PISCES: a protein sequence culling server

By Guoli Wang, Roland L. Dunbrack. 2003

1,674 citations recorded by the source corpus.

Subfields: Materials Chemistry, Molecular Biology, Spectroscopy, 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

1. Yang Zhang
2. Jinbo Xu
3. Sheng Wang
4. David Baker
5. Torsten Schwede
6. Lukasz Kurgan
7. Sergey Ovchinnikov
8. Yaoqi Zhou

In Molecular Biology

1. Jinbo Xu
2. Yang Zhang
3. Sheng Wang
4. David Baker
5. Torsten Schwede
6. Jianlin Cheng
7. Yaoqi Zhou
8. David T. Jones

In Spectroscopy

1. Yang Zhang
2. Jinbo Xu
3. Lukasz Kurgan
4. Santrupti Nerli
5. David Baker
6. Nikolaos G. Sgourakis
7. Sergey Ovchinnikov
8. Kevin J. Karplus

In Computational Biology & Bioinformatics

1. Jinbo Xu
2. Yang Zhang
3. Sheng Wang
4. David Baker
5. Mohammed Alquraishi
6. Arne Elofsson
7. Sergey Ovchinnikov
8. Badri Adhikari

Citations in the corpus

• Toward the estimation of the absolute quality of individual protein structure models (2010, methodology): “‘PDB training set’: the statistical potentials were extracted from a nonredundant set of high-resolution structures from the PDB (Berman et al., 2000) selected using the PISCES server (Wang and Dunbrack, 2003).”
• 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].”
• DEEPCON: Protein Contact Prediction using Dilated Convolutional Neural Networks with Dropout (2019, methodology): “On these proteins, if we perform some basic redundancy reductions such as keeping only the proteins with more than 20% sequence similarity and those with high resolution structures, the number of proteins available for training reduces to only around a five thousand [14].”
• ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing (2020, background): “On top, PISCES [46] removed any protein considered by its procedure to have > 20% PIDE.”
• Folding membrane proteins by deep transfer learning (2017, background): “So far there are more than 10,000 proteins in PDB25, a representative set of non-redundant proteins in PDB in which any two proteins share less than 25% sequence identity (Wang and Dunbrack, 2003).”
• ProteinNet: a standardized data set for machine learning of protein structure (2019, methodology): “otein Data Bank (PDB) (Bernstein et al., 1977) provide raw protein structures, but require postprocessing before they are usable by machine learning frameworks. Processed data sets such as CulledPDB (Wang and Dunbrack, 2003) provide a more standardized preparation of protein structures, but lack evo”
• Large-scale determination of previously unsolved protein structures using evolutionary information (2015, methodology): “To account for these dependencies, we constructed a model ( Figure 16 ) that estimates the probability of being in contact using a pdb30 data set from PISCES (resolution limited to 2.5A or better, from 04 January, 2014; [ Wang and Dunbrack, 2003 ]), with length of at least 100 residues.”
• A position-specific distance-dependent statistical potential for protein structure and functional study (2012, methodology): “We used the PDB25 set of the PISCES server (Wang and Dunbrack, 2003) early in 2011 as the training and validation data.”
• Energy-based models for atomic-resolution protein conformations (2020, methodology): “We constructed a curated dataset of high-resolution PDB structures using the CullPDB database, with the following criteria: resolution finer than 1.8 ˚A; sequence identity less than 90%; and R value less than 0.25 as defined in Wang & R. L. Dunbrack (2003).”