Prediction of β-turns in proteins using neural networks

McGregor, Malcolm J.; Flores, Tomas P.; Sternberg, Michael J.E.

doi:10.1093/protein/2.7.521

Cited by 97 publications

(40 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Two methods were used: the protein sequence analysis method (20) and neural network prediction (21).…”

Section: Expression Vectors Encoding Deletion Mutants Of Fshr-mentioning

confidence: 99%

“…The activity of this signal is mainly dependent on Tyr 684 and Leu 689 , while other residues play a less important role. Protein structure predictions (20,21) suggest the existence of a ␤-turn starting at Thr 680 and involving four residues (see Table I). It is followed by a ␤-sheet involving …”

Section: The C-terminal Region Of the Intracellular Domain Of Fhsr Ismentioning

confidence: 99%

“…Only in the case of the basolateral targeting signal of the rat lysosomal glycoprotein 120 and of vesicular stomatitis virus glycoprotein G have a Tyr and an Ile been shown to be of special importance for function (49,52). Structure predictions using several algorithms (20,21) have indicated that the basolateral localization signal of FSHR contains a ␤-turn structure. Mutation of residues located within or at close proximity to this putative structure have been shown to alter the basolateral targeting of the receptor.…”

Section: The Basolateral Localization Signal Of the Fshr Is Differentmentioning

confidence: 99%

See 2 more Smart Citations

The Basolateral Localization Signal of the Follicle-stimulating Hormone Receptor

Beau¹,

Groyer-Picard²,

Bivic³

et al. 1998

Journal of Biological Chemistry

View full text Add to dashboard Cite

The follicle-stimulating hormone receptor (FSHR) is physiologically localized in the basolateral compartment of the membrane of Sertoli cells. This localization is also observed when the receptor is experimentally expressed in Madin-Darby canine kidney cells. We thus used in vitro mutagenesis and transfection into these polarized cells to delineate the basolateral localization signal of the receptor.The signal was localized in the C-terminal tail of the intracellular domain (amino acids 678 -691) at a marked distance of the membrane. Mutation of individual amino acids highlighted the importance of Tyr 684 and Leu 689 . The 14-amino acid sequence was grafted onto the p75 neurotrophin receptor and redirected this apical protein to the basolateral cell membrane compartment. Deletion of amino acids 677-695 did not modify the internalization of the FSHR, showing that the basolateral localization signal of the FSHR is not colinear with its internalization signal.The FSH 1 receptor (FSHR), along with the LH and TSH receptors, belongs to a subgroup of G protein-coupled receptors (reviewed in Refs. 1-5). These highly homologous proteins are unusual among G protein-coupled receptors in that they contain a very large extracellular hormone binding domain. FSH transduction pathways involve mainly G s proteins coupling and the ensuing activation of adenylate cyclase (5).The FSH receptor has a central role in reproduction through the control of gonadal development and gamete production (5). In males it is expressed in testicular Sertoli cells. These cells form an epithelial blood barrier and control the development of spermatogenesis (6). In females, the FSHR is expressed in the granulosa cells of the ovaries. It controls follicular growth and, in cooperation with the LH receptor, ovarian steroidogenesis (2).Little is known of the intracellular trafficking of G proteincoupled receptors and, more specifically, of this subgroup of receptors. The pathways of internalization of the LH and TSH receptors have been studied at the ultrastructural level (7), 2 but the molecular signals involved are still unknown. The LH receptor is also present in the vascular endothelium of the testes (8). This endothelial LH receptor is involved in receptormediated hormone transcytosis, leading to the accumulation of the hormone in close proximity to the target cells. FSHR has been detected in the vascular endothelial cells of the testes (9), but its role in hormone transcytosis has not been studied to date.Another particularity of gonadotrophin and thyrostimulin receptors is their polarized cellular expression in several target tissues. Immunocytochemical studies with monoclonal antibodies have shown that the FSH receptor in Sertoli cells and the TSH receptor in thyroid follicular cells have a polarized basolateral expression (9, 10). By contrast, the LH receptor is expressed circumferentially in the ovarian granulosa and theca cells and in the testicular Leydig cells (11,12). This difference in receptor distribution could result from either a diffe...

show abstract

“…Two methods were used: the protein sequence analysis method (20) and neural network prediction (21).…”

Section: Expression Vectors Encoding Deletion Mutants Of Fshr-mentioning

confidence: 99%

Section: The C-terminal Region Of the Intracellular Domain Of Fhsr Ismentioning

confidence: 99%

Section: The Basolateral Localization Signal Of the Fshr Is Differentmentioning

confidence: 99%

See 1 more Smart Citation

The Basolateral Localization Signal of the Follicle-stimulating Hormone Receptor

Beau¹,

Groyer-Picard²,

Bivic³

et al. 1998

Journal of Biological Chemistry

View full text Add to dashboard Cite

show abstract

“…Although some progress has been made in predicting the secondary structure of proteins (1)(2)(3)(4)(5)(6)(7)(8)(9), no algorithm exists that can decode an amino acid sequence into a three-dimensional structure and predict the chemical properties of the resultant protein. If such an algorithm did exist, one could design and engineer proteins to solve problems in fields as diverse as industrial catalysis (10), bioremediation (11), and medicine (12).…”

mentioning

confidence: 99%

An algorithm for protein engineering: simulations of recursive ensemble mutagenesis.

Arkin

Youvan

1992

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

An algorithm for protein engineering, termed recursive ensemble mutagenesis, has been developed to produce diverse populations of phenotypically related mutants whose members differ in amino acid sequence. This method uses a feedback mechanism to control successive rounds of combinatorial cassette mutagenesis. Starting from partially randomized "wild-type" DNA sequences, a highly parallel search of sequence space for peptides fitting an experimenter's criteria is performed. Each iteration uses information gained from the previous rounds to search the space more efficiently. Simulations of the technique indicate that, under a variety of conditions, the algorithm can rapidly produce a diverse population of proteins fitting specific criteria. In the experimental analog, genetic selection or screening applied during recursive ensemble mutagenesis should force the evolution of an ensemble of mutants to a targeted cluster of related phenotypes.One might envision the solution to the protein folding problem as a complex algorithm that accurately predicts the three-dimensional structure and function of proteins from primary amino acid sequence data. Although some progress has been made in predicting the secondary structure of proteins (1-9), no algorithm exists that can decode an amino acid sequence into a three-dimensional structure and predict the chemical properties of the resultant protein. If such an algorithm did exist, one could design and engineer proteins to solve problems in fields as diverse as industrial catalysis (10), bioremediation (11), and medicine (12). Although much progress has been made toward a semiempirical solution to the protein folding problem, a complete solution to this quandary seems to lie in the distant future (1).From the viewpoint of a molecular geneticist, and in the absence of a solution to the protein folding problem, how does one effectively search for specific proteins with desired structures and functions? In this communication, we present computer simulations of an algorithm that efficiently searches "sequence space" (13) for proteins with specified properties, while treating the protein folding problem as a black box. Each step in this simulated process is exactly analogous to standard laboratory processes: DNA synthesis, cloning, expression, screening, and sequencing. Both the simulated process and the putative experimental process are termed "recursive" because information gained in one round of mutagenesis is used to control the next. We have been successful in simulating recursive ensemble mutagenesis (REM) on as many as eight interactive amino acid sites and have embarked on analogous experiments with model proteins.Simultaneously randomizing eight amino acid positions in a protein leads to a sequence complexity of 208, or >25 billion different sequences. The principal advantage of REM over other mutagenesis methods is that one can assay a relatively small volume (e.g., 10,000 mutants) in this large sequence space, find a few "positives," and generate a much larger fr...

show abstract

“…Results of neural networks applied to that problem have been reported between 63 and 64% (Qian & Sejnowski, 1988;Holley & Karplus, 1989) and a limit of 65% has been suggested (see review by Hirst & Sternberg, 1992). For binary models such as predicting a-helix vs. non-ahelix (Hayward & Collins, 1992) or &turns vs. non-0-turns (McGregor et al, 1989), there has been proposed a theoretical limit of 73-78%. The improvement of the binary model over the ternary model can be ascribed purely to the reduction in the number of predictable classes (Kneller et al, 1990).…”

Section: Effects Of Sequence Homology On Test Set Sorting Accuracymentioning

confidence: 99%

Analysis of protein transmembrane helical regions by a neural network

Dombi

Lawrence²

1994

Protein Science

View full text Add to dashboard Cite

Neural networks were used to generalize common themes found in transmembrane-spanning protein helices. Various-sized databases were used containing nonoverlapping sequences, each 25 amino acids long. Training consisted of sorting these sequences into 1 of 2 groups: transmembrane helical peptides or nontransmembrane peptides. Learning was measured using a test set 10% the size of the training set. As training set size increased from 214 sequences to 1,751 sequences, learning increased in a nonlinear manner from 75% to a high of 98%, then declined to a low of 87%. The final training database consisted of roughly equal numbers of transmembrane (928) and nontransmembrane (1,018) sequences. All transmembrane sequences were entered into the database with respect to their lipid membrane orientation: from inside the membrane to outside. Generalized transmembrane helix and nontransmembrane peptides were constructed from the maximally weighted connecting strengths of fully trained networks. Four generalized transmembrane helices were found to contain 9 consensus residues: a K-R-F triplet was found at the inside lipid interface, 2 isoleucine and 2 other phenylalanine residues were present in the helical body, and 2 tryptophan residues were found near the outside lipid interface. As a test of the training method, bacteriorhodopsin was examined to determine the position of its 7 transmembrane helices.

show abstract

Prediction of β-turns in proteins using neural networks

Cited by 97 publications

References 0 publications

The Basolateral Localization Signal of the Follicle-stimulating Hormone Receptor

The Basolateral Localization Signal of the Follicle-stimulating Hormone Receptor

An algorithm for protein engineering: simulations of recursive ensemble mutagenesis.

Analysis of protein transmembrane helical regions by a neural network

Contact Info

Product

Resources

About