A deep dense inception network for protein beta‐turn prediction

Fang, Chao; Shang, Yi; Xu, Dong

doi:10.1002/prot.25780

Cited by 10 publications

(7 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This seems to be a very minor issue as these two states are highly similar, as (i) the repetitive secondary structure rules are identical and (2) the Cα–Cα distance threshold is always true when a hydrogen bond is present. In some papers, it is even considered as a unique state, e.g., “The beta-turn, which has also been referred to as the beta-bend, beta-loop or reverse turn” in [ 44 ]; they are always merged for prediction purposes [ 45 , 46 ].…”

Section: The Alpha and The Omega Of The βmentioning

confidence: 99%

A Perspective on the (Rise and Fall of) Protein β-Turns

Brevern

2022

IJMS

View full text Add to dashboard Cite

The β-turn is the third defined secondary structure after the α-helix and the β-sheet. The β-turns were described more than 50 years ago and account for more than 20% of protein residues. Nonetheless, they are often overlooked or even misunderstood. This poor knowledge of these local protein conformations is due to various factors, causes that I discuss here. For example, confusion still exists about the assignment of these local protein structures, their overlaps with other structures, the potential absence of a stabilizing hydrogen bond, the numerous types of β-turns and the software’s difficulty in assigning or visualizing them. I also propose some ideas to potentially/partially remedy this and present why β-turns can still be helpful, even in the AlphaFold 2 era.

show abstract

Section: The Alpha and The Omega Of The βmentioning

confidence: 99%

A Perspective on the (Rise and Fall of) Protein β-Turns

Brevern

2022

IJMS

View full text Add to dashboard Cite

show abstract

“…As observed from our results, the percentage of extended strands is lowest in the hyperthermophiles, followed by thermophiles and mesophiles, again confirming the high structural rigidity of the T. aquaticus origin GT. β-turns play an important role in mediating interactions between enzymes and their ligands/receptors, thus playing a great role in the functional activity of a protein [ 44 ]. In our study, it has been interestingly observed that though hyperthermophilic GT was highly stable and rigid in its conformation, mesophilic and thermophilic origin GTs demonstrated better plasticity.…”

Section: Resultsmentioning

confidence: 99%

Computational Study on Temperature Driven Structure–Function Relationship of Polysaccharide Producing Bacterial Glycosyl Transferase Enzyme

et al. 2021

View full text Add to dashboard Cite

Glycosyltransferase (GTs) is a wide class of enzymes that transfer sugar moiety, playing a key role in the synthesis of bacterial exopolysaccharide (EPS) biopolymer. In recent years, increased demand for bacterial EPSs has been observed in pharmaceutical, food, and other industries. The application of the EPSs largely depends upon their thermal stability, as any industrial application is mainly reliant on slow thermal degradation. Keeping this in context, EPS producing GT enzymes from three different bacterial sources based on growth temperature (mesophile, thermophile, and hyperthermophile) are considered for in silico analysis of the structural–functional relationship. From the present study, it was observed that the structural integrity of GT increases significantly from mesophile to thermophile to hyperthermophile. In contrast, the structural plasticity runs in an opposite direction towards mesophile. This interesting temperature-dependent structural property has directed the GT–UDP-glucose interactions in a way that thermophile has finally demonstrated better binding affinity (−5.57 to −10.70) with an increased number of hydrogen bonds (355) and stabilizing amino acids (Phe, Ala, Glu, Tyr, and Ser). The results from this study may direct utilization of thermophile-origin GT as best for industrial-level bacterial polysaccharide production.

show abstract

“…The observed gain derives from several factors, which include (i) the quantity of the available data on protein structures; (ii) the efficient protein sequence encoding; and (iii) the implementation and tuning of a deep learning model. In our method, each of these factors were chosen in accordance with the results reported for the similar problems of structural bioinformatics, such as secondary structure prediction [29][30][31][32] and flexibility prediction [8]. At the same time, the final network architecture as well as the combination of descriptors chosen for the sequence encoding are original and demonstrate the best results during model tuning.…”

Section: Discussionmentioning

confidence: 99%

PYTHIA: Deep Learning Approach for Local Protein Conformation Prediction

Cretin

Galochkina

Brevern

et al. 2021

IJMS

View full text Add to dashboard Cite

Protein Blocks (PBs) are a widely used structural alphabet describing local protein backbone conformation in terms of 16 possible conformational states, adopted by five consecutive amino acids. The representation of complex protein 3D structures as 1D PB sequences was previously successfully applied to protein structure alignment and protein structure prediction. In the current study, we present a new model, PYTHIA (predicting any conformation at high accuracy), for the prediction of the protein local conformations in terms of PBs directly from the amino acid sequence. PYTHIA is based on a deep residual inception-inside-inception neural network with convolutional block attention modules, predicting 1 of 16 PB classes from evolutionary information combined to physicochemical properties of individual amino acids. PYTHIA clearly outperforms the LOCUSTRA reference method for all PB classes and demonstrates great performance for PB prediction on particularly challenging proteins from the CASP14 free modelling category.

show abstract

A deep dense inception network for protein beta‐turn prediction

Cited by 10 publications

References 58 publications

A Perspective on the (Rise and Fall of) Protein β-Turns

A Perspective on the (Rise and Fall of) Protein β-Turns

Computational Study on Temperature Driven Structure–Function Relationship of Polysaccharide Producing Bacterial Glycosyl Transferase Enzyme

PYTHIA: Deep Learning Approach for Local Protein Conformation Prediction

Contact Info

Product

Resources

About