Using Neural Network Predicted Secondary Structure Information in Automatic Protein NMR Assignment

In CAPRI, an automated NMR assignment software package that was developed in our laboratory, both chemical shift values and coupling topologies of spin patterns are used in a procedure for amino acids recognition. By using a knowledge base of chemical shift distributions of the 20 amino acid types, fuzzy mathematics, and pattern recognition theory, the spin coupling topological graphs are mapped onto specific amino acid residues. In this work, we investigated the feasibility of using secondary structure information of proteins as predicted by neural networks in the automated NMR assignment. As the 1H and 13C chemical shifts of proteins are known to correlate to their secondary structures, secondary structure information is useful in improving the amino acid recognition. In this study, the secondary structures of proteins predicted by the PHD protein server and our own trained neural networks are used in the amino acid type recognition. The results show that the predicted secondary structure information can help to improve the accuracy of the amino acid recognition.

[1]  The NMR solution structure of the pheromone Er‐2 from the ciliated protozoan Euplotes raikovi , 1994 .

[2]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[3]  S. Choung,et al.  Complex formation of peptide antibiotic Ro09-0198 with lysophosphatidylethanolamine: 1H NMR analyses in dimethyl sulfoxide solution. , 1990, Biochemistry.

[4]  M Ottiger,et al.  The NMR solution structure of the pheromone Er‐2 from the ciliated protozoan Euplotes raikovi , 1994, Protein science : a publication of the Protein Society.

[5]  K. Wüthrich,et al.  The secondary structure of the toxin ATX Ia from Anemonia sulcata in aqueous solution determined on the basis of complete sequence-specific 1H-NMR assignments. , 1988, European Journal of Biochemistry.

[6]  G. Wagner,et al.  Toward the complete assignment of the carbon nuclear magnetic resonance spectrum of the basic pancreatic trypsin inhibitor. , 1986, Biochemistry.

[7]  A M Gronenborn,et al.  Assignment of the side-chain 1H and 13C resonances of interleukin-1 beta using double- and triple-resonance heteronuclear three-dimensional NMR spectroscopy. , 1990, Biochemistry.

[8]  R. Ogden,et al.  Construction of a synthetic gene for an R-plasmid-encoded dihydrofolate reductase and studies on the role of the N-terminus in the protein. , 1991, Biochemistry.

[9]  T. Logan,et al.  1H,13C and 15N backbone assignments of cyclophilin when bound to cyclosporin A (CsA) and preliminary structural characterization of the CsA binding site , 1991, FEBS letters.

[10]  S. Rackovsky,et al.  Protein sequence randomness and sequence/structure correlations. , 1995, Biophysical journal.

[11]  J H Prestegard,et al.  Secondary structure of acyl carrier protein as derived from two-dimensional 1H NMR spectroscopy. , 1986, Biochemistry.

[12]  J. Neira,et al.  Sequential 1H-NMR assignment and solution structure of bovine pancreatic ribonuclease A. , 1989, European journal of biochemistry.

[13]  T. Pochapsky,et al.  1H NMR identification of a beta-sheet structure and description of folding topology in putidaredoxin. , 1991, Biochemistry.

[14]  K. Wüthrich,et al.  Determination of the nuclear magnetic resonance structure of the DNA-binding domain of the P22 c2 repressor (1 to 76) in solution and comparison with the DNA-binding domain of the 434 repressor. , 1994, Journal of molecular biology.

[15]  Jun Xu,et al.  Automated extraction of spin coupling topologies from 2D NMR correlation spectra for protein proton resonance assignment , 1993, Journal of chemical information and computer sciences.

[16]  B. Rost,et al.  Prediction of protein secondary structure at better than 70% accuracy. , 1993, Journal of molecular biology.

[17]  S. Mandrup,et al.  The secondary structure in solution of acyl-coenzyme A binding protein from bovine liver using 1H nuclear magnetic resonance spectroscopy. , 1991, Biochemistry.

[18]  N. Go,et al.  Structure of melittin bound to perdeuterated dodecylphosphocholine micelles as studied by two-dimensional NMR and distance geometry calculations , 1989 .

[19]  Jun Xu,et al.  CPA: Constrained partitioning algorithm for initial assignment of protein proton resonances from MQF-COSY , 1993, J. Chem. Inf. Comput. Sci..

[20]  A. Wand,et al.  1H and 15N NMR resonance assignments and preliminary structural characterization of Escherichia coli apocytochrome b562. , 1991, Biochemistry.

[21]  A. Padilla,et al.  Two-dimensional 1H nuclear magnetic resonance study of pike pI 5.0 parvalbumin (Esox lucius). Sequential resonance assignments and folding of the polypeptide chain. , 1988, Journal of molecular biology.

[22]  Scott E. Fahlman,et al.  An empirical study of learning speed in back-propagation networks , 1988 .

[23]  F. Richards,et al.  Relationship between nuclear magnetic resonance chemical shift and protein secondary structure. , 1991, Journal of molecular biology.

[24]  K. Constantine,et al.  Sequence-specific 1H NMR assignments and structural characterization of bovine seminal fluid protein PDC-109 domain b. , 1991, Biochemistry.

[25]  I. Campbell,et al.  1H NMR assignment and secondary structure of the cell adhesion type III module of fibronectin. , 1992, Biochemistry.

[26]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[27]  I. Campbell,et al.  Secondary structure of a complement control protein module by two-dimensional 1H NMR. , 1991, Biochemistry.

[28]  M. Summers,et al.  Determinants of protein hyperthermostability: purification and amino acid sequence of rubredoxin from the hyperthermophilic archaebacterium Pyrococcus furiosus and secondary structure of the zinc adduct by NMR. , 1991, Biochemistry.

[29]  L. Chiche,et al.  1H 2D NMR and distance geometry study of the folding of Ecballium elaterium trypsin inhibitor, a member of the squash inhibitors family. , 1989, Biochemistry.

[30]  Y. Kyōgoku,et al.  1H-NMR assignment and secondary structure of human insulin-like growth factor-I (IGF-I) in solution. , 1992, Journal of Biochemistry (Tokyo).

[31]  R. van Grondelle,et al.  Study of the binding of single-stranded DNA-binding protein to DNA and poly(rA) using electric field induced birefringence and circular dichroism spectroscopy. , 1990, Biochemistry.

[32]  Three-dimensional 15N-1H-1H and 15N-13C-1H nuclear-magnetic resonance studies of HPr a central component of the phosphoenolpyruvate-dependent phosphotransferase system from Escherichia coli. Assignment of backbone resonances. , 1992, European journal of biochemistry.

[33]  Cbrister,et al.  Empirical Correlation between Protein Backbone Conformation and Ca and C @ 13 C Nuclear Magnetic Resonance Chemical Shifts , 2022 .

[34]  Kathryn M. Murphy,et al.  Bilateral amblyopia after a short period of reverse occlusion in kittens , 1986, Nature.

[35]  R. M. Justice,et al.  Complete sequence-specific 1H NMR assignments for human insulin. , 1990, Biochemistry.

[36]  A. Arseniev,et al.  Sequence-specific resonance assignment and secondary structure of (1–71) bacterioopsin , 1992, Journal of biomolecular NMR.

[37]  H. Nakamura,et al.  Assignments of backbone 1H, 13C, and 15N resonances and secondary structure of ribonuclease H from Escherichia coli by heteronuclear three-dimensional NMR spectroscopy. , 1991, Biochemistry.

[38]  L. Kay,et al.  A novel approach for sequential assignment of proton, carbon-13, and nitrogen-15 spectra of larger proteins: heteronuclear triple-resonance three-dimensional NMR spectroscopy. Application to calmodulin , 1990 .

[39]  R. J. Williams,et al.  Identification and description of beta-structure in horse muscle acylphosphatase by nuclear magnetic resonance spectroscopy. , 1989, Journal of molecular biology.

[40]  K Wüthrich,et al.  Sequential resonance assignments in protein 1H nuclear magnetic resonance spectra. Glucagon bound to perdeuterated dodecylphosphocholine micelles. , 1982, Journal of molecular biology.

[41]  N. C. Veitch,et al.  An analysis of pseudocontact shifts and their relationship to structural features of the redox states of cytochrome b 5 , 1990, FEBS letters.

[42]  W. Kabsch,et al.  Dictionary of protein secondary structure: Pattern recognition of hydrogen‐bonded and geometrical features , 1983, Biopolymers.

[43]  M. Billeter,et al.  Sequence-specific 1H n.m.r. assignments and determination of the three-dimensional structure of reduced Escherichia coli glutaredoxin. , 1991, Journal of molecular biology.

[44]  Kuo-Bin Li,et al.  Automated Extracting of Amino Acid Spin Systems in Proteins Using 3D HCCH-COSY/TOCSY Spectroscopy and Constrained Partitioning Algorithm (CPA) , 1996, J. Chem. Inf. Comput. Sci..

[45]  K Wüthrich,et al.  Complete sequence-specific 1H nuclear magnetic resonance assignments for the alpha-amylase polypeptide inhibitor tendamistat from Streptomyces tendae. , 1986, Journal of molecular biology.

[46]  A. Arseniev,et al.  Sequence-specific 1H-NMR assignment and conformation of proteolytic fragment 163-231 of bacterioopsin. , 1990, European journal of biochemistry.

[47]  T. King,et al.  Preparation of protein conjugates via intermolecular hydrazone linkage. , 1986, Biochemistry.

[48]  A. Bax,et al.  Empirical correlation between protein backbone conformation and C.alpha. and C.beta. 13C nuclear magnetic resonance chemical shifts , 1991 .

[49]  László Szilágyi,et al.  Chemical shifts in proteins come of age , 1995 .

[50]  Jun Xu,et al.  Automation of protein 2D proton NMR assignment by means of fuzzy mathematics and graph theory , 1993, J. Chem. Inf. Comput. Sci..

[51]  S. Straus,et al.  Use of fuzzy mathematics for complete automated assignment of peptide 1H 2D NMR spectra. , 1994, Journal of Magnetic Resonance - Series B.

[52]  S. Brown,et al.  1H NMR assignment and secondary structural elements of human transforming growth factor alpha. , 1989, Biochemistry.

[53]  M. Llinás,et al.  Kringle-2 domain of the tissue-type plasminogen activator. 1H-NMR assignments and secondary structure. , 1991, European journal of biochemistry.

[54]  K Wüthrich,et al.  Nuclear magnetic resonance spectroscopy of a DNA complex with the uniformly 13C-labeled Antennapedia homeodomain and structure determination of the DNA-bound homeodomain. , 1993, Journal of molecular biology.

[55]  R. Woodworth,et al.  Mössbauer spectroscopy of iron-ovotransferrin: a crystal field interpretation. , 1991, Biochemistry.

[56]  P Argos,et al.  A sensitive procedure to compare amino acid sequences. , 1987, Journal of molecular biology.

[57]  S. Hyberts,et al.  Stereospecific assignments of side-chain protons and characterization of torsion angles in Eglin c. , 1987, European journal of biochemistry.

[58]  B. Oh,et al.  14,15N, 13C, 57Fe, and 1,2H Q-band ENDOR study of Fe-S proteins with clusters that have endogenous sulfur ligands. , 1992, Biochemistry.

[59]  R. Norton,et al.  Sequence-specific 1H NMR assignments and secondary structure in the sea anemone polypeptide Stichodactyla helianthus neurotoxin I. , 1989, Biochemistry.

[60]  E. Laue,et al.  Sequence-specific 1H-NMR assignments and secondary structure of the lipoyl domain of the Bacillus stearothermophilus pyruvate dehydrogenase multienzyme complex. , 1991, European journal of biochemistry.

[61]  M. Kretschmer,et al.  Yeast 6-phosphofructo-2-kinase: sequence and mutant. , 1991, Biochemistry.

[62]  C. Sander,et al.  Database of homology‐derived protein structures and the structural meaning of sequence alignment , 1991, Proteins.

[63]  K. Wüthrich,et al.  Biosynthetic 15N and 13C isotope labelling of glutathione in the mixed disulfide with Escherichia coli glutaredoxin documented by sequence-specific NMR assignments. , 1993, European journal of biochemistry.

[64]  R. Meadows,et al.  1H, 13C, and 15N assignments and secondary structure of the FK506 binding protein when bound to ascomycin , 1993, Biopolymers.