A nonparametric statistical approach in noisy chaos identification

Lai, Dejian; Harrist, Ronald B.

doi:10.1080/03610919708813380

Cited by 101 publications

(201 citation statements)

References 7 publications

Supporting

Mentioning

199

Contrasting

Unclassified

Order By: Relevance

“…To further access the stability of the clusters under change of the clustering algorithm, we have also implemented the Mean shift clustering algorithm [14][15][16] , which similarly reproduces the same clustering with minor variations. Please see Supplementary Note 3 for a discussion of the selection of the clustering algorithms and Supplementary Note 4 and Supplementary Table 1 for a comprehensive comparison of all clustering runs.…”

Section: Article Nature Communications | Doi: 101038/ncomms6803mentioning

confidence: 99%

“…In this case, the next hydrogen bond belongs to the longrange clusters. Still assuming that the conformational angles between the two hydrogen bonds correspond to an ideal antiparallel beta strand, we get equation (16) instead of equation (15). We have probed for the existence of pairs R H and R H 1 subject to either (15) or (16) as follows.…”

mentioning

confidence: 99%

“…Still assuming that the conformational angles between the two hydrogen bonds correspond to an ideal antiparallel beta strand, we get equation (16) instead of equation (15). We have probed for the existence of pairs R H and R H 1 subject to either (15) or (16) as follows. For each turn cluster, we find candidate R H 's as those hydrogen bonds with conformational angles outwards of the turn close to the ideal antiparallel conformational angles ( À 135°, 150°) allowing for a deviation of 30°.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Hydrogen bond rotations as a uniform structural tool for analyzing protein architecture

et al. 2014

View full text Add to dashboard Cite

Proteins fold into three-dimensional structures, which determine their diverse functions. The conformation of the backbone of each structure is locally at each C a effectively described by conformational angles resulting in Ramachandran plots. These, however, do not describe the conformations around hydrogen bonds, which can be non-local along the backbone and are of major importance for protein structure. Here, we introduce the spatial rotation between hydrogen bonded peptide planes as a new descriptor for protein structure locally around a hydrogen bond. Strikingly, this rotational descriptor sampled over high-quality structures from the protein data base (PDB) concentrates into 30 localized clusters, some of which correlate to the common secondary structures and others to more special motifs, yet generally providing a unifying systematic classification of local structure around protein hydrogen bonds. It further provides a uniform vocabulary for comparison of protein structure near hydrogen bonds even between bonds in different proteins without alignment.

show abstract

Section: Article Nature Communications | Doi: 101038/ncomms6803mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Hydrogen bond rotations as a uniform structural tool for analyzing protein architecture

et al. 2014

View full text Add to dashboard Cite

show abstract

“…In this section, we extend the MEM algorithm, proposed by Li et al (2007) to maximise (2.3). Since the SCAD penalty is irregular at the origin, maximising (2.3) directly may be difficult.…”

Section: A Modified Modal Expectation-maximization Algorithmmentioning

confidence: 99%

Robust variable selection for nonlinear models with diverging number of parameters

Zhu

2014

Statistics & Probability Letters

View full text Add to dashboard Cite

show abstract

“…iii) DBScan clustering algorithm [24]; iv) Mode identification based clustering algorithm [25]; v) Random swap algorithm [26]; vi) Density peak algorithm [27].…”

Section: Numerical Examples and Analysismentioning

confidence: 99%

A new type of distance metric and its use for clustering

Angelov

Kangin

et al. 2017

Evolving Systems

View full text Add to dashboard Cite

Abstract-In order to address high dimensional problems, a new 'direction-aware' metric is introduced in this paper. This new distance is a combination of two components: i) the traditional Euclidean distance and ii) an angular/directional divergence, derived from the cosine similarity. The newly introduced metric combines the advantages of the Euclidean metric and cosine similarity, and is defined over the Euclidean space domain. Thus, it is able to take the advantage from both spaces, while preserving the Euclidean space domain. The directionaware distance has wide range of applicability and can be used as an alternative distance measure for various traditional clustering approaches to enhance their ability of handling high dimensional problems. A new evolving clustering algorithm using the proposed distance is also proposed in this paper. Numerical examples with benchmark datasets reveal that the direction-aware distance can effectively improve the clustering quality of the k-means algorithm for high dimensional problems and demonstrate the proposed evolving clustering algorithm to be an effective tool for high dimensional data streams processing.

show abstract

A nonparametric statistical approach in noisy chaos identification

Cited by 101 publications

References 7 publications

Hydrogen bond rotations as a uniform structural tool for analyzing protein architecture

Hydrogen bond rotations as a uniform structural tool for analyzing protein architecture

Robust variable selection for nonlinear models with diverging number of parameters

A new type of distance metric and its use for clustering

Contact Info

Product

Resources

About