Template-based and free modeling of I-TASSER and QUARK pipelines using predicted contact maps in CASP12

By Chengxin Zhang, S. Mortuza, Baoji He, Yanting Wang, Yang Zhang. 2017

88 citations recorded by the source corpus.

We develop two complementary pipelines, “Zhang‐Server” and “QUARK”, based on I‐TASSER and QUARK pipelines for template‐based modeling (TBM) and free modeling (FM), and test them in the CASP12 experiment. The combination of I‐TASSER and QUARK successfully folds three medium‐size FM targets that have more than 150 residues, even though the interplay between the two pipelines still awaits further optimization. Newly developed sequence‐based contact prediction by NeBcon plays a critical role to enhance the quality of models, particularly for FM targets, by the new pipelines. The inclusion of NeBcon predicted contacts as restraints in the QUARK simulations results in an average TM‐score of 0.41 for the best in top five predicted models, which is 37% higher than that by the QUARK simulations without contacts. In particular, there are seven targets that are converted from non‐foldable to foldable (TM‐score >0.5) due to the use of contact restraints in the simulations. Another additional feature in the current pipelines is the local structure quality prediction by ResQ, which provides a robust residue‐level modeling error estimation. Despite the success, significant challenges still remain in ab initio modeling of multi‐domain proteins and folding of β‐proteins with complicated topologies bound by long‐range strand‐strand interactions. Improvements on domain boundary and long‐range contact prediction, as well as optimal use of the predicted contacts and multiple threading alignments, are critical to address these issues seen in the CASP12 experiment.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

1. Mohammed Alquraishi
2. Robin Pearce
3. Yang Zhang
4. Pushmeet Kohli
5. David Silver
6. Karen Simonyan

In Materials Chemistry

1. Robin Pearce
2. Yang Zhang
3. Chengxin Zhang
4. Yang Li
5. Wei Zheng
6. Mohammed Alquraishi
7. David T. Jones
8. Eric W. Bell

In Molecular Biology

1. Robin Pearce
2. Yang Zhang
3. Chengxin Zhang
4. Yang Li
5. Eric W. Bell
6. Wei Zheng
7. David T. Jones
8. Mohammed Alquraishi

Citations in the corpus

• End-to-end differentiable learning of protein structure (2018, methodology): “Diagram ismodeled on the I-Tasser and Quark pipelines (Zhang et al., 2018).”
• Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13) (2019, methodology): “Fragment-insertion-based simulated annealing has previously been used 6,15,27,34 to predict protein structure.”
• Deep learning methods in protein structure prediction (2020, methodology): “lem [92], heuristic methods have been devised to solve it approximately [89,93,94] and optimised for computational efficiency [90].”
• Deep learning techniques have significantly impacted protein structure prediction and protein design. (2021, methodology): “Both QUARK and Rosetta have demonstrated excellent performance in the FM section of the CASP experiment by successfully folding protein targets that lack identifiable homology templates [16 ,17,18].”
• Folding non-homologous proteins by coupling deep-learning contact maps with I-TASSER assembly simulations (2021, background): “It is important to note that sequence-based contact-map predictions have been of little to no use for TBM until the most recent CASP experiments (Kryshtafovych et al., 2018; Zhang et al., 2018).”