ComplexContact: a web server for inter-protein contact prediction using deep learning
By Hong Zeng, Sheng Wang, Tian-Ming Zhou, Feifeng Zhao, Xiufeng Li, Qing Wu, Jinbo Xu. 2018
124 citations recorded by the source corpus.
Abstract ComplexContact (http://raptorx2.uchicago.edu/ComplexContact/) is a web server for sequence-based interfacial residue-residue contact prediction of a putative protein complex. Interfacial residue-residue contacts are critical for understanding how proteins form complex and interact at residue level. When receiving a pair of protein sequences, ComplexContact first searches for their sequence homologs and builds two paired multiple sequence alignments (MSA), then it applies co-evolution analysis and a CASP-winning deep learning (DL) method to predict interfacial contacts from paired MSAs and visualizes the prediction as an image. The DL method was originally developed for intra-protein contact prediction and performed the best in CASP12. Our large-scale experimental test further shows that ComplexContact greatly outperforms pure co-evolution methods for inter-protein contact prediction, regardless of the species.
Subfields: Materials Chemistry, Molecular Biology
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
- Brian G. Pierce
- Sai Pooja Mahajan
- Pushmeet Kohli
- Jeffrey J. Gray
- Chen Chen
- Wenhao Gao
- Jeremias Sulam
- Jianlin Cheng
In Molecular Biology
- Brian G. Pierce
- Sai Pooja Mahajan
- Jeffrey J. Gray
- Rui Yin
- Amitabh Varshney
- Brandon Yushan Feng
- Jason Yim
- Pushmeet Kohli
Citations in the corpus
- Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants (2021, methodology): “28,43,44 MSAs with paired sequences were obtained from the ColabFold Google Colab site (on September 4, 2021); 29 these sequence pairs were generated with an automated algorithm intended for prokaryotic proteins, thus a set of 17 cases from BM5.”
- Deep Learning in Protein Structural Modeling and Design (2020, background): “Unlike those starting from the unbound structures, Zeng et al.172 reuse the model trained on single-chain proteins (i.e., RaptorX-Contact) to predict PPI with sequence information alone, which resulted in the RaptorX-Complex that outperforms ECA-based methods at contact prediction.”
- Protein complex prediction with AlphaFold-Multimer (2021, methodology): “Various heuristic methods exist to perform this pairing [27, 28, 29, 12].”
- Geometric Transformers for Protein Interface Contact Prediction (2021, methodology): “…we have included the methods BIPSPI (an XGBoost-based algorithm) (Sanchez-Garcia et al. (2018)), DeepHomo (a CNN for homodimers) (Yan & Huang Published as a conference paper at ICLR 2022 2018)) since they are either easy to reproduce or simple for the general public to use to make predictions.”