FoldRec-C2C: protein fold recognition by combining cluster-to-cluster model and protein similarity network

Abstract As a key for studying the protein structures, protein fold recognition is playing an important role in predicting the protein structures associated with COVID-19 and other important structures. However, the existing computational predictors only focus on the protein pairwise similarity or the similarity between two groups of proteins from 2-folds. However, the homology relationship among proteins is in a hierarchical structure. The global protein similarity network will contribute to the performance improvement. In this study, we proposed a predictor called FoldRec-C2C to globally incorporate the interactions among proteins into the prediction. For the FoldRec-C2C predictor, protein fold recognition problem is treated as an information retrieval task in nature language processing. The initial ranking results were generated by a surprised ranking algorithm Learning to Rank, and then three re-ranking algorithms were performed on the ranking lists to adjust the results globally based on the protein similarity network, including seq-to-seq model, seq-to-cluster model and cluster-to-cluster model (C2C). When tested on a widely used and rigorous benchmark dataset LINDAHL dataset, FoldRec-C2C outperforms other 34 state-of-the-art methods in this field. The source code and data of FoldRec-C2C can be downloaded from http://bliulab.net/FoldRec-C2C/download.

Download Full-text

Fold-LTR-TCP: protein fold recognition based on triadic closure principle

Briefings in Bioinformatics ◽

10.1093/bib/bbz139 ◽

2019 ◽

Vol 21 (6) ◽

pp. 2185-2193 ◽

Cited By ~ 22

Author(s):

Bin Liu ◽

Yulin Zhu ◽

Ke Yan

Keyword(s):

Learning To Rank ◽

Fold Recognition ◽

Query Protein ◽

Protein Fold ◽

Closure Principle ◽

Retrieval Task ◽

Ranking List ◽

Protein Fold Recognition ◽

Triadic Closure ◽

The Relationship

Abstract As an important task in protein structure and function studies, protein fold recognition has attracted more and more attention. The existing computational predictors in this field treat this task as a multi-classification problem, ignoring the relationship among proteins in the dataset. However, previous studies showed that their relationship is critical for protein homology analysis. In this study, the protein fold recognition is treated as an information retrieval task. The Learning to Rank model (LTR) was employed to retrieve the query protein against the template proteins to find the template proteins in the same fold with the query protein in a supervised manner. The triadic closure principle (TCP) was performed on the ranking list generated by the LTR to improve its accuracy by considering the relationship among the query protein and the template proteins in the ranking list. Finally, a predictor called Fold-LTR-TCP was proposed. The rigorous test on the LE benchmark dataset showed that the Fold-LTR-TCP predictor achieved an accuracy of 73.2%, outperforming all the other competing methods.

Download Full-text

NONSYMMETRIC TWO-BODY SCORE FUNCTION FOR PROTEIN FOLD RECOGNITION: NEXT NEAREST NEIGHBOR-ADJACENCY OF TWO AMINO ACIDS

International Journal of Modern Physics C ◽

10.1142/s0129183104006546 ◽

2004 ◽

Vol 15 (08) ◽

pp. 1087-1094

Author(s):

MUYOUNG HEO ◽

MOOKYUNG CHEON ◽

IKSOO CHANG

Keyword(s):

Amino Acids ◽

Nearest Neighbor ◽

Protein Structures ◽

Score Function ◽

Fold Recognition ◽

Protein Fold ◽

Score Functions ◽

Protein Fold Recognition ◽

Protein Threading ◽

Perceptron Learning

The usual two-body score (energy) function to recognize native folds of proteins is Miyazawa–Jernigan (MJ) pairwise-contact function. The pairwise-contact parameters between two amino acids in MJ function are symmetric in a sense that a directional order of amino acids sequence along the backbone of a protein is ignored in constructing score parameters. Here we report that we succeeded in constructing a nonsymmetric two-body score function, capturing a directional order of amino acids sequence, by a perceptron learning and a protein threading. We considered pairs of two adjacent amino acids that are separated by two consecutive peptide bonds with the backbone directionality from the N-terminus to the C-terminus of a protein. We also considered the local environmental character, such as the secondary structures and the hydrophobicity (solvation), of amino acids in protein structures. The score is a corresponding propensity for a directional alignment of these two adjacent amino acids with their local environments. The resulting score function simultaneously recognized native folds of 1006 proteins covering all representative proteins with a homology less than 30% among them. The quality of this score function was validated by a threading test of new distinct 382 proteins with a homology less than 90% among them, and it entailed a high success ratio for recognizing native folds of 364 (95.3%) proteins. It showed a good feasibility of designing protein score functions for protein fold recognition by a perceptron learning and a protein threading.

Download Full-text

From local structure to a global framework: recognition of protein folds

Journal of The Royal Society Interface ◽

10.1098/rsif.2013.1147 ◽

2014 ◽

Vol 11 (95) ◽

pp. 20131147 ◽

Cited By ~ 6

Author(s):

Agnel Praveen Joseph ◽

Alexandre G. de Brevern

Keyword(s):

Local Structure ◽

Structure Prediction ◽

Structural Information ◽

Protein Structures ◽

Fold Recognition ◽

Protein Fold ◽

Major Area ◽

Huge Amount ◽

Protein Fold Recognition ◽

Structural Environment

Protein folding has been a major area of research for many years. Nonetheless, the mechanisms leading to the formation of an active biological fold are still not fully apprehended. The huge amount of available sequence and structural information provides hints to identify the putative fold for a given sequence. Indeed, protein structures prefer a limited number of local backbone conformations, some being characterized by preferences for certain amino acids. These preferences largely depend on the local structural environment. The prediction of local backbone conformations has become an important factor to correctly identifying the global protein fold. Here, we review the developments in the field of local structure prediction and especially their implication in protein fold recognition.

Download Full-text