanchez, J. G.; Henkel, A.; Steinegger, M.; Rost, B. ProstT5: Bilingual language model for protein sequence and structure. bioRxiv 2023, 2023–07.</p>
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>
Predictive modeling of moonlighting DNA-binding proteins
<p>This repository contains the codes used for the prediction of moonlighting proteins in the paper "Predictive modeling of moonlighting DNA binding proteins".</p> <p>The repository is organized as the following:</p> <p>1. The DNA binding protein identifiers and their features that were used to train the models for the prediction of DNA binding Moonlighting proteins.</p> <p>2. Five feature sets were used to create Catboost models that make predictions. The source code for generating predictions based on all the features and predictions based on particular features is supplied. In addition, the source code for generating maximum and average ensemble predictions has been made available. A detailed explanation is given in README file.</p>
Data for: The structure of evolutionary model space for proteins across the tree of life
<p>Supporting data for "The structure of evolutionary model space for proteins across the tree of life," submitted by GE Scolaro and EL Braun. The data files correspond to three gzipped tarballs including protein multiple sequence alignments, PAML format models of protein evolution, and model fit data; see included README for details.</p>
Data for the article: "Molecular Modelling Reveals Eight Novel Druggable Binding Sites in SARS-CoV-2's Spike Protein" by Ilke Ugur and Antoine Marion
<p>This upload contains data related to the article<br> published as a preprint on ChemRxiv with DOI<br> https://doi.org/10.26434/chemrxiv.13292768</p> <p>"Molecular Modelling Reveals Eight Novel Druggable Binding Sites in SARS-CoV-2's Spike Protein"<br> by Ilke Ugur and Antoine Marion (2020)<br> Department of Chemistry, Middle East Technical University, Ankara, Turkey.</p> <p>For further information, please contact:<br> ilkeugur@metu.edu.tr ; amarion@metu.edu.tr</p> <p>The manuscript is currently under peer-review.</p> <p>Content:</p> <p>Library of molecules derived from DrugBank v 5.1.5:<br> - DrugBank_2020_5.1.5/ # All necessary files for the docking and refinement of the library of molecules.<br> -- DB_5.1.5_pH7.4_pdbqt/ ## PDBQT readily usable for docking with AutoDock Vina.<br> -- DB_5.1.5_pH7.4_mol2amber/ ## mol2 files containing assigned GAFF atom types and Gasteiger atomic charges.<br> -- DB_5.1.5_pH7.4_frcmod/ ## frcmod files containing missing molecular mechanics parameters<br> -- dbID_name.dat ## DrugBank ID to generic name dictionary</p> <p>Note: The files were prepared automatically via a series of operations handling openbabel and antechamber.<br> The protonation state of ionizable groups as well as Gasteiger atomic charges were assigned by openbabel for a pH of 7.4<br> mol2 and frcmod files can be used readily via the tleap module of AmberTools to produce topology files.</p> <p><br> Receptor structures:<br> - receptors/ # PDB files for the four structures of the spike protein considered in this work<br> -- CS00ns.pdb ## Closed state after the remodelling of missing loops (PDB ID 6vxx)<br> -- OS00ns.pdb ## Open state after the remodelling of missing loops (PDB ID 6vyb)<br> -- CS25ns.pdb ## Closed state after 25 ns of molecular dynamics in explicit water<br> -- OS25ns.pdb ## Open state after 25 ns of molecular dynamics in explicit water</p> <p>Note: All structures are aligned to CS00ns.pdb and can be converted to pdbqt for docking with AutoDock Vina</p> <p><br> Docking grid centers:<br> - dockingCenters/ # XYZ files containing the coordinates of each docking grid center considered in this work</p> <p>Note: The coordinates are given in the same frame as that of the four structures of the receptor.</p> <p><br> Binding sites:<br> - bindingSites/ # XYZ files with the coordinates of the representative atomic centres<br> # of each binding site identified in this work (A-H).</p> <p>Note: These files can be used to get a clearer picture of the binding sites within the structures<br> of the spike protein shared in the receptors directory.</p> <p><br> Final modelling results:<br> - allData.txt # data for all molecules in the set (approved and investigational)<br> - appData.txt # data for approved molecules only<br> - data.xlsx # data for all molecules in the set (approved and investigational)<br> # as a formatted excel spreadsheet</p> <p>Note: The columns are delimited with semi-colons ";".<br> The files contain the results for the best pose of all approved molecules for which<br> molecular mechanics-based geometry optimization succeeded, regardless of their score.<br> For other molecules, the result of their best pose is reported only for those complexes<br> having MM interaction energy lower or equal to -22.00 kcal/mol.</p> <p><br> Visualization:<br> - bs.pse # pymol session representing the binding sites within the<br> # closed state structure of the spike protein (CS00ns)<br> - pt.pse # pymol session representing the docking grid centres within<br> # closed statestructure of the spike protein (CS00ns)</p> <p>Note: the PSE files should be compatible with version 7.0 of pymol and later</p>
Protein secondary-structure description with a coarse-grained model: code and datasets in ActivePapers format
<p>This file contains the supplementary material for the publication</p> <p><em>Protein secondary-structure description with a coarse-grained model</em><br /> by Gerald R. Kneller and K. Hinsen<br /> http://dx.doi.org/10.1107/S1399004715007191<br /> Acta Cryst. (2015). D<strong>71</strong>, 1411-1422</p> <p><strong>Datasets in this file</strong></p> <p>1) ScrewFit and ScrewFrame parameters for ideal secondary-structure elements</p> <p> Scripts:<br /> /code/import_ideal_structures<br /> /code/analyze_ideal_structures</p> <p>1.1) The PDB files generated with Chimera</p> <p> /data/ideal_structures/3-10.pdb<br /> /data/ideal_structures/alpha.pdb<br /> /data/ideal_structures/beta-antiparallel.pdb<br /> /data/ideal_structures/beta-parallel.pdb<br /> /data/ideal_structures/pi.pdb</p> <p>1.2) The corresponding MOSAIC datasets</p> <p> /data/ideal_structures/3-10<br /> /data/ideal_structures/alpha<br /> /data/ideal_structures/beta-antiparallel<br /> /data/ideal_structures/beta-parallel<br /> /data/ideal_structures/pi</p> <p>1.3) The ScrewFit parameters</p> <p> /data/ideal_structures/screwfit/3-10<br /> /data/ideal_structures/screwfit/alpha<br /> /data/ideal_structures/screwfit/beta-antiparallel<br /> /data/ideal_structures/screwfit/beta-parallel<br /> /data/ideal_structures/screwfit/pi</p> <p>1.4) The ScrewFrame parameters</p> <p> /data/ideal_structures/screwframe/3-10<br /> /data/ideal_structures/screwframe/alpha<br /> /data/ideal_structures/screwframe/beta-antiparallel<br /> /data/ideal_structures/screwframe/beta-parallel<br /> /data/ideal_structures/screwframe/pi</p> <p><br /> 2) Statistics for ScrewFit and ScrewFrame parameters computed<br /> for the ASTRAL SCOPe subset with less than 40% sequence identity.</p> <p> Scripts:<br /> /code/astral_analysis<br /> /code/fit_rho_distributions<br /> /code/plot_histograms</p> <p>2.1) The ASTRAL database (link to published ActivePaper)</p> <p> /data/astral_2.04</p> <p>2.2) The histograms for the ScrewFit and ScrewFrame parameters<br /> for the all-alpha and all-beta subsets</p> <p> /data/histograms/astral_alpha/screwfit<br /> /data/histograms/astral_alpha/screwframe</p> <p> /data/histograms/astral_beta/screwfit<br /> /data/histograms/astral_beta/screwframe</p> <p>2.3) The Gaussians fitted to the peaks in the distributions for rho</p> <p> /data/fitted_rho_distributions/screwfit<br /> /data/fitted_rho_distributions/screwframe</p> <p>2.4) Plots</p> <p> /documentation/delta.pdf<br /> /documentation/delta_q.pdf<br /> /documentation/delta_r.pdf<br /> /documentation/p.pdf<br /> /documentation/rho-detail.pdf<br /> /documentation/rho.pdf<br /> /documentation/sigma.pdf<br /> /documentation/tau.pdf</p> <p><br /> 3) Comparison of secondary-structure identification between ScrewFrame<br /> and DSSP.</p> <p> Script:<br /> /code/compare_secondary_structure_assignments<br /> /code/plot_histograms</p> <p>3.1) The histograms of the lengths of secondary-structure elements</p> <p> /data/histograms/secondary_structure/length-alpha-dssp<br /> /data/histograms/secondary_structure/length-alpha-screwframe<br /> /data/histograms/secondary_structure/length-beta-dssp<br /> /data/histograms/secondary_structure/length-beta-screwframe</p> <p>3.2) The 2D histograms of the number of residues inside identified<br /> secondary-structure elements</p> <p> /data/histograms/secondary_structure/n-alpha<br /> /data/histograms/secondary_structure/n-beta</p> <p>3.3) The distribution of rho inside alpha helices</p> <p> /data/histograms/secondary_structure/rho-alpha-dssp</p> <p>3.3) Plots</p> <p> /documentation/lengths-alpha.pdf<br /> /documentation/lengths-beta.pdf<br /> /documentation/n-alpha.pdf<br /> /documentation/n-beta.pdf<br /> /documentation/rho-alpha-dssp.pdf</p> <p><br /> 4) Illustration for myoglobin and VADC-1</p> <p> Scripts:<br /> /code/import_myoglobin_vdac<br /> /code/analyze_myoglobin<br /> /code/analyze_vdac<br /> /code/perturbation_analysis</p> <p>4.1) Imported structures in MOSAIC format:<br /> PDB code 1A6G for myoglobin<br /> PDB code 2K4T for VDAC-1</p> <p> /data/myoglobin<br /> /data/VDAC-1</p> <p>4.2) Plots showing rho and delta</p> <p> /documentation/rho-myoglobin.pdf<br /> /documentation/delta-myoglobin.pdf</p> <p>4.3) Tube models for visualization with Chimera</p> <p> /documentation/myoglobin-tube.bld<br /> /documentation/VDAC-1-tube.bld</p> <p>4.4) Sensitivity to perturbations in the coordinates</p> <p> /documentation/rho-perturbed-myoglobin.pdf<br /> /documentation/delta-perturbed-VDAC-1.pdf<br /> /documentation/rho-perturbed-myoglobin.pdf<br /> /documentation/delta-perturbed-VDAC-1.pdf<br /> /documentation/myoglobin-perturbation.pdf<br /> /documentation/VDAC-1-perturbation.pdf</p> <p>5) Analysis of CA-only structures in the PDB</p> <p> Scripts:<br /> /code/ca_analysis<br /> /code/import_calpha_structures<br /> /code/plot_histograms</p> <p>5.1) Imported CA-only structures in MOSAIC format</p> <p> /data/pdb_ca_only_structures</p> <p>5.2) Histograms for ScrewFrame parameters</p> <p> /data/histograms/ca_only_structures</p> <p>5.3) Plots</p> <p> /documentation/delta_ca.pdf<br /> /documentation/delta_q_ca.pdf<br /> /documentation/delta_r_ca.pdf<br /> /documentation/p_ca.pdf<br /> /documentation/rho_ca.pdf<br /> /documentation/sigma_ca.pdf<br /> /documentation/tau_ca.pdf</p> <p> </p>
Modeling and measuring how codon usage modulates the relationship between burden and yield during protein overexpression in bacteria
<p>Additional data from experiments associated with paper revisions.</p> <p>Also added codon optimizer script.</p>
Interformer: An Interaction-Aware Model for Protein-Ligand Docking and Affinity Prediction
<p>The code, dataset, and model weights are described in the paper "Interformer: An Interaction-Aware Model for Protein-Ligand Docking and Affinity Prediction."</p> <p> </p> <p><strong>experiment_results.zip:</strong> Contains generated results that can reproduce the result from the reported paper.</p> <p><strong>benchmark.zip:</strong> Contains docking and affinity input data of the interformer. You can use the source code to make predictions and reproduce the number of the reported paper.</p> <p><strong>checkpoints.zip: </strong>Contains one weight for the Energy and four PoseScore and Affinity models.</p> <p><strong>source_code_1.0.zip:</strong> Contains the initial version of the source code.</p> <p><strong>interformer_train.tar.gz:</strong> Contains prepared training data for interformer. poses/ contains all structure need for training, poses/ligand contains the re-docking poses generated by interformer energy, poses/ligand/rcsb contains the conformation of reference ligand, poses/pocket contains all pocket extract by raw PDB from rcsb, poses/uff contains all ligand conformation minimized using UFF from reference ligand, and train/ contains the training csv.</p> <p><strong>baseline_results.tar.gz:</strong> Contains the predictions from three methods: Interformer, DiffDock, and DeepDock. The results align with the exact numbers reported in the paper. For further details, please refer to the <em>eda/ </em>directory.</p> <p> </p> <p>You can also find the newest version of the source code at <a href="https://github.com/tencent-ailab/Interformer" target="_blank" rel="noopener">https://github.com/tencent-ailab/Interformer</a></p> <p> </p>
DMFold models for 5,042 human proteins
<p>This dataset contains structural models predicted by DMFold with DeepMSA2 MSAs as inputs for 5,042 difficult proteins (AlphaFold2 pLDDT<0.7) in the human proteome. </p>
Data for: Caspase-Based Fusion Protein Technology: Substrate Cleavability Described by Computational Modeling and Simulation
<p>This dataset contains all files necessary to set up the simulations conducted in this work. It further contains the scripts that were used to do the stitching and combining of the CASPON-tag and the N-termini of the POIs. The manuscript was just submitted and accepted: <a href="https://doi.org/10.1021/acs.jcim.4c00316">10.1021/acs.jcim.4c00316</a></p>
Small molecules targeting the structural dynamics of AR-V7 partially disordered protein using deep learning and physics based models.
<p>Partially disordered proteins can contain both stable and unstable secondary structure segments and are involved in various (mis)functions in the cell. The extensive conformational dynamics of partially disordered proteins scaling with extent of disorder and length of the protein hampers the efficiency of traditional experimental and in-silico structure-based drug discovery approaches. Therefore new efficient paradigms in drug discovery taking into account conformational ensembles of proteins need to emerge. In this study, using as a test case the AR-V7 transcription factor splicing variant related to prostate cancer, we present an automated methodology that can accelerate the screening of small molecule binders targeting partially disordered proteins. By swiftly identifying the conformational ensemble of AR-V7, and reducing the dimension of binding-sites by a factor of 90 by applying appropriate physicochemical filters, we combine physics based molecular docking and multi-objective classification machine learning models that speed up the screening of thousands of compounds targeting AR-V7 multiple binding sites. Our method not only identifies previously known binding sites of AR-V7, but also discovers new ones, as well as increases the multi-binding site hit-rate of small molecules by a factor of 17 compared to naive physics-based molecular docking. </p>
Data generated for the publication: Keeping it in the family: Using protein family templates to rescue poor AlphaFold models unliked
<p>Data and manuscript of:</p> <p>Keeping it in the family: Using protein family templates to rescue low confidence AlphaFold2 models</p> <p>Francesco Costa1, Matthias Blum1 and Alex Bateman1</p> <ol> <li>European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton. CB10 1SD. UK</li> </ol> <ul> <li>results contains the workflow results;</li> <li>AF2_seed contains results of the comparison with AF2 run with multiple seeds;</li> </ul>
Supplementary data frames, AlphaFold models, Normal Mode Analysis (NMA) Data, and NMA of Corresponding NMR Ensembles in the S2RCI, MD, and S2 Datasets for "Gradations in protein dynamics captured by experimental NMR are not well represented by AlphaFold2 models and other computational metrics"
<h1><strong>Changes applied to V2</strong></h1> <p>In addition to the supplementary dataframes and AlphaFold models from each dataset in V1, V2 includes the additional data outlined below.</p> <p>The <strong>S2RCI</strong> and <strong>MD</strong> datasets include comprehensive analyses of AlphaFold2 models (both before and after truncation). These datasets feature: </p> <ul> <li><strong>AlphaFold2 Models</strong>: Both original and truncated structures. </li> <li><strong>WEBnma Modes</strong>: `modes.txt` files generated from WEBnma analysis, available for both non-truncated and truncated AF2 models. </li> <li><strong>Root-Mean-Square-Fluctuations (RMSF)</strong>: Profiles calculated before and after truncation of AF2 models. </li> <li><strong>NMR Data: Normal Mode Analysis (NMA)</strong>: Performed on corresponding NMR ensembles (see below). </li> </ul> <p> </p> <p>The <strong>NMR Data</strong> of NMA in these datasets includes: </p> <ul> <li>NMR ensembles </li> <li>Individual NMR models extracted from each ensemble </li> <li>STRIDE secondary structure calculations per-individual NMR models</li> <li>RMSF profiles per-individual NMR models</li> </ul> <p>For detailed information, please refer to the `Readme.txt` file within each corresponding folder. </p> <p>The <strong>S2 dataset</strong> includes all the features listed above, except for the NMR analysis.</p>
Flavivirus NS1 protein models
<p>Four <em>Flavivirus</em> NS1 protein models based on ZIKV-UG (Zika virus from Uganda), ZIKV-BR (Zika virus from Brazil), DENV2 (Dengue virus variant 2), and WNV (West Nile Virus). Due to the crystals for these four NS1 are having missing regions (i.e., X-ray structures with PDB ids 5K6K, 5GS6, 4O6B, and 4O6D, respectively) a homology protocol was applied. Models were built using Modeller 9.24 and default parameters and were selected the structures with the best DOPE score. NS1<sub>ZIKV-UG</sub> and NS1<sub>ZIKV-BR</sub> models are based on the templates with PDB ids 5K6K and 5GS6, respectively. For NS1<sub>DENV2</sub> three templates were used the two complete structures from NS1<sub>ZIKV-UG</sub> and NS1<sub>ZIKV-BR</sub>, and the crystal PDB id 4O6B. For NS1<sub>WNV</sub>, was followed the same strategy as for NS1<sub>DENV2</sub>, but the third template was changed for the crystal PDB id 4O6D.</p> <p>For more details check the SI of <a href="https://doi.org/10.1016/j.virusres.2022.198838">https://doi.org/10.1016/j.virusres.2022.198838</a>.</p>
Dataset for "Molecular modeling of the interface of an egg yolk protein-based emulsion"
<p>Dataset for figures of upcoming article "Molecular modeling of the interface of an egg yolk protein-based emulsion" submitted to the journal "Physics of Fluids".</p> <p>dimerApovitellenin1_AA.pdb is the all-atom protein structure file used in MD simulations.</p> <p>DPDparameters.csv is the parametrization file used in DPD simulations.</p>
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>
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.