Amino acid "little Big Bang": Representing amino acid substitution matrices as dot products of Euclidian vectors

Zimmermann, Karel; Gibrat, Jean‐François

doi:10.1186/1471-2105-11-4

Cited by 12 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 Based on AA preferences to form the secondary structures ( sheet, helix). 4 AAs are represented based on the proposed codon encoding, and each of the four adjacent 0s and 1s is converted to an integer.…”

Section: Resultsmentioning

confidence: 99%

“…Note that, in this study we tried to identify effective encoding schemes by evaluating them using scoring matrices, as opposed to constructing an encoding scheme specifically designed to compute substitution scoring matrices such as [3]. In this regard, we hope to get a general assessment of the performance of these encoding schemes across a broad class of problems, rather than a specific method to perform optimally on the scoring matrix problem.…”

Section: B Encoding Schemesmentioning

confidence: 98%

“…For example, the important data required to solve one problem may be noise in the context of another. This proves to be a challenge in any work attempting to identify a "best" encoding scheme [1]- [3].…”

Section: Introductionmentioning

confidence: 97%

See 2 more Smart Citations

Amino acid encoding schemes for machine learning methods

Zamani

Kremer

2011

2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)

View full text Add to dashboard Cite

In this paper, we investigate the efficiency of a number of commonly used amino acid encodings by using artificial neural networks and substitution scoring matrices. An important step in many machine learning techniques applied in computational biology is encoding the symbolic data of protein sequences reasonably efficient in numeric vector representations. This encoding can be achieved by either considering the amino acid physicochemical properties or a generic numerical encoding. In order to be effective in the context of a machine learning system, an encoding must preserve information relative to the problem at hand, while diminishing superfluous data. To this end, it is important to measure how much an encoding scheme can conserve the underlying similarities and differences that exist among the amino acids. One way to evaluate the effectiveness of an amino acid encoding scheme is to compare it to the roles that amino acids are actually found to play in biological systems. A numerical representation of the similarities and differences between amino acids can be found in substitution matrices commonly used for sequence alignment, since these substitution matrices are based on measures of the interchangeability of amino acids in biological specimens. In this study, a new encoding scheme is also proposed based on the genetic codon coding occurs during protein synthesis. The experimental results indicate better performances compared to the other commonly used encodings.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: B Encoding Schemesmentioning

confidence: 98%

See 1 more Smart Citation

Amino acid encoding schemes for machine learning methods

Zamani

Kremer

2011

2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)

View full text Add to dashboard Cite

show abstract

“…Biological sequences and amino acids are clearly multi-dimensional objects 17–20. It has been recently demonstrated that the high-dimensionality of biological sequences leads to emergent computational features like similarity measure and particular probability distribution of this similarity 21–23.…”

Section: Introductionmentioning

confidence: 99%

How Fitch-Margoliash Algorithm can Benefit from Multi Dimensional Scaling

Lespinats

Grando

Maréchal

et al. 2011

Evol Bioinform Online

View full text Add to dashboard Cite

Whatever the phylogenetic method, genetic sequences are often described as strings of characters, thus molecular sequences can be viewed as elements of a multi-dimensional space. As a consequence, studying motion in this space (ie, the evolutionary process) must deal with the amazing features of high-dimensional spaces like concentration of measured phenomenon.To study how these features might influence phylogeny reconstructions, we examined a particular popular method: the Fitch-Margoliash algorithm, which belongs to the Least Squares methods. We show that the Least Squares methods are closely related to Multi Dimensional Scaling. Indeed, criteria for Fitch-Margoliash and Sammon’s mapping are somewhat similar. However, the prolific research in Multi Dimensional Scaling has definitely allowed outclassing Sammon’s mapping.Least Square methods for tree reconstruction can now take advantage of these improvements. However, “false neighborhood” and “tears” are the two main risks in dimensionality reduction field: “false neighborhood” corresponds to a widely separated data in the original space that are found close in representation space, and neighbor data that are displayed in remote positions constitute a “tear”. To address this problem, we took advantage of the concepts of “continuity” and “trustworthiness” in the tree reconstruction field, which limit the risk of “false neighborhood” and “tears”. We also point out the concentration of measured phenomenon as a source of error and introduce here new criteria to build phylogenies with improved preservation of distances and robustness.The authors and the Evolutionary Bioinformatics Journal dedicate this article to the memory of Professor W.M. Fitch (1929–2011).

show abstract

“…In this study, we analysed the exercise and play sport level of citizens (all adults aged 15 and above) of the European Union, by means of a graphic representation, using metric Multidimensional Scaling (MDS) [20] [21] [22]. Data on the exercise and playing sport level reported in European Commission as reported by Townsend et al (2012) [23] were summarized in order to facilitate the study of exercise and play sport D. Ríos et al…”

Section: Introductionmentioning

confidence: 99%

A Graphical Classification of European Countries According to Physical Activity Level of Its Citizens

Ríos¹,

Monleón-Getino²,

Cubedo³

et al. 2016

OALib

View full text Add to dashboard Cite

Data on self-reported frequency of exercising or playing sport of adults aged 15 and above in 27 EU countries were collected, from the European Commission's Special Eurobarometer. A graphical output was obtained using classical a statistical methodology known as metric Multidimensional Scaling method to better define the interrelationships between a large set of variables for the data from the 27 European countries and "average" country included in the study. People in Sweden, Denmark and Finland had the highest level of exercise and playing sport level. High level of exercise and play sport level were detected in Slovenia, the Netherlands, Belgium, Germany, Luxembourg, the United Kingdom and France while low level of exercise and play sport level were found in Romania, Hungary, Italy, Poland and Portugal. The lowest level of exercise and play sport was observed in Bulgaria and Greece. The groups of countries that result from this classification also are characterized by the extent of the difference between the lowest levels of activity (never practising) and the highest (regularly practising); Austria, Czech Republic and Slovakia, have the highest proportion of people who seldom practising. In 4 countries, Ireland, Malta, Republic of Cyprus and Portugal, the proportion of citizens who practice exercise or play sport regularly or never (extreme behaviour) is high. This study shows what a high level and regularly of exercise and playing sport are associated with adults participating in education and training, satisfaction with household financial situation and kind of work activity.

show abstract

Amino acid "little Big Bang": Representing amino acid substitution matrices as dot products of Euclidian vectors

Cited by 12 publications

References 20 publications

Amino acid encoding schemes for machine learning methods

Amino acid encoding schemes for machine learning methods

How Fitch-Margoliash Algorithm can Benefit from Multi Dimensional Scaling

A Graphical Classification of European Countries According to Physical Activity Level of Its Citizens

Contact Info

Product

Resources

About