Based on the research of predictingβ-hairpin motifs in proteins, we apply Random Forest and Support Vector Machine algorithm to predictβ-hairpin motifs in ArchDB40 dataset. The motifs with the loop length of 2 to 8 ...Based on the research of predictingβ-hairpin motifs in proteins, we apply Random Forest and Support Vector Machine algorithm to predictβ-hairpin motifs in ArchDB40 dataset. The motifs with the loop length of 2 to 8 amino acid residues are extracted as research object and thefixed-length pattern of 12 amino acids are selected. When using the same characteristic parameters and the same test method, Random Forest algorithm is more effective than Support Vector Machine. In addition, because of Random Forest algorithm doesn’t produce overfitting phenomenon while the dimension of characteristic parameters is higher, we use Random Forest based on higher dimension characteristic parameters to predictβ-hairpin motifs. The better prediction results are obtained;the overall accuracy and Matthew’s correlation coefficient of 5-fold cross-validation achieve 83.3% and 0.59, respectively.展开更多
Five hybrid tetrapeptides,each consisting a central dipeptide segment ofα-amino acid residues flanked by two aromaticγ-amino acid residues,are found to fold into well-definedβ-hairpin conformations as shown by NMR,...Five hybrid tetrapeptides,each consisting a central dipeptide segment ofα-amino acid residues flanked by two aromaticγ-amino acid residues,are found to fold into well-definedβ-hairpin conformations as shown by NMR,computational study,and X-ray structures.The turn loop of thisβ-hairpin motif accommodates different two-residueα-amino acid sequences from the highly flexible Gly-Gly,to the more restricted D-Pro-Gly.The presence ofα-amino acid side chains enhances the stabilities of theβ-hairpins with the exception of D-Pro-Gly-which results in destabilization.Based on this hairpin/turn motif,a variety of different dipeptide sequences ofα-amino acids which rarely occur inβ-turns can be introduced and presented as two-residue loops.展开更多
A poly-L β-hairpin bent stereochemically as a boat-shaped protein of mixed-L,D structure is scrutinized in basis of ordering as minimum of energy specific for its sequenceand solvent. The model suitable for the scrut...A poly-L β-hairpin bent stereochemically as a boat-shaped protein of mixed-L,D structure is scrutinized in basis of ordering as minimum of energy specific for its sequenceand solvent. The model suitable for the scrutiny is accomplished by design. A terminally-blocked oligoalanine is nucleated overDPro6-Gly7 and DPro6-LAsp7 dipeptide structures as a twelve-residue β-hairpin and bent stereochemically as a boat-shaped fold. The structure is inverse designed with side chains suitable to bind substrate p-nitophenyl phosphate, a surrogate substrate of acetyl choline and CO2. The designed sequences were proven by spectroscopy and molecular dynamics to order with solvent effects of water and display high binding affinity for the substrate. One of the proteins and a cognate oligoalanine are evolved with molecular dynamics to equilibrium in a solvent bath of water. Molecular dynamics studies establish that heteropolypeptide well ordered as β-hairpin fold and cognate oligoalanine as an ensemble of hairpin-like folds in water. The ordering of cognate oligoalanine as ensembles of hairpin-like folds manifests combined role of water as strong dielectric and weak dipolar solvent of peptides. The roles of stereochemistry and chemical details of sequence in defining polypeptides as energy minima under specific effect of solvent are illuminated and have been discussed.展开更多
文摘Based on the research of predictingβ-hairpin motifs in proteins, we apply Random Forest and Support Vector Machine algorithm to predictβ-hairpin motifs in ArchDB40 dataset. The motifs with the loop length of 2 to 8 amino acid residues are extracted as research object and thefixed-length pattern of 12 amino acids are selected. When using the same characteristic parameters and the same test method, Random Forest algorithm is more effective than Support Vector Machine. In addition, because of Random Forest algorithm doesn’t produce overfitting phenomenon while the dimension of characteristic parameters is higher, we use Random Forest based on higher dimension characteristic parameters to predictβ-hairpin motifs. The better prediction results are obtained;the overall accuracy and Matthew’s correlation coefficient of 5-fold cross-validation achieve 83.3% and 0.59, respectively.
基金supported by the National Natural Science Foundation of China(No.21778012 to Z.L.Lu,21801020 to R.Liu)the American Chemical Society–Petroleum Research Fund(PRF#58364-ND7,to B.Gong)+1 种基金the Center for Computational Research(CCR)(to D.P.Miller and E.Zurek)Hofstra University(to D.P.Miller)。
文摘Five hybrid tetrapeptides,each consisting a central dipeptide segment ofα-amino acid residues flanked by two aromaticγ-amino acid residues,are found to fold into well-definedβ-hairpin conformations as shown by NMR,computational study,and X-ray structures.The turn loop of thisβ-hairpin motif accommodates different two-residueα-amino acid sequences from the highly flexible Gly-Gly,to the more restricted D-Pro-Gly.The presence ofα-amino acid side chains enhances the stabilities of theβ-hairpins with the exception of D-Pro-Gly-which results in destabilization.Based on this hairpin/turn motif,a variety of different dipeptide sequences ofα-amino acids which rarely occur inβ-turns can be introduced and presented as two-residue loops.
文摘A poly-L β-hairpin bent stereochemically as a boat-shaped protein of mixed-L,D structure is scrutinized in basis of ordering as minimum of energy specific for its sequenceand solvent. The model suitable for the scrutiny is accomplished by design. A terminally-blocked oligoalanine is nucleated overDPro6-Gly7 and DPro6-LAsp7 dipeptide structures as a twelve-residue β-hairpin and bent stereochemically as a boat-shaped fold. The structure is inverse designed with side chains suitable to bind substrate p-nitophenyl phosphate, a surrogate substrate of acetyl choline and CO2. The designed sequences were proven by spectroscopy and molecular dynamics to order with solvent effects of water and display high binding affinity for the substrate. One of the proteins and a cognate oligoalanine are evolved with molecular dynamics to equilibrium in a solvent bath of water. Molecular dynamics studies establish that heteropolypeptide well ordered as β-hairpin fold and cognate oligoalanine as an ensemble of hairpin-like folds in water. The ordering of cognate oligoalanine as ensembles of hairpin-like folds manifests combined role of water as strong dielectric and weak dipolar solvent of peptides. The roles of stereochemistry and chemical details of sequence in defining polypeptides as energy minima under specific effect of solvent are illuminated and have been discussed.
