I-TASSER: Fully automated protein structure prediction in CASP8

By Yang Zhang. 2009

461 citations recorded by the source corpus.

The I‐TASSER algorithm for 3D protein structure prediction was tested in CASP8, with the procedure fully automated in both the Server and Human sections. The quality of the server models is close to that of human ones but the human predictions incorporate more diverse templates from other servers which improve the human predictions in some of the distant homology targets. For the first time, the sequence‐based contact predictions from machine learning techniques are found helpful for both template‐based modeling (TBM) and template‐free modeling (FM). In TBM, although the accuracy of the sequence based contact predictions is on average lower than that from template‐based ones, the novel contacts in the sequence‐based predictions, which are complementary to the threading templates in the weakly or unaligned regions, are important to improve the global and local packing in these regions. Moreover, the newly developed atomic structural refinement algorithm was tested in CASP8 and found to improve the hydrogen‐bonding networks and the overall TM‐score, which is mainly due to its ability of removing steric clashes so that the models can be generated from cluster centroids. Nevertheless, one of the major issues of the I‐TASSER pipeline is the model selection where the best models could not be appropriately recognized when the correct templates are detected only by the minority of the threading algorithms. There are also problems related with domain‐splitting and mirror image recognition which mainly influences the performance of I‐TASSER modeling in the FM‐based structure predictions. Proteins 2009. © 2009 Wiley‐Liss, Inc.

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

In Molecular Biology

Citations in the corpus

Evaluation of residue-residue contact predictions in CASP9 (2011, background): “43 Similarly to previous CASPs, targets for residue contact prediction were limited to the FM and TBM/FM domains, because in the case of closer homology, contacts can easily be derived from templates.”
Protein Structure and Function Prediction Using I-TASSER (2015, methodology): “The I-TASSER protocol (with the group name “Zhang-Server”) was ranked as the top server for automated protein structure prediction in the 7th to 11th CASP competitions (Zhang, 2007; Zhang, 2009; Xu et al., 2011; Zhang, 2014).”
Atomic-level protein structure refinement using fragment guided molecular dynamics conformation sampling (2011, methodology): “…for removing steric clashes, MD simulations without restraints often drive the structure away from the native state, especially when relaxing the overly compact structural models, such as the structures constructed by the recombination of multiple homologous templates (Zhang, 2007, 2009b).”
I-TASSER: a unified platform for automated protein structure and function prediction (2010, methodology): “is one example of the composite approaches and has been ranked as the best method for the automated protein structure prediction in the last two CASP experiment”
Recognizing protein substructure similarity using segmental threading. (2010, methodology): “, 1997), or excising structural fragments from whole-chain threading alignments (Wu et al., 2007; Zhang, 2009; Zhang and Skolnick, 2004a), or constructing substructures by ab initio modeling (Zhou and Skolnick, 2007), or threading sequences from a predetermined substructure library (Bjorkholm et al.”
Interplay of I-TASSER and QUARK for template-based and ab initio protein structure prediction in CASP10 (2013, methodology): “16 There are several other advancements of the I-TASSER pipelines which have been discussed in detail in previous CASP reports12,19,20 but not in this report although they have critical importance to the success of our structure modeling in CASP10.”
Template-based and free modeling of I-TASSER and QUARK pipelines using predicted contact maps in CASP12 (2017, background): “to select the consensus but less accurate models for these targets, an issue which has been extensively discussed in the previous CASP studies.(13,16,49) Here these data highlight again the remarkable gap that the current model ranking process remains to fill up.”
CASP9 Assessment of Free Modeling Target Predictions (2011, methodology): “With these definitions, QCS simplifies the target and the model, respectively, into a set of SSE vectors and several key contacts, which allows direct comparison between the target and the model for the following four global features: (1) the correct prediction of SSE boundaries measured by the leng”
Automated protein structure modeling in CASP9 by I-TASSER pipeline combined with QUARK-based ab initio folding and FG-MD-based structure refinement (2011, methodology): “In view of these major difficulties in the field and especially the issues of the I-TASSER pipeline as reflected in the previous CASP experiments,13,25 we have been working on the development of two types of methods.”
Improving protein structure prediction using multiple sequence-based contact predictions. (2011, background): “The accuracy of the contact prediction can be very high when closely homologous templates are identified, which has been shown to be extremely useful for highresolution template-based protein structure prediction (Raman et al., 2009; Sali and Blundell, 1993; Zhang, 2009).”