Protein structure prediction in the deep learning era

Peng, Zhenling; Wang, Wenkai; Han, Renmin; Zhang, Fa

doi:10.1016/j.sbi.2022.102495

Cited by 20 publications

(11 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As also stated by Peng et al Peng et al. ( 2022 ), there are proteins in which deep learning based methods relying on MSA information present poor predictions, such as proteins from viruses without homologous sequences in genetic databases, which is the case of the last example with a protein of the SARS-CoV-2 virus. In this sense, a work to be done will be an analysis of the correlation between the quality of the MSA information and the confidence of the prediction using a large number of proteins.…”

Section: Discussionmentioning

confidence: 92%

“…However, deep learning-based methods cannot provide different predicted structures for proteins mutated in a few amino acids, as discussed in Buel and Walters ( 2022 ); Callaway ( 2022 ); Peng et al. ( 2022 ). Moreover, predictions with deep learning schemes present solutions with high energy, in most cases due to conflicts between atoms in the side chains.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Protein structure prediction with energy minimization and deep learning approaches

2023

View full text Add to dashboard Cite

In this paper we discuss the advantages and problems of two alternatives for ab initio protein structure prediction. On one hand, recent approaches based on deep learning, which have significantly improved prediction results for a wide variety of proteins, are discussed. On the other hand, methods based on protein conformational energy minimization and with different search strategies are analyzed. In this latter case, our methods based on a memetic combination between differential evolution and the fragment replacement technique are included, incorporating also the possibility of niching in the evolutionary search. Different proteins have been used to analyze the pros and cons in both approaches, proposing possibilities of integration of both alternatives.

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Discussionmentioning

confidence: 99%

Protein structure prediction with energy minimization and deep learning approaches

2023

View full text Add to dashboard Cite

show abstract

“…The major reason for using the energy minimization step is to reduce the complexity of the network training, so that we could implement the algorithm under limited computer hardware condition. Tests on the CASP14 targets suggest that trRX2 outperforms RoseTTAFold and has comparable accuracy to AF2 1 . More details about the trRX2 methodology and benchmark results will be published elsewhere (Wang et al, in preparation).…”

Section: Methodsmentioning

confidence: 99%

“…Tests on the CASP14 targets suggest that trRX2 outperforms RoseTTAFold and has comparable accuracy to AF2. 1 More details about the trRX2 methodology and benchmark results will be published elsewhere (Wang et al, in preparation).…”

Section: Trrosettax2mentioning

confidence: 99%

“…The accuracy of protein structure prediction has reached an unprecedented level due to the development of artificial intelligence (AI) algorithms, the accumulation of big protein sequence/structure data, and the advance of hardware 1 . The major methods for protein structure prediction are shifting from template‐based modeling (e.g., I‐TASSER 2 ) and fragment assembly (e.g., Rosetta 3 ) to AI‐based prediction (e.g., AlphaFold2, 4 RoseTTAFold, 5 and trRosetta 6 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved protein structure prediction with trRosettaX2, AlphaFold2, and optimized MSAs in CASP15

et al. 2023

Self Cite

View full text Add to dashboard Cite

We present the monomer and multimer structure prediction results of our methods in CASP15. We first designed an elaborate pipeline that leverages complementary sequence databases and advanced database searching algorithms to generate high‐quality multiple sequence alignments (MSAs). Top MSAs were then selected for the subsequent step of structure prediction. We utilized trRosettaX2 and AlphaFold2 for monomer structure prediction (group name Yang‐Server), and AlphaFold‐Multimer for multimer structure prediction (group name Yang‐Multimer). Yang‐Server and Yang‐Multimer are ranked at the top and the fourth, respectively, for monomer and multimer structure prediction. For 94 monomers, the average TM‐score of the predicted structure models by Yang‐Server is 0.876, compared to 0.798 by the default AlphaFold2 (i.e., the group NBIS‐AF2‐standard). For 42 multimers, the average DockQ score of the predicted structure models by Yang‐Multimer is 0.464, compared to 0.389 by the default AlphaFold‐Multimer (i.e., the group NBIS‐AF2‐multimer). Detailed analysis of the results shows that several factors contribute to the improvement, including improved MSAs, iterated modeling for large targets, interplay between monomer and multimer structure prediction for intertwined structures, etc. However, the structure predictions for orphan proteins and multimers remain challenging, and breakthroughs in this area are anticipated in the future.

show abstract

An efficient and accurate approach to identify similarities between biological sequences using pair amino acid composition and physicochemical properties

Hooshyar,

Hernández-Jiménez,

Khastan

et al. 2024

Soft Comput

View full text Add to dashboard Cite

Protein structure prediction in the deep learning era

Cited by 20 publications

References 43 publications

Protein structure prediction with energy minimization and deep learning approaches

Protein structure prediction with energy minimization and deep learning approaches

Improved protein structure prediction with trRosettaX2, AlphaFold2, and optimized MSAs in CASP15

An efficient and accurate approach to identify similarities between biological sequences using pair amino acid composition and physicochemical properties

Contact Info

Product

Resources

About