Large-scale structure prediction by improved contact predictions and model quality assessment
By Mirco Michel, David Ménendez Hurtado, Karolis Uziela, Arne Elofsson. 2017
34 citations recorded by the source corpus.
Motivation Accurate contact predictions can be used for predicting the structure of proteins. Until recently these methods were limited to very big protein families, decreasing their utility. However, recent progress by combining direct coupling analysis with machine learning methods has made it possible to predict accurate contact maps for smaller families. To what extent these predictions can be used to produce accurate models of the families is not known. Results We present the PconsFold2 pipeline that uses contact predictions from PconsC3, the CONFOLD folding algorithm and model quality estimations to predict the structure of a protein. We show that the model quality estimation significantly increases the number of models that reliably can be identified. Finally, we apply PconsFold2 to 6379 Pfam families of unknown structure and find that PconsFold2 can, with an estimated 90% specificity, predict the structure of up to 558 Pfam families of unknown structure. Out of these 415 have not been reported before. Availability Datasets as well as models of all the 558 Pfam families are available at http://c3.pcons.net/. All programs used here are freely available. Contact arne@bioinfo.se Supplementary information No supplementary data
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
- Badri Adhikari
- Jianlin Cheng
- Jie Hou
- David Ménendez Hurtado
- David T. Jones
- Arne Elofsson
- Shaun M. Kandathil
- Joe G. Greener
In Molecular Biology
- Badri Adhikari
- Jianlin Cheng
- David T. Jones
- Joe G. Greener
- Arne Elofsson
- Shaun M. Kandathil
- David Ménendez Hurtado
- Jie Hou
Citations in the corpus
- DNCON2: improved protein contact prediction using two-level deep convolutional neural networks (2017, background): “In recent years, protein residue–residue contacts have been identified as a key feature for accurate de novo protein structure prediction (Jones, 2001; Mabrouk et al. , 2016; Marks et al. , 2012; Michel et al. , 2014, 2017a).”
- PconsC4: fast, free, easy, and accurate contact predictions (2018, methodology): “One validation set is identical to the benchmark set in PconsC3 (Michel et al. , 2017b).”
- Ultrafast end-to-end protein structure prediction enables high-throughput exploration of uncharacterized proteins (2022, unknown): “To date, only a few published methods attempt to use an encoding of the MSA itself as the input to a neural network-based predictor of protein structural features.”
- CONFOLD2: improved contact-driven ab initio protein structure modeling (2017, methodology): “Methods that can build models faster and are more residue contact sensitive are needed to realize the promise of ab initio protein structure prediction driven by the recent advances in contact prediction [1, 2].”
- Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints (2018, background): “A number of previous studies have also done this [13,19,20], so this represents a good indication of how effective deep learning is on an important structural biology problem.”