Textmining, feature selection and datarnining for proteins classification

Mhamdi, Faouzi; Elloumi, Mourad; Rakotomalala, Ricco

doi:10.1109/ictta.2004.1307829

Cited by 12 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the second stage, we will determine the best size of k-grams by applying the off-line extraction algorithm [14] In the TABLE II, it can be seen that number of k-grams becomes too high from k=4, which degrades the performance of classifiers and increases the storage space and computing time. We then conclude that the compromise: k= 3grams / SVM is more appropriate in the evaluation of biological sequences which we will use in the next experiment to compare filter correlation based filter method and our contribution FCDBF.…”

Section: A Compromise: Classifier/ K-gramsmentioning

confidence: 98%

A Filter Correlation Method for Feature Selection

Hosni

Mhamdi

2014

2014 25th International Workshop on Database and Expert Systems Applications

View full text Add to dashboard Cite

Biological data is undergoing exponential growth in volume and complexity. Often, the selection of biological features is a crucial step that aims to defy the curse of dimensionality to improve prediction performance in classification systems, facilitate viewing, understanding and analyzing data. In this paper we present an adaptation of the Fast Correlation Based Filter algorithm (FCBF) whose aims is to identify relevant, not redundant features to improve the capacity of prediction and reduce the search space.

show abstract

Section: A Compromise: Classifier/ K-gramsmentioning

confidence: 98%

A Filter Correlation Method for Feature Selection

Hosni

Mhamdi

2014

2014 25th International Workshop on Database and Expert Systems Applications

View full text Add to dashboard Cite

show abstract

“…In the current study, we use transformations that have their foundations in the field of symbolic language analysis instead. They treat protein sequences as text from a 20 amino acid alphabet [30,31]. Here, short sequence fragments known as n-grams are understood as "words".…”

Section: Alignment Free Sequence Transformationsmentioning

confidence: 99%

Systematic Analysis of Primary Sequence Domain Segments for the Discrimination Between Class C GPCR Subtypes

König

Alquézar

Vellido

et al. 2018

Interdiscip Sci Comput Life Sci

View full text Add to dashboard Cite

G-protein-coupled receptors (GPCRs) are a large and diverse super-family of eukaryotic cell membrane proteins that play an important physiological role as transmitters of extracellular signal. In this paper, we investigate Class C, a member of this super-family that has attracted much attention in pharmacology. The limited knowledge about the complete 3D crystal structure of Class C receptors makes necessary the use of their primary amino acid sequences for analytical purposes. Here, we provide a systematic analysis of distinct receptor sequence segments with regard to their ability to differentiate between seven class C GPCR subtypes according to their topological location in the extracellular, transmembrane, or intracellular domains. We build on the results from the previous research that provided preliminary evidence of the potential use of separated domains of complete class C GPCR sequences as the basis for subtype classification. The use of the extracellular N-terminus domain alone was shown to result in a minor decrease in subtype discrimination in comparison with the complete sequence, despite discarding much of the sequence information. In this paper, we describe the use of Support Vector Machine-based classification models to evaluate the subtype-discriminating capacity of the specific topological sequence segments.

show abstract

“…Previous works showed that the choice of n = 3 (3-grams) and boolean descriptors give a good compromise to produce accurate classifier [1]. We obtain a Boolean attribute -value dataset with several thousands of descriptors ( Figure 3).…”

Section: The Protein Classification Problemmentioning

confidence: 99%

“…Their number is very high, which induces drawbacks: the computing time is very high and the quality of the learning classifier is often poor because we have a sparse dataset, and it is difficult to estimate in a reliable way the probability distribution ("The curse of Dimensionality Problem"). In a protein discrimination process from their primary structures [1], the native description of a protein is a succession of characters representing amino acids. It is not possible to run directly a learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

Improved Singular Value Decomposition for Supervised Learning in a High Dimensional Dataset

Rakotomalala¹,

Mhamdi²

2006

6th International Workshop on Pattern Recognition in Information Systems

View full text Add to dashboard Cite

Singular Value Decomposition (SVD) is a useful technique for dimensionality reduction with a controlled loss of information. This paper makes the very simple but worthwhile observation that many attributes that contain no information about the class label, may thus be selected erroneously for a supervised learning task. We propose to first use a very tolerant filter to select on a univariate basis which attributes to include in the subsequent SVD. The features, "the latent variables", extracted from relevant descriptors allow to build a better classifier with a significant improvement of the generalization error rate and less cpu time. We show the efficiency of this combination of feature selection and construction approaches on a protein classification context.

show abstract

Textmining, feature selection and datarnining for proteins classification

Cited by 12 publications

References 8 publications

A Filter Correlation Method for Feature Selection

A Filter Correlation Method for Feature Selection

Systematic Analysis of Primary Sequence Domain Segments for the Discrimination Between Class C GPCR Subtypes

Improved Singular Value Decomposition for Supervised Learning in a High Dimensional Dataset

Contact Info

Product

Resources

About