Protein tertiary structure prediction and refinement using deep learning and Rosetta in <scp>CASP14</scp>

Anishchenko, Ivan; Baek, Minkyung; Park, Hahnbeom; Hiranuma, Naozumi; Kim, David E.; Dauparas, Justas; Mansoor, Sanaa; Humphreys, Ian R.; Baker, David

doi:10.1002/prot.26194

Cited by 45 publications

(43 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 31 Smaller, but still useful, improvements were achieved by the BAKER protocol, which complemented Rosetta refinement with penalties for large residue‐pair distance error estimates. 32 …”

Section: Resultsmentioning

confidence: 99%

Assessing the utility of CASP14 models for molecular replacement

et al. 2021

View full text Add to dashboard Cite

The assessment of CASP models for utility in molecular replacement is a measure of their use in a valuable real-world application. In CASP7, the metric for molecular replacement assessment involved full likelihood-based molecular replacement searches; however, this restricted the assessable targets to crystal structures with only one copy of the target in the asymmetric unit, and to those where the search found the correct pose. In CASP10, full molecular replacement searches were replaced by likelihood-based rigid-body refinement of models superimposed on the target using the LGA algorithm, with the metric being the refined log-likelihood-gain (LLG) score. This enabled multi-copy targets and very poor models to be evaluated, but a significant further issue remained: the requirement of diffraction data for assessment. We introduce here the relative-expected-LLG (reLLG), which is independent of diffraction data. This reLLG is also independent of any crystal form, and can be calculated regardless of the source of the target, be it X-ray, NMR or cryo-EM.We calibrate the reLLG against the LLG for targets in CASP14, showing that it is a robust measure of both model and group ranking. Like the LLG, the reLLG shows that accurate coordinate error estimates add substantial value to predicted models. We find that refinement by CASP groups can often convert an inadequate initial model into a successful MR search model. Consistent with findings from others, we show that the AlphaFold2 models are sufficiently good, and reliably so, to surpass other current model generation strategies for attempting molecular replacement phasing.

show abstract

Section: Resultsmentioning

confidence: 99%

Assessing the utility of CASP14 models for molecular replacement

et al. 2021

View full text Add to dashboard Cite

show abstract

“…They all make use of deep learning and structure templates but with different approaches. BAKER‐ROSETTASERVER, with a released method named trRosetta2, [ 55 ] employs deep learning to refine the models generated by trRosetta; while trRosettaX focuses on improving the precision of inter‐residue geometries prediction by re‐designing the deep neural network architecture. We use the multi‐scale network Res2Net, instead of ResNet in trRosetta2.…”

Section: Resultsmentioning

confidence: 99%

Improved Protein Structure Prediction Using a New Multi‐Scale Network and Homologous Templates

Wang

et al. 2021

Advanced Science

View full text Add to dashboard Cite

The accuracy of de novo protein structure prediction has been improved considerably in recent years, mostly due to the introduction of deep learning techniques. In this work, trRosettaX, an improved version of trRosetta for protein structure prediction is presented. The major improvement over trRosetta consists of two folds. The first is the application of a new multi‐scale network, i.e., Res2Net, for improved prediction of inter‐residue geometries, including distance and orientations. The second is an attention‐based module to exploit multiple homologous templates to increase the accuracy further. Compared with trRosetta, trRosettaX improves the contact precision by 6% and 8% on the free modeling targets of CASP13 and CASP14, respectively. A preliminary version of trRosettaX is ranked as one of the top server groups in CASP14's blind test. Additional benchmark test on 161 targets from CAMEO (between Jun and Sep 2020) shows that trRosettaX achieves an average TM‐score ≈0.8, outperforming the top groups in CAMEO. These data suggest the effectiveness of using the multi‐scale network and the benefit of incorporating homologous templates into the network. The trRosettaX algorithm is incorporated into the trRosetta server since Nov 2020. The web server, the training and inference codes are available at: https://yanglab.nankai.edu.cn/trRosetta/.

show abstract

“…First, we modeled the structures of 25 FM/TBM and TBM-hard targets of CASP14. The average TM-score and lDDT score of the models were compared with those of the following server groups: FEIG-S [ 36 ], BAKER-ROSETTASERVER [ 37 ], Zhang-Server, and QUARK [ 38 ]. The model structures of the other groups were downloaded from the archive of the CASP14 website, and TM-score and lDDT scores were recalculated with the crystal structures and domain information for a fair comparison.…”

Section: Resultsmentioning

confidence: 99%

A-Prot: protein structure modeling using MSA transformer

Hong¹,

Lee

Ko³

2022

BMC Bioinformatics

View full text Add to dashboard Cite

Background The accuracy of protein 3D structure prediction has been dramatically improved with the help of advances in deep learning. In the recent CASP14, Deepmind demonstrated that their new version of AlphaFold (AF) produces highly accurate 3D models almost close to experimental structures. The success of AF shows that the multiple sequence alignment of a sequence contains rich evolutionary information, leading to accurate 3D models. Despite the success of AF, only the prediction code is open, and training a similar model requires a vast amount of computational resources. Thus, developing a lighter prediction model is still necessary. Results In this study, we propose a new protein 3D structure modeling method, A-Prot, using MSA Transformer, one of the state-of-the-art protein language models. An MSA feature tensor and row attention maps are extracted and converted into 2D residue-residue distance and dihedral angle predictions for a given MSA. We demonstrated that A-Prot predicts long-range contacts better than the existing methods. Additionally, we modeled the 3D structures of the free modeling and hard template-based modeling targets of CASP14. The assessment shows that the A-Prot models are more accurate than most top server groups of CASP14. Conclusion These results imply that A-Prot accurately captures the evolutionary and structural information of proteins with relatively low computational cost. Thus, A-Prot can provide a clue for the development of other protein property prediction methods.

show abstract

Protein tertiary structure prediction and refinement using deep learning and Rosetta in CASP14

Cited by 45 publications

References 36 publications

Assessing the utility of CASP14 models for molecular replacement

Assessing the utility of CASP14 models for molecular replacement

Improved Protein Structure Prediction Using a New Multi‐Scale Network and Homologous Templates

A-Prot: protein structure modeling using MSA transformer

Contact Info

Product

Resources

About