Salamov, A.A. and Solovyev, V.V., Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments, Journal of Molecular Biology, 247:11--15, 1995.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....sequence information in the form of carefully selected pairwise alignment fragments, and reliance on a large collection of known protein primary structures. Its claimed Q 3 is 75 . NNSSP is a program that predicts secondary structure based on neural networks and nearest neighbour techniques [16]. The main idea of the nearest neighbour approach is the prediction of the secondary structure state of the central residue of a test segment, based on the secondary structure of similar segments from proteins with known three dimensional structure. The information coming from the different ....

Salamov AA and Solovyev VV. 1995. Prediction of protein secondary structure by combining nearestneighbor algorithms and multiple sequence alignment. J Mol Biol. Vol. 247, Pages: 11-15.

....chains to predict the secondary structure [170] If they include protein family information in the form of multiple sequence alignments, they get an overall three state accuracy of 71 . Salamov Solovyev s nearest neighbor algorithms give slightly better results (threestate accuracy to 72.2 ) [171]. The DSC method (Discrimination of Secondary structure Class) which is very similar in conception to GOR but uses multiple sequences, achieves 70.1 accuracy [172] Finally, the method of Livingstone Barton [173] groups residues based on the similarities and differences in their ....

Salamov, A & Solovyev, V (1995) Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol. 247, 11-15.

....An MSA is more informative than statistics of sequences considered individually since the information is grouped by position. Researchers have reported improvements in the accuracy of secondary structure prediction methods from roughly 60 without the use of MSA s up to 70 with the use of MSA s [55, 63, 64]. Statistical approaches to multiple sequence alignment have also been used to characterize motifs such as the EF hand [47] and the Helix Loop Helix [49, 50] motifs. However, Krogh et al. 47] point out that while these methods find patterns associated with these motifs in the primary sequence, it ....

A. A. Salamov and V. V. Solovyev. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. Journal of Molecular Biology, 247:11--15, 1995.

.... (singlets) are combined with the frequencies of all 136 possible di residue pairs (doublets) The GOR method uses only single sequence information and because of this achieves lower accuracy (65 versus 71 ) than the current state of the art methods that incorporate multiple sequence information [3,82 84]. However, it is not possible to obtain multiple sequence alignments for most of the proteins in each of the genomes. Consequently, bulk predictions of all the proteins in a genome based on multiple alignment approaches are skewed, in the same sense as discussed above for multiple sequence based ....

Salamov, A. & Solovyev, V. (1995). Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol. 247, 11-15.

.... active HIV 1 viruses (isolate names are given in the legend of figure 1) The average sequence similarity was 77 (range 67 99 ) We use two different prediction methods: The PHD (Profile Network System Heidelberg) method [35] and the NNSSP (Nearest Neighbor Secondary Structure Prediction) method [36], which combine multiple sequence alignment with neural networks and nearest neighbor algorithms, respectively. The accuracy of secondary structure prediction schemes has been improved significantly by the use of aligned protein sequences [37] The two methods were chosen because they have been ....

....algorithms, respectively. The accuracy of secondary structure prediction schemes has been improved significantly by the use of aligned protein sequences [37] The two methods were chosen because they have been assessed to be the most accurate compared to previous prediction schemes [35, 36, 38, 39]. Both methods can use single sequences or multiple aligned sequences as query input. The methods take markedly different approaches to the secondary structure prediction problem. The PHD method (version 5.94 317) uses a 3 layered neural network approach [35, 38, 40] where a jury decision [41] ....

[Article contains additional citation context not shown here]

Salamov, A.A., Solovyev, V.V. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol. 247:11--15, 1995.

....classification. The classifaction of these sequential fragments relies either directly or indirectly on a measure of distance between residue hexamers. 5. 1 Nearest neighbour classification Nearest neighbour classification techniques have been successfully applied to protein structure prediction [19, 18, 25]. These methods are based on the assumption that examples which are closer in the feature space are of the same class. As a measure of distance we use the non Euclidean value difference metric defined by Stanfill and Waltz [23] which relates the distance between two symbolic values to the ....

A.A. Salamanov and V.V. Solovyev. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol., 247:11--15, 1995.

....takes the predictions made for individual members of a protein family and combines them according to some weighting scheme to arrive at a consensus prediction. The two most recent applications 2 M.J. Thompson R.A. Goldstein of this approach have yielded high accuracies over large datasets (Salamov and Solovyev, 1995; Riis and Krogh, 1996) While this approach is generally applicable and can provide competitive statistical accuracy, it does not model the underlying sequence to structure correlations or evolutionary process. Thus, few questions regarding such relationships can be addressed and this technique ....

....will be major influences. It has been observed that ff helices and fi strands can possess characteristic patterns of exposure to solvent, and this information has been successfully exploited in previous secondary structure predictions (Lim, 1974; Yi and Lander, 1993; Wako and Blundell, 1994b; Salamov and Solovyev, 1995). We can capture these patterns through the use of a richer alphabet for denoting local structure. We take OE j to be the descriptor of the structure at each residue location, j. In this work, we explore the use of 4 categories of secondary structure, s j , combined with either 1, 2, or 3 ....

[Article contains additional citation context not shown here]

Salamov A and Solovyev V. 1995. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J Mol Biol 247:11--15.

....class balanced voting that weights the votes from members of each class such that the sum of weighted votes over all members of a class is equal for all classes. This approach was successfully applied by Salamov and Solovyev in their knn approach to the prediction of protein secondary structure [9]. 2.2 The genetic algorithm The chromosome for the masking GA knn is composed of two parts. The first part consists of one real valued weight for each of the features being considered. In this implementation, the weights range from 0 to 100 and are represented as 32 bit, unsigned, floating point ....

A. A. Salamov and V. V. Solovyev, Prediction of Protein Secondary Structure by Combining NearestNeighbor Algorithms and Multiple Sequence Alignments, J. Mol. Biol. vol. 247, pp. 11-15, 1995.

No context found.

Salamov, A.A. and Solovyev, V.V., Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments, Journal of Molecular Biology, 247:11--15, 1995.

No context found.

A. A. Salamov and V. V. Solovyev. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol., 247(1):11--15, 1995.

No context found.

A. A. Salamov and V. V. Solovyev. Prediction of protein secondary structure by combining nearestneighbor algorithms and multiple sequence alignments. J. Mol. Biol., 247(1):11--15, 1995.

No context found.

Salamov, A. A. & Solovyev, V. V. (1995). Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol. ###, 11-15.

No context found.

Salamov, A.A., Solovyev, V.V. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol. 247:11--15, 1995.

No context found.

Salamov, A.A., Solovyev, V.V. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. J. Mol. Biol. 247:11--15, 1995.

No context found.

Salamov, A.A., Solovyev, V.V. Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignment. J. Mol. Biol. 247:11--15, 1995.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC