The Protein Data Bank

By Helen M. Berman, John D. Westbrook, Zukang Feng, Gary Gilliland, Talapady N. Bhat, H. Weissig, Ilya N. Shindyalov, Philip E. Bourne. 2000

10,261 citations recorded by the source corpus.

Subfields: Materials Chemistry, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

End-to-end protein–ligand complex structure generation with diffusion-based generative models (2022, methodology): “In addition, the dataset size was small compared to the total number of entries in the PDB. Extensive use of PDB-6 registered structures, including apo protein structures, for training would improve the reproducibility of protein structures and help better capture the eﬀects of ligand binding.”
Multi-State Modeling of G-protein Coupled Receptors at Experimental Accuracy (2021, background): “As of January 05, 2022, 689 GPCR structures have been deposited to the protein data bank (PDB).(22) However, a majority of GPCR structures are still unknown.”
Protein Sequence Analysis Using the MPI Bioinformatics Toolkit (2020, background): “Such databases are, for example, the Pfam (El-Gebali et al., 2019), CDD (Lu et al., 2020), and SMART (Letunic & Bork, 2018) domain databases; the SCOPe (Fox et al., 2014) and ECOD (Cheng et al., 2014) structural classification databases; the Protein Data Bank (Berman et al., 2000); and proteomes of ”
Improved protein structure prediction using predicted interresidue orientations (2019, neutral): “Multiple groups showed that application of deep learning-based methods to the protein structure-prediction problem makes it possible to generate fold-level accuracy models of proteins lacking homologs in the Protein Data Bank (PDB) (2) directly from multiple sequence alignments (MSAs) (3–6).”
IntFOLD: an integrated web resource for high performance protein structure and function prediction (2019, background): “An additional new feature is the provision of a link that allows users to download all of the ASE annotated models in PDB format (with the error estimates, in Angstroms, in place of temperature factor data) as a zipped archive.”
HH-suite3 for fast remote homology detection and deep protein annotation (2019, methodology): “The PDB70 contains profile HMMs for a representative set of sequences from the PDB [22], filtered with a maximum pairwise sequence identity of 70%.”
IUPred2A: context-dependent prediction of protein disorder as a function of redox state and protein binding (2018, background): “The first negative dataset ( ordered monomers ) comprises sequence regions (also filtered for 30% sequence identity) that encode single structural domains with determined monomeric structures in the PDB (4,549 protein regions).”
Improvement of molecular-replacement models with Sculptor (2011, methodology): “A benchmark suite was compiled using randomly selected structures with experimental data available from the PDB (Berman et al., 2002).”
BERTology Meets Biology: Interpreting Attention in Protein Language Models (2020, methodology): “We used two protein sequence datasets from the TAPE repository for the analysis: the ProteinNet dataset [3, 10, 26, 52] and the Secondary Structure dataset [10, 38, 52, 60].”
Modeling aspects of the language of life through transfer-learning protein sequences (2019, methodology): “The set contains 10,837 sequence-unique (at 25% PIDE) proteins of experimentally known 3D structures from the PDB [66] with a resolution of 2.5 Å (0.25 nm) or better, collected by the PISCES server [67].”
Unified rational protein engineering with sequence-based deep representation learning (2019, methodology): “We computed the full sequence of hidden states at every position of 3,720 single-domain proteins from the SCOP database 60 (for which we had secondary structure annotation for each of the positions obtained from the PDB 80 ).”
Evaluating Protein Transfer Learning with TAPE (2019, background): “(Labeling) Each fold is annotated from the structure of the sequence, which SCOP pulls from the Protein DataBank [57, 58].”
DEEPCON: Protein Contact Prediction using Dilated Convolutional Neural Networks with Dropout (2019, neutral): “The total number of protein structures determined through experimental methods such as X-ray crystallography and Nuclear magnetic resonance spectroscopy are currently limited to 147,817 as of January 2019 [1].”
NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning (2018, methodology): “An example of the ASA and SS3 predictions for the human Orotate phosphoribosyltransferase (OPRTase) domain, displayed on its solved structure (PDB id 2WNS) is illustrated in Figure 2.”
Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13) (2019, methodology): “All the neural network models are trained on structures extracted from the PDB.(9) We extract nonredundant domains by utilizing the CATH(7) 35% sequence similarity cluster representatives (CATH ver-”
ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing (2020, methodology): “We included proteins from the PDB [44] with resolutions (cid”